SlideShare ist ein Scribd-Unternehmen logo
1 von 42
Architecture proposal for AWF by Tier IV Inc.
2019. .172020.03
Version 1.0
Autoware Architecture Proposal
.
.
.
●
●
.
.
Here is subtitle
Requirement
01
Why we need a new architecture
1
4
4
Why we need a new architecture
Problem
● It’s diffcult to improve
Autoware.AI capabilities
Why?
● No concrete architecture design
● A lot of technical debt
○ Tight coupling between
modules
○ Unclear responsibility of
modules
Tier IV's proposal
● Define a layered
architecture
● Clarify the role of each
module
● Simplify the interface
between modules
Here is subtitle
Requirement
01
Considered use cases
2
6
6
Considered use cases
Example use cases that were considered during architecture design:
Features that are not considered yet (for the sake of development speed)
● Real-time processing
● HMI / Fail safe / Redundant system / State monitoring system / etc…
Will consider these items at AWF WGs
Module Use cases
Sensing ● 360-degree sensing by the camera-LiDAR fusion
Perception ● Recognition of dynamic objects and traffic lights
Localization ● Robust Localization using multiple data sources
Planning
● Route planning, dynamic planning based on vector map
(not only waypoint following)
● Automatic parking
● Object avoidance
Control ● High control performance on many kinds of vehicle-controllers
7
7
Demo video
Module Contents
Whole Scenario demo
Sensing+Perception 360° FOV, Prediction
Localization Robustness of localization, Return from error
Planning Lane change, Obstacle avoid, Parking
Control Slow brake (normal stop), Rapid brake (emergency stop)
Here is subtitle
Requirement
01
Architecture overview
3 Layered architecture
High level introduction of each module
9
Map
Sensor Vehicle
Autoware
DRAFT: https://github.com/tier4/Autoware_architecture_proposal
Control
Sensing
Detection Tracking Prediction
Mission
Detection Classifier
Traffic light
Perception
Dynamic object
Planning
Scenario
Vehicle command
Vehicle sensorMap dataSensor data
Surrounding
environment Trajectory
Current pose/velocity
Scenario selector
Parking
Lane
following
etc.
Vehicle interface
Perception Planning
Map
Localization
steering/velocity
feedback
10
Map
Sensor Vehicle
Autoware
DRAFT: https://github.com/tier4/Autoware_architecture_proposal
Control
Sensing
Detection Tracking Prediction
Mission
Detection Classifier
Traffic light
Perception
Dynamic object
Planning
Scenario
Vehicle command
Vehicle sensorMap dataSensor data
Surrounding
environment Trajectory
Current pose/velocity
Scenario selector
Parking
Lane
following
etc.
Vehicle interfaceMap
steering/velocity
feedback
Detection Tracking Prediction
Mission
Detection Classifier
Traffic light
Perception
Dynamic object
Planning
Scenario
Scenario selector
Parking
Lane
Driving
etc.
Localization
11
Map
Sensor Vehicle
Autoware
DRAFT: https://github.com/tier4/Autoware_architecture_proposal
Control
Sensing
Detection Tracking Prediction
Mission
Detection Classifier
Traffic light
Perception
Dynamic object
Planning
Scenario
Vehicle command
Vehicle sensorMap dataSensor data
Surrounding
environment Trajectory
Current pose/velocity
Scenario selector
Parking
Lane
following
etc.
Vehicle interfaceMap
Localization
steering/velocity
feedback
Detection Tracking Prediction
Mission
Detection Classifier
Traffic light
Perception
Dynamic object
Planning
Scenario
Scenario selector
Parking
Lane
following
etc.
12
[Architecture] Sensing
Camera
driver
GNSS
driver
IMU driver
Localization Perception Planning
LiDAR
driver
Pointcloud
preprocessor
/sensing/gnss/[name]/
pose_with_covariance
/sensing/imu/[name]/imu_raw /sensing/lidar/pointcloud
/sensing/lidar/
no_ground/pointcloud
Sensing
GNSS
preprocessor
IMU
preprocessor
Camera
preprocessor
/sensing/camera/
[name]/image_raw
Design Doc
Role : Conversion of sensing data to ROS message
Driver
Preprocessor
Examples of preprocessors
● Distortion correction
● Outlier filter
● Concat filter
● Ground filter
ROS drivers (mainly from upstream)
13
[Architecture] Map
Map
Pointcloud
map
Vector map
Pointcloud
map loader
Vector map
loader
PerceptionLocalization Planning
Design Doc
Conversion to on-memory data structure
Coordinate transformation
Map library Map libraryMap library
Map is distributed as a single
message, and accessed through
library API
Role : Distribute static environment information to other modules
14
[Architecture] Localization
Pose
twist
fusion
filter
GNSS
LiDAR
(Camera)
CAN
IMU
tf (map to base_link)
twist
Localization
TwistWith
Covariance.msg
Pose Estimator
Pose estimator
PoseWith
Covariance.msg
Pose Estimator
Twist estimator
Support multiple localization methods
based on different sensors(LiDAR/Camera/GNSS)
Fuse pose and twist (e.g.EKF)
Merge sensor inputs
Design Doc
Role : Integration of each sensor data and estimation of self-pose and self-twist
15
[Architecture] Perception
Perception
Detection Classifier
TrackingDetection Prediction
Sensor data
(e.g. Camera, LiDAR)
Sensor data
(e.g. Camera, LiDAR)
Map
Dynamic object
Traffic light
15
DynamicObjectArray.msg
TrafficLightStateArray.msg
Map
Dynamic object’s information including:
● ID
● Semantic (label, confidence)
● Shape
● State (pose, velocity, acceleration,
predicted path, etc)
Traffic light’s information including:
● State (red, green, yellow, etc)
Could be customized for unique traffic
light types.
Design Doc
Role : Dynamic object recognition and traffic light recognition
16
[Architecture] Planning
Mission
planning
Planning
Scenario planning
Scenario selector
Route.msg
Trajectory.msg
ParkingOn road etc.
Select
Route planning from
vector map
Selects appropriate module
depending on situation
Moduled scenarios allow:
● distributed development
● Easier parameter tuning
per situation
Dynamic objects
Traffic lights
Map
Obstacles
tf(map to base_link)
Design Doc
Role : From a calculation of the route to the goal to drive trajectory generation
17
[Architecture] Control
VehicleCmd.msg (autoware.ai)
-----------------------------------------
header
steer_cmd
-header
-steer
accel_cmd
-header
-accel
brake_cmd
-header
-brake
gear
twist_cmd
-header
-linear
-angular
ctrl_cmd
-linear velocity
-linear acceleration
-steering angle
VehicleCommand.msg
(proposed architecture)
-----------------------------------------
header
control
-steering angle
-velocity
-steering angle velocity
-acceleration
shift
-data
Remove
redundant output
VehicleStatus.msg
Support low level control
Generate signals for
trajectory following
Final gateway for commands to vehicle:
● engage
● acceleration limits
● etc
Vehicle
cmd gate
Trajectory.msg
Vehicle
Command.msg
RemoteCmdEngage
Control
Trajectory
follower
ControlCommand
Stamped.msg
Vehicle
velocity
Steer
angle
Design Doc
Role : Generation of control signals to drive a vehicle following trajectories
Here is subtitle
Requirement
01
Contribution steps to
Autoware community
4
19
Detailed doc
Sample impl
Today's
presentation
Contribution steps to Autoware community
End of December
Autonomous Valet Parking
Architecture clean up
Technical debt clean up
Documentation clean up
Architecture discussion and refinement
at Discourse and GitLab
Design additional modules(mainly related to Safety)
Architecture validation in real-environment
Develop cutting edge features
Next ODD
development
Design and implement new
architecture
Feb. Jan.Mar. Apr. Mai. Jun. Jul. Aug. Sep. Oct. Nov. Dec.
AWF
(Including
Tier IV)
Tier IV
Architecture proposal
Documentation writing
Clean up sample impl
Feedback design
and sample impl
Here is subtitle
Requirement
01
Conclusion
5
21
21
Conclusion
● We proposed a new architecture of Autoware
● Tier IV will contribute our achievements to Autoware community
○ Detailed design documents
○ Reference source code
● We would like to discuss the new architecture at WGs
○ Any feedback is welcome
● We will make an effort to implement the new architecture in Autoware.Auto
22
22
Appendix
23
23
Appendix - Table of Contents
● Design alternative
● Module implementation
○ Implementation details
○ Achevements
24
24
Appendix - Table of Contents
● Design alternative
● Module implementation
○ Implementation details
○ Achevements
25
Pre-study of the planning architecture
Type Structure Pros. Cons.
BOSS type
(Junior type)
・Structure is intuitive and easy to
understand.
・Easy to handle separately.
・Behavior has to make a
conservative decision in order to
reduce discrepancies with a
motion’s decision.
CMU Dr. paper
type
・It solves and optimizes both
behavior and motion simultaneously
to overcome a cons. of the BOSS
type.
・Difficult to improve if any issue was
found.
・Optimization of the whole
autonomous driving functions is not
realistic..
Victor Tango
type
・Behavior and motion are tightly
coupled to overcome a cons. of the
BOSS type.
・Easy to improve if any issue was
found
・Difficult to take a new research
result into the modules.
Apollo type ・Scenario is one layer upper
concept.
・We can adopt prefered types of the
planning structure according to each
scenario.
・In the scenario, cons. such as
things described above are still
remained.
・If scenarios increased, switching
mechanism can be complicated.
[Design alternative] Planning (1/2)
TrajectoryMission
BehaviorMission Motion
Scenario
Mission
Scenario
︙
25
BehaviorMission Motion
26
[Design alternative] Planning (2/2)
Mission
** scenario
︙
Finally, we adopted Apollo + Boss type
26
Behavior Motion
Free space
Parking scenario
On road scenario
Lane following scenario : BOSS type
● It’s clear and convenient to develop as
OSS
Whole module : Apollo type
● New scenario can be added as needed
Future challenge
● In lane following scenario, behavior still
makes a conservative decision. And an
aggressive driving like changing lane
by entering into crowded lane cannot
be executed.
27
27
Appendix - Table of Contents
● Design alternative
● Module implementation
○ Implementation details
○ Achevements
28
TF Tree
The origin of MGRS coordinate
The point projected vertically downwards
from the center point of the rear wheel axle
to the ground.
The bottom of the velodyne_top
map
base_link
aipxx
velodyne_* camera_* imu_*gnss_*
28
Vehicle specified setting
(Here is an example of Tier
IV’s implementation)
29
[Sensing] Components
Camera
driver
GNSS
driver
IMU driver
Localization Perception Planning
LiDAR
driver
Points
preprocessor
MGRS
convertion
/sensing/gnss/[name]/
pose_with_covariance
/sensing/gnss/[name]/nav_sat_fix
/sensing/imu/[name]/imu_raw /sensing/camera/
[name]/image_raw
/sensing/lidar/pointcloud
/sensing/lidar/
no_ground/pointcloud
Sensing
30
30
[Sensing] Feature
● Distortion correction
○ Corrects a distortion of the pointclouds due to an observation time gap
⇨ Accuracy of the localization is improved
● Ground filter
○ Removes a ground from pointclouds (.ai has same feature)
● Outlier filter
○ Removes outliers by ring-base method ⇨ Reduce impacts of leaves
and insects
● Concat filter
○ Integrates some pointclouds
○ Reduces an impact when a part of sensors stop
○ Corrects time gaps between each LiDAR with odometry ⇨ Accuracy of
the localization is improved
31
Localization
Pose Estimator
Twist Estimator
/localization/fusion_localizer/t
wist
DownSampler
NDT Scan
Matcher
Pose Initializer
IMU-VehicleTwist fuser
Pose Twist
Fusion Filter
EKF
Loader
map
Sensing
Sensing
Sensing
IMU-GNSS-VehicleTwist fuser
/sensing/imu/[name]/imu_raw
/sensing/gnss/[name]/pose_with_covariance
/sensing/lidar/pointcloud
/map/pointcloud
/tf
Crop
Measurement
Range
Localizer Diagnostics
Localization System
Diagnostic Node
diagnostic /localization/diagnostic
Safety NodeSafety Diagnostic Node
diagnostic/vehicle/status/twist_with_covar
iance
[Localization] Components
31
32
32
[Localization] Feature
● Pose initializer
○ Automatic initial self position estimation by GNSS + Monte-Carlo method
● NDT scan matcher
○ Uses an estimated value of EKF as an initial position of the scan matching ⇨ If scan matching was failed,
localization can be returned
○ Performance and accuracy are improved (Open-MP implementation, accuracy improvement of the initial
position, improvement of the gradient method, distortion correction of pointclouds, and etc.)
● Scan matching failure judgement
○ Monitors statuses of scan matching based on a score
○ If score is lower than a threshold, an estimated result isn’t output
● EKF localization
○ Integrates the estimated self position of the scan matching and the velocity of CAN+IMU
○ If scan matching broke down, the vehicle can drive a certain distance with odometry only
● IMU Vehicle-twist fusion
○ Uses a translation velocity of CAN and yaw rate of IMU ⇨ Accuracy of odometry is improved
● Localizer Diagnostics
○ Monitors a status of a whole localization module
(Temporary implementation)
※ Only NDT is implemented in Pose Estimator now.
 In future, other estimators like a white line recognition based one will
be added.
33
[Perception] Components
33
Loader
Map
/map/semantic
Sensing
Planning
/sensing/camera/[name]/camera_info
/planning/mission_planning/route
Map based
detection
Detection
Fine detection
TrafficLightRoiArray
/perception/traffic_light/rois
Traffic Light
Detection
PointCloud
Segmentation
Image
Detection
Fusion
Shape
Estimation
Tracking
Multi Object
Tracking
Map Based
Prediction
Prediction
Classifier
Classification
Dynamic Object
sensing/lidar/pointcloud
sensing/camera/*/image_raw
sensing/camera/*/camera_info
Image
DetectionImage
Detection
perception/detection/objects perception/tracking/objects perception/prediction/objects
Loader
Map
/map/semantic
34
34
[Perception] Feature
Dynamic Object
● Point Cloud Segmentation : Splits pointclouds into object clusters
○ Becomes faster by algorithm improvement (It can work in real-time on CPU)
● Image Detection : Detects objects on an image as ROI
○ Becomes to work on 40FPS on Jetson AGX by Tensor RT and int8 quantization
● Fusion : Matches the result of Pointclouds Segmentation and the ROI of the image detection result
○ Matching accuracy is improved by using IoU
● Shape Estimation : Geometrically approximates the whole size of the objects by Point Cloud Segmentation
○ Shape estimations by each object class
○ Accuracy improvement by changing fitting algorithm of Bounding Box
● Multi-Object Tracking : Assigns IDs based on time series data, estimates the velocity and the acceleration, and removes outliers
○ Performance improvement by changing a tracking model by class labeling
○ Data association considering the class label and the size
● Map Based Prediction : Predicts moving path of the objects with the lane information in a map
○ Infers objects’ intent of the behavior and estimates each reliability of the predicted moving paths.
Traffic Light
● Map Based Detection : Extracts an ROI of the traffic light in camera image based on the self position and map data
○ Takes errors of a self position, a calibration and a hardware vibration into consideration
● Fine Detection
○ Extracts the ROI of the traffic light more precisely with a learner
● Classifier : Recognizes a state of the traffic light by a color information in the image
○ Reduces detection errors by fine noise removement process
35
[Planning] Components
Route.msg
/planning/mission_planning/route
Lane change
planner
Behavior
velocity planner
Motion path planner
Obstacle stop
planner
Jerk filter
On road
Path.msg
/planning/scenario_planning/scenarios/
lane_following/behavior_planning/path
Trajectory.msg
/planning/scenario_planning/scenarios/
lane_following/motion_planning/trajectory
MotionBehavior
35
Mission
planner
Mission
Trajectory.msg
/planning/scenario_planning/scenarios/
parking/freespace_planner/trajectory
Costmap
generator
Freespace
planner
OccupancyGrid.msg
/planning/scenario_planning/scenarios/parking/
freespace_planner/costmap_generator/occupancy_grid
Parking
freespace
Scenario selector
Trajectory.msg
/planning/scenario_planning/trajectory
36
36
[Planning] Feature
● Scenario selector
○ Chooses and executes “lane_following” or “parking” scenario according to the information of the mission
● Mission planner
○ Automatically searches the route from a self position to a goal via certain pass through points (by using lanelet
function)
○ Automatically generates a route by using a map information
● Lane change
○ Judges a situation which needs lane change (Drive route limitation / street parking avoidance)
○ Judges whether a collision with a dynamic will happen obstacle and if a lane change is possible, it will be executed
● Behavior Velocity Planner
○ Plans a velocity based on traffic rules
○ Supports intersections, crosswalks, back-side check when turning right/left, stop with traffic lights and temporary
stop line
○ Uses results of the perception (dynamic object information)
● Obstacle avoidance (motion path planner)
○ Plans a path to avoid the obstacle while driving (A* + QP)
○ Generate a smooth path considering a drivable area and the obstacle
● Obstacle stop (obstacle stop planner)
○ Judges whether a collision with obstacle pointcoulds considering the vehicle shape, and fill a stop velocity
● Jerk filter
○ Smoothens the velocity under the limitation of max speed, acceleration and lateral acceleration (QP)
○ Enables to switch rapid/slow acceleration and deceleration plans
37
[Control] Components
Vehicle
CmdGate
Longitudinal
Controller
Lateral
Controller
Trajectory
/control/vehicle_cmd
RemoteCmd /autoware/engage
37
Control
LatLon
Coupler
Trajectory Follower
/control/longitudinal/
control_cmd
/control/lateral/
control_cmd
/control/control_cmd
● Longitudinal Controller
○ Calculates a target velocity and a target
acceleration by PID
○ Supports a gradient correction and
start/stop at a slope
○ Supports a smoothly stop
● Lateral Controller
○ Calculates a steering angle and an angular
velocity (pure pursuit or MPC)
● LatLon Coupler
○ Integrates the longitudinal and lateral
control command values
● Vehicle Cmd Gate
○ Switches the some command values like
“remote” and “auto”
○ Attaches a limitation for the control
command
■ longitudinal/lateral acceleration,
longitudinal/lateral jerk
・In this implementation, longitudinal and lateral controls are
separately culcurated
・In future implementation, these might be culcurated collectively
38
[Vehicle Interface] Components
38
Vehicle Interface
Accel Map
Converter
Vehicle_interface
/control/vehicle_cmd
/control/vehicle_cmd /vehicle/pedal_cmd
To Vehicle
/vehicle/turn_signal_cmd
/vehicle/status/twist
/vehicle/status/steering
/vehicle/status/turn_signal
/vehicle/status/shift
● Accel Map Converter
○ Converts a target acceleration to a vehicle specific
accel/brake pedal value by Accel Map
○ If the vehicle_interface supports a velocity/acceleration
command, this converter isn’t necessary
● Vehicle Interface (vehicle specific)
○ Interface between Autoware and a vehicle
○ Communicates control signals
○ Obtains the vehicle information
39
39
Other features
● Web Controller
○ Through this controller, we can engage and specify the max velocity and also use “Go Home” button,
“lane change OK” button and sensor Hz monitor
● Autoware State Monitor
○ State monitoring (Initializing / WaitForEngage / Driving / …)
40
40
Appendix - Table of Contents
● Design alternative
● Module implementation
○ Implementation details
○ Achevements
41
Achievements (1/2)
● Automatic initial self pose estimation
● Robustness of self pose estimation improvement
● CAN / imu fusion, EKF feedback, Gradient method algorithm
improvement, pointclouds distortion correction, estimation speed
improvement by Open-MP implementation
● 3D objects class recognition and shape estimation
● Performance improvement of dynamic objects tracking
● Moving path prediction of dynamic objects by using map
information
● 360-degree sensing by the camera-LiDAR fusion
● Automatic lane change planning & decision
● Object avoidance (with lane change/ in the same lane)
● Intersection support (consider the oncoming vehicles and
crossing vehicles)
● Person recognition at pedestrian crossing
42
Achievements (2/2)
● Performance improvement of the traffic light recognition
● Blind spot check when turning right/left
● Route generation from current position to a destination (via
specified passing points)
○ With this feature, “Go Home button” can be implemented
● Automatic parking
● Slope support
● Slow / rapid brake planning support
● Performance improvement of the vehicle control
● Automatic deceleration at curve
● Collision judgement considering a vehicle shape

Weitere ähnliche Inhalte

Was ist angesagt?

第1回ROS勉強会発表資料 ROS+Gazeboではじめるロボットシミュレーション
第1回ROS勉強会発表資料 ROS+Gazeboではじめるロボットシミュレーション第1回ROS勉強会発表資料 ROS+Gazeboではじめるロボットシミュレーション
第1回ROS勉強会発表資料 ROS+Gazeboではじめるロボットシミュレーションakio19937
 
SSII2019企画: 画像および LiDAR を用いた自動走行に関する動向
SSII2019企画: 画像および LiDAR を用いた自動走行に関する動向SSII2019企画: 画像および LiDAR を用いた自動走行に関する動向
SSII2019企画: 画像および LiDAR を用いた自動走行に関する動向SSII
 
Minecraft による強化学習の実践 (MineRL)
Minecraft による強化学習の実践 (MineRL)Minecraft による強化学習の実践 (MineRL)
Minecraft による強化学習の実践 (MineRL)Tusyoshi Matsuzaki
 
SSII2021 [TS1] Visual SLAM ~カメラ幾何の基礎から最近の技術動向まで~
SSII2021 [TS1] Visual SLAM ~カメラ幾何の基礎から最近の技術動向まで~SSII2021 [TS1] Visual SLAM ~カメラ幾何の基礎から最近の技術動向まで~
SSII2021 [TS1] Visual SLAM ~カメラ幾何の基礎から最近の技術動向まで~SSII
 
ROS2勉強会 4章前半
ROS2勉強会 4章前半ROS2勉強会 4章前半
ROS2勉強会 4章前半tomohiro kuwano
 
Scenario-Based Development & Testing for Autonomous Driving
Scenario-Based Development & Testing for Autonomous DrivingScenario-Based Development & Testing for Autonomous Driving
Scenario-Based Development & Testing for Autonomous DrivingYu Huang
 
ロボティクスにおける SLAM 手法と実用化例
ロボティクスにおける SLAM 手法と実用化例ロボティクスにおける SLAM 手法と実用化例
ロボティクスにおける SLAM 手法と実用化例Yoshitaka HARA
 
NEDO講座 MoveIt! チュートリアル 第1部
NEDO講座 MoveIt! チュートリアル 第1部NEDO講座 MoveIt! チュートリアル 第1部
NEDO講座 MoveIt! チュートリアル 第1部openrtm
 
オープンソース SLAM の分類
オープンソース SLAM の分類オープンソース SLAM の分類
オープンソース SLAM の分類Yoshitaka HARA
 
End to End Communication protection
End to End Communication protectionEnd to End Communication protection
End to End Communication protectionSibiKrishnan
 
Autoware: ROSを用いた一般道自動運転向けソフトウェアプラットフォーム
Autoware: ROSを用いた一般道自動運転向けソフトウェアプラットフォームAutoware: ROSを用いた一般道自動運転向けソフトウェアプラットフォーム
Autoware: ROSを用いた一般道自動運転向けソフトウェアプラットフォームTakuya Azumi
 
ROS を用いた自律移動ロボットのシステム構築
ROS を用いた自律移動ロボットのシステム構築ROS を用いた自律移動ロボットのシステム構築
ROS を用いた自律移動ロボットのシステム構築Yoshitaka HARA
 
AIのラボからロボティクスへ --- 東大松尾研究室のWRS2020パートナーロボットチャレンジへの挑戦
AIのラボからロボティクスへ --- 東大松尾研究室のWRS2020パートナーロボットチャレンジへの挑戦AIのラボからロボティクスへ --- 東大松尾研究室のWRS2020パートナーロボットチャレンジへの挑戦
AIのラボからロボティクスへ --- 東大松尾研究室のWRS2020パートナーロボットチャレンジへの挑戦Tatsuya Matsushima
 
生成系ニューラルネットワークまとめ Summary of Generative Neural Network
生成系ニューラルネットワークまとめ Summary of  Generative Neural Network生成系ニューラルネットワークまとめ Summary of  Generative Neural Network
生成系ニューラルネットワークまとめ Summary of Generative Neural NetworkYouichiro Miyake
 
3次元SLAMは誰でもできるよ。そう、TX2とTurtleBot3ならね。
3次元SLAMは誰でもできるよ。そう、TX2とTurtleBot3ならね。3次元SLAMは誰でもできるよ。そう、TX2とTurtleBot3ならね。
3次元SLAMは誰でもできるよ。そう、TX2とTurtleBot3ならね。ROBOTIS Japan
 
20190307 visualslam summary
20190307 visualslam summary20190307 visualslam summary
20190307 visualslam summaryTakuya Minagawa
 

Was ist angesagt? (20)

第1回ROS勉強会発表資料 ROS+Gazeboではじめるロボットシミュレーション
第1回ROS勉強会発表資料 ROS+Gazeboではじめるロボットシミュレーション第1回ROS勉強会発表資料 ROS+Gazeboではじめるロボットシミュレーション
第1回ROS勉強会発表資料 ROS+Gazeboではじめるロボットシミュレーション
 
SSII2019企画: 画像および LiDAR を用いた自動走行に関する動向
SSII2019企画: 画像および LiDAR を用いた自動走行に関する動向SSII2019企画: 画像および LiDAR を用いた自動走行に関する動向
SSII2019企画: 画像および LiDAR を用いた自動走行に関する動向
 
Minecraft による強化学習の実践 (MineRL)
Minecraft による強化学習の実践 (MineRL)Minecraft による強化学習の実践 (MineRL)
Minecraft による強化学習の実践 (MineRL)
 
SSII2021 [TS1] Visual SLAM ~カメラ幾何の基礎から最近の技術動向まで~
SSII2021 [TS1] Visual SLAM ~カメラ幾何の基礎から最近の技術動向まで~SSII2021 [TS1] Visual SLAM ~カメラ幾何の基礎から最近の技術動向まで~
SSII2021 [TS1] Visual SLAM ~カメラ幾何の基礎から最近の技術動向まで~
 
ROS2勉強会 4章前半
ROS2勉強会 4章前半ROS2勉強会 4章前半
ROS2勉強会 4章前半
 
Scenario-Based Development & Testing for Autonomous Driving
Scenario-Based Development & Testing for Autonomous DrivingScenario-Based Development & Testing for Autonomous Driving
Scenario-Based Development & Testing for Autonomous Driving
 
学ロボの制御
学ロボの制御学ロボの制御
学ロボの制御
 
ロボティクスにおける SLAM 手法と実用化例
ロボティクスにおける SLAM 手法と実用化例ロボティクスにおける SLAM 手法と実用化例
ロボティクスにおける SLAM 手法と実用化例
 
NEDO講座 MoveIt! チュートリアル 第1部
NEDO講座 MoveIt! チュートリアル 第1部NEDO講座 MoveIt! チュートリアル 第1部
NEDO講座 MoveIt! チュートリアル 第1部
 
オープンソース SLAM の分類
オープンソース SLAM の分類オープンソース SLAM の分類
オープンソース SLAM の分類
 
End to End Communication protection
End to End Communication protectionEnd to End Communication protection
End to End Communication protection
 
Autoware: ROSを用いた一般道自動運転向けソフトウェアプラットフォーム
Autoware: ROSを用いた一般道自動運転向けソフトウェアプラットフォームAutoware: ROSを用いた一般道自動運転向けソフトウェアプラットフォーム
Autoware: ROSを用いた一般道自動運転向けソフトウェアプラットフォーム
 
ROS を用いた自律移動ロボットのシステム構築
ROS を用いた自律移動ロボットのシステム構築ROS を用いた自律移動ロボットのシステム構築
ROS を用いた自律移動ロボットのシステム構築
 
AIのラボからロボティクスへ --- 東大松尾研究室のWRS2020パートナーロボットチャレンジへの挑戦
AIのラボからロボティクスへ --- 東大松尾研究室のWRS2020パートナーロボットチャレンジへの挑戦AIのラボからロボティクスへ --- 東大松尾研究室のWRS2020パートナーロボットチャレンジへの挑戦
AIのラボからロボティクスへ --- 東大松尾研究室のWRS2020パートナーロボットチャレンジへの挑戦
 
生成系ニューラルネットワークまとめ Summary of Generative Neural Network
生成系ニューラルネットワークまとめ Summary of  Generative Neural Network生成系ニューラルネットワークまとめ Summary of  Generative Neural Network
生成系ニューラルネットワークまとめ Summary of Generative Neural Network
 
3次元SLAMは誰でもできるよ。そう、TX2とTurtleBot3ならね。
3次元SLAMは誰でもできるよ。そう、TX2とTurtleBot3ならね。3次元SLAMは誰でもできるよ。そう、TX2とTurtleBot3ならね。
3次元SLAMは誰でもできるよ。そう、TX2とTurtleBot3ならね。
 
5分でわかる Sensor SDK
5分でわかる Sensor SDK5分でわかる Sensor SDK
5分でわかる Sensor SDK
 
20190307 visualslam summary
20190307 visualslam summary20190307 visualslam summary
20190307 visualslam summary
 
Visual slam
Visual slamVisual slam
Visual slam
 
Survey 1 (project overview)
Survey 1 (project overview)Survey 1 (project overview)
Survey 1 (project overview)
 

Ähnlich wie Autoware Architecture Proposal

2018.07 Self-driving cars meetup
2018.07 Self-driving cars meetup2018.07 Self-driving cars meetup
2018.07 Self-driving cars meetupPunnu Phairatt
 
toyota-Challenges towards New Software Platform for Automated Driving.pdf
toyota-Challenges towards New Software Platform for Automated Driving.pdftoyota-Challenges towards New Software Platform for Automated Driving.pdf
toyota-Challenges towards New Software Platform for Automated Driving.pdfxmumiao
 
"Micro-frontends from A to Z. How and Why we use Micro-frontends in Namecheap...
"Micro-frontends from A to Z. How and Why we use Micro-frontends in Namecheap..."Micro-frontends from A to Z. How and Why we use Micro-frontends in Namecheap...
"Micro-frontends from A to Z. How and Why we use Micro-frontends in Namecheap...Fwdays
 
mago3D FOSS4G NA 2018
mago3D FOSS4G NA 2018mago3D FOSS4G NA 2018
mago3D FOSS4G NA 2018정대 천
 
IRJET- Front View Identification of Vehicles by using Machine Learning Te...
IRJET-  	  Front View Identification of Vehicles by using Machine Learning Te...IRJET-  	  Front View Identification of Vehicles by using Machine Learning Te...
IRJET- Front View Identification of Vehicles by using Machine Learning Te...IRJET Journal
 
Webinar1 darpa07
Webinar1 darpa07Webinar1 darpa07
Webinar1 darpa07MKGJUICE
 
“Autonomous Driving AI Workloads: Technology Trends and Optimization Strategi...
“Autonomous Driving AI Workloads: Technology Trends and Optimization Strategi...“Autonomous Driving AI Workloads: Technology Trends and Optimization Strategi...
“Autonomous Driving AI Workloads: Technology Trends and Optimization Strategi...Edge AI and Vision Alliance
 
deep-reinforcement-learning-framework.pdf
deep-reinforcement-learning-framework.pdfdeep-reinforcement-learning-framework.pdf
deep-reinforcement-learning-framework.pdfYugank Aman
 
Autonomous Vehicle Simulation Project
Autonomous Vehicle Simulation ProjectAutonomous Vehicle Simulation Project
Autonomous Vehicle Simulation ProjectSangho LEE
 
Shaping serverless architecture with domain driven design patterns
Shaping serverless architecture with domain driven design patternsShaping serverless architecture with domain driven design patterns
Shaping serverless architecture with domain driven design patternsShimon Tolts
 
Shaping serverless architecture with domain driven design patterns
Shaping serverless architecture with domain driven design patternsShaping serverless architecture with domain driven design patterns
Shaping serverless architecture with domain driven design patternsAsher Sterkin
 
Model Execution and System Simulation
Model Execution and System SimulationModel Execution and System Simulation
Model Execution and System SimulationObeo
 
[Capella Day 2019] Model execution and system simulation in Capella
[Capella Day 2019] Model execution and system simulation in Capella[Capella Day 2019] Model execution and system simulation in Capella
[Capella Day 2019] Model execution and system simulation in CapellaObeo
 
Resume-Rohit_Vijay_Bapat_December_2016
Resume-Rohit_Vijay_Bapat_December_2016Resume-Rohit_Vijay_Bapat_December_2016
Resume-Rohit_Vijay_Bapat_December_2016Rohit Bapat
 
Mercedes - Autonomous Driving - The S500 Intelligent drive
Mercedes - Autonomous Driving - The S500 Intelligent driveMercedes - Autonomous Driving - The S500 Intelligent drive
Mercedes - Autonomous Driving - The S500 Intelligent driveGonzague Dambricourt
 
[Unite Seoul 2019] Mali GPU Architecture and Mobile Studio
[Unite Seoul 2019] Mali GPU Architecture and Mobile Studio [Unite Seoul 2019] Mali GPU Architecture and Mobile Studio
[Unite Seoul 2019] Mali GPU Architecture and Mobile Studio Owen Wu
 
'Architecture of modern frontend apps' by YURIY DOBRYANSKYY at OdessaJS'2020
'Architecture of modern frontend apps' by YURIY DOBRYANSKYY at OdessaJS'2020'Architecture of modern frontend apps' by YURIY DOBRYANSKYY at OdessaJS'2020
'Architecture of modern frontend apps' by YURIY DOBRYANSKYY at OdessaJS'2020OdessaJS Conf
 

Ähnlich wie Autoware Architecture Proposal (20)

Embedded ppt
Embedded pptEmbedded ppt
Embedded ppt
 
2018.07 Self-driving cars meetup
2018.07 Self-driving cars meetup2018.07 Self-driving cars meetup
2018.07 Self-driving cars meetup
 
Slides SDC Controls
Slides SDC ControlsSlides SDC Controls
Slides SDC Controls
 
toyota-Challenges towards New Software Platform for Automated Driving.pdf
toyota-Challenges towards New Software Platform for Automated Driving.pdftoyota-Challenges towards New Software Platform for Automated Driving.pdf
toyota-Challenges towards New Software Platform for Automated Driving.pdf
 
"Micro-frontends from A to Z. How and Why we use Micro-frontends in Namecheap...
"Micro-frontends from A to Z. How and Why we use Micro-frontends in Namecheap..."Micro-frontends from A to Z. How and Why we use Micro-frontends in Namecheap...
"Micro-frontends from A to Z. How and Why we use Micro-frontends in Namecheap...
 
Mechatronics engineer
Mechatronics engineerMechatronics engineer
Mechatronics engineer
 
mago3D FOSS4G NA 2018
mago3D FOSS4G NA 2018mago3D FOSS4G NA 2018
mago3D FOSS4G NA 2018
 
IRJET- Front View Identification of Vehicles by using Machine Learning Te...
IRJET-  	  Front View Identification of Vehicles by using Machine Learning Te...IRJET-  	  Front View Identification of Vehicles by using Machine Learning Te...
IRJET- Front View Identification of Vehicles by using Machine Learning Te...
 
Webinar1 darpa07
Webinar1 darpa07Webinar1 darpa07
Webinar1 darpa07
 
“Autonomous Driving AI Workloads: Technology Trends and Optimization Strategi...
“Autonomous Driving AI Workloads: Technology Trends and Optimization Strategi...“Autonomous Driving AI Workloads: Technology Trends and Optimization Strategi...
“Autonomous Driving AI Workloads: Technology Trends and Optimization Strategi...
 
deep-reinforcement-learning-framework.pdf
deep-reinforcement-learning-framework.pdfdeep-reinforcement-learning-framework.pdf
deep-reinforcement-learning-framework.pdf
 
Autonomous Vehicle Simulation Project
Autonomous Vehicle Simulation ProjectAutonomous Vehicle Simulation Project
Autonomous Vehicle Simulation Project
 
Shaping serverless architecture with domain driven design patterns
Shaping serverless architecture with domain driven design patternsShaping serverless architecture with domain driven design patterns
Shaping serverless architecture with domain driven design patterns
 
Shaping serverless architecture with domain driven design patterns
Shaping serverless architecture with domain driven design patternsShaping serverless architecture with domain driven design patterns
Shaping serverless architecture with domain driven design patterns
 
Model Execution and System Simulation
Model Execution and System SimulationModel Execution and System Simulation
Model Execution and System Simulation
 
[Capella Day 2019] Model execution and system simulation in Capella
[Capella Day 2019] Model execution and system simulation in Capella[Capella Day 2019] Model execution and system simulation in Capella
[Capella Day 2019] Model execution and system simulation in Capella
 
Resume-Rohit_Vijay_Bapat_December_2016
Resume-Rohit_Vijay_Bapat_December_2016Resume-Rohit_Vijay_Bapat_December_2016
Resume-Rohit_Vijay_Bapat_December_2016
 
Mercedes - Autonomous Driving - The S500 Intelligent drive
Mercedes - Autonomous Driving - The S500 Intelligent driveMercedes - Autonomous Driving - The S500 Intelligent drive
Mercedes - Autonomous Driving - The S500 Intelligent drive
 
[Unite Seoul 2019] Mali GPU Architecture and Mobile Studio
[Unite Seoul 2019] Mali GPU Architecture and Mobile Studio [Unite Seoul 2019] Mali GPU Architecture and Mobile Studio
[Unite Seoul 2019] Mali GPU Architecture and Mobile Studio
 
'Architecture of modern frontend apps' by YURIY DOBRYANSKYY at OdessaJS'2020
'Architecture of modern frontend apps' by YURIY DOBRYANSKYY at OdessaJS'2020'Architecture of modern frontend apps' by YURIY DOBRYANSKYY at OdessaJS'2020
'Architecture of modern frontend apps' by YURIY DOBRYANSKYY at OdessaJS'2020
 

Mehr von Tier_IV

自動運転技術を活用した運転技能教習システムのご紹介
自動運転技術を活用した運転技能教習システムのご紹介自動運転技術を活用した運転技能教習システムのご紹介
自動運転技術を活用した運転技能教習システムのご紹介Tier_IV
 
自動運転技術を活用した運転技能教習システムの開発
自動運転技術を活用した運転技能教習システムの開発自動運転技術を活用した運転技能教習システムの開発
自動運転技術を活用した運転技能教習システムの開発Tier_IV
 
自動運転業界のSRE活動
自動運転業界のSRE活動自動運転業界のSRE活動
自動運転業界のSRE活動Tier_IV
 
トランクベース開発を活用して爆速に開発した話
トランクベース開発を活用して爆速に開発した話トランクベース開発を活用して爆速に開発した話
トランクベース開発を活用して爆速に開発した話Tier_IV
 
自動運転の会社でなぜデータ基盤が必要なのか?そこで今やっていること
自動運転の会社でなぜデータ基盤が必要なのか?そこで今やっていること自動運転の会社でなぜデータ基盤が必要なのか?そこで今やっていること
自動運転の会社でなぜデータ基盤が必要なのか?そこで今やっていることTier_IV
 
AWS X-Rayを使ったマイクロサービスのトレーサビリティ向上
AWS X-Rayを使ったマイクロサービスのトレーサビリティ向上AWS X-Rayを使ったマイクロサービスのトレーサビリティ向上
AWS X-Rayを使ったマイクロサービスのトレーサビリティ向上Tier_IV
 
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割Tier_IV
 
Tier Ⅳ Tech Meetup #2 - 自動運転を作るのはCloudシステムの集合体?? 活用技術を大解剖 -
Tier Ⅳ Tech Meetup #2 - 自動運転を作るのはCloudシステムの集合体?? 活用技術を大解剖 -Tier Ⅳ Tech Meetup #2 - 自動運転を作るのはCloudシステムの集合体?? 活用技術を大解剖 -
Tier Ⅳ Tech Meetup #2 - 自動運転を作るのはCloudシステムの集合体?? 活用技術を大解剖 -Tier_IV
 
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割Tier_IV
 
Self-Driving System with IoT
Self-Driving System with IoTSelf-Driving System with IoT
Self-Driving System with IoTTier_IV
 
Mobilitydev2019 10 31_slideshare
Mobilitydev2019 10 31_slideshareMobilitydev2019 10 31_slideshare
Mobilitydev2019 10 31_slideshareTier_IV
 

Mehr von Tier_IV (11)

自動運転技術を活用した運転技能教習システムのご紹介
自動運転技術を活用した運転技能教習システムのご紹介自動運転技術を活用した運転技能教習システムのご紹介
自動運転技術を活用した運転技能教習システムのご紹介
 
自動運転技術を活用した運転技能教習システムの開発
自動運転技術を活用した運転技能教習システムの開発自動運転技術を活用した運転技能教習システムの開発
自動運転技術を活用した運転技能教習システムの開発
 
自動運転業界のSRE活動
自動運転業界のSRE活動自動運転業界のSRE活動
自動運転業界のSRE活動
 
トランクベース開発を活用して爆速に開発した話
トランクベース開発を活用して爆速に開発した話トランクベース開発を活用して爆速に開発した話
トランクベース開発を活用して爆速に開発した話
 
自動運転の会社でなぜデータ基盤が必要なのか?そこで今やっていること
自動運転の会社でなぜデータ基盤が必要なのか?そこで今やっていること自動運転の会社でなぜデータ基盤が必要なのか?そこで今やっていること
自動運転の会社でなぜデータ基盤が必要なのか?そこで今やっていること
 
AWS X-Rayを使ったマイクロサービスのトレーサビリティ向上
AWS X-Rayを使ったマイクロサービスのトレーサビリティ向上AWS X-Rayを使ったマイクロサービスのトレーサビリティ向上
AWS X-Rayを使ったマイクロサービスのトレーサビリティ向上
 
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
 
Tier Ⅳ Tech Meetup #2 - 自動運転を作るのはCloudシステムの集合体?? 活用技術を大解剖 -
Tier Ⅳ Tech Meetup #2 - 自動運転を作るのはCloudシステムの集合体?? 活用技術を大解剖 -Tier Ⅳ Tech Meetup #2 - 自動運転を作るのはCloudシステムの集合体?? 活用技術を大解剖 -
Tier Ⅳ Tech Meetup #2 - 自動運転を作るのはCloudシステムの集合体?? 活用技術を大解剖 -
 
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
Unity x 自動運転シミュレーション、自動運転におけるGame Engineの役割
 
Self-Driving System with IoT
Self-Driving System with IoTSelf-Driving System with IoT
Self-Driving System with IoT
 
Mobilitydev2019 10 31_slideshare
Mobilitydev2019 10 31_slideshareMobilitydev2019 10 31_slideshare
Mobilitydev2019 10 31_slideshare
 

Kürzlich hochgeladen

Top profile Call Girls In Darbhanga [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Darbhanga [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Darbhanga [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Darbhanga [ 7014168258 ] Call Me For Genuine Models...nirzagarg
 
Vip Begusarai Escorts Service Girl ^ 9332606886, WhatsApp Anytime Begusarai
Vip Begusarai Escorts Service Girl ^ 9332606886, WhatsApp Anytime BegusaraiVip Begusarai Escorts Service Girl ^ 9332606886, WhatsApp Anytime Begusarai
Vip Begusarai Escorts Service Girl ^ 9332606886, WhatsApp Anytime Begusaraimeghakumariji156
 
一比一原版(UdeM学位证书)蒙特利尔大学毕业证学历认证怎样办
一比一原版(UdeM学位证书)蒙特利尔大学毕业证学历认证怎样办一比一原版(UdeM学位证书)蒙特利尔大学毕业证学历认证怎样办
一比一原版(UdeM学位证书)蒙特利尔大学毕业证学历认证怎样办ezgenuh
 
What Does It Mean When Mercedes Says 'ESP Inoperative See Owner's Manual'
What Does It Mean When Mercedes Says 'ESP Inoperative See Owner's Manual'What Does It Mean When Mercedes Says 'ESP Inoperative See Owner's Manual'
What Does It Mean When Mercedes Says 'ESP Inoperative See Owner's Manual'Euromotive Performance
 
+97470301568>>buy vape oil,thc oil weed,hash and cannabis oil in qatar doha}}
+97470301568>>buy vape oil,thc oil weed,hash and cannabis oil in qatar doha}}+97470301568>>buy vape oil,thc oil weed,hash and cannabis oil in qatar doha}}
+97470301568>>buy vape oil,thc oil weed,hash and cannabis oil in qatar doha}}Health
 
John Deere Tractors 5415 Diagnostic Repair Service Manual.pdf
John Deere Tractors 5415 Diagnostic Repair Service Manual.pdfJohn Deere Tractors 5415 Diagnostic Repair Service Manual.pdf
John Deere Tractors 5415 Diagnostic Repair Service Manual.pdfExcavator
 
Top profile Call Girls In Mangalore [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Mangalore [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Mangalore [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Mangalore [ 7014168258 ] Call Me For Genuine Models...gajnagarg
 
如何办理多伦多大学毕业证(UofT毕业证书)成绩单原版一比一
如何办理多伦多大学毕业证(UofT毕业证书)成绩单原版一比一如何办理多伦多大学毕业证(UofT毕业证书)成绩单原版一比一
如何办理多伦多大学毕业证(UofT毕业证书)成绩单原版一比一opyff
 
9352852248 Call Girls Gota Escort Service Available 24×7 In Gota
9352852248 Call Girls  Gota Escort Service Available 24×7 In Gota9352852248 Call Girls  Gota Escort Service Available 24×7 In Gota
9352852248 Call Girls Gota Escort Service Available 24×7 In Gotagargpaaro
 
Is Your BMW PDC Malfunctioning Discover How to Easily Reset It
Is Your BMW PDC Malfunctioning Discover How to Easily Reset ItIs Your BMW PDC Malfunctioning Discover How to Easily Reset It
Is Your BMW PDC Malfunctioning Discover How to Easily Reset ItEuroService Automotive
 
Muslim Call Girls Churchgate WhatsApp +91-9930687706, Best Service
Muslim Call Girls Churchgate WhatsApp +91-9930687706, Best ServiceMuslim Call Girls Churchgate WhatsApp +91-9930687706, Best Service
Muslim Call Girls Churchgate WhatsApp +91-9930687706, Best Servicemeghakumariji156
 
如何办理新西兰林肯大学毕业证(Lincoln毕业证书)成绩单原版一比一
如何办理新西兰林肯大学毕业证(Lincoln毕业证书)成绩单原版一比一如何办理新西兰林肯大学毕业证(Lincoln毕业证书)成绩单原版一比一
如何办理新西兰林肯大学毕业证(Lincoln毕业证书)成绩单原版一比一opyff
 
Premium Call Girls Nagpur Call Girls (Adult Only) 💯Call Us 🔝 6378878445 🔝 💃 E...
Premium Call Girls Nagpur Call Girls (Adult Only) 💯Call Us 🔝 6378878445 🔝 💃 E...Premium Call Girls Nagpur Call Girls (Adult Only) 💯Call Us 🔝 6378878445 🔝 💃 E...
Premium Call Girls Nagpur Call Girls (Adult Only) 💯Call Us 🔝 6378878445 🔝 💃 E...vershagrag
 
Why Does My Porsche Cayenne's Exhaust Sound So Loud
Why Does My Porsche Cayenne's Exhaust Sound So LoudWhy Does My Porsche Cayenne's Exhaust Sound So Loud
Why Does My Porsche Cayenne's Exhaust Sound So LoudRoyalty Auto Service
 
Effortless Driving Experience Premier Mercedes Sprinter Suspension Service
Effortless Driving Experience Premier Mercedes Sprinter Suspension ServiceEffortless Driving Experience Premier Mercedes Sprinter Suspension Service
Effortless Driving Experience Premier Mercedes Sprinter Suspension ServiceSprinter Gurus
 
Is Your Mercedes Benz Trunk Refusing To Close Here's What Might Be Wrong
Is Your Mercedes Benz Trunk Refusing To Close Here's What Might Be WrongIs Your Mercedes Benz Trunk Refusing To Close Here's What Might Be Wrong
Is Your Mercedes Benz Trunk Refusing To Close Here's What Might Be WrongMomentum Motorworks
 
Nangloi Jat Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nangloi Jat
Nangloi Jat Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nangloi JatNangloi Jat Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nangloi Jat
Nangloi Jat Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nangloi Jatmeghakumariji156
 
一比一原版伯明翰城市大学毕业证成绩单留信学历认证
一比一原版伯明翰城市大学毕业证成绩单留信学历认证一比一原版伯明翰城市大学毕业证成绩单留信学历认证
一比一原版伯明翰城市大学毕业证成绩单留信学历认证62qaf0hi
 
CELLULAR RESPIRATION. Helpful slides for
CELLULAR RESPIRATION. Helpful slides forCELLULAR RESPIRATION. Helpful slides for
CELLULAR RESPIRATION. Helpful slides foreuphemism22
 

Kürzlich hochgeladen (20)

Top profile Call Girls In Darbhanga [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Darbhanga [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Darbhanga [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Darbhanga [ 7014168258 ] Call Me For Genuine Models...
 
Vip Begusarai Escorts Service Girl ^ 9332606886, WhatsApp Anytime Begusarai
Vip Begusarai Escorts Service Girl ^ 9332606886, WhatsApp Anytime BegusaraiVip Begusarai Escorts Service Girl ^ 9332606886, WhatsApp Anytime Begusarai
Vip Begusarai Escorts Service Girl ^ 9332606886, WhatsApp Anytime Begusarai
 
一比一原版(UdeM学位证书)蒙特利尔大学毕业证学历认证怎样办
一比一原版(UdeM学位证书)蒙特利尔大学毕业证学历认证怎样办一比一原版(UdeM学位证书)蒙特利尔大学毕业证学历认证怎样办
一比一原版(UdeM学位证书)蒙特利尔大学毕业证学历认证怎样办
 
What Does It Mean When Mercedes Says 'ESP Inoperative See Owner's Manual'
What Does It Mean When Mercedes Says 'ESP Inoperative See Owner's Manual'What Does It Mean When Mercedes Says 'ESP Inoperative See Owner's Manual'
What Does It Mean When Mercedes Says 'ESP Inoperative See Owner's Manual'
 
+97470301568>>buy vape oil,thc oil weed,hash and cannabis oil in qatar doha}}
+97470301568>>buy vape oil,thc oil weed,hash and cannabis oil in qatar doha}}+97470301568>>buy vape oil,thc oil weed,hash and cannabis oil in qatar doha}}
+97470301568>>buy vape oil,thc oil weed,hash and cannabis oil in qatar doha}}
 
John Deere Tractors 5415 Diagnostic Repair Service Manual.pdf
John Deere Tractors 5415 Diagnostic Repair Service Manual.pdfJohn Deere Tractors 5415 Diagnostic Repair Service Manual.pdf
John Deere Tractors 5415 Diagnostic Repair Service Manual.pdf
 
Top profile Call Girls In Mangalore [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Mangalore [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Mangalore [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Mangalore [ 7014168258 ] Call Me For Genuine Models...
 
如何办理多伦多大学毕业证(UofT毕业证书)成绩单原版一比一
如何办理多伦多大学毕业证(UofT毕业证书)成绩单原版一比一如何办理多伦多大学毕业证(UofT毕业证书)成绩单原版一比一
如何办理多伦多大学毕业证(UofT毕业证书)成绩单原版一比一
 
9352852248 Call Girls Gota Escort Service Available 24×7 In Gota
9352852248 Call Girls  Gota Escort Service Available 24×7 In Gota9352852248 Call Girls  Gota Escort Service Available 24×7 In Gota
9352852248 Call Girls Gota Escort Service Available 24×7 In Gota
 
Is Your BMW PDC Malfunctioning Discover How to Easily Reset It
Is Your BMW PDC Malfunctioning Discover How to Easily Reset ItIs Your BMW PDC Malfunctioning Discover How to Easily Reset It
Is Your BMW PDC Malfunctioning Discover How to Easily Reset It
 
Muslim Call Girls Churchgate WhatsApp +91-9930687706, Best Service
Muslim Call Girls Churchgate WhatsApp +91-9930687706, Best ServiceMuslim Call Girls Churchgate WhatsApp +91-9930687706, Best Service
Muslim Call Girls Churchgate WhatsApp +91-9930687706, Best Service
 
如何办理新西兰林肯大学毕业证(Lincoln毕业证书)成绩单原版一比一
如何办理新西兰林肯大学毕业证(Lincoln毕业证书)成绩单原版一比一如何办理新西兰林肯大学毕业证(Lincoln毕业证书)成绩单原版一比一
如何办理新西兰林肯大学毕业证(Lincoln毕业证书)成绩单原版一比一
 
Abortion pills Dubai (+918133066128) Cytotec 200mg pills UAE Abudhabi
Abortion pills Dubai (+918133066128) Cytotec 200mg pills UAE AbudhabiAbortion pills Dubai (+918133066128) Cytotec 200mg pills UAE Abudhabi
Abortion pills Dubai (+918133066128) Cytotec 200mg pills UAE Abudhabi
 
Premium Call Girls Nagpur Call Girls (Adult Only) 💯Call Us 🔝 6378878445 🔝 💃 E...
Premium Call Girls Nagpur Call Girls (Adult Only) 💯Call Us 🔝 6378878445 🔝 💃 E...Premium Call Girls Nagpur Call Girls (Adult Only) 💯Call Us 🔝 6378878445 🔝 💃 E...
Premium Call Girls Nagpur Call Girls (Adult Only) 💯Call Us 🔝 6378878445 🔝 💃 E...
 
Why Does My Porsche Cayenne's Exhaust Sound So Loud
Why Does My Porsche Cayenne's Exhaust Sound So LoudWhy Does My Porsche Cayenne's Exhaust Sound So Loud
Why Does My Porsche Cayenne's Exhaust Sound So Loud
 
Effortless Driving Experience Premier Mercedes Sprinter Suspension Service
Effortless Driving Experience Premier Mercedes Sprinter Suspension ServiceEffortless Driving Experience Premier Mercedes Sprinter Suspension Service
Effortless Driving Experience Premier Mercedes Sprinter Suspension Service
 
Is Your Mercedes Benz Trunk Refusing To Close Here's What Might Be Wrong
Is Your Mercedes Benz Trunk Refusing To Close Here's What Might Be WrongIs Your Mercedes Benz Trunk Refusing To Close Here's What Might Be Wrong
Is Your Mercedes Benz Trunk Refusing To Close Here's What Might Be Wrong
 
Nangloi Jat Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nangloi Jat
Nangloi Jat Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nangloi JatNangloi Jat Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nangloi Jat
Nangloi Jat Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nangloi Jat
 
一比一原版伯明翰城市大学毕业证成绩单留信学历认证
一比一原版伯明翰城市大学毕业证成绩单留信学历认证一比一原版伯明翰城市大学毕业证成绩单留信学历认证
一比一原版伯明翰城市大学毕业证成绩单留信学历认证
 
CELLULAR RESPIRATION. Helpful slides for
CELLULAR RESPIRATION. Helpful slides forCELLULAR RESPIRATION. Helpful slides for
CELLULAR RESPIRATION. Helpful slides for
 

Autoware Architecture Proposal

  • 1. Architecture proposal for AWF by Tier IV Inc. 2019. .172020.03 Version 1.0 Autoware Architecture Proposal
  • 3. Here is subtitle Requirement 01 Why we need a new architecture 1
  • 4. 4 4 Why we need a new architecture Problem ● It’s diffcult to improve Autoware.AI capabilities Why? ● No concrete architecture design ● A lot of technical debt ○ Tight coupling between modules ○ Unclear responsibility of modules Tier IV's proposal ● Define a layered architecture ● Clarify the role of each module ● Simplify the interface between modules
  • 6. 6 6 Considered use cases Example use cases that were considered during architecture design: Features that are not considered yet (for the sake of development speed) ● Real-time processing ● HMI / Fail safe / Redundant system / State monitoring system / etc… Will consider these items at AWF WGs Module Use cases Sensing ● 360-degree sensing by the camera-LiDAR fusion Perception ● Recognition of dynamic objects and traffic lights Localization ● Robust Localization using multiple data sources Planning ● Route planning, dynamic planning based on vector map (not only waypoint following) ● Automatic parking ● Object avoidance Control ● High control performance on many kinds of vehicle-controllers
  • 7. 7 7 Demo video Module Contents Whole Scenario demo Sensing+Perception 360° FOV, Prediction Localization Robustness of localization, Return from error Planning Lane change, Obstacle avoid, Parking Control Slow brake (normal stop), Rapid brake (emergency stop)
  • 8. Here is subtitle Requirement 01 Architecture overview 3 Layered architecture High level introduction of each module
  • 9. 9 Map Sensor Vehicle Autoware DRAFT: https://github.com/tier4/Autoware_architecture_proposal Control Sensing Detection Tracking Prediction Mission Detection Classifier Traffic light Perception Dynamic object Planning Scenario Vehicle command Vehicle sensorMap dataSensor data Surrounding environment Trajectory Current pose/velocity Scenario selector Parking Lane following etc. Vehicle interface Perception Planning Map Localization steering/velocity feedback
  • 10. 10 Map Sensor Vehicle Autoware DRAFT: https://github.com/tier4/Autoware_architecture_proposal Control Sensing Detection Tracking Prediction Mission Detection Classifier Traffic light Perception Dynamic object Planning Scenario Vehicle command Vehicle sensorMap dataSensor data Surrounding environment Trajectory Current pose/velocity Scenario selector Parking Lane following etc. Vehicle interfaceMap steering/velocity feedback Detection Tracking Prediction Mission Detection Classifier Traffic light Perception Dynamic object Planning Scenario Scenario selector Parking Lane Driving etc. Localization
  • 11. 11 Map Sensor Vehicle Autoware DRAFT: https://github.com/tier4/Autoware_architecture_proposal Control Sensing Detection Tracking Prediction Mission Detection Classifier Traffic light Perception Dynamic object Planning Scenario Vehicle command Vehicle sensorMap dataSensor data Surrounding environment Trajectory Current pose/velocity Scenario selector Parking Lane following etc. Vehicle interfaceMap Localization steering/velocity feedback Detection Tracking Prediction Mission Detection Classifier Traffic light Perception Dynamic object Planning Scenario Scenario selector Parking Lane following etc.
  • 12. 12 [Architecture] Sensing Camera driver GNSS driver IMU driver Localization Perception Planning LiDAR driver Pointcloud preprocessor /sensing/gnss/[name]/ pose_with_covariance /sensing/imu/[name]/imu_raw /sensing/lidar/pointcloud /sensing/lidar/ no_ground/pointcloud Sensing GNSS preprocessor IMU preprocessor Camera preprocessor /sensing/camera/ [name]/image_raw Design Doc Role : Conversion of sensing data to ROS message Driver Preprocessor Examples of preprocessors ● Distortion correction ● Outlier filter ● Concat filter ● Ground filter ROS drivers (mainly from upstream)
  • 13. 13 [Architecture] Map Map Pointcloud map Vector map Pointcloud map loader Vector map loader PerceptionLocalization Planning Design Doc Conversion to on-memory data structure Coordinate transformation Map library Map libraryMap library Map is distributed as a single message, and accessed through library API Role : Distribute static environment information to other modules
  • 14. 14 [Architecture] Localization Pose twist fusion filter GNSS LiDAR (Camera) CAN IMU tf (map to base_link) twist Localization TwistWith Covariance.msg Pose Estimator Pose estimator PoseWith Covariance.msg Pose Estimator Twist estimator Support multiple localization methods based on different sensors(LiDAR/Camera/GNSS) Fuse pose and twist (e.g.EKF) Merge sensor inputs Design Doc Role : Integration of each sensor data and estimation of self-pose and self-twist
  • 15. 15 [Architecture] Perception Perception Detection Classifier TrackingDetection Prediction Sensor data (e.g. Camera, LiDAR) Sensor data (e.g. Camera, LiDAR) Map Dynamic object Traffic light 15 DynamicObjectArray.msg TrafficLightStateArray.msg Map Dynamic object’s information including: ● ID ● Semantic (label, confidence) ● Shape ● State (pose, velocity, acceleration, predicted path, etc) Traffic light’s information including: ● State (red, green, yellow, etc) Could be customized for unique traffic light types. Design Doc Role : Dynamic object recognition and traffic light recognition
  • 16. 16 [Architecture] Planning Mission planning Planning Scenario planning Scenario selector Route.msg Trajectory.msg ParkingOn road etc. Select Route planning from vector map Selects appropriate module depending on situation Moduled scenarios allow: ● distributed development ● Easier parameter tuning per situation Dynamic objects Traffic lights Map Obstacles tf(map to base_link) Design Doc Role : From a calculation of the route to the goal to drive trajectory generation
  • 17. 17 [Architecture] Control VehicleCmd.msg (autoware.ai) ----------------------------------------- header steer_cmd -header -steer accel_cmd -header -accel brake_cmd -header -brake gear twist_cmd -header -linear -angular ctrl_cmd -linear velocity -linear acceleration -steering angle VehicleCommand.msg (proposed architecture) ----------------------------------------- header control -steering angle -velocity -steering angle velocity -acceleration shift -data Remove redundant output VehicleStatus.msg Support low level control Generate signals for trajectory following Final gateway for commands to vehicle: ● engage ● acceleration limits ● etc Vehicle cmd gate Trajectory.msg Vehicle Command.msg RemoteCmdEngage Control Trajectory follower ControlCommand Stamped.msg Vehicle velocity Steer angle Design Doc Role : Generation of control signals to drive a vehicle following trajectories
  • 18. Here is subtitle Requirement 01 Contribution steps to Autoware community 4
  • 19. 19 Detailed doc Sample impl Today's presentation Contribution steps to Autoware community End of December Autonomous Valet Parking Architecture clean up Technical debt clean up Documentation clean up Architecture discussion and refinement at Discourse and GitLab Design additional modules(mainly related to Safety) Architecture validation in real-environment Develop cutting edge features Next ODD development Design and implement new architecture Feb. Jan.Mar. Apr. Mai. Jun. Jul. Aug. Sep. Oct. Nov. Dec. AWF (Including Tier IV) Tier IV Architecture proposal Documentation writing Clean up sample impl Feedback design and sample impl
  • 21. 21 21 Conclusion ● We proposed a new architecture of Autoware ● Tier IV will contribute our achievements to Autoware community ○ Detailed design documents ○ Reference source code ● We would like to discuss the new architecture at WGs ○ Any feedback is welcome ● We will make an effort to implement the new architecture in Autoware.Auto
  • 23. 23 23 Appendix - Table of Contents ● Design alternative ● Module implementation ○ Implementation details ○ Achevements
  • 24. 24 24 Appendix - Table of Contents ● Design alternative ● Module implementation ○ Implementation details ○ Achevements
  • 25. 25 Pre-study of the planning architecture Type Structure Pros. Cons. BOSS type (Junior type) ・Structure is intuitive and easy to understand. ・Easy to handle separately. ・Behavior has to make a conservative decision in order to reduce discrepancies with a motion’s decision. CMU Dr. paper type ・It solves and optimizes both behavior and motion simultaneously to overcome a cons. of the BOSS type. ・Difficult to improve if any issue was found. ・Optimization of the whole autonomous driving functions is not realistic.. Victor Tango type ・Behavior and motion are tightly coupled to overcome a cons. of the BOSS type. ・Easy to improve if any issue was found ・Difficult to take a new research result into the modules. Apollo type ・Scenario is one layer upper concept. ・We can adopt prefered types of the planning structure according to each scenario. ・In the scenario, cons. such as things described above are still remained. ・If scenarios increased, switching mechanism can be complicated. [Design alternative] Planning (1/2) TrajectoryMission BehaviorMission Motion Scenario Mission Scenario ︙ 25 BehaviorMission Motion
  • 26. 26 [Design alternative] Planning (2/2) Mission ** scenario ︙ Finally, we adopted Apollo + Boss type 26 Behavior Motion Free space Parking scenario On road scenario Lane following scenario : BOSS type ● It’s clear and convenient to develop as OSS Whole module : Apollo type ● New scenario can be added as needed Future challenge ● In lane following scenario, behavior still makes a conservative decision. And an aggressive driving like changing lane by entering into crowded lane cannot be executed.
  • 27. 27 27 Appendix - Table of Contents ● Design alternative ● Module implementation ○ Implementation details ○ Achevements
  • 28. 28 TF Tree The origin of MGRS coordinate The point projected vertically downwards from the center point of the rear wheel axle to the ground. The bottom of the velodyne_top map base_link aipxx velodyne_* camera_* imu_*gnss_* 28 Vehicle specified setting (Here is an example of Tier IV’s implementation)
  • 29. 29 [Sensing] Components Camera driver GNSS driver IMU driver Localization Perception Planning LiDAR driver Points preprocessor MGRS convertion /sensing/gnss/[name]/ pose_with_covariance /sensing/gnss/[name]/nav_sat_fix /sensing/imu/[name]/imu_raw /sensing/camera/ [name]/image_raw /sensing/lidar/pointcloud /sensing/lidar/ no_ground/pointcloud Sensing
  • 30. 30 30 [Sensing] Feature ● Distortion correction ○ Corrects a distortion of the pointclouds due to an observation time gap ⇨ Accuracy of the localization is improved ● Ground filter ○ Removes a ground from pointclouds (.ai has same feature) ● Outlier filter ○ Removes outliers by ring-base method ⇨ Reduce impacts of leaves and insects ● Concat filter ○ Integrates some pointclouds ○ Reduces an impact when a part of sensors stop ○ Corrects time gaps between each LiDAR with odometry ⇨ Accuracy of the localization is improved
  • 31. 31 Localization Pose Estimator Twist Estimator /localization/fusion_localizer/t wist DownSampler NDT Scan Matcher Pose Initializer IMU-VehicleTwist fuser Pose Twist Fusion Filter EKF Loader map Sensing Sensing Sensing IMU-GNSS-VehicleTwist fuser /sensing/imu/[name]/imu_raw /sensing/gnss/[name]/pose_with_covariance /sensing/lidar/pointcloud /map/pointcloud /tf Crop Measurement Range Localizer Diagnostics Localization System Diagnostic Node diagnostic /localization/diagnostic Safety NodeSafety Diagnostic Node diagnostic/vehicle/status/twist_with_covar iance [Localization] Components 31
  • 32. 32 32 [Localization] Feature ● Pose initializer ○ Automatic initial self position estimation by GNSS + Monte-Carlo method ● NDT scan matcher ○ Uses an estimated value of EKF as an initial position of the scan matching ⇨ If scan matching was failed, localization can be returned ○ Performance and accuracy are improved (Open-MP implementation, accuracy improvement of the initial position, improvement of the gradient method, distortion correction of pointclouds, and etc.) ● Scan matching failure judgement ○ Monitors statuses of scan matching based on a score ○ If score is lower than a threshold, an estimated result isn’t output ● EKF localization ○ Integrates the estimated self position of the scan matching and the velocity of CAN+IMU ○ If scan matching broke down, the vehicle can drive a certain distance with odometry only ● IMU Vehicle-twist fusion ○ Uses a translation velocity of CAN and yaw rate of IMU ⇨ Accuracy of odometry is improved ● Localizer Diagnostics ○ Monitors a status of a whole localization module (Temporary implementation) ※ Only NDT is implemented in Pose Estimator now.  In future, other estimators like a white line recognition based one will be added.
  • 33. 33 [Perception] Components 33 Loader Map /map/semantic Sensing Planning /sensing/camera/[name]/camera_info /planning/mission_planning/route Map based detection Detection Fine detection TrafficLightRoiArray /perception/traffic_light/rois Traffic Light Detection PointCloud Segmentation Image Detection Fusion Shape Estimation Tracking Multi Object Tracking Map Based Prediction Prediction Classifier Classification Dynamic Object sensing/lidar/pointcloud sensing/camera/*/image_raw sensing/camera/*/camera_info Image DetectionImage Detection perception/detection/objects perception/tracking/objects perception/prediction/objects Loader Map /map/semantic
  • 34. 34 34 [Perception] Feature Dynamic Object ● Point Cloud Segmentation : Splits pointclouds into object clusters ○ Becomes faster by algorithm improvement (It can work in real-time on CPU) ● Image Detection : Detects objects on an image as ROI ○ Becomes to work on 40FPS on Jetson AGX by Tensor RT and int8 quantization ● Fusion : Matches the result of Pointclouds Segmentation and the ROI of the image detection result ○ Matching accuracy is improved by using IoU ● Shape Estimation : Geometrically approximates the whole size of the objects by Point Cloud Segmentation ○ Shape estimations by each object class ○ Accuracy improvement by changing fitting algorithm of Bounding Box ● Multi-Object Tracking : Assigns IDs based on time series data, estimates the velocity and the acceleration, and removes outliers ○ Performance improvement by changing a tracking model by class labeling ○ Data association considering the class label and the size ● Map Based Prediction : Predicts moving path of the objects with the lane information in a map ○ Infers objects’ intent of the behavior and estimates each reliability of the predicted moving paths. Traffic Light ● Map Based Detection : Extracts an ROI of the traffic light in camera image based on the self position and map data ○ Takes errors of a self position, a calibration and a hardware vibration into consideration ● Fine Detection ○ Extracts the ROI of the traffic light more precisely with a learner ● Classifier : Recognizes a state of the traffic light by a color information in the image ○ Reduces detection errors by fine noise removement process
  • 35. 35 [Planning] Components Route.msg /planning/mission_planning/route Lane change planner Behavior velocity planner Motion path planner Obstacle stop planner Jerk filter On road Path.msg /planning/scenario_planning/scenarios/ lane_following/behavior_planning/path Trajectory.msg /planning/scenario_planning/scenarios/ lane_following/motion_planning/trajectory MotionBehavior 35 Mission planner Mission Trajectory.msg /planning/scenario_planning/scenarios/ parking/freespace_planner/trajectory Costmap generator Freespace planner OccupancyGrid.msg /planning/scenario_planning/scenarios/parking/ freespace_planner/costmap_generator/occupancy_grid Parking freespace Scenario selector Trajectory.msg /planning/scenario_planning/trajectory
  • 36. 36 36 [Planning] Feature ● Scenario selector ○ Chooses and executes “lane_following” or “parking” scenario according to the information of the mission ● Mission planner ○ Automatically searches the route from a self position to a goal via certain pass through points (by using lanelet function) ○ Automatically generates a route by using a map information ● Lane change ○ Judges a situation which needs lane change (Drive route limitation / street parking avoidance) ○ Judges whether a collision with a dynamic will happen obstacle and if a lane change is possible, it will be executed ● Behavior Velocity Planner ○ Plans a velocity based on traffic rules ○ Supports intersections, crosswalks, back-side check when turning right/left, stop with traffic lights and temporary stop line ○ Uses results of the perception (dynamic object information) ● Obstacle avoidance (motion path planner) ○ Plans a path to avoid the obstacle while driving (A* + QP) ○ Generate a smooth path considering a drivable area and the obstacle ● Obstacle stop (obstacle stop planner) ○ Judges whether a collision with obstacle pointcoulds considering the vehicle shape, and fill a stop velocity ● Jerk filter ○ Smoothens the velocity under the limitation of max speed, acceleration and lateral acceleration (QP) ○ Enables to switch rapid/slow acceleration and deceleration plans
  • 37. 37 [Control] Components Vehicle CmdGate Longitudinal Controller Lateral Controller Trajectory /control/vehicle_cmd RemoteCmd /autoware/engage 37 Control LatLon Coupler Trajectory Follower /control/longitudinal/ control_cmd /control/lateral/ control_cmd /control/control_cmd ● Longitudinal Controller ○ Calculates a target velocity and a target acceleration by PID ○ Supports a gradient correction and start/stop at a slope ○ Supports a smoothly stop ● Lateral Controller ○ Calculates a steering angle and an angular velocity (pure pursuit or MPC) ● LatLon Coupler ○ Integrates the longitudinal and lateral control command values ● Vehicle Cmd Gate ○ Switches the some command values like “remote” and “auto” ○ Attaches a limitation for the control command ■ longitudinal/lateral acceleration, longitudinal/lateral jerk ・In this implementation, longitudinal and lateral controls are separately culcurated ・In future implementation, these might be culcurated collectively
  • 38. 38 [Vehicle Interface] Components 38 Vehicle Interface Accel Map Converter Vehicle_interface /control/vehicle_cmd /control/vehicle_cmd /vehicle/pedal_cmd To Vehicle /vehicle/turn_signal_cmd /vehicle/status/twist /vehicle/status/steering /vehicle/status/turn_signal /vehicle/status/shift ● Accel Map Converter ○ Converts a target acceleration to a vehicle specific accel/brake pedal value by Accel Map ○ If the vehicle_interface supports a velocity/acceleration command, this converter isn’t necessary ● Vehicle Interface (vehicle specific) ○ Interface between Autoware and a vehicle ○ Communicates control signals ○ Obtains the vehicle information
  • 39. 39 39 Other features ● Web Controller ○ Through this controller, we can engage and specify the max velocity and also use “Go Home” button, “lane change OK” button and sensor Hz monitor ● Autoware State Monitor ○ State monitoring (Initializing / WaitForEngage / Driving / …)
  • 40. 40 40 Appendix - Table of Contents ● Design alternative ● Module implementation ○ Implementation details ○ Achevements
  • 41. 41 Achievements (1/2) ● Automatic initial self pose estimation ● Robustness of self pose estimation improvement ● CAN / imu fusion, EKF feedback, Gradient method algorithm improvement, pointclouds distortion correction, estimation speed improvement by Open-MP implementation ● 3D objects class recognition and shape estimation ● Performance improvement of dynamic objects tracking ● Moving path prediction of dynamic objects by using map information ● 360-degree sensing by the camera-LiDAR fusion ● Automatic lane change planning & decision ● Object avoidance (with lane change/ in the same lane) ● Intersection support (consider the oncoming vehicles and crossing vehicles) ● Person recognition at pedestrian crossing
  • 42. 42 Achievements (2/2) ● Performance improvement of the traffic light recognition ● Blind spot check when turning right/left ● Route generation from current position to a destination (via specified passing points) ○ With this feature, “Go Home button” can be implemented ● Automatic parking ● Slope support ● Slow / rapid brake planning support ● Performance improvement of the vehicle control ● Automatic deceleration at curve ● Collision judgement considering a vehicle shape