SlideShare ist ein Scribd-Unternehmen logo
1 von 16
Downloaden Sie, um offline zu lesen
NUAV – A Testbed for Development of Unmanned
Aerial Vehicles
Saleh Habib Mahgul Malik Shams Ur Rahman Muhammad Adil
Raja
Namal College, Mianwali
Pakistan
cbna
May 6, 2017
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 1 / 16
Overview
1 Introduction
2 Our Methodology
Communications Module
ML Algorithms
NUAV Testbed
3 Experimental Setup
A Scheme for Reducing the Simulation Time
A Simple Experiment
On Fitness Functions
4 Results and Analysis
5 Conclusion
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 2 / 16
Introduction
Contemporary models of Unmanned Aerial Vehicles (UAVs) are
largely developed using simulators.
In a typical scheme, a ïŹ‚ight simulator is dovetailed with a machine
learning (ML) algorithm. A good simulator provides a realistic
environment for simulated aircraft.
The process of development can be accelerated largely by employing a
testbed that allows a seamless dovetailing between the ïŹ‚ight
simulator and an ML algorithm of choice.
However, an extensive testbed is largely missing from the academic
landscape both in terms of implementation and technical details.
This papers proposes a new testbed for the development of fully
autonomous UAVs.
The proposed system allows researchers to simulate UAVs for various
scenarios.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 3 / 16
Our Methodology I
Figure: A simple schematic diagram of NUAV testbed.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 4 / 16
Our Methodology II
NUAV Testbed has three modules to it.
Communications Module
In order to develop the communications module we have used the
APIs of FlightGear and taken inspiration from GaTAC [Sonu, 2012].
GaTAC accomplishes its communication with FlightGear by using
UDP sockets.
ML Algorithms
Currently NUAV makes use of two ML algorithms. One is a simple
feed forward error back propagation artiïŹcialn neural network (ANN)
[Bishop, 1995][Mitchell, 1997].
The other is a renowned genetic algithm for multi-objective
optimization known as NSGA-II [Pratap, 2002].
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 5 / 16
Our Methodology III
NUAV Testbed
The main code of NUAV testbed basically integrates FlightGear with
an ML algorithm and serves as a data tunnel between the two.
In its simple scheme, it fetches data from FlightGear and presents it
to the ML algorithm.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 6 / 16
Experimental Setup
A Simple Experiment
In our scheme, we create a neural network structure, and optimize its
weights with NSGA-II.
A single run was performed. We start oïŹ€ with a population size of
150 and gradually decrease it to a size of 50 over 50 generations.
Similarly, we start oïŹ€ with a simulation time of 1 second for every
individual, and increase it to up to 20 seconds.
The purpose of reporting this simple experiment is more to deliver a
proof of concept of the working of NUAV testbed at this stage, as
opposed to exhibiting wondrous marvels of ML.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 7 / 16
On Reducing Simulation Time
A Scheme for Reducing the Simulation Time
We performed a handful of simple experiments.
The main hurdle we had to overcome in performing a full ïŹ‚edged
experiment involving a GA, containing multiple runs of evolution, was
simulation time.
A simple experiment with a single run of GA up to ïŹfty generations,
requiring a plane to be ïŹ‚own for as small a duration as thirty seconds
requires a simulation time in order of days.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 8 / 16
On Fitness Functions
On Fitness Functions
Our ïŹrst ïŹtness function is to minimize the absolute diïŹ€erence
between the altitude of the plane and a target altitude value of 2500
ft.
The second objective is to minimize the Euclidean distance between
the orientation of the plane against a reference value of zero.
To this end, we provide the values of roll, pitch and yaw as a vector
that serves collectively for orientation.
The third objective is to minimize the absolute diïŹ€erence between the
calibrated air speed of the plane and a target calibrated air speed of
75 knots.
Our ïŹnal objective minimizes the absolute diïŹ€erence between the
climb rate of the plane with a target value of 7.5 ft/s.
The goal for the GA is to minimize all of these objectives.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 9 / 16
Results and Analysis I
At the end of training, we tested all the 50 individuals of the ïŹnal
generation produced by GA.
We plugged them in one by one in the ANN and ïŹ‚ew the plane with
them. From these 50 ïŹ‚ights, we scavenged 14 which seemed well
visually.
Graphical results of two of these ïŹ‚ights are shown in Figure(s): 2– ??.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 10 / 16
Results and Analysis II
(a) (b)
Figure: Values of roll, pitch (degrees) and altitude (%) for two individuals of the
GA run.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 11 / 16
Results and Analysis III
(a) (b)
Figure: Trajectories of the corresponding individuals shown in Figure: 2.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 12 / 16
Results and Analysis IV
(a) (b)
Figure: Calibrated air speeds of the corresponding individuals shown in Figure: 2.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 13 / 16
Conclusion
In this paper we introduced a testbed for development of UAVs.
We call it NUAV testbed.
Our testbed allows modeling autonomous drones that can perform a
user deïŹned task.
We have developed this testbed by integrating FlightGear ïŹ‚ight
simulator with NSGA-II, a well known GA.
In future we look forward to extending our testbed to be able to train
UAVs that can perform a plethora of user deïŹned tasks.
In particular, we are eager to develop a capacity to develop fully
autonomous, cooperative and self-coordinating ïŹ‚eets of UAVs.
We also want our testbed to be a distributed and scalable system.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 14 / 16
References
E. Sonu and P. Doshi (2012)
Gatac: A scalable and realistic testbed for multiagent decision.
11th International Conference on Autonomous Agents and Multiagent Systems
1507 – 1508.
C. M. Bishop (1995)
Neural Networks for Pattern Recognition.
Oxford University Press, Inc
T. Mitchell (1997)
Machine Learning.
New York: McGraw Hill
K. Deb, A. Pratap, S. Agarwal, T. Meyarivan (2002)
A fast and elitist multiobjective genetic algorithm: NSGA-II.
Evolutionary Computation, IEEE Transactions on, vol. 6, no. 2, pp. 182197.
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 15 / 16
The End
Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 16 / 16

Weitere Àhnliche Inhalte

Ähnlich wie NUAV Testbed Develop Autonomous Drones

Reserch wearable devices ppt
Reserch wearable devices pptReserch wearable devices ppt
Reserch wearable devices pptShalini Toluchuri
 
CV - Aravind Kamsanahally Sriramamurthy
CV - Aravind Kamsanahally Sriramamurthy CV - Aravind Kamsanahally Sriramamurthy
CV - Aravind Kamsanahally Sriramamurthy Aravind K S
 
Modelling Open-Source Software Reliability Incorporating Swarm Intelligence-B...
Modelling Open-Source Software Reliability Incorporating Swarm Intelligence-B...Modelling Open-Source Software Reliability Incorporating Swarm Intelligence-B...
Modelling Open-Source Software Reliability Incorporating Swarm Intelligence-B...AIRCC Publishing Corporation
 
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...Editor IJCATR
 
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...Editor IJCATR
 
IRJET- Self Driving Car using Deep Q-Learning
IRJET-  	  Self Driving Car using Deep Q-LearningIRJET-  	  Self Driving Car using Deep Q-Learning
IRJET- Self Driving Car using Deep Q-LearningIRJET Journal
 
Advanced UAV Trajectory Generation Planning And Guidance
Advanced UAV Trajectory Generation  Planning And GuidanceAdvanced UAV Trajectory Generation  Planning And Guidance
Advanced UAV Trajectory Generation Planning And GuidanceStephen Faucher
 
January 2021: Top Ten Cited Article in Computer Science, Engineering
January 2021: Top Ten Cited Article in Computer Science, Engineering January 2021: Top Ten Cited Article in Computer Science, Engineering
January 2021: Top Ten Cited Article in Computer Science, Engineering IJCSEA Journal
 
Vehicle make and model recognition using mixed sample data augmentation techn...
Vehicle make and model recognition using mixed sample data augmentation techn...Vehicle make and model recognition using mixed sample data augmentation techn...
Vehicle make and model recognition using mixed sample data augmentation techn...IAESIJAI
 
A review on distributed control of
A review on distributed control ofA review on distributed control of
A review on distributed control ofijaia
 
A review on distributed control of
A review on distributed control ofA review on distributed control of
A review on distributed control ofijaia
 
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS.
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS.AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS.
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS.ijaia
 
Real time pedestrian detection with deformable part models [h. cho, p. rybski...
Real time pedestrian detection with deformable part models [h. cho, p. rybski...Real time pedestrian detection with deformable part models [h. cho, p. rybski...
Real time pedestrian detection with deformable part models [h. cho, p. rybski...tino
 
Performance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO Objects
Performance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO ObjectsPerformance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO Objects
Performance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO ObjectsIJECEIAES
 
Air_Quality_Index_Forecasting Prediction BP
Air_Quality_Index_Forecasting Prediction BPAir_Quality_Index_Forecasting Prediction BP
Air_Quality_Index_Forecasting Prediction BPAnbuShare
 
Dd3210971099
Dd3210971099Dd3210971099
Dd3210971099IJMER
 

Ähnlich wie NUAV Testbed Develop Autonomous Drones (20)

Nadim(093048) stz sir
Nadim(093048) stz sirNadim(093048) stz sir
Nadim(093048) stz sir
 
Reserch wearable devices ppt
Reserch wearable devices pptReserch wearable devices ppt
Reserch wearable devices ppt
 
Ahmed Momtaz Hosny's Resume
Ahmed Momtaz Hosny's ResumeAhmed Momtaz Hosny's Resume
Ahmed Momtaz Hosny's Resume
 
CV - Aravind Kamsanahally Sriramamurthy
CV - Aravind Kamsanahally Sriramamurthy CV - Aravind Kamsanahally Sriramamurthy
CV - Aravind Kamsanahally Sriramamurthy
 
Ijciet 06 10_006
Ijciet 06 10_006Ijciet 06 10_006
Ijciet 06 10_006
 
Modelling Open-Source Software Reliability Incorporating Swarm Intelligence-B...
Modelling Open-Source Software Reliability Incorporating Swarm Intelligence-B...Modelling Open-Source Software Reliability Incorporating Swarm Intelligence-B...
Modelling Open-Source Software Reliability Incorporating Swarm Intelligence-B...
 
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
 
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
Software Architecture Evaluation of Unmanned Aerial Vehicles Fuzzy Based Cont...
 
IRJET- Self Driving Car using Deep Q-Learning
IRJET-  	  Self Driving Car using Deep Q-LearningIRJET-  	  Self Driving Car using Deep Q-Learning
IRJET- Self Driving Car using Deep Q-Learning
 
Technical Writing Paper Presentation .pptx
Technical Writing Paper Presentation .pptxTechnical Writing Paper Presentation .pptx
Technical Writing Paper Presentation .pptx
 
Advanced UAV Trajectory Generation Planning And Guidance
Advanced UAV Trajectory Generation  Planning And GuidanceAdvanced UAV Trajectory Generation  Planning And Guidance
Advanced UAV Trajectory Generation Planning And Guidance
 
January 2021: Top Ten Cited Article in Computer Science, Engineering
January 2021: Top Ten Cited Article in Computer Science, Engineering January 2021: Top Ten Cited Article in Computer Science, Engineering
January 2021: Top Ten Cited Article in Computer Science, Engineering
 
Vehicle make and model recognition using mixed sample data augmentation techn...
Vehicle make and model recognition using mixed sample data augmentation techn...Vehicle make and model recognition using mixed sample data augmentation techn...
Vehicle make and model recognition using mixed sample data augmentation techn...
 
A review on distributed control of
A review on distributed control ofA review on distributed control of
A review on distributed control of
 
A review on distributed control of
A review on distributed control ofA review on distributed control of
A review on distributed control of
 
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS.
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS.AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS.
AUTO-MOBILE VEHICLE DIRECTION IN ROAD TRAFFIC USING ARTIFICIAL NEURAL NETWORKS.
 
Real time pedestrian detection with deformable part models [h. cho, p. rybski...
Real time pedestrian detection with deformable part models [h. cho, p. rybski...Real time pedestrian detection with deformable part models [h. cho, p. rybski...
Real time pedestrian detection with deformable part models [h. cho, p. rybski...
 
Performance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO Objects
Performance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO ObjectsPerformance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO Objects
Performance Evaluation of Fine-tuned Faster R-CNN on specific MS COCO Objects
 
Air_Quality_Index_Forecasting Prediction BP
Air_Quality_Index_Forecasting Prediction BPAir_Quality_Index_Forecasting Prediction BP
Air_Quality_Index_Forecasting Prediction BP
 
Dd3210971099
Dd3210971099Dd3210971099
Dd3210971099
 

Mehr von adil raja

ANNs.pdf
ANNs.pdfANNs.pdf
ANNs.pdfadil raja
 
A Software Requirements Specification
A Software Requirements SpecificationA Software Requirements Specification
A Software Requirements Specificationadil raja
 
DevOps Demystified
DevOps DemystifiedDevOps Demystified
DevOps Demystifiedadil raja
 
On Research (And Development)
On Research (And Development)On Research (And Development)
On Research (And Development)adil raja
 
The Knock Knock Protocol
The Knock Knock ProtocolThe Knock Knock Protocol
The Knock Knock Protocoladil raja
 
File Transfer Through Sockets
File Transfer Through SocketsFile Transfer Through Sockets
File Transfer Through Socketsadil raja
 
Remote Command Execution
Remote Command ExecutionRemote Command Execution
Remote Command Executionadil raja
 
Thesis
ThesisThesis
Thesisadil raja
 
CMM Level 3 Assessment of Xavor Pakistan
CMM Level 3 Assessment of Xavor PakistanCMM Level 3 Assessment of Xavor Pakistan
CMM Level 3 Assessment of Xavor Pakistanadil raja
 
Data Warehousing
Data WarehousingData Warehousing
Data Warehousingadil raja
 
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...adil raja
 
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...adil raja
 
Real-Time Non-Intrusive Speech Quality Estimation for VoIP
Real-Time Non-Intrusive Speech Quality Estimation for VoIPReal-Time Non-Intrusive Speech Quality Estimation for VoIP
Real-Time Non-Intrusive Speech Quality Estimation for VoIPadil raja
 
ULMAN GUI Specifications
ULMAN GUI SpecificationsULMAN GUI Specifications
ULMAN GUI Specificationsadil raja
 
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...adil raja
 
ULMAN-GUI
ULMAN-GUIULMAN-GUI
ULMAN-GUIadil raja
 
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...adil raja
 
Modeling the Effect of packet Loss on Speech Quality: GP Based Symbolic Regre...
Modeling the Effect of packet Loss on Speech Quality: GP Based Symbolic Regre...Modeling the Effect of packet Loss on Speech Quality: GP Based Symbolic Regre...
Modeling the Effect of packet Loss on Speech Quality: GP Based Symbolic Regre...adil raja
 
Modelling the Effect of Packet Loss on Speech Quality
Modelling the Effect of Packet Loss on Speech QualityModelling the Effect of Packet Loss on Speech Quality
Modelling the Effect of Packet Loss on Speech Qualityadil raja
 

Mehr von adil raja (20)

ANNs.pdf
ANNs.pdfANNs.pdf
ANNs.pdf
 
A Software Requirements Specification
A Software Requirements SpecificationA Software Requirements Specification
A Software Requirements Specification
 
DevOps Demystified
DevOps DemystifiedDevOps Demystified
DevOps Demystified
 
On Research (And Development)
On Research (And Development)On Research (And Development)
On Research (And Development)
 
The Knock Knock Protocol
The Knock Knock ProtocolThe Knock Knock Protocol
The Knock Knock Protocol
 
File Transfer Through Sockets
File Transfer Through SocketsFile Transfer Through Sockets
File Transfer Through Sockets
 
Remote Command Execution
Remote Command ExecutionRemote Command Execution
Remote Command Execution
 
Thesis
ThesisThesis
Thesis
 
CMM Level 3 Assessment of Xavor Pakistan
CMM Level 3 Assessment of Xavor PakistanCMM Level 3 Assessment of Xavor Pakistan
CMM Level 3 Assessment of Xavor Pakistan
 
Data Warehousing
Data WarehousingData Warehousing
Data Warehousing
 
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
 
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
Implementation of a Non-Intrusive Speech Quality Assessment Tool on a Mid-Net...
 
Real-Time Non-Intrusive Speech Quality Estimation for VoIP
Real-Time Non-Intrusive Speech Quality Estimation for VoIPReal-Time Non-Intrusive Speech Quality Estimation for VoIP
Real-Time Non-Intrusive Speech Quality Estimation for VoIP
 
VoIP
VoIPVoIP
VoIP
 
ULMAN GUI Specifications
ULMAN GUI SpecificationsULMAN GUI Specifications
ULMAN GUI Specifications
 
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
 
ULMAN-GUI
ULMAN-GUIULMAN-GUI
ULMAN-GUI
 
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
Modeling the Effect of Packet Loss on Speech Quality: Genetic Programming Bas...
 
Modeling the Effect of packet Loss on Speech Quality: GP Based Symbolic Regre...
Modeling the Effect of packet Loss on Speech Quality: GP Based Symbolic Regre...Modeling the Effect of packet Loss on Speech Quality: GP Based Symbolic Regre...
Modeling the Effect of packet Loss on Speech Quality: GP Based Symbolic Regre...
 
Modelling the Effect of Packet Loss on Speech Quality
Modelling the Effect of Packet Loss on Speech QualityModelling the Effect of Packet Loss on Speech Quality
Modelling the Effect of Packet Loss on Speech Quality
 

KĂŒrzlich hochgeladen

Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...gurkirankumar98700
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel AraĂșjo
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 

KĂŒrzlich hochgeladen (20)

Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 

NUAV Testbed Develop Autonomous Drones

  • 1. NUAV – A Testbed for Development of Unmanned Aerial Vehicles Saleh Habib Mahgul Malik Shams Ur Rahman Muhammad Adil Raja Namal College, Mianwali Pakistan cbna May 6, 2017 Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 1 / 16
  • 2. Overview 1 Introduction 2 Our Methodology Communications Module ML Algorithms NUAV Testbed 3 Experimental Setup A Scheme for Reducing the Simulation Time A Simple Experiment On Fitness Functions 4 Results and Analysis 5 Conclusion Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 2 / 16
  • 3. Introduction Contemporary models of Unmanned Aerial Vehicles (UAVs) are largely developed using simulators. In a typical scheme, a ïŹ‚ight simulator is dovetailed with a machine learning (ML) algorithm. A good simulator provides a realistic environment for simulated aircraft. The process of development can be accelerated largely by employing a testbed that allows a seamless dovetailing between the ïŹ‚ight simulator and an ML algorithm of choice. However, an extensive testbed is largely missing from the academic landscape both in terms of implementation and technical details. This papers proposes a new testbed for the development of fully autonomous UAVs. The proposed system allows researchers to simulate UAVs for various scenarios. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 3 / 16
  • 4. Our Methodology I Figure: A simple schematic diagram of NUAV testbed. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 4 / 16
  • 5. Our Methodology II NUAV Testbed has three modules to it. Communications Module In order to develop the communications module we have used the APIs of FlightGear and taken inspiration from GaTAC [Sonu, 2012]. GaTAC accomplishes its communication with FlightGear by using UDP sockets. ML Algorithms Currently NUAV makes use of two ML algorithms. One is a simple feed forward error back propagation artiïŹcialn neural network (ANN) [Bishop, 1995][Mitchell, 1997]. The other is a renowned genetic algithm for multi-objective optimization known as NSGA-II [Pratap, 2002]. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 5 / 16
  • 6. Our Methodology III NUAV Testbed The main code of NUAV testbed basically integrates FlightGear with an ML algorithm and serves as a data tunnel between the two. In its simple scheme, it fetches data from FlightGear and presents it to the ML algorithm. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 6 / 16
  • 7. Experimental Setup A Simple Experiment In our scheme, we create a neural network structure, and optimize its weights with NSGA-II. A single run was performed. We start oïŹ€ with a population size of 150 and gradually decrease it to a size of 50 over 50 generations. Similarly, we start oïŹ€ with a simulation time of 1 second for every individual, and increase it to up to 20 seconds. The purpose of reporting this simple experiment is more to deliver a proof of concept of the working of NUAV testbed at this stage, as opposed to exhibiting wondrous marvels of ML. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 7 / 16
  • 8. On Reducing Simulation Time A Scheme for Reducing the Simulation Time We performed a handful of simple experiments. The main hurdle we had to overcome in performing a full ïŹ‚edged experiment involving a GA, containing multiple runs of evolution, was simulation time. A simple experiment with a single run of GA up to ïŹfty generations, requiring a plane to be ïŹ‚own for as small a duration as thirty seconds requires a simulation time in order of days. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 8 / 16
  • 9. On Fitness Functions On Fitness Functions Our ïŹrst ïŹtness function is to minimize the absolute diïŹ€erence between the altitude of the plane and a target altitude value of 2500 ft. The second objective is to minimize the Euclidean distance between the orientation of the plane against a reference value of zero. To this end, we provide the values of roll, pitch and yaw as a vector that serves collectively for orientation. The third objective is to minimize the absolute diïŹ€erence between the calibrated air speed of the plane and a target calibrated air speed of 75 knots. Our ïŹnal objective minimizes the absolute diïŹ€erence between the climb rate of the plane with a target value of 7.5 ft/s. The goal for the GA is to minimize all of these objectives. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 9 / 16
  • 10. Results and Analysis I At the end of training, we tested all the 50 individuals of the ïŹnal generation produced by GA. We plugged them in one by one in the ANN and ïŹ‚ew the plane with them. From these 50 ïŹ‚ights, we scavenged 14 which seemed well visually. Graphical results of two of these ïŹ‚ights are shown in Figure(s): 2– ??. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 10 / 16
  • 11. Results and Analysis II (a) (b) Figure: Values of roll, pitch (degrees) and altitude (%) for two individuals of the GA run. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 11 / 16
  • 12. Results and Analysis III (a) (b) Figure: Trajectories of the corresponding individuals shown in Figure: 2. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 12 / 16
  • 13. Results and Analysis IV (a) (b) Figure: Calibrated air speeds of the corresponding individuals shown in Figure: 2. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 13 / 16
  • 14. Conclusion In this paper we introduced a testbed for development of UAVs. We call it NUAV testbed. Our testbed allows modeling autonomous drones that can perform a user deïŹned task. We have developed this testbed by integrating FlightGear ïŹ‚ight simulator with NSGA-II, a well known GA. In future we look forward to extending our testbed to be able to train UAVs that can perform a plethora of user deïŹned tasks. In particular, we are eager to develop a capacity to develop fully autonomous, cooperative and self-coordinating ïŹ‚eets of UAVs. We also want our testbed to be a distributed and scalable system. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 14 / 16
  • 15. References E. Sonu and P. Doshi (2012) Gatac: A scalable and realistic testbed for multiagent decision. 11th International Conference on Autonomous Agents and Multiagent Systems 1507 – 1508. C. M. Bishop (1995) Neural Networks for Pattern Recognition. Oxford University Press, Inc T. Mitchell (1997) Machine Learning. New York: McGraw Hill K. Deb, A. Pratap, S. Agarwal, T. Meyarivan (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. Evolutionary Computation, IEEE Transactions on, vol. 6, no. 2, pp. 182197. Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 15 / 16
  • 16. The End Muhammad Adil Raja ( Namal College, Mianwali Pakistan cbna)NUAV – A Testbed for Development of Autonomous Unmanned Aerial VehiclesMay 6, 2017 16 / 16