Software Agents : Agents for Intelligence Learning

1. National Institute of Technology
Tiruchirappalli
CA 7B3 – Software Agents
Write-Up
of
Agents for Learning Intelligence
Assistance II
Submittedto - Submitted by –
Dr. B. Ramadoss 205114025 Palash Maran
205114026 Prateek Soni
205114027 Jinendra PratapSingh
205114028 Priyanka Kothari
205114029 Shubham Prajapati

2. Life-like Computer Character
Introduction
Life-like characters are one of the most exciting technologies for human– computer interface
applications. They convincingly take the roles of virtual presenters, synthetic actors and sales
personas, teammates and tutors. In social computing, a paradigm that aims to support the
tendency of humans to interact with computers as social actors, life-like characters are key.
They may embody the interface between humans and computers.
Definition -A Life-like character is a software agent with a virtual face and body on a computer
screen and behaves likes a creature or a person.
The success of life-like character applications today relies on the careful crafting of their
designers, mostly programmers. The wide dissemination of life-like character technology in
interactive systems, however, will greatly depend on the availability of tools that facilitate
scripting of intelligent life-like behaviour. The core tasks include the synchronization of
synthetic speech and gestures, the expression of emotion and personality by means of body
movement and facial display, the coordination of the embodied conversational behaviour of
multiple characters possibly including the user, and the design of artificial minds for synthetic
characters.
General Types –
Based on the applications usage and the environment in which it has to be implemented they
are categorised in following way :
 Animated : characters that are graphically represented.
 Robotic : agents that are realized as physical entities to operate in the physical world.
Towards Social Computing
Since human–human communication is a highly effective and efficient way of interaction, life-
like characters are promising candidates to improve human– computer interaction (HCI).
Embodied agents may use multiple modalities such as voice, gestures, and facial expression
to convey information and regulate communication.
As an HCI paradigm, the goal of character-based human–computer interfaces seems to be
diametrically opposed to that of the “disappearing computer” concept in ubiquitous and
invisible computing. Those technologies are intended to “weave themselves into the fabric of

3. everyday life until they are indistinguishable from it”. By contrast, the power of character
based HCI derives from the fact that people know how to interact with other people by using
the modalities of their body (voice, gesture, gaze, etc.) and interpret the bodily signals oftheir
interlocutors.
The authors carried out a series of classical psychological tests of human–human social
interaction, The results of those experiments suggest that humans treat computers in an
essentially natural way – as social actors – with a tendency, for instance, to be nicer in “face-
to-face” interactions than in third-party conversations, who investigated the impact of
animated agents in educational software along the dimensions of motivation and helpfulness,
and coined the term “persona effect”, “which is that the presence of a lifelike character in an
interactive learning environment – even one that is not expressive – canhave a strong positive
effect on students’ perception of their learning experience”
Social computing can be characterized as
• computing that intentionally displays social and affective cues to users and aims to
trigger social reactions in users; and
• computing that recognizes affective user states and gives affective feedback to users.
Authoring Life-Like Characters
One of the most challenging tasks in life-like character research is the design of powerful and
flexible authoring tools for content experts. Animating the visual appearance of life-like
characters and integrating them into an application environment involves a large number of
complex and highly inter-related tasks, such as:
• The synchronization of synthetic speech, gaze, and gestures.
• The expression of personality and affective state by means of body movement, facial
display, and speech.
• The coordination of the bodily behaviour of multiple characters, including the
synchronization of the characters’ conversational behaviour.
• The communication between one or more characters and the user.
Platform
• Character Markup Language - (CML) contains both low-level and medium-level tags
to define the gesture behaviour of a character.
• Virtual Human Markup Language - (VHML) provides high-level and low-level tagging
structures for facial and bodily animation, gesture, speech, emotion, as well as
dialogue management.
• Scripting Technology for Embodied Persona - (STEP) language contains high-level
control specifications for scripting communicative gestures of 3D animated agents.
APPLICATIONS

4. • One of the most successful application fields of life-like character technology is
computer-based learning environments where life-like character can perform in a
variety of student-related roles, especially as tutors and trainers.
• Life-like virtual characters existing in PC computer games.
• Life-like character appear as well on a computer screen in productivity applications. A
well-known paperclip Clippy, officially named Clipp it, is an example of an life-like
character present in the Microsoft Word application.
• Life-likecharacter and virtual animals populating real world 3D simulations and virtual
worlds. Thesesynthetic characters are capable of taking physical actions within virtual
reality environments and their bodies are actually submitted to physical constraints.
Fig.PersonaProjectat Microsoft
The diagram represents the modules and communication paths among the various
components of the Persona system. Without the vision component, there is a unidirectional
flow of control, from spoken input to graphics, speech, and audio output. At the core of the
Dialog module is a state machine which enumerates the character’s possible states and state
transitions.
Conclusion
• Social interfaces are already part of consumer multimedia products.
• More and more CD-ROM titles have animated characters to provide help, lead the
user through the story, or make regular GUI interactions more friendly.
• These are currently simple, deterministic, 2D animated characters.

5. • The next generation of social interfaces will include lifelike 3D characters that provide
a more intuitive mode of user interaction.
References
 Life-like Characters by Helmut Prendinger, Mitsuru Ishizuka
 https://www.cs.ucsb.edu/~mturk/Papers/FG96.pdf
 G. Ball et al., “Lifelike computer characters”, in Jeffrey Bradshaw (ed.), Software
Agents, M.I.T. Press, 1995
 https://en.wikipedia.org/wiki/Procedural_reasoning_system
 https://en.wikipedia.org/wiki/Subsumption_architecture
 Ingrand, F.; M. Georgeff; A Rao (1992). "An architecture for real-time reasoning and
system control". IEEE Expert: Intelligent Systems and Their Applications. IEEE
Press. 7 (6): 34–44. doi:10.1109/64.180407
 https://www.cs.cmu.edu/~softagents/retsina_agent_arch.html
 Jeffrey M . Bradshaw , Software Agents , MIT Press, 2000.
 http://agents.umbc.edu/introduction/01-Bradshaw.pdf
 http://www.researchgate.net/publication/234783334_Software_agents_for_cooperativ
e_learning