EMBODIED INTELLIGENCE
Satpreet Arora (07d05003) Rachit Gupta (07d05008) Devendra Shelar (07d05010) Amrose Birani (07005003)
Father of Embodied Intelligence
Rodney Brooks suggested the
design of intelligent machines through interaction with the environment driven by perception and action, rather than by a pre-specified algorithm.
Brooks showed
that robots could be more effective if they 'thought' (planned or processed) and perceived as little as possible.
Precursors of Embodied Intelligence
In the early stages of robotics robots were built on cybernetic principles. Brooks proposed that vision and locomotion are the 2 primary needs of natural intelligence. He proposed that environment is best model and not representation These propositions revolutionized the way of thinking !!
Goal seeking behavior
Homeostasis
Learning abilities
The Rationale and Objectives
New Technologies and design approaches for building physically embodied intelligent agents and artefacts, with emphasis on the relationship between shape, function and the physical and social environment
What is Embodied Intelligence
Embodied Intelligence (EI) is a mechanism that learns
how to survive in a hostile environment Mechanism: biological, mechanical or virtual agent with embodied sensors and actuators EI acts on environment and perceives its actions Hostility: direct aggression, pain, anxiety or scarcity of resources EI learns so it must have associative self-organizing memory
Source: Ohio Univ CSE
Continued ...
It should have a purpose of being
it should maintain and pursue multiple goals, choosing
which goal to implement based on the environmental conditions. In addition, the complexity of a creatures behavior would reflect the complexity of the environment in which it operates rather than its own.
Source: Ohio Univ CSE
Waste Allocation Load Lifter Earth Class
He is better known as Wall-e He stays in a very hostile
environment
reflects the complexity of the
environment it stays in !
Has an excellent purpose of
being
Can collect garbage, repair his
own tire and perform a lot more stuff multiple goals !!
In nutshell excellent example
of embodied intelligence
Source : Pixar Animations
How to create machine intelligence?
Specialized Problems in AI
Knowledge Representation Natural language and scene understanding
Semantic Cognition
Reinforcement Learning
Nature Vs Machines
It took nature over 3 billion years to create insects 200 million more years to create mammals 15 million years for the transformation of great apes to modern man about 3 million years ago
Major developments of the civilized world within the last 10,000 years.
It seems that in nature it is easier to append a primitive brain to create a complex brain. While this may justify an approach in which a machines reflexes are developed first, the lack of a mechanism to add complexity at a low design cost is a major problem that cannot be left to chance.
Challenges of Embodied Intelligence
Outline
Traditional Artificial Intelligence Embodied Intelligence (EI) Challenges of EI
We need to know how We need means to implement it We need resources to build and sustain its operation
Promises of EI
To economy To society
Intelligence
Evolve
Solve
Plan Comprehend Reason Learn Think
Traditional AI
Attempt to simulate highest
Embodied Intelligence
knowledge is implicit in the fact
human faculties like language, reasoning, problem solving
that we have a body
Embodiment is a foundation for
Brain is taken to be an abstract problem solver
brain development
Intelligence develops through
Environment model based
approach. Note that environment is extremely difficult to model.
Pre-specified problems are
constant interaction with environment
Problems are identified and
solved by goal seeking behavior solved using abstract ways
Source : Ohio Univ
Design principles of intelligent systems
Interaction with complex environment
cheap design
ecological balance redundancy principle
asynchronous
parallel, loosely coupled processes sensory-motor coordination value principle
Source : Design Principles for Intelligent Systems Department of Information Technology, University of Zurich
Agent
Embodiment of Mind
Necessary for development of
intelligence
Hosts brains interfaces that
interact with environment
Not necessarily constant or in
Embodiment Intelligence core
the form of a physical body
Boundary transforms modifying
brains self-determination
Environment
Continued ...
Brain learns own bodys dynamic Self-awareness results from
identification with own embodiment
Embodiment can be extended
by using tools and machines
Successful operation depends on
correct perception of environment and own embodiment
The Brain
While we learn its functions can
we emulate its operation ?
How can we design intelligence?
We need to know how We need means to implement it We need resources to build and sustain its
operation
Name: Dav Source: MSU Univ CSE
Requirements for Embodied Intelligence
State oriented
Learns spatio-temporal patterns Situated in time and space
Learning
Perpetual learning Screening for novelty
Value driven
Goal creation Competing goals Artificial evolution Self-organization
Emergence
EI Interaction with Environment
Agent Architecture Reason
Short-term Memory
Perceive
RETRIEVAL LEARNING
Act
Long-term Memory
INPUT
OUTPUT
Task Environment
Simulation or
Real-World System
We need to develop ..
Sensory Interfaces
Active Vision Speech Processing Tactile, Smell, Taste, Temperature, Pressure Sensing Additional Sensing Infrared, Radar, Ultrasound, GPS, Etc. Can Too Many Senses Be Less Useful? Reinforcement Interfaces Energy, Temperature, Pressure, Acceleration Level Teacher Input Motor Interfaces Arms, Legs, Fingers, Eye Movement
Continued ...
Algorithmic Solutions For
Association, Memory, Sequence Learning, Invariance Building,
Representation, Anticipation, Value Learning (Pain Reduction), Goal Creation, Planning
Circuits For Neural Computing
Determine Organization Of Artificial Minicolumn Self-organized Hierarchy Of Minicolumns For Sensing And Motor
Control Self-organization Of Goal Creation Pathway
Source : Univ. of Sussex Alastair Channon
Goal Driven Behavior
Goal driven behavior is one of the
required elements of intelligence Perceptions and actions are activated selectively to serve the machines objectives In the existing EI models, the goal is defined by designers and is given to the learning agent Humans and animals create their own goals The goal creation may be one of the most important elements of EI mechanism
Source: Janusz A. Starzyk -- Challenges of EI
Goal Creation
Goals must be built and understood in a
similar way to building perceptions
complex goals can be understood only if
representations are build
It should result from EI interaction with
environment, by perceiving successes or failures of its actions
essential for developing intelligence
We will create goals based on simple
structures interacting with sensory and motor pathways
Source: Janusz A. Starzyk -- Challenges of EI
How can we design intelligence?
We need to know how
We need means to implement it We need resources to build and sustain its operation
Doubling (or Halving) times
Clock speed Dynamic RAM Memory Half Pitch Feature Size Dynamic RAM Memory (bits per dollar) Average Transistor Price Microprocessor Cost per Transistor Cycle Total Bits Shipped Processor Performance in MIPS
2.7 years 5.4 years 1.5 years 1.6 years 1.1 years 1.1 years 1.8 years
Transistors in Intel Microprocessors
Microprocessor Clock Speed
2.0 years
2.7 years
Source: Chemheritage.org, IEEE Explore IITB
Is It Possible ?
the area occupied by the new logic must be gradually reduced from
over 60% in 1999 to less than 5% in 2010.
It is a way to shorten the design time, but it doesnt create high-value
designs !!!
Yet the structure of interconnections in human brain is very complex.
Thus a design of EI could be tremendously costly even if we know how
to build it.
Promises of embodied intelligence
To society
Advanced use of technology Robots Tutors Intelligent gadgets Society of minds Superhuman intelligence Progress in science Solution to societies ills
To industry
Technological development New markets Economical growth
Name : Sail Source: MSU Univ CSE
Sounds like science fiction
If youre trying to look far
ahead, and what you see seems like science fiction, it might be wrong. But if it doesnt seem like science fiction, its definitely wrong.
Name : Wall-E Source: Pixar Animations
THANK YOU
References
Motivation in Embodied Intelligence (2005) janusz Starzyk (Ohio Univ. USA) Challenges of Embodied Intelligence (2001) - Janusz A. Starzyk, Yinyin Liu, and Haibo He (Ohio Univ. USA) Moravec, H.P. (1999) -- Rise of the Robots Pixar Animations http://www.pixar.com/featurefilms/walle/ The Evolutionary Emergence route to Artificial Intelligence -- Alastair Channon (UNIVERSITY OF SUSSEX 1995-96) Design Principles for Intelligent Systems (2003) Rolf Pfeifer1, Fumiya Iida1, Josh Bongard2 Department of Information Technology, University of Zurich Michigan State Univ. http://www.cse.msu.edu/ei/ Chemheritage.org & IEEE Explore IITB Wikipedia