Introduction To Cognitive Robots
Prof. Brian Williams
Wednesday, February 2nd, 2004
Copyright B. Williams
16.412J/6.834J, Fall 02
Outline
•
•
•
•
Examples of Robots as Explorers
Course Objectives
Student Introductions and Goals
Introduction to Model-based Programming
Copyright B. Williams
16.412J/6.834J, Fall 02
Course Objective 1
To understand the main types of cognitive robots
and their driving requirements:
• “Immobile” Robots and Engineering Operations
– Robust space probes, ubiquitous computing
• Robots That Navigate
– Hallway robots, Field robots, Underwater explorers, stunt air vehicles
• Cooperating Robots
– Cooperative Space/Air/Land/Underwater vehicles, distributed traffic networks,
smart dust.
Accomplished by:
¾ Case studies, invited lectures & final projects.
Copyright B. Williams
16.412J/6.834J, Fall 02
Immobile Robots in Space
Copyright B. Williams
16.412J/6.834J, Fall 02
Copyright
Williams
courtesy B.
NASA
Ames
16.412J/6.834J, Fall 02
Autonomous Systems use Models to
Anticipate or Detect Subtle Failures
CO2 concentration (ppm)
1200
NASA Mars Habitat
lighting system
Crew Chamber
pulse injection valves
crew requests entry to
plant growth chamber
1100
1000
900
800
crew enters chamber
700
crew leaves
chamber
lighting fault
600
500
Airlock
Plant Growth Chamber
400
flow regulator 1
CO2
CO2
tank
600
700
800
900
1000 1100
time (minutes)
1200
1300
1400
flow regulator 2
chamber
control
Copyright B. Williams
16.412J/6.834J, Fall 02
The Role of Robots in Human Exploration
Copyright B. Williams
16.412J/6.834J, Fall 02
Robonaut: Robotic Assistance For
Orbital Assembly and Repair
Copyright B. Williams
16.412J/6.834J, Fall 02
Outline
•
•
•
•
Examples of Robots as Explorers
Course Objectives
Student Introductions and Goals
Introduction to Model-based Programming
Copyright B. Williams
16.412J/6.834J, Fall 02
Course Objective 2
• To understand advanced methods for creating
highly capable cognitive robots.
Plan Activities
Localize
in World
Monitor &
Diagnosis
Interpret
Scenes
Manage Dialogue
Execute &
Adapt
Navigation &
Manipulation
Manipulation
Map and Explore
Accomplished by:
¾ Lectures on advanced core methods
¾ ~ Implement & empirically compare two core methods.
Copyright B. Williams
16.412J/6.834J, Fall 02
Lectures: Planning and Acting Robustly
Monitoring, and Diagnosis
• Diagnosing Multiple Faults
• Constraint-based Monitoring
• Hybrid Monitoring and
Estimation
Planning Missions
• Planning using Informed
Search
• Planning with Time and
Resources
• Robust Plan Execution
Through Dynamic Scheduling
• Reactive Planning and
Execution
Plan Activities
Monitor &
Diagnosis
Copyright B. Williams
Execute &
Adapt
16.412J/6.834J, Fall 02
Lectures: Interacting With The World
Simultaneous Localization and
Mapping
• Basic SLAM
• Vision-based SLAM
Cognitive Vision
• Visual Interpretation using
Probabilistic Grammars
• Context-based Vision
Localize
in World
Navigation & Manipulation
• Probabilistic Path Planning
• Exploring Unknown
Environments
Human - Robot Interaction
• Discourse Management &
Nursebot
• Social Robotics
Navigation &
Manipulation
Interpret
Scenes
Manipulation
Manage Dialogue
Copyright B. Williams
Map and Explore
16.412J/6.834J, Fall 02
Lectures: Fast, Large-scale Reasoning
Optimality and Soft Constraints
• Optimal CSPs and
Conflict-Learning
• Valued CSPs and
Dynamic Programming
• Solving CSPS through
Tree Decomposition
Incremental Methods
• Incremental Satisfiability
• Incremental Scheduling
• Incremental Path Planning
Any-Time
Enumeration
Incremental
Reasoning
Copyright B. Williams
Symbolic State
Space Encodings
Structural
Decomposition
16.412J/6.834J, Fall 02
Topics On Cognitive Robot Capabilities
• Robots that Plan and Act in the World
– Robots that Deftly Navigate
– Planning and Executing Complex Missions
• Robots that Are State-Aware
– Robots that Find Their Way In The World
– Robots that Deduce Their Internal State
• Robots that Preplan For An Uncertain
Future
– Theoretic Planning in a Hidden World
– State and Fault Aware Systems
Copyright B. Williams
16.412J/6.834J, Fall 02
Course Objective 3
• To dive into the recent literature, and collectively
synthesize, clearly explain and evaluate the state
of the art in cognitive robotics.
Accomplished by:
¾ Group lectures on advance topic
¾ One 40 minute lecture per student
¾ tutorial article on ~2 methods, to support lectures.
¾ Groups of size ~2.
Copyright B. Williams
16.412J/6.834J, Fall 02
Course Objective 4
To apply one or more core reasoning methods to create a
simple agent that is driven by goals or rewards
Plan Activities
Localize
in World
Monitor &
Diagnosis
Interpret
Scenes
Manage Dialogue
Execute &
Adapt
Navigation &
Manipulation
Manipulation
Map and Explore
Accomplished by: Final project during half of course
¾ Implement and demonstrate one or more reasoning methods in a
simple cognitive robot scenario (simulated or hardware).
¾ Final project report.
¾ Short project demonstration.
Copyright B. Williams
16.412J/6.834J, Fall 02
Outline
•
•
•
•
Examples of Robots as Explorers
Course Objectives
Student Introductions and Goals
Introduction to Model-based Programming
Copyright B. Williams
16.412J/6.834J, Fall 02