7/30/2019 l1a Cogn Robotic

1/17

Copyright B. Williams 16.412J/6.834J, Fall 02

Introduction To Cognitive Robots

Prof. Brian Williams

Wednesday, February 2nd, 2004

7/30/2019 l1a Cogn Robotic

2/17

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

7/30/2019 l1a Cogn Robotic

3/17

Copyright B. Williams 16.412J/6.834J, Fall 02

Course Objective 1

To understand the main types of cognitive robotsand 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:

Case studies, invited lectures & final projects.

7/30/2019 l1a Cogn Robotic

4/17Copyright B. Williams 16.412J/6.834J, Fall 02

Immobile Robots in Space

7/30/2019 l1a Cogn Robotic

5/17Copyright B. Williams 16.412J/6.834J, Fall 02courtesy NASA Ames

7/30/2019 l1a Cogn Robotic

6/17Copyright B. Williams 16.412J/6.834J, Fall 02

Autonomous Systems use Models to

Anticipate or Detect Subtle Failures

NASA Mars Habitat

600 700 800 900 1000 1100 1200 1300 1400

400

500

600

700

800

900

1000

1100

1200

time (minutes)

CO

2concentratio

n

(ppm)

crew requests entry toplant growth chamber

crew enters chamber

lighting fault

crew leaves

chamber

Airlock Plant Growth Chamber

CrewChambe

r

CO2

tank

lighting system

chambercontrol

flow regulator 2

pulse injection valves

CO2

flow regulator 1

7/30/2019 l1a Cogn Robotic

7/17Copyright B. Williams 16.412J/6.834J, Fall 02

The Role of Robots in Human Exploration

7/30/2019 l1a Cogn Robotic

8/17Copyright B. Williams 16.412J/6.834J, Fall 02

Robonaut: Robotic Assistance For

Orbital Assembly and Repair

7/30/2019 l1a Cogn Robotic

9/17

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

7/30/2019 l1a Cogn Robotic

10/17

Copyright B. Williams 16.412J/6.834J, Fall 02

Course Objective 2

To understand advanced methods for creatinghighly capable cognitive robots.

Accomplished by:

Lectures on advanced core methods

~ Implement & empirically compare two core methods.

Plan Activities

Execute &

Adapt

Monitor &

Diagnosis

Localize

in WorldNavigation &

Manipulation

Map and Explore

Interpret

ScenesManipulation

Manage Dialogue

7/30/2019 l1a Cogn Robotic

11/17

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 andExecution

Plan Activities

Execute &

Adapt

Monitor &

Diagnosis

7/30/2019 l1a Cogn Robotic

12/17

Copyright B. Williams 16.412J/6.834J, Fall 02

Lectures: Interacting With The World

Simultaneous Localization and

Mapping

Basic SLAM

Vision-based SLAM

Cognitive Vision

Visual Interpretation usingProbabilistic Grammars

Context-based Vision

Navigation & Manipulation

Probabilistic Path Planning

Exploring Unknown

Environments

Human - Robot Interaction

Discourse Management &Nursebot

Social Robotics

Localize

in WorldNavigation &

Manipulation

Interpret

ScenesManipulation

Map and ExploreManage Dialogue

7/30/2019 l1a Cogn Robotic

13/17

Copyright B. Williams 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

EnumerationSymbolic State

Space EncodingsIncremental

Reasoning Structural

Decomposition

7/30/2019 l1a Cogn Robotic

14/17

Copyright B. Williams 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

7/30/2019 l1a Cogn Robotic

15/17

Copyright B. Williams 16.412J/6.834J, Fall 02

Course Objective 3

To dive into the recent literature, and collectivelysynthesize, clearly explain and evaluate the state

of the art in cognitive robotics.

Accomplished by:Group lectures on advance topic

One 40 minute lecture per student

tutorial article on ~2 methods, to support lectures.Groups of size ~2.

7/30/2019 l1a Cogn Robotic

16/17

Copyright B. Williams 16.412J/6.834J, Fall 02

Course Objective 4

To apply one or more core reasoning methods to create asimple agent that is driven by goals or rewards

Accomplished by: Final project during half of course Implement and demonstrate one or more reasoning methods in a

simple cognitive robot scenario (simulated or hardware).

Final project report. Short project demonstration.

Plan Activities

Execute &

Adapt

Monitor &

Diagnosis

Localizein World Navigation &Manipulation

Map and Explore

InterpretScenes Manipulation

Manage Dialogue

7/30/2019 l1a Cogn Robotic

17/17

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