Copyright B. Williams16.412J/6.834J, Fall 02Introduction To Cognitive RobotsProf. Brian WilliamsRm 33-418Wednesday, February 2nd, 2004Copyright B. Williams16.412J/6.834J, Fall 02Outline• Examples of Robots as Explorers• Course Objectives• Student Introductions and Goals• Introduction to Model-based ProgrammingCopyright B. Williams16.412J/6.834J, Fall 02Course Objective 1To 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. Williams16.412J/6.834J, Fall 02Immobile Robots in SpaceCopyright B. Williams16.412J/6.834J, Fall 02courtesy NASA AmesCopyright B. Williams16.412J/6.834J, Fall 02Autonomous Systems use Models toAnticipate or Detect Subtle FailuresNASA Mars Habitat600 700 800 900 1000 1100 1200 1300 1400400500600700800900100011001200time (minutes)CO2 concentration (ppm)crew requests entry toplant growth chambercrew enters chamberlighting faultcrew leaveschamberAirlockPlant Growth ChamberCrew ChamberCO2tanklighting systemchamber controlflow regulator 2pulse injection valvesCO2flow regulator 1Copyright B. Williams16.412J/6.834J, Fall 02The Role of Robots in Human ExplorationCopyright B. Williams16.412J/6.834J, Fall 02Robonaut: Robotic Assistance For Orbital Assembly and RepairCopyright B. Williams16.412J/6.834J, Fall 02Exploration by Quadrapeds and Bi-PedsMarc Raibert, MIT Leg Lab & Boston DynamicsCopyright B. Williams16.412J/6.834J, Fall 02Outline• Examples of Robots as Explorers• Course Objectives• Student Introductions and Goals• Introduction to Model-based ProgrammingCopyright B. Williams16.412J/6.834J, Fall 02Course Objective 2• To understand advanced methods for creating highly capable cognitive robots.Accomplished by:¾ Lectures on advanced core methods¾ ~ Implement & empirically compare two core methods.Plan ActivitiesExecute &AdaptMonitor &DiagnosisLocalize in WorldNavigation &ManipulationMap and ExploreInterpretScenesManipulationManage DialogueCopyright B. Williams16.412J/6.834J, Fall 02Lectures: Planning and Acting RobustlyMonitoring, and Diagnosis• Diagnosing Multiple Faults• Constraint-based Monitoring • Hybrid Monitoring and EstimationPlanning Missions• Planning using Informed Search• Planning with Time and Resources• Robust Plan Execution Through Dynamic Scheduling• Reactive Planning and ExecutionPlan ActivitiesExecute &AdaptMonitor &DiagnosisCopyright B. Williams16.412J/6.834J, Fall 02Lectures: Interacting With The WorldSimultaneous Localization and Mapping•Basic SLAM• Vision-based SLAMCognitive Vision• Visual Interpretation using Probabilistic Grammars• Context-based VisionNavigation & Manipulation• Probabilistic Path Planning• Exploring Unknown EnvironmentsHuman - Robot Interaction• Discourse Management & Nursebot• Social RoboticsLocalize in WorldNavigation &ManipulationInterpretScenesManipulationMap and ExploreManage DialogueCopyright B. Williams16.412J/6.834J, Fall 02Lectures: Fast, Large-scale ReasoningOptimality and Soft Constraints• Optimal CSPs and Conflict-Learning• Valued CSPs and Dynamic Programming • Solving CSPS through Tree DecompositionIncremental Methods• Incremental Satisfiability• Incremental Scheduling• Incremental Path PlanningAny-TimeEnumerationSymbolic State Space EncodingsIncremental ReasoningStructuralDecompositionCopyright B. Williams16.412J/6.834J, Fall 02Topics 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 SystemsCopyright B. Williams16.412J/6.834J, Fall 02Course 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 topic¾ One 40 minute lecture per student¾ tutorial article on ~2 methods, to support lectures.¾ Groups of size ~2.Copyright B. Williams16.412J/6.834J, Fall 02Course Objective 4To apply one or more core reasoning methods to create a simple agent that is driven by goals or rewardsAccomplished by: Final project during half of course¾ 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.Plan ActivitiesExecute &AdaptMonitor &DiagnosisLocalize in WorldNavigation &ManipulationMap and ExploreInterpretScenesManipulationManage DialogueCopyright B. Williams16.412J/6.834J, Fall 02Outline• Examples of Robots as Explorers• Course Objectives• Student Introductions and Goals• Introduction to Model-based
View Full Document