Presentation on theme: "From Intelligent Control to Cognitive Control: A Perspective from Cognitive Robot Engineering Point of View Kaz Kawamura Center for Intelligent Systems."— Presentation transcript:
1From Intelligent Control to Cognitive Control: A Perspective from Cognitive Robot Engineering Point of ViewKaz KawamuraCenter for Intelligent SystemsVanderbilt University
2BackgroundOur group have been working on a robotic system called ISAC (Intelligent Soft Arm Control) since late 1980s (as an industry-sponsored project.)ISAC was initially developed as a robotic aid system using vision, voice and haptic-based adaptive control.
3BackgroundOur group have been working on a robotic system called ISAC (Intelligent Soft Arm Control) since late 1980s (as an industry-sponsored project.)Long-term goal was to develop an assembly “horon” (i.e. a cognitive co-worker) for intelligent manufacturing systems.
4BackgroundOur group have been working on a robotic system called ISAC (Intelligent Soft Arm Control) for the last fifteen years.ISAC was initially developed as a robotic aid system using vision, voice and haptic-based adaptive control.Over the years, we gradually added hardware components and adopted a modular software development approach, i.e. multi-agent-based “hybrid architecture ( more like one Troy Kelly mentioned)”.
5BackgroundOur group have been working on a humanoid robotic system called ISAC (Intelligent Soft Arm Control) for the last ten years.ISAC was initially developed as a robotic aid system using haptic-based adaptive control.In the last several years, we are adding computational modules to incorporate some of cognitive psychology (i.e. an central executive (A. Baddeley)) and neuroscience (i.e. an adaptive working memory (David Noelle))-based models to realize “cognitive control “ functionalities to ISAC.
6Are these robots intelligent, cognitive or neither? COG, MIT (Is COG the “Father of cognitive robots”?)ISAC, VanderbiltRobonaut, NASA (Is it a vision of an ultimate cognitive robot?)Many others shown by the workshop participants (Rolf, Olaf, Owen, etc.)
7HypothesisArtificial cognitive agents must share key features and “neurobiological and cognitive principles” (Jeff Krichmar) with humans if they are to become effective partners and coworkers in the human society.
8Process of Cognitive (or Executive) Control Human (and some animal) brain is known to process a variety of stimuli in parallel and choose appropriate action under conflicting goals. (Figure below was taken from: P. Haikonen, The Cognitive Approach to Conscious Machine, 2003)
9Human Cognitive Control Functions Ability of the brain to execute task and resolve conflictsFocus on task context and ignore distractionInvolves action selection and control where reactive sensorimotor-based action execution falls short of task demands. Example: Stroop testCognitive ControlModified from: Miller, E.K., Cognitive Control: Understanding the brain’s executive, in Fundamentals of the Brain and Mind, Lecture 8, June 11-13, 2003, MIT.Vanderbilt University
10Stroop Test (Experiment) (J. R Stroop Test (Experiment) (J.R. Stroop, Studies of interference in serial verbal reaction, J. of Experimental Psychology, 1935)One classic experiment used to demonstrate and test the ability of human cognitive control to inhibit competing responses.The participants are asked to do the following task:In this task, a lists of words is presented on colored papers.“name the color” of the written text (red, blue, green, etc.) as fast as possible.Experiments found that people are more easily distracted by words than color, i.e. they had a harder time to name the color different from the text written on it.Cognitive Control
12Key Features of Cognitive Robots (A Partial/Unproven/Controvertial List ) Ability to perceive the world in a similar way to humans (or better) (e.g., “active perception”, Olaf Sporns, “ecological approach to perception”, JJ Gibson)Ability to develop cognition through sensorymotor coordination (e.g., “morphological computation”, Rolf Pfeifer)Ability to communicate with humans using natural language and mental models (robust HRI such as overcoming the frame of reference problem, Alan Schultz)Ability to have a sense of self awareness (internal model and machine consciousness, Igor Alexander, Owen Holland vs. Kevin O”Reagan)Ability to use attention and emotion to control behaviors (cognitive control)NASA’s RobonautVanderbilt University
13Concept of a Cognitive Robotic System Adapted from a DARPA ITPO Program web site, 2003.
14Working DefinitionCognitive Control for robots is the attention- and emotion-based robust sensory-motor intelligence to execute the task in hand or switch tasks under conflicting goals.
15Working Memory System STM LTM Action Stimuli Atomic Agents Head Agent Arm AgentsActionActuatorsHumanAgentHand AgentsLegendSES= Sensory EgoSpherePM= Procedural MemorySM=Semantic MemoryEM=Episodic MemoryCEA=Central Executive AgentSelf AgentStimuliPerceptionEncodingsSensorsCEAWorkingMemorySystemCompletedSESCurrently being implementedAttentionNetworkSTMBehavior 1…Behavior N…SMEMPMLTMBehaviors
16Cognitive Control on ISAC Ability to use attention and emotion to control behaviors (i.e., cognitive control) is being implemented using the Sensory EgoSphere, the Attention Network, Emotion, the Working Memory System, the Central Executive Agent, and others.Vanderbilt University
17Current WorkCurrent Work is aimed at testing how modules involved in cognitive control work together as a system:1. Working Memory System Training[Poster Presentation by Stephen Gordon]2. Situation-based Action Selection
181. Control Structure used during working memory system training
19Experiment I: Working Memory Training for a Percept-Action Task ISAC is trained to recognize specific objectsi.e., several colored bean bags.2. ISAC is taught a small set of motion behaviorsi.e., reach, wave, handshake.3. Bean bags are rearranged.4. ISAC is asked to “reach to the bean bag”(color is not specified).Vanderbilt University
20Experiment IISAC is trained to recognize specific objects ,i.e., several colored bean bags.ISAC is taught a small set of motion behaviors ,i.e., reach, wave, handshake.Bean bags are rearranged.ISAC is asked to “reach to the bean bag” (color is not specified).ISAC will attempt to load the relevant “chunks” into WMS for appropriate:action to take (reach, wave, etc.)percept to act upon.Over time, ISAC should learnwhich “chunk” (i.e., a percept-behavior combination) is the most appropriate to chooseVanderbilt University
25Experiment II: Situation-Based Task Switching (Under Investigation) Vanderbilt University
26Experiment IIA simulation experiment to test key system components for cognitive control using CEA, attention network, and emotionA simple situation-based task switching using the Focus of Attention (next slide) is being
30What have we learned so far? Effectiveness of using a computational neuroscience-based working memory model for perception-behavior learning on a robot (proof of concept)Computational time of the WM software library is expected to grow exponentially as the robot accumulates experience (classical AI problem) (effective use of episodic memory?)WM model does not seem effective for task switchingNeeds a better mechanism than a FOA-based situational change for task switching (=> dynamic modeling of situations)
31Thank you!For further information, please visit our website at:Vanderbilt University
32BackgroundOur group have been working on a humanoid robotic system called ISAC (Intelligent Soft Arm Control) for the last ten years.ISAC was initially developed as a robotic aid system using sensor-based intelligent control.
34Self AgentThe key agent in our cognitive architecture is the Self Agent.Minsky calles it the “Self Model” in his forthcoming book, The Emotion Machine.Actually he uses the term “Self Models” which include both the Self Agent and the Human Agent in our architecture.
35Self Agent STM LTM Human Agent Atomic Agents SES Working Memory System DescriptionAgentIntention AgentAtomicAgentsAnomaly DetectionAgentActivator AgentMental ExperimentAgentEmotion AgentLegendSES= Sensory EgoSpherePM= Procedural MemorySM=Semantic MemoryEM=Episodic MemoryCEA=Central Executive AgentFirst-orderResponse AgentCentral ExecutiveAgentCompletedCurrently being implementedNot yet implementedSESWorkingMemorySystemSMPMBehavior 1…Behavior NEMSTM…LTMBehaviors
36Central Executive Agent (CEA): Robotic Frontal Lobes responsible for cognitive control functions Inspired by the “central executive” from Baddeley’s working memory model (Baddeley, 1986)Functions of CEA includeObtaining task sequence for task executionDecision makingAction executionTask monitoringDecisionMakingTaskExecutionTask-relatedPerceptsResponseTo PerceptsFromInitialKnowledgeEnvironmentTask executionsequencesCandidate TaskExecution SequencesSelected TaskActionFeedbackA. Baddeley, Working Memory, 11, Oxford Psychology Series, Oxford: Clarendon Press, 1986.Vanderbilt University
37Questions1. How could cognitive control be implemented in robotics? (model or no model?)2. How does one know when a robot becomes a cognitive robot?Vanderbilt University