embodied thought — recent robotics (some highlights)
DESCRIPTION
Embodied Thought — Recent Robotics (some highlights). 1948 — Grey Walter’s “Tortoises”. Simple neural net-inspired “brain” Showed simple “brains” can lead to complex, life-like, intelligent behavior Could find their way to recharging station Simple (Pavlovian) learning - PowerPoint PPT PresentationTRANSCRIPT
CS 102 with Robots
Embodied Thought —
Recent Robotics (some highlights)
2009-08-20
1
1948 — Grey Walter’s “Tortoises”
Simple neural net-inspired “brain”Showed simple “brains” can lead to complex, life-like, intelligent behaviorCould find their way to recharging stationSimple (Pavlovian) learningSimilarities to “Braitenberg vehicles” (LCR, ch. 6) and Scribblers
2009-08-20 2
Ancestors of the Scribbler
2009-08-20 3
Grey Walter’s tortoises
Seymour Papert’s turtles
turtle graphics
the Scribbler
2009-08-204
Importance ofEmbodied Intelligence
Traditional (dualist) view: mind is essentially independent of the body
in principle, could have an intelligent “brain in a vat”Now we understand that much of our knowledge is implicit in the fact that we have a bodyAlso, our body teaches us about the worldStructure of body is foundation for structure of knowledgeKnowledge is in the environment, rather than a representation of the environment
2009-08-205
Structure of Embodied Intelligence
Representational primitives are skills, not concepts
Higher-level skills are built on lower-level
Lowest-level skills are grounded in the body
2009-08-206
Embodied & Situated Artificial Intelligence
Therefore a genuine AI must be:embedded in a body (embodied)capable of interacting significantly with its world (situated)
Intelligence develops as consequence of interaction of body with environment, including other agentsHow can we investigate embodied, situated intelligence?
2009-08-20 7
1990s — “Ant” Microrobots (Rodney Brooks, MIT)
About 1 cubic inch17 sensorsCan communicate with each otherGoal: push limits of microroboticsGoal: explore social interactions inspired by ant colonyApplications: explosives disposal, Mars exploration
1990s — Clustering Around “Food”
“Food” amongst other objects in environmentFirst “ant” to encounter food, signals othersOthers cluster at food source
2009-08-20 8
1990s — Tag Game
“It” robot wanders until bumps somethingTransmits “Tag”A “Not It” robot replies “I got tagged”First becomes “Not It”Second becomes “It”
2009-08-20 9
2009-08-20 10
1990s — Genghis (Brooks, MIT)
Subsumption architecture
Inspired by evolution: more complex behaviors build on simpler onesIndividual legs “do their jobs”Legs are coordinated to achieve stabilityLeg motion coordinated to achieve locomotion to goal
2009-08-20 11
1990s — Genghis (Brooks, MIT)
Front view & infrared sensing of person
2009-08-20 12
1998 — Cog (Brooks, MIT)
“Humanoid intelligence requires humanoid interactions with the world”Form of body is fundamental to cognitive representation
no “brains in vats”Human-like intelligence requires human-like body
2009-08-20 13
2001 — Leonardo
Cynthia Breazeal’s Lab, MIT“Sociable Robots” ProjectVehicle for exploring socially guided learning & cooperative activity
(video < Breazeal’s Lab)
2001 — Touch-Sensitive “Skin”
Touch-sensitive silicone skin over entire bodyMapped to neural net-like “homunculus”Here Leo is programmed to notice & withdraw from contact
2009-08-20 14
(video < Breazeal’s Lab)
2009-08-20 15
2004–7 — Socially Guided Learning
Leo is taught to “turn on all the lights”Leo generalizes to new situationLeo displays commitment to joint activity in spite of incorrect action
(video < Breazeal’s Lab)
2004–7 — Collaborative tasks
Leo and human collaborate on a task (making sailboat and smiley face from colored blocks)Have a common goal toward which the are workingUse gestures and social cues to cooperate
2009-08-20 16
2009-08-2017
???? — Consciousness and self-awareness?
Algorithms