Intelligence without Reason Rodney A Brooks CS 790
Intelligence without Reason Rodney A. Brooks CS 790 X Anil Shankar 1
Overview of the talk • Status-check on research in AI • Intelligence without explicit reasoning systems • Influence of various disciplines and technology on the development of AI • Situatedness, Embodiment, Intelligence and Emergence CS 790 X Anil Shankar 2
Robotics • Static environments • Off board computation • Sense-Model-Plan-Act architectures (SMPA) • Assuming that the static world can scale to the real dynamic world Were these robots “intelligent”? CS 790 X Anil Shankar 3
Re-think Intelligence • Do we always problem-solve and plan? • An agent’s internal representation compared with real-world object representation • Where should the agents be? • Can an agent have goals and beliefs? So how do we re-think then ? CS 790 X Anil Shankar 4
The new manifesto • Situatedness (S) • Embodiment (E) • Intelligence (I) • Emergence (E) • Compare SEIE with SMPA Check your computer for intelligence CS 790 X Anil Shankar 5
Us and Them • Silicon based machines – Von Neumann architecture • Biological machines – Low speed, massively parallel, fixed and bounded network topology, redundancies in design What would the classical AI guys say? CS 790 X Anil Shankar 6
Classical A. I • Turing Test – Allowed disembodiment • Chess – What about Go? • Dartmouth Conference – Search • AI techniques – Search, Pattern recognition, learning, planning and induction (disembodied and non-situated, reliance on performance increases Where did all these ideas come from ? CS 790 X Anil Shankar 7
Other Disciplines • Cybernetics – Organism and it’s environment should be modeled together (situatedness) • Abstraction – Blocks world, controlled environments, Shakey, internal models, complacence with performance in static environments • Knowledge Representation – Represent knowledge, problem-solve, learn …ungrounded! CS 790 X Anil Shankar 8
Other disciplines (2) • Vision – Reconstruct static external world as a three dimensional model • Parallelism – Neural networks, no situatedness, hand-crafted problems, real-world performance missing • Biology – Use ethology to make an ungrounded assumption about hierarchical models of thinking/intelligence CS 790 X Anil Shankar 9
Other disciplines (3) • Psychology – Marr’s view of vision maybe different from biological vision – Representation of knowledge as • Central storage (concepts, individuals, categories, goals, intentions, etc. ) • Knowledge stored independent of the circumstances in which it is acquired • Modality-specific organization of meaning CS 790 X Anil Shankar 10
Other disciplines (4) • Neuroscience – What about the hormones? – Do we know enough about the neurological organization simple creatures? Do we want to consider something that might actually work? CS 790 X Anil Shankar 11
Brave New World • Situatedness – The world is its own best model • Embodiment – The world grounds regress • Intelligence – Intelligence is determined by the dynamics of interaction with the world • Emergence – Intelligence is in the eye of the observer Will these work ? CS 790 X Anil Shankar 12
Brooks’ Approach • Situatedness • Embodiment • Highly reactive architectures with manipulable representations • No symbols and decentralized computation What do we need next? CS 790 X Anil Shankar 13
Domain Principles • Complete integrated intelligent autonomous agents • Embodiment in the real world • Efficient performance in dynamic environments • Operate on time-scales in proportion to that used by humans How do we realize them ? CS 790 X Anil Shankar 14
Computation Principles • Asynchronous network having active computational components • No implicit semantics in exchanged messages • Asynchronously connected sensors and actuators to two-sided buffers What will these ideas help us realize? CS 790 X Anil Shankar 15
Some consequences • A state enabled system and not just a reactive one • Bounded search space • Simple data structures • No implicit separation of data and computation Practice and Principles ? CS 790 X Anil Shankar 16
More on Brooks’ robots • No central model, no central control locus • Network components can perform more than one function • Behavior specific networks, build and test method • No hierarchical arrangement, parallel operation of behaviors (layers) • Use the world itself as a communication medium • Simpler design, on-board computation, miniaturization possible • Limitations – Power, computational capability The real robots please CS 790 X Anil Shankar 17
A few specific robots • Allen – Reactive, sonar, non-reactive goal selecting layer, same computational mechanism for both reactive and non-reactive components • Herbert – World as it’s own model, opportunistic control system, adapt to dynamic changes • Toto – Extract only relevant representations, decentralized, active-maps • Complex goal-directed and intentional behavior with no long term internal state Everything is not peachy CS 790 X Anil Shankar 18
A few issues • Complexity – Environment, sensors and actuators, layers • Learning – Representations for a task, calibration, interaction of modules, new modules • Behaviors – Specification, number, interaction What else is there to do next? CS 790 X Anil Shankar 19
Issues • • • • Convergence Synthesis Complexity Learning Coherence Relevance Adequacy Representation Emergence Communication Cooperation Interference Density Individuality Almost done CS 790 X Anil Shankar 20
Main Points • Status-check on research in AI • Intelligence without explicit reasoning systems, emergent property and evolutionary basis • Influence of various disciplines and technology on the development of AI • Situatedness, Embodiment, Intelligence and Emergence CS 790 X Questions ? Comments? Suggestions ? Anil Shankar 21
- Slides: 21