Language and Learning for Robots
Center for the Study of Language (CSLI), 1994 - Computers - 276 pages
Robot technology will find wide-scale use only when a robotic device can be given commands and taught new tasks in a natural language. How could a robot understand instructions expressed in English? How could a robot learn from instructions? Crangle and Suppes begin to answer these questions through a theoretical approach to language and learning for robots and by experimental work with robots.
The authors develop the notion of an instructable robot—one which derives its intelligence in part from interaction with humans. Since verbal interaction with a robot requires a natural language semantics, the authors propose a natural-model semantics which they then apply to the interpretation of robot commands. Two experimental projects are described which provide natural-language interfaces to robotic aids for the physically disabled. The authors discuss the specific challenges posed by the interpretation of "stop" commands and the interpretation of spatial prepositions.
The authors also examine the use of explicit verbal instruction to teach a robot new procedures, propose ways a robot can learn from corrective commands containing qualitative spatial expressions, and discuss the machine-learning of a natural language use to instruct a robot in the performance of simple physical tasks. Two chapters focus on probabilistic techniques in learning.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Natural Models for the Interpretation
Contextfixing Semantics and Model
Models for Arithmetic Instruction
Verbal Commands to a Mobile Robot
Verbal Commands to a Robotic Arm
Saying Stop to a Robot
Learning Natural Language from Robot Task
Partial tree for Case 4
Mean learning curve for Case 4
Partial tree for Case 5
Mean learning curve for Case 6
Mean learning curve for Case 7
Mean learning curve for Case 8
Mean learning curve for Case 10
Discourse on Arithmetic Instruction
Robot Learning from Corrective Instruction
absolute geometry action affine geometry agent analysis ARG1 ARG2 argument associated axiom beta distribution chair chapter cognitive and perceptual complex computation context context-free grammar defined described dialog digit distance English environment Euclidean geometry example execution expression feedback Figure geometry given grammatical form gripper horizontal instance instructible robots intention interaction internal representation interpretation lexical linguistic LISP Look mean learning curve model-theoretic motion routines move MOVE-GRIPPER natural language natural-language commands noun phrase operation ordering relation orientation parse tree parser perceptual object perceptual situation physical plate POBJ prepositions procedure Production Rule recursive reference region relative response robot-level programming sample Section Semantic tree sentences sequence set of models shelf simple space specific stop symbol syntactic syntactic categories tasks theory tion top spot trial typically verb phrase verbal command vertically West Coast Conference