Using Stochastic Grammars to Learn Robotic Tasks
نویسندگان
چکیده
The paper introduces a reinforcement learning-based methodology for performance improvement of Intelligent Controllers. The translation interfaces of a 3-level Hierarchical Goal-Directed Intelligent Machine (HGDIM) are modeled by a 2-stage Hierarchical Learning Stochas-tic Automaton (HLSA). The decision probabilities at the two stages are recursively updated from the success and failure signals received by the bottom stage whenever a primitive action of the HGDIM is applied to the environment where the machine operates. The top translation stage and the use of regular stochastic grammars to accomplish the translation of commands into tasks are described here. Under this framework, subsets of connicting grammar productions represent diierent task strategies to accomplish a command. At this stage, an LSA is associated to each subset of connicting grammar productions. Results of simulations show the application of the methodology to an Intelligent Robotic System.
منابع مشابه
Human Action Forecasting by Learning Task Grammars
For effective human-robot interaction, it is important that a robotic assistant can forecast the next action a human will consider in a given task. Unfortunately, real-world tasks are often very long, complex, and repetitive; as a result forecasting is not trivial. In this paper, we propose a novel deep recurrent architecture that takes as input features from a twostream Residual action recogni...
متن کاملSoccer Goalkeeper Task Modeling and Analysis by Petri Nets
In a robotic soccer team, goalkeeper is an important challenging role, which has different characteristics from the other teammates. This paper proposes a new learning-based behavior model for a soccer goalkeeper robot by using Petri nets. The model focuses on modeling and analyzing, both qualitatively and quantitatively, for the goalkeeper role so that we have a model-based knowledge of the ta...
متن کاملTwo Algorithms for Learning the Parameters of Stochastic Context-Free Grammars
Stochastic context-free grammars (SCFGs) are often used to represent the syntax of natural languages. Most algorithms for learning them require storage and repeated processing of a sentence corpus. The memory and computational demands of such algorithms are illsuited for embedded agents such as a mobile robot. Two algorithms are presented that incrementally learn the parameters of stochastic co...
متن کاملDeep Reinforcement Learning for Robotic Manipulation - The state of the art
The focus of this work is to enumerate the various approaches and algorithms that center around application of reinforcement learning in robotic manipulation tasks. Earlier methods utilized specialized policy representations and human demonstrations to constrict the policy. Such methods worked well with continuous state and policy space of robots but failed to come up with generalized policies....
متن کاملIncrementally Learning Parameters of Stochastic Context-Free Grammars using Summary Statistics and Repeated Sampling
We are interested in how robots might learn language from exposure to utterances and sensory information about the physical contexts in which they occur. Although stochastic context free grammars are often used to represent the syntactic structure of natural languages, most algorithms for learning them from data require repeated processing of a corpus of sentences. The memory and computational ...
متن کامل