Learning models of human-robot interaction from small data
Ashkan Zehfroosh,Elena Kokkoni,Herbert G. Tanner,Jeffrey Heinz +3 more
- Vol. 2017, pp 223-228
Reads0
Chats0
TLDR
This paper offers a new approach to learning discrete models for human-robot interaction (HRI) from small data, and adopts a Markov decision process (MDP) as such a model, and selects the transition probabilities through an empirical approximation procedure called smoothing.Abstract:
This paper offers a new approach to learning discrete models for human-robot interaction (HRI) from small data. In the motivating application, HRI is an integral part of a pediatric rehabilitation paradigm that involves a play-based, social environment aiming at improving mobility for infants with mobility impairments. Designing interfaces in this setting is challenging, because in order to harness, and eventually automate, the social interaction between children and robots, a behavioral model capturing the causality between robot actions and child reactions is needed. The paper adopts a Markov decision process (MDP) as such a model, and selects the transition probabilities through an empirical approximation procedure called smoothing. Smoothing has been successfully applied in natural language processing (NLP) and identification where, similarly to the current paradigm, learning from small data sets is crucial. The goal of this paper is two-fold: (i) to describe our application of HRI, and (ii) to provide evidence that supports the application of smoothing for small data sets.read more
Citations
More filters
Journal ArticleDOI
GEARing smart environments for pediatric motor rehabilitation.
Elena Kokkoni,Elena Kokkoni,Effrosyni Mavroudi,Ashkan Zehfroosh,James C. Galloway,René Vidal,Jeffrey Heinz,Herbert G. Tanner +7 more
TL;DR: Preliminary results from this study support the feasibility of both the physical and cyber components of the GEAR system and demonstrate its potential for use in future studies to assess the effects on the co-development of the motor, cognitive, and social systems of very young children with mobility challenges.
Journal ArticleDOI
Statistical Relational Learning With Unconventional String Models
Mai H. Vu,Ashkan Zehfroosh,Kristina Strother-Garcia,Michael A. Sebok,Jeffrey Heinz,Herbert G. Tanner +5 more
TL;DR: Comparison of conventional and unconventional word models shows that in the domains of phonology and robotic planning and control, Markov Logic Networks With unconventional models achieve better performance and less runtime with smaller networks than Markov logic Networks With conventional models.
Proceedings ArticleDOI
Learning option MDPs from small data
TL;DR: An abstraction method for MDPs, with a parameter estimation method originally developed for natural language processing, designed specifically to operate on small data, expedites learning from small data and offers more accurate models that lend themselves to more effective decision-making.
Proceedings ArticleDOI
Infants Respond to Robot's Need for Assistance in Pursuing Action-based Goals
TL;DR: In this article, a decision tree model was created to evaluate a set of annotated variables as potential predictors to infants' spontaneous instrumental helping to robots exhibiting motion challenges, and a Markovian model for robot control was developed where these predictors were used as parameters to promote, in turn, action-based goals for the infants.
Proceedings ArticleDOI
Reactive motion planning for temporal logic tasks without workspace discretization
TL;DR: This paper argues that a large portion of these atomic propositions in the discretization of the robot's workspace is unnecessary, and demonstrates this point by introducing local navigation functions within a temporal logic planning framework, and utilizing register automata for reactive motion planning without explicit, high-resolution workspace discretized.
References
More filters
Book
The Nature of Statistical Learning Theory
TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
Book
Introduction to Discrete Event Systems
TL;DR: This edition includes recent research results pertaining to the diagnosis of discrete event systems, decentralized supervisory control, and interval-based timed automata and hybrid automata models.
Proceedings Article
The complexity of decentralized control of Markov decision processes
TL;DR: In this paper, the authors considered the problem of planning for distributed agents with partial state information from a decision-theoretic perspective, and provided mathematical evidence corresponding to the intuition that decentralized planning problems cannot easily be reduced to centralized problems and solved exactly using established techniques.
Journal ArticleDOI
Nash q-learning for general-sum stochastic games
Junling Hu,Michael P. Wellman +1 more
TL;DR: This work extends Q-learning to a noncooperative multiagent context, using the framework of general-sum stochastic games, and implements an online version of Nash Q- learning that balances exploration with exploitation, yielding improved performance.
Journal ArticleDOI
The Complexity of Decentralized Control of Markov Decision Processes
TL;DR: This work considers decentralized control of Markov decision processes and gives complexity bounds on the worst-case running time for algorithms that find optimal solutions and describes generalizations that allow for decentralized control.