Publication
Leveraging multiple environments for learning and decision making: a dismantling use case
Conference Article
Conference
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Edition
2020
Pages
6902-6908
Doc link
https://dx.doi.org/10.1109/IROS45743.2020.9341182
File
Authors
-
Suárez Hernández, Alejandro
-
Gaugry, Thierry
-
Segovia Aguas, Javier
-
Bernardin, Antonin
-
Torras Genís, Carme
-
Marchal, Maud
-
Alenyà Ribas, Guillem
Projects associated
Abstract
Learning is usually performed by observing real robot executions. Physics-based simulators are a good alternative for providing highly valuable information while avoiding costly and potentially destructive robot executions. We present a novel approach for learning the probabilities of symbolic robot action outcomes. This is done leveraging different environments, such as physics-based simulators, in execution time. To this end, we propose MENID (Multiple Environment Noise Indeterministic Deictic) rules, a novel representation able to cope with the inherent uncertainties present in robotic tasks. MENID rules explicitly represent each possible outcomes of an action, keep memory of the source of the experience, and maintain the probability of success of each outcome. We also introduce an algorithm to distribute actions among environments, based on previous experiences and expected gain. Before using physics-based simulations, we propose a methodology for evaluating different simulation settings and determining the least time-consuming model that could be used while still producing coherent results. We demonstrate the validity of the approach in a dismantling use case, using a simulation with reduced quality as simulated system, and a simulation with full resolution where we add noise to the trajectories and some physical parameters as a representation of the real system.
Categories
learning (artificial intelligence), planning (artificial intelligence).
Author keywords
Uncertainty, Decision making, Simulation
Scientific reference
A. Suárez, T. Gaugry, J. Segovia, A. Bernardin, C. Torras, M. Marchal and G. Alenyà. Leveraging multiple environments for learning and decision making: a dismantling use case, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020, Las Vegas, NV, USA, pp. 6902-6908.
Follow us!