Leveraging Multiple Environments for Learning and Decision Making: a Dismantling Use Case

TL;DR

This paper introduces MENID rules, a novel method for learning probabilistic outcomes of robotic actions across multiple environments, including physics-based simulators, to improve decision making in robotic tasks.

Contribution

It presents MENID rules for representing uncertain action outcomes and an algorithm for environment action distribution, along with a methodology for selecting optimal simulation settings.

Findings

MENID effectively models outcome uncertainties in robotic tasks.

The approach reduces reliance on costly real robot executions.

Validation in a dismantling scenario demonstrates practical applicability.

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.