Leveraging Multiple Environments for Learning and Decision Making: a Dismantling Use Case
Leveraging Multiple Environments for Learning and Decision Making: a Dismantling Use Case
复制标题
DOI：
10.1109/iros45743.2020.9341182
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Alejandro Suárez-Hernández;Thierry Gaugry;Javier Segovia Aguas;Antonin Bernardin;C. Torras;M. Marchal;G. Alenyà
中科院分区：
文献类型：
--
作者：
Alejandro Suárez-Hernández;Thierry Gaugry;Javier Segovia Aguas;Antonin Bernardin;C. Torras;M. Marchal;G. Alenyà
学习通常通过观察真实的机器人执行来执行。基于物理的模拟器是一个很好的选择，可以提供非常有价值的信息，同时避免昂贵的和潜在的破坏性机器人执行。我们提出了一种新的方法来学习象征性的机器人动作结果的概率。这是通过在执行时间中利用不同的环境（例如基于物理的模拟器）来完成的。为此，我们提出了MENID（多环境噪声不确定指示）规则，这是一种能够科普机器人任务中存在的固有不确定性的新型表示法。MENID规则明确表示动作的每个可能结果，保持对经验来源的记忆，并保持每个结果的成功概率。我们还介绍了一种算法来分配环境之间的行动，根据以前的经验和预期的增益。在使用基于物理的模拟之前，我们提出了一种方法来评估不同的模拟设置，并确定可以使用的最耗时的模型，同时仍然产生一致的结果。我们证明了该方法在拆卸用例中的有效性，使用降低质量的模拟作为模拟系统，以及具有全分辨率的模拟，其中我们将噪声添加到轨迹和一些物理参数作为真实的系统的表示。
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.