基于最小模拟器的工业卡车卸货机器人学习优化决策
Learning Optimal Decision Making for an Industrial Truck Unloading Robot using Minimal Simulator Runs
摘要:
考虑一辆装满不同大小和未知质量的箱子的卡车,以及一个带有末端执行器的工业机器人,它可以从任何可到达的位置卸载多个箱子。在这项工作中,我们将研究如何将机器人与模拟器的帮助下,学习最大限度地减少每个动作卸载的箱子的数量。大多数像我们这样的高保真机器人模拟器都很耗时。因此,我们研究了上述学习问题,重点是最小化所需的模拟运行次数。在这种情况下的最优决策问题可以表述为一个多类分类问题。然而,为了获得任何动作的结果,需要我们运行耗时的模拟器,从而限制了可以收集的训练数据的量。因此,我们需要一种数据高效的方法来学习分类器,并以最小的数据量对其进行泛化。高保真物理模拟器通常用于涉及多体相互作用的复杂操作任务。为此,我们训练一个最佳的决策树作为分类器,并为每个分支的决策树,我们的原因在决策中的信心使用可能近似正确(PAC)的框架,以确定是否更多的模拟器数据将有助于达到一定的置信水平。这为我们提供了一种机制来评估何时可以避免某些决策的模拟,以及何时模拟将改善决策。对于卡车卸载问题,我们的实验表明,一个显着减少模拟器运行可以实现使用所提出的方法相比,天真地运行模拟器收集数据,以训练同样执行决策树。
英文摘要:
Consider a truck filled with boxes of varying size and unknown mass and an industrial robot with end-effectors that can unload multiple boxes from any reachable location. In this work, we investigate how would the robot with the help of a simulator, learn to maximize the number of boxes unloaded by each action. Most high-fidelity robotic simulators like ours are time-consuming. Therefore, we investigate the above learning problem with a focus on minimizing the number of simulation runs required. The optimal decision-making problem under this setting can be formulated as a multi-class classification problem. However, to obtain the outcome of any action requires us to run the time-consuming simulator, thereby restricting the amount of training data that can be collected. Thus, we need a data-efficient approach to learn the classifier and generalize it with a minimal amount of data. A high-fidelity physics-based simulator is common in general for complex manipulation tasks involving multi-body interactions. To this end, we train an optimal decision tree as the classifier, and for each branch of the decision tree, we reason about the confidence in the decision using a Probably Approximately Correct (PAC) framework to determine whether more simulator data will help reach a certain confidence level. This provides us with a mechanism to evaluate when simulation can be avoided for certain decisions, and when simulation will improve the decision making. For the truck unloading problem, our experiments show that a significant reduction in simulator runs can be achieved using the proposed method as compared to naively running the simulator to collect data to train equally performing decision trees.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。