arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.01667cs.ROcs.AI
收藏

连续动作空间中结合机器人先验的低维状态表示学习

Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces

University of Twente(特文特大学);IAV GmbH (Volkswagen Group)(IAV有限公司(大众集团));Jönköping University(延雪平大学);Saxion University of Applied Sciences(萨克逊应用科学大学)

Nicolò Botteghi, Khaled Alaa, Mannes Poel, Beril Sirmacek, Christoph Brune, Abeje Mersha, Stefano Stramigioli

AI总结:

本文提出联合学习低维状态表示与最优策略的强化学习框架,以提升连续状态和动作空间中移动机器人导航的样本效率,并验证仿真到真实机器人的无再训练迁移能力。

摘要:

自主机器人要进入我们的日常生活,需要具备高度的认知与运动智能。在非结构化环境以及存在不确定性的情况下,这样的智能水平并不容易获得。强化学习算法已经被证明能够以端到端方式解决复杂的机器人任务,而无需任何手工设计的特征或策略。特别是在机器人领域,真实世界数据的成本通常极高,因此需要能够实现高样本效率的强化学习解决方案。本文提出一个框架,将两方面学习结合起来:一是从机器人原始传感器读数产生的高维观测中学习低维状态表示,二是在给定所学状态表示的情况下学习最优策略。我们在连续状态空间和动作空间情形下的移动机器人导航场景中评估该框架。此外,我们研究了在存在视觉和深度干扰因素(例如光照变化和移动障碍物)的情况下,如何将在模拟虚拟环境中学到的内容迁移到真实机器人,而无需使用真实世界数据进行进一步再训练。

英文摘要:

Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, such degrees of intelligence are not easy to obtain. Reinforcement learning algorithms have proven to be capable of solving complicated robotics tasks in an end-to-end fashion without any need for hand-crafted features or policies. Especially in the context of robotics, in which the cost of real-world data is usually extremely high, reinforcement learning solutions achieving high sample efficiency are needed. In this paper, we propose a framework combining the learning of a low-dimensional state representation, from high-dimensional observations coming from the robot's raw sensory readings, with the learning of the optimal policy, given the learned state representation. We evaluate our framework in the context of mobile robot navigation in the case of continuous state and action spaces. Moreover, we study the problem of transferring what learned in the simulated virtual environment to the real robot without further retraining using real-world data in the presence of visual and depth distractors, such as lighting changes and moving obstacles.

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。

↑