arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.02440cs.ROcs.AI
收藏

多约束最优性下的局部导航多样化技能学习

Learning Diverse Skills for Local Navigation under Multi-constraint Optimality

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);ETH Zürich(苏黎世联邦理工学院);University of Tübingen(图宾根大学)

Jin Cheng, Marin Vlastelica, Pavel Kolev, Chenhao Li, Georg Martius

AI总结:

针对数据驱动控制中多样化行为提取难、需牺牲任务性能的问题,本研究从约束优化视角处理质量-多样性权衡,结合范德华力启发的吸引-排斥奖励项控制多样性,在四足机器人局部导航任务中验证有效,且可迁移至真实Solo12机器人实现多样化敏捷避障。

摘要:

尽管数据驱动控制在机器人领域已有诸多成功应用,但提取有意义的多样化行为仍是一项挑战。通常情况下,为实现多样性需要牺牲任务性能。在许多场景中,任务要求被指定为多个奖励项,每一项都需要不同的权衡。本研究从约束优化的视角看待质量-多样性权衡问题,表明我们可以在对由不同奖励定义的值函数施加约束的同时,获得多样化策略。与先前研究一致,我们可以通过受范德华力启发的吸引-排斥奖励项,进一步实现对多样性水平的控制。我们在四足机器人需在有限时间内到达目标的局部导航任务上验证了方法的有效性。最后,我们训练得到的策略可良好迁移到真实的12自由度四足机器人Solo12上,并展现出多样化的敏捷行为,能成功穿越障碍物。

英文摘要:

Despite many successful applications of data-driven control in robotics, extracting meaningful diverse behaviors remains a challenge. Typically, task performance needs to be compromised in order to achieve diversity. In many scenarios, task requirements are specified as a multitude of reward terms, each requiring a different trade-off. In this work, we take a constrained optimization viewpoint on the quality-diversity trade-off and show that we can obtain diverse policies while imposing constraints on their value functions which are defined through distinct rewards. In line with previous work, further control of the diversity level can be achieved through an attract-repel reward term motivated by the Van der Waals force. We demonstrate the effectiveness of our method on a local navigation task where a quadruped robot needs to reach the target within a finite horizon. Finally, our trained policies transfer well to the real 12-DoF quadruped robot, Solo12, and exhibit diverse agile behaviors with successful obstacle traversal.

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。

↑