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 2305.02554cs.RO
收藏

学习具备泛化能力的枢转操作技能

Learning Generalizable Pivoting Skills

UC Berkeley(加州大学伯克利分校);Mitsubishi Electric Research Laboratories(三菱电机研究实验室);Rutgers University(罗格斯大学)

Xiang Zhang, Siddarth Jain, Baichuan Huang, Masayoshi Tomizuka, Diego Romeres

AI总结:

针对机器人枢转操作技能泛化难的问题,提出含三步的学习框架:用RL学基准物体枢转策略、监督学习编码物体运动学特征、基于特征学习投影适配新任务,实现仅单张深度图的零样本 sim-to-real 迁移与多物体泛化。

摘要:

由于主要由接触交互产生的外力作用于系统,利用机器人系统完成物体枢转操作的技能颇具挑战性。当要求该技能可在不同物体间泛化时,复杂度会进一步提升。本文提出一种用于学习鲁棒且具备泛化能力的枢转技能的框架,该框架包含三个步骤。首先,我们使用强化学习(Reinforcement Learning,RL)在一个“基准”物体上学习枢转策略。随后,我们通过监督学习获取物体的特征空间,以对任意物体的运动学特性进行编码。最后,为使基准策略适配多种物体,我们基于物体特征学习数据驱动的投影变换,以调整新枢转任务的状态空间与动作空间。所提方法完全在仿真环境中训练,仅需物体的一张深度图像,即可零样本迁移至现实世界中的物体。我们验证了该方法在仿真到现实迁移中的鲁棒性,以及对多种物体的泛化能力。

英文摘要:

The skill of pivoting an object with a robotic system is challenging for the external forces that act on the system, mainly given by contact interaction. The complexity increases when the same skills are required to generalize across different objects. This paper proposes a framework for learning robust and generalizable pivoting skills, which consists of three steps. First, we learn a pivoting policy on an ``unitary'' object using Reinforcement Learning (RL). Then, we obtain the object's feature space by supervised learning to encode the kinematic properties of arbitrary objects. Finally, to adapt the unitary policy to multiple objects, we learn data-driven projections based on the object features to adjust the state and action space of the new pivoting task. The proposed approach is entirely trained in simulation. It requires only one depth image of the object and can zero-shot transfer to real-world objects. We demonstrate robustness to sim-to-real transfer and generalization to multiple objects.

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。

↑