DexArt：使用关节对象对可泛化的熟练操作进行基准测试

DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects

May 9, 2023

作者: Chen Bao, Helin Xu, Yuzhe Qin, Xiaolong Wang

cs.AI

摘要

为了实现通用用途的机器人，我们需要让机器人像人类一样每天操作关节物体。目前的机器人操作在很大程度上依赖于使用平行夹持器，这限制了机器人只能操作有限的一组物体。另一方面，使用多指机器人手操作将更好地逼近人类行为，并使机器人能够操作各种关节物体。为此，我们提出了一个名为DexArt的新基准，其中涉及在物理模拟器中进行关节物体的熟练操作。在我们的基准中，我们定义了多个复杂的操作任务，机器人手将需要在每个任务中操作各种关节物体。我们的主要重点是评估在看不见的关节物体上学习策略的泛化能力。鉴于双手和物体的高自由度，这是非常具有挑战性的。我们使用强化学习与3D表示学习来实现泛化。通过广泛的研究，我们提供了有关3D表示学习如何影响具有3D点云输入的强化学习决策制定的新见解。更多详细信息请访问https://www.chenbao.tech/dexart/。

English

To enable general-purpose robots, we will require the robot to operate daily articulated objects as humans do. Current robot manipulation has heavily relied on using a parallel gripper, which restricts the robot to a limited set of objects. On the other hand, operating with a multi-finger robot hand will allow better approximation to human behavior and enable the robot to operate on diverse articulated objects. To this end, we propose a new benchmark called DexArt, which involves Dexterous manipulation with Articulated objects in a physical simulator. In our benchmark, we define multiple complex manipulation tasks, and the robot hand will need to manipulate diverse articulated objects within each task. Our main focus is to evaluate the generalizability of the learned policy on unseen articulated objects. This is very challenging given the high degrees of freedom of both hands and objects. We use Reinforcement Learning with 3D representation learning to achieve generalization. Through extensive studies, we provide new insights into how 3D representation learning affects decision making in RL with 3D point cloud inputs. More details can be found at https://www.chenbao.tech/dexart/.