arXiv 2002.024182020-02-05cs.ROcs.LG

触觉力对手内操作自主学习的效用是依赖于任务的

The utility of tactile force to autonomous learning of in-hand manipulation is task-dependent

University of California San Diego（加利福尼亚大学圣迭戈分校）；University of Southern California（南加利福尼亚大学）

Romina Mir, Ali Marjaninejad, Francisco J. Valero-Cuevas

备注：: 4 pages, 3 figures

摘要：

触觉传感器提供可用于学习和执行操纵任务的信息。然而，不同的任务可能需要不同水平的感官信息，这反过来又可能影响学习率和表现。本文评估了触觉信息的作用，自主学习的操作与模拟3指肌腱驱动的手。我们比较了相同的学习算法（近端策略优化，PPO）学习两个操作任务（滚动一个球的水平轴与旋转刚度和没有）与三个级别的触觉感知：无感测，一维法向力，三维力矢量的能力。令人惊讶的是，与最近的操纵工作相反，与没有感知相比，添加1D力感知并不总是提高学习率-可能是由于正常力是否与任务相关。尽管如此，尽管3D力感测增加了感觉输入的维度--这通常会阻碍算法收敛--但它导致了更快的学习率和更好的性能。我们的结论是，在一般情况下，感官输入是有用的学习，只有当它是相关的任务-是3D力感测的情况下，手操纵重力。此外，3D力感测的效用甚至可以抵消使用更高维的感觉输入学习所增加的计算成本。

英文摘要：

Tactile sensors provide information that can be used to learn and execute manipulation tasks. Different tasks, however, might require different levels of sensory information; which in turn likely affect learning rates and performance. This paper evaluates the role of tactile information on autonomous learning of manipulation with a simulated 3-finger tendon-driven hand. We compare the ability of the same learning algorithm (Proximal Policy Optimization, PPO) to learn two manipulation tasks (rolling a ball about the horizontal axis with and without rotational stiffness) with three levels of tactile sensing: no sensing, 1D normal force, and 3D force vector. Surprisingly, and contrary to recent work on manipulation, adding 1D force-sensing did not always improve learning rates compared to no sensing---likely due to whether or not normal force is relevant to the task. Nonetheless, even though 3D force-sensing increases the dimensionality of the sensory input---which would in general hamper algorithm convergence---it resulted in faster learning rates and better performance. We conclude that, in general, sensory input is useful to learning only when it is relevant to the task---as is the case of 3D force-sensing for in-hand manipulation against gravity. Moreover, the utility of 3D force-sensing can even offset the added computational cost of learning with higher-dimensional sensory input.

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。

摘要：

英文摘要：

相关论文