Khin P M, Low Jin H, Ang Marcelo H, Yeow Chen H
Advanced Robotics Centre, National University of Singapore, Singapore, Singapore.
Department of Mechanical Engineering, National University of Singapore, Singapore, Singapore.
Front Robot AI. 2021 Mar 31;8:619390. doi: 10.3389/frobt.2021.619390. eCollection 2021.
This paper introduces the development of an anthropomorphic soft robotic hand integrated with multiple flexible force sensors in the fingers. By leveraging on the integrated force sensing mechanism, grip state estimation networks have been developed. The robotic hand was tasked to hold the given object on the table for 1.5 s and lift it up within 1 s. The object manipulation experiment of grasping and lifting the given objects were conducted with various pneumatic pressure (50, 80, and 120 kPa). Learning networks were developed to estimate occurrence of object instability and slippage due to acceleration of the robot or insufficient grasp strength. Hence the grip state estimation network can potentially feedback object stability status to the pneumatic control system. This would allow the pneumatic system to use suitable pneumatic pressure to efficiently handle different objects, i.e., lower pneumatic pressure (50 kPa) for lightweight objects which do not require high grasping strength. The learning process of the soft hand is made challenging by curating a diverse selection of daily objects, some of which displays dynamic change in shape upon grasping. To address the cost of collecting extensive training datasets, we adopted one-shot learning (OSL) technique with a long short-term memory (LSTM) recurrent neural network. OSL aims to allow the networks to learn based on limited training data. It also promotes the scalability of the network to accommodate more grasping objects in the future. Three types of LSTM-based networks have been developed and their performance has been evaluated in this study. Among the three LSTM networks, triplet network achieved overall stability estimation accuracy at 89.96%, followed by LSTM network with 88.00% and Siamese LSTM network with 85.16%.
本文介绍了一种集成了多个手指柔性力传感器的拟人化软机器人手的开发。通过利用集成力传感机制，开发了抓握状态估计网络。该机器人手的任务是将给定物体放在桌子上1.5秒，然后在1秒内将其举起。在不同气压（50、80和120千帕）下进行了抓取和举起给定物体的物体操纵实验。开发了学习网络来估计由于机器人加速或抓握力不足导致的物体不稳定和滑动的发生。因此，抓握状态估计网络有可能将物体稳定性状态反馈给气动控制系统。这将使气动系统能够使用合适的气压来有效地处理不同的物体，即对于不需要高抓握力的轻质物体使用较低的气压（50千帕）。通过精心挑选各种日常物体来进行软手的学习过程具有挑战性，其中一些物体在抓握时形状会发生动态变化。为了解决收集大量训练数据集的成本问题，我们采用了带有长短期记忆（LSTM）循环神经网络的一次性学习（OSL）技术。OSL旨在让网络基于有限的训练数据进行学习。它还促进了网络的可扩展性，以便将来能够适应更多的抓取物体。本研究开发了三种基于LSTM的网络，并对其性能进行了评估。在这三种LSTM网络中，三元组网络的整体稳定性估计准确率达到89.96%，其次是LSTM网络，准确率为88.00%，连体LSTM网络的准确率为85.16%。
