Neuro-inspired continual anthropomorphic grasping

Wanyi Li; Wei Wei; Peng Wang

doi:10.1016/j.isci.2023.106735

Neuro-inspired continual anthropomorphic grasping

iScience. 2023 Apr 25;26(6):106735. doi: 10.1016/j.isci.2023.106735. eCollection 2023 Jun 16.

Authors

Wanyi Li¹, Wei Wei^{1

2}, Peng Wang^{1

3

4}

Affiliations

¹ State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
² School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China.
³ CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai 200031, China.
⁴ Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong 999077, China.

Abstract

Humans can learn continuously grasping various objects dexterously. This ability is enabled partly by underlying neural mechanisms. Most current works of anthropomorphic robotic grasping learning lack the capability of continual learning (CL). They utilize large datasets to train grasp models and the trained models are difficult to improve incrementally. By incorporating several discovered neural mechanisms supporting CL, we propose a neuro-inspired continual anthropomorphic grasping (NICAG) approach. It consists of a CL framework of anthropomorphic grasping and a neuro-inspired CL algorithm. Compared with other methods, our NICAG approach achieves better CL capability with lower loss and forgetting, and gets higher grasping success rate. It indicates that our approach performs better on alleviating forgetting and preserving grasp knowledge. The proposed system offers an approach for endowing anthropomorphic robotic hands with the ability to learn grasping objects continually and has great potential to make a profound impact on robots in households and factories.

Keywords: Control engineering; Neuroscience; Robotics.