Saved in:
Bibliographic Details
Main Authors: Zhang, Liwen, Zhou, Dong, Shao, Shibo, Su, Zihao, Sun, Guanghui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.07287
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909731084304384
author Zhang, Liwen
Zhou, Dong
Shao, Shibo
Su, Zihao
Sun, Guanghui
author_facet Zhang, Liwen
Zhou, Dong
Shao, Shibo
Su, Zihao
Sun, Guanghui
contents This paper presents a multimodal control framework based on spiking neural networks (SNNs) for robotic arms aboard space stations. It is designed to cope with the constraints of limited onboard resources while enabling autonomous manipulation and material transfer in space operations. By combining geometric states with tactile and semantic information, the framework strengthens environmental awareness and contributes to more robust control strategies. To guide the learning process progressively, a dual-channel, three-stage curriculum reinforcement learning (CRL) scheme is further integrated into the system. The framework was tested across a range of tasks including target approach, object grasping, and stable lifting with wall-mounted robotic arms, demonstrating reliable performance throughout. Experimental evaluations demonstrate that the proposed method consistently outperforms baseline approaches in both task success rate and energy efficiency. These findings highlight its suitability for real-world aerospace applications.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07287
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multimodal Spiking Neural Network for Space Robotic Manipulation
Zhang, Liwen
Zhou, Dong
Shao, Shibo
Su, Zihao
Sun, Guanghui
Robotics
This paper presents a multimodal control framework based on spiking neural networks (SNNs) for robotic arms aboard space stations. It is designed to cope with the constraints of limited onboard resources while enabling autonomous manipulation and material transfer in space operations. By combining geometric states with tactile and semantic information, the framework strengthens environmental awareness and contributes to more robust control strategies. To guide the learning process progressively, a dual-channel, three-stage curriculum reinforcement learning (CRL) scheme is further integrated into the system. The framework was tested across a range of tasks including target approach, object grasping, and stable lifting with wall-mounted robotic arms, demonstrating reliable performance throughout. Experimental evaluations demonstrate that the proposed method consistently outperforms baseline approaches in both task success rate and energy efficiency. These findings highlight its suitability for real-world aerospace applications.
title Multimodal Spiking Neural Network for Space Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2508.07287