Human-centered Entrepreneurship in Assistive Robotics Optimization

Chaoqun Xiang; Mincong Kong

doi:10.47297/taposatWSP2633-456944.20250610

PDF
导出
分享
收藏
专辑

Human-centered Entrepreneurship in Assistive Robotics Optimization

6卷第10期

浏览量: 0 Downloads: 0

Human-centered Entrepreneurship in Assistive Robotics Optimization
Human-centered Entrepreneurship in Assistive Robotics Optimization
Qingdao City University Gutenberg College, Qingdao, Shandong, 266000, China
2025年6卷第10期页码：224-228
纸质出版：2025-10-30
DOI：10.47297/taposatWSP2633-456944.20250610
Accepted：

Scan QR Code

Chaoqun Xiang & Mincong Kong. (2025). Human-centered Entrepreneurship in Assistive Robotics Optimization. 科技理论与实践（英文版）, 6(10), 224-228.

Xiang Chaoqun,Kong Mincong.Human-centered Entrepreneurship in Assistive Robotics Optimization[J].Theory and Practice of Science and Technology,2025,06(10):224-228.
Chaoqun Xiang & Mincong Kong. (2025). Human-centered Entrepreneurship in Assistive Robotics Optimization. 科技理论与实践（英文版）, 6(10), 224-228. DOI： 10.47297/taposatWSP2633-456944.20250610.

Xiang Chaoqun,Kong Mincong.Human-centered Entrepreneurship in Assistive Robotics Optimization[J].Theory and Practice of Science and Technology,2025,06(10):224-228. DOI： 10.47297/taposatWSP2633-456944.20250610.

摘要

Abstract

This study explores multi-agent reinforcement learning for assistive robotics and proposes a Transformer-based Proximal Policy Optimization algorithm (TSPPO) with a cooper-active robot cluster for dynamic multi-task collaboration. TSPPO integrates temporal sequence encoding and dual-attention to enhance policy coordination and generalization. A hierarchical design unifies high-level planning and low-level control via multimodal perception. In Bi-DexHands simulation

TSPPO achieves an 89.7% task completion rate

outperforming PPO and MAPPO by 17. 1% and 12.2%

with better convergence and ro- bustness. The framework offers a scalable

interpretable solution for collaborative assistive robotics and advances human-center multi-agent reinforcement learning.

关键词

Keywords

references

Yang L, Zhan X, Li K, et al. Learning a contact potential field for modeling the hand-object interaction[J]. IEEE transactions on pattern analysis and machine intelligence, 2024, 46(8): 5645-5662.

Yang Y, Feng L, Sun Y, et al. Multi-cluster cooperative offloading for VR task: A MARL approach with graph embedding[J]. IEEE Transactions on Mobile Computing, 2024, 23(9): 8773-8788.

Yang T, Shi X, Zeng Q, et al. Optimization methods in fully cooperative scenarios: a review of multiagent reinforcement learning[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(4): 479-509.

Gu S, Huang D, Wen M, et al. Safe multiagent learning with soft constrained policy optimization in real robot control[J]. IEEE Transactions on Industrial Informatics, 2024, 20(9): 10706-10716.

Chen Y, Geng Y, Zhong F, et al. Bi-dexhands: Towards human-level bimanual dexterous manipulation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 46(5): 2804-2818.

Huang Y, Liu D, Liu Z, et al. A novel robotic grasping method for moving objects based on multi-agent deep reinforcement learning[J]. Robotics and Computer-Integrated Manufacturing, 2024, 86: 102644-102654.

Luo J, Xu C, Wu J, et al. Precise and dexterous robotic manipulation via human-in-the-loop reinforcement learning[J]. Science Robotics, 2025, 10(105): 5033-5050.

Jia P, Li X, Zhu T, et al. Multi-fingered hand grasps with visuo-tactile fusion via multi-agent deep reinforcement learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2025, 39(14): 14594-14601.

Li K, Wang J, Yang L, et al. Semgrasp: Semantic grasp generation via language aligned discretization[C]//European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024: 109-127.

Yang L, Zhan X, Li K, et al. Learning a contact potential field for modeling the hand-object interaction[J]. IEEE transactions on pattern analysis and machine intelligence, 2024, 46(8): 5645-5662.