Robust Visuomotor Control for Humanoid Loco-Manipulation Using Hybrid Reinforcement Learning
Chenzheng Wang, Qiang Huang, Xuechao Chen, Zeyu Zhang, Jing Shi
TL;DR
This paper introduces a new control framework for humanoid robots that improves visuomotor control in complex tasks like carrying loads and opening doors.
Contribution
The novel framework combines model-free and model-based reinforcement learning for efficient visuomotor control in humanoid loco-manipulation tasks.
Findings
The framework achieves an 83% success rate in loco-manipulation tasks like load carrying and door opening.
Mid-way initialization and prioritized experience sampling accelerate policy convergence in visuomotor control.
The method enables automatic robot motion adjustment in response to environmental changes.
Abstract
Loco-manipulation tasks using humanoid robots have great practical value in various scenarios. While reinforcement learning (RL) has become a powerful tool for versatile and robust whole-body humanoid control, visuomotor control in loco-manipulation tasks with RL remains a great challenge due to their high dimensionality and long-horizon exploration issues. In this paper, we propose a loco-manipulation control framework for humanoid robots that utilizes model-free RL upon model-based control in the robot’s tasks space. It implements a visuomotor policy with depth-image input, and uses mid-way initialization and prioritized experience sampling to accelerate policy convergence. The proposed method is validated on typical loco-manipulation tasks of load carrying and door opening resulting in an overall success rate of 83%, where our framework automatically adjusts the robot motion in…
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Click any figure to enlarge with its caption.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobotic Locomotion and Control · Prosthetics and Rehabilitation Robotics · Reinforcement Learning in Robotics