期刊
IEEE TRANSACTIONS ON ROBOTICS
卷 38, 期 5, 页码 2908-2927出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2022.3172469
关键词
Robots; Quadrupedal robots; Planning; Training; Computational modeling; Legged locomotion; Tracking; AI-based methods; deep learning in robotics and automation; legged robots; robust; adaptive control of robotic systems
类别
资金
- UKRI/EPSRC RAINHub [EP/R026084/1]
- EU
- EPSRC [EP/S002383/1]
- Royal Society University Research Fellowship
We propose a unified approach for quadrupedal planning and control using both model-based and data-driven methods. By utilizing reinforcement learning, sensory information and velocity commands are mapped into footstep plans, which are then tracked by a model-based motion controller. The results demonstrate the robustness of our method over a variety of complex terrains.
We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a reinforcement learning (RL) policy. This RL policy is trained in simulation over a wide range of procedurally generated terrains. When run online, the system tracks the generated footstep plans using a model-based motion controller. We evaluate the robustness of our method over a wide variety of complex terrains. It exhibits behaviors that prioritize stability over aggressive locomotion. Additionally, we introduce two ancillary RL policies for corrective whole-body motion tracking and recovery control. These policies account for changes in physical parameters and external perturbations. We train and evaluate our framework on a complex quadrupedal system, ANYmal version B, and demonstrate transferability to a larger and heavier robot, ANYmal C, without requiring retraining.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据