用单个LiDAR实现足式机器人实时安全避障导航
REASAN: Learning Reactive Safe Navigation for Legged Robots
- 模块化设计：四模块协同，分别负责行走、安全防护、导航和感知
- 全机载实时运行，在复杂环境中多机器人场景下表现稳定
- 无需启发式规则或复杂切换机制，训练简单且泛化能力强
我们提出一种新型模块化端到端框架，用于在复杂动态环境中通过单个激光雷达（LiDAR）实现足式机器人的反应式安全导航。系统包含四个在仿真中训练的模块：三个基于强化学习（RL）的策略（用于步态控制、安全屏蔽和导航），以及一个基于Transformer的外感受估计器，用于处理原始点云输入。该模块化分解使神经网络轻量化、结构简单，仅依赖标准强化学习方法与针对性奖励设计和课程训练，无需启发式规则或复杂策略切换机制。通过全面消融实验验证设计合理性，并在挑战性导航任务中展现出优于现有方法的鲁棒性。所提出的反应式安全导航（REASAN）系统实现了复杂环境下的全机载、实时反应式导航，适用于单机器人与多机器人场景。训练与部署代码已开源：https://github.com/ASIG-X/REASAN。
原文摘要 · Abstract (English)
We present a novel modularized end-to-end framework for legged reactive navigation in complex dynamic environments using a single light detection and ranging (LiDAR) sensor. The system comprises four simulation-trained modules: three reinforcement-learning (RL) policies for locomotion, safety shielding, and navigation, and a transformer-based exteroceptive estimator that processes raw point-cloud inputs. This modular decomposition of complex legged motor-control tasks enables lightweight neural networks with simple architectures, trained using standard RL practices with targeted reward shaping and curriculum design, without reliance on heuristics or sophisticated policy-switching mechanisms. We conduct comprehensive ablations to validate our design choices and demonstrate improved robustness compared to existing approaches in challenging navigation tasks. The resulting reactive safe navigation (REASAN) system achieves fully onboard and real-time reactive navigation across both single- and multi-robot settings in complex environments. We release our training and deployment code at https://github.com/ASIG-X/REASAN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。