arXiv 2505.192142025-08-28cs.RO

Omni-Perception：动态环境中腿式运动的全向避障

Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environments

The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Spatialtemporal AI（时空AI）；The Hong Kong University of Science and Technology（香港科技大学）；Department of Eletronic Engineering, Tsinghua University（清华大学电子工程系）；Beijing Innovation Center of Humanoid Robotics Co., Ltd.（北京人形机器人创新中心有限公司）

Zifan Wang, Teli Ma, Yufei Jia, Xun Yang, Jiaming Zhou, Wenlong Ouyang, Qiang Zhang, Junwei Liang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 Omni-Perception 端到端腿式运动策略，利用原始 LiDAR 点云和 PD-RiskNet 进行风险评估，实现动态复杂环境中的全向避障与 sim-to-real 迁移。

摘要：

在复杂三维环境中进行敏捷运动，需要鲁棒的空间感知能力，以安全避开空中杂物、不平坦地形和动态智能体等多种障碍物。基于深度的感知方法通常难以应对传感器噪声、光照变化、中间表示（例如高程图）带来的计算开销，以及非平面障碍物造成的困难，从而限制了其在非结构化环境中的性能。相比之下，将 LiDAR 感知直接集成到腿式运动的端到端学习中仍未得到充分研究。我们提出 Omni-Perception，这是一种端到端运动策略，通过直接处理原始 LiDAR 点云来实现三维空间感知和全向避障。其核心是 PD-RiskNet（Proximal-Distal Risk-Aware Hierarchical Network，近端-远端风险感知分层网络），这是一个新型感知模块，用于解释时空 LiDAR 数据以进行环境风险评估。为促进高效的策略学习，我们开发了一个高保真 LiDAR 仿真工具包，具有逼真的噪声建模和快速光线投射能力，并兼容 Isaac Gym、Genesis 和 MuJoCo 等平台，从而支持可扩展训练和有效的 sim-to-real 迁移。直接从原始 LiDAR 数据学习反应式控制策略，使机器人能够在包含静态和动态障碍物的复杂环境中导航，并且比依赖中间地图或有限感知的方法更加鲁棒。我们通过真实世界实验和大量仿真验证了 Omni-Perception，证明其在高度动态环境中具有强大的全向避障能力和优越的运动性能。

英文摘要：

Agile locomotion in complex 3D environments requires robust spatial awareness to safely avoid diverse obstacles such as aerial clutter, uneven terrain, and dynamic agents. Depth-based perception approaches often struggle with sensor noise, lighting variability, computational overhead from intermediate representations (e.g., elevation maps), and difficulties with non-planar obstacles, limiting performance in unstructured environments. In contrast, direct integration of LiDAR sensing into end-to-end learning for legged locomotion remains underexplored. We propose Omni-Perception, an end-to-end locomotion policy that achieves 3D spatial awareness and omnidirectional collision avoidance by directly processing raw LiDAR point clouds. At its core is PD-RiskNet (Proximal-Distal Risk-Aware Hierarchical Network), a novel perception module that interprets spatio-temporal LiDAR data for environmental risk assessment. To facilitate efficient policy learning, we develop a high-fidelity LiDAR simulation toolkit with realistic noise modeling and fast raycasting, compatible with platforms such as Isaac Gym, Genesis, and MuJoCo, enabling scalable training and effective sim-to-real transfer. Learning reactive control policies directly from raw LiDAR data enables the robot to navigate complex environments with static and dynamic obstacles more robustly than approaches relying on intermediate maps or limited sensing. We validate Omni-Perception through real-world experiments and extensive simulation, demonstrating strong omnidirectional avoidance capabilities and superior locomotion performance in highly dynamic environments.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。