arXiv 2602.127242026-05-30cs.RO

TRANS：面向社交互动下四足机器人敏捷导航的地形感知强化学习

TRANS: Terrain-aware Reinforcement Learning for Agile Navigation of Quadruped Robots under Social Interactions

Department of Robotics, Graduate School of Engineering, Tohoku University（东邦大学机器人学系）；Laboratory for Intelligent Decision and Autonomous Robots, Woodruff School of Mechanical Engineering, Georgia Institute of Technology（佐治亚理工学院智能决策与自主机器人实验室）

Wei Zhu, Irfan Tito Kurniawan, Ye Zhao, Mitsuhiro Hayashibe

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出一个名为TRANS的两阶段深度强化学习框架，通过三个DRL流水线（TRANS-Loco、TRANS-Nav和统一TRANS）实现四足机器人在非结构化地形上的社交导航，克服了传统方法中运动规划与运动控制分离、缺乏地形感知以及假设静态环境等局限。

摘要：

本研究介绍了TRANS：面向社交互动下敏捷导航的地形感知强化学习，这是一个用于四足机器人在非结构化地形上进行社交导航的深度强化学习（DRL）框架。传统的四足导航通常将运动规划与运动控制分离，忽略了全身约束和地形感知。另一方面，端到端方法更加集成，但需要高频传感，这通常噪声大且计算成本高。此外，大多数现有方法假设静态环境，限制了它们在有人环境中的使用。为了解决这些限制，我们提出了一个包含三个DRL流水线的两阶段训练框架。（1）TRANS-Loco采用非对称演员-评论家（AC）模型进行四足运动，无需显式的地形或接触观测即可穿越不平坦地形。（2）TRANS-Nav采用对称AC框架进行社交导航，在差速驱动运动学下直接将变换后的LiDAR数据映射到自我智能体动作。（3）统一流水线TRANS集成了TRANS-Loco和TRANS-Nav，支持在不平坦和社交互动环境中的地形感知四足导航。针对运动导航和社交导航基线的全面基准测试证明了TRANS的有效性。硬件实验进一步证实了其从仿真到实际迁移的潜力。

英文摘要：

This study introduces TRANS: Terrain-aware Reinforcement learning for Agile Navigation under Social interactions, a deep reinforcement learning (DRL) framework for quadrupedal social navigation over unstructured terrains. Conventional quadrupedal navigation typically separates motion planning from locomotion control, neglecting whole-body constraints and terrain awareness. On the other hand, end-to-end methods are more integrated but require high-frequency sensing, which is often noisy and computationally costly. In addition, most existing approaches assume static environments, limiting their use in human-populated settings. To address these limitations, we propose a two-stage training framework with three DRL pipelines. (1) TRANS-Loco employs an asymmetric actor-critic (AC) model for quadrupedal locomotion, enabling traversal of uneven terrains without explicit terrain or contact observations. (2) TRANS-Nav applies a symmetric AC framework for social navigation, directly mapping transformed LiDAR data to ego-agent actions under differential-drive kinematics. (3) A unified pipeline, TRANS, integrates TRANS-Loco and TRANS-Nav, supporting terrain-aware quadrupedal navigation in uneven and socially interactive environments. Comprehensive benchmarks against locomotion and social navigation baselines demonstrate the effectiveness of TRANS. Hardware experiments further confirm its potential for sim-to-real transfer.

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。