JEPLO：基于LiDAR的四足运动的联合嵌入预测学习
JEPLO: Joint-Embedding Predictive Learning for LiDAR-Based Legged Locomotion
- University of Groningen（格罗宁根大学）
- Linköping University（林雪平大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
JEPLO提出一种基于LiDAR的无建图单阶段学习框架，利用PE-JEPA世界模型和CJTS流程训练运动策略，实现鲁棒的仿真到现实迁移，支持四足机器人穿越多样地形。
AI中文摘要：
光检测和测距（LiDAR）在感知四足运动方面的探索程度低于RGB-D传感，且现有的基于LiDAR的方法通常依赖于显式建图。我们提出了JEPLO（四足运动的联合嵌入预测学习），一种用于四足机器人无建图、基于LiDAR的感知运动的单阶段学习框架。我们引入了一个本体感觉-外部感觉JEPA（PE-JEPA）世界模型，从机载观测（包括原始LiDAR扫描）中学习预测性以自我为中心的地形表示。进一步提出了一种并行的JEPA教师-学生（CJTS）流程，利用深度强化学习和简单的奖励公式，在仿真中训练由JEPA潜在表示指导的运动策略。该框架实现了成功的仿真到现实迁移，使机器人能够以轻量级机载计算全方位穿越各种地形，包括长楼梯和高箱子。评估表明，与现有的感知运动框架相比，该框架具有更强的鲁棒性，尤其是在由遮挡、稀疏性和噪声引起的感知退化情况下。进一步的分析验证了JEPLO在这些具有挑战性的条件下保留任务相关信息的能力。我们开源了我们的实现、实验数据集和硬件设置设计，网址为https://this https URL。
英文摘要：
Light detection and ranging (LiDAR) remains less explored than RGB-D sensing for perceptive legged locomotion, and existing LiDAR-based approaches often rely on explicit mapping. We present JEPLO (Joint-Embedding Predictive learning for legged LOcomotion), a single-stage learning framework for mapping-free, LiDAR-based perceptive locomotion for legged robots. We introduce a proprio-exteroceptive JEPA (PE-JEPA) world model to learn predictive egocentric terrain representations from onboard observations, including raw LiDAR scans. A concurrent JEPA-teacher-student (CJTS) pipeline is further proposed to train a locomotion policy informed by JEPA latent representations in simulation using deep reinforcement learning with a simple reward formulation. The framework achieves successful sim-to-real transfer, enabling omnidirectional traversal of diverse terrains, including long staircases and high boxes, with lightweight onboard computation. Evaluations demonstrate greater robustness than existing perceptive locomotion frameworks, particularly under degraded perception caused by occlusion, sparsity and noise. Further analysis validates JEPLO's ability to retain task-relevant information under these challenging conditions. We open-source our implementation, experimental datasets, and hardware setup designs https://github.com/ASIG-X/JEPLO.
