arXiv 2610.130072026-10-12cs.RO

CeDR-Nav：基于离线演示重构的跨 embodiments 无地图导航

CeDR-Nav: Cross-Embodiment Mapless Navigation via Offline Demonstration Recasting

The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute of Technology（宁波工程学院）；University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）

Xianghui Wang, Xinming Zhang, Yiwei Qian, Siwei Cheng, Shanze Wang, Dan Zhang, Wei Zhang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

CeDR-Nav 是一种无需在线数据收集的跨 embodiment 无地图导航框架，通过重构源演示训练目标策略，在多机器人平台实验中相比 DRL-DCLP 平均成功率提升13.8个百分点，训练耗时仅数秒。

摘要：

基于学习的方法在无地图机器人导航中已展现出强大性能，但学习到的策略仍受限于其训练所用的 embodiment。许多跨 embodiment 导航方法需要耗时的在线训练，且性能仍可能逊于针对特定目标的策略。实际上，在源 embodiment 上收集的演示已包含可复用的导航经验，用于推导每个目标 embodiment 的策略，但 embodiment 不匹配导致这些演示无法直接作为目标的有效监督。本文提出 CeDR-Nav，一种跨 embodiment 演示重构框架，无需在线数据收集，即可从现有源演示中为每个目标 embodiment 训练专用导航策略。该框架采用与每个演示有效性评估相结合的几何一致性缩放，将源演示转换为目标训练数据，再通过针对特定目标的高斯混合策略为每个目标 embodiment 生成可行的避障动作。在多个机器人平台上开展的大量定量模拟与真实部署实验表明，CeDR-Nav 具有有效性：在跨 embodiment 模拟中，其相比 DRL-DCLP 的平均成功率提升了13.8个百分点，且针对特定目标的策略训练可在数秒内完成。

英文摘要：

Learning-based methods have demonstrated strong performance in mapless robot navigation. However, a learned policy remains restricted to the embodiment on which it was trained. Many cross-embodiment navigation methods require time-consuming online training and can still underperform target-specific policies. In fact, demonstrations collected on a source embodiment already contain navigation experience that is potentially reusable for deriving a policy for each target embodiment, but the embodiment mismatch prevents these demonstrations from directly serving as valid supervision for the target. In this article, we present CeDR-Nav, a cross-embodiment demonstration recasting framework that trains a dedicated navigation policy for each target embodiment from existing source demonstrations without online data collection. Geometry-consistent scaling with per-demonstration validity assessment converts the source demonstrations into target training data, and a target-specific Gaussian mixture policy generates feasible avoidance maneuvers for each target embodiment. Extensive quantitative simulations and real-world deployments across multiple robot platforms demonstrate the effectiveness of CeDR-Nav, with an average success-rate gain of 13.8 percentage points over DRL-DCLP in cross-embodiment simulations and target-specific policy training completed within seconds.

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。