外观
论文arXiv 2609.3975528 天前
四足机器人地形可通行性的经验驱动持续学习
针对陌生地形安全高效导航，提出用运动经验从接触前图像持续学习交互结果，并在仿真与真机导航测试中验证。
宇树 Go2原文链接：Experience-Driven Continual Learning of Terrain Traversability for Quadruped Robots（arXiv 2609.39755 · 发布日期：2026-09-30）
Experience-Driven Continual Learning of Terrain Traversability for Quadruped Robots
针对陌生地形安全高效导航，提出用运动经验从接触前图像持续学习交互结果，并在仿真与真机导航测试中验证。
核心要点
- 几何与视觉外观不足以预知打滑、足端受力或能耗等地形交互。
- 冻结DINOv3提取接触前描述符，回归五类本体指标及不确定性。
- 采用有界经验回放与验证门控，仅在兼顾新旧数据表现时替换模型。
- ROS2实现在Unitree Go2仿真和硬件评估，门控回放降低最终NLL退化23.1%。
验证范围与局限：验证包括Unitree Go2仿真与硬件，硬件为三个此前未见地形的顺序数据流。
英文摘要 (Abstract)
Safe and efficient quadruped navigation over unfamiliar terrain requires predicting terrain-robot interaction before contact: geometry and visual appearance alone cannot reveal how the robot will slip, load its feet, or expend energy. This paper presents a continual learning pipeline that uses locomotion experience to learn these interaction outcomes from pre-contact images and continually updates the predictions as new contacts are observed. Pre-contact descriptors, produced by a DINOv3 backbone model frozen during training, are mapped to five proprioceptive indicators weighted according to measurement reliability: planar foot slip, mean normal ground-reaction force, traction index, cost of transport, and touchdown loading rate. A compact evidential regressor allows us to predict these indicators together with aleatoric and epistemic uncertainty from the visual descriptors. Continual adaptation combines bounded experience replay with a validation gate: candidate models replace the deployed predictor only when they improve performance on recent held-out data while keeping degradation on historical held-out data within a prescribed tolerance. Predictions and epistemic uncertainty are projected into a local multilayer map and combined into a conservative traversability score map whose property weights can be adjusted without retraining. The resulting map is used for downstream navigation tests. The ROS2 implementation supports evaluation on a Unitree Go2 in simulation and on hardware, with models trained separately in each domain. On a sequential hardware stream over three previously unseen terrains, gated replay reduces final anchor negative log-likelihood (NLL) degradation by 23.1% relative to replay without the gate while attaining similar new-terrain adaptation.
作者：Luca Bricarello, João Carlos Virgolino Soares, Alberto Sánchez-Delgado, Fulvio Mastrogiovanni, Claudio Semini
来源
本页事实对应的公开页面，以原文为准。