发表机构
Purdue University; Korea Institute of Science and Technology (KIST)（普渡大学; 韩国科学技术研究院（KIST））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Go2-DrivoR，通过目标条件化改编DrivoR框架，实现四足机器人城市导航的短视界局部规划，并在仿真与真实场景中验证性能。
AI 中文摘要
我们提出了Go2-DrivoR，这是对端到端自动驾驶轨迹规划框架DrivoR的一种目标条件化改编，用于四足机器人的城市导航。通过目标令牌将轨迹生成条件化为局部框架子目标，并调整以车辆为中心的评分公式，该方法将DrivoR扩展到短视界目标条件化的局部规划，而无需重新设计其核心解码器。具体而言，我们重新定义了面向人行道导航的可行驶区域合规性，并将原始的自我进度项重新表述为目标条件化的自我进度。仅在TartanGround仿真数据上训练，Go2-DrivoR在未见过的仿真环境中提高了路点条件化规划性能，并零样本迁移到开环的真实世界轨迹预测。
英文摘要
We present Go2-DrivoR, a goal-conditioned adaptation of the end-to-end autonomous driving trajectory planning framework DrivoR for urban navigation with quadrupedal robots. By conditioning trajectory generation on a local-frame subgoal through a goal token and adapting the vehicle-centric scoring formulation, the method extends DrivoR to short-horizon goal-conditioned local planning without redesigning its core decoders. Specifically, we redefine drivable-area compliance for sidewalk-oriented navigation and reformulate the original ego progress term as goal-conditioned ego progress. Trained exclusively on TartanGround simulation data, Go2-DrivoR improves waypoint-conditioned planning performance on unseen simulation environments and transfers zero-shot to open-loop real-world trajectory prediction.
CommentsAccepted to IROS 2026 Workshop on AI Meets Autonomy
