论文arXiv 2611.219054 天前
FlowRRT规划器实现单足机器人复杂地形敏捷跳跃,成功率达80%
本文由 AI 根据公开内容整理,可能有误,请以原文为准:Agile Monoped Hopping on Complex and Discrete Terrain via Kinodynamic Planning with Distilled MPPI Steering(arXiv 2611.21905)
核心内容
arXiv论文提出FlowRRT运动学动力学规划器,解决单足机器人在复杂离散地形上的敏捷跳跃控制难题。传统RRT转向依赖运动原语或闭环策略,限制了动作多样性与规划速度。该方法核心创新是将转向视为集合值问题,利用多起点MPPI专家离线收集可行解集,并通过条件流匹配蒸馏为生成式采样器,从而协调长时域连续跳跃并发现非贪婪机动策略。
基准测试显示FlowRRT在多种地形上规划时间与成功率均优于采样基线。在倾斜平台场景中,FlowRRT在1秒内达到80%成功率,而RL-RRT需24秒、SST需77秒。MuJoCo仿真环境下的Sim-to-sim跟踪实验证实,该规划器生成的轨迹在全阶动力学模型下具备高精度可执行性,有效克服了单足系统可行域狭窄且不连通的控制挑战。
关键看点
- 算法架构:采用条件流匹配蒸馏多起点MPPI专家策略,将转向从单点回归转为可行动作分布预测,解决单足跳跃可行域窄且不连通问题
- 规划性能:倾斜平台测试中1秒内规划成功率达80%,对比RL-RRT的24秒和SST的77秒,计算效率提升数十倍且保持高成功率
- 动力学验证:在MuJoCo中进行Sim-to-sim全阶动力学跟踪测试,确认生成轨迹在实际物理约束下可精准执行,无简化模型误差
工程与产业观察
FlowRRT证明了基于生成模型的集合值转向策略在欠驱动单足系统中的有效性,为具身智能在非结构化地形的长时域规划提供了新范式。其将高成本优化器蒸馏为轻量采样器的思路,对解决腿足机器人实时运动规划瓶颈具有直接工程参考价值,尤其适用于需要精确落点控制的跳跃任务。
英文摘要 (Abstract)
This paper presents FlowRRT, a kinodynamic planner for agile monoped hopping on discrete terrain. Steering for kinodynamic RRT on complex dynamical systems currently relies on motion primitives or closed-loop policies, limiting the diversity of motions or the planning speed. Distilling a trajectory optimizer avoids both, but existing methods regress a single solution per query, which fails on monoped hopping, where the feasible action set is narrow and disconnected. Our key insight is to treat steering as set-valued and predict the distribution of feasible actions instead. A multi-start MPPI expert collects the entire feasible set of each query offline, and conditional flow matching distills it into a generative sampler. With this sampler, FlowRRT coordinates successive jumps over long horizons and finds non-greedy maneuvers that are hard for reactive policies to discover. Benchmarks across different terrains show higher success rates and substantially shorter planning times than sampling-based baselines. On terrains with inclined platforms, FlowRRT reaches $80%$ success within $1$~s, versus $24$~s for RL-RRT and $77$~s for SST. Sim-to-sim tracking in MuJoCo confirms accurate execution under full-order dynamics.
作者:Yue Qin, Denglin Cheng, Jingyu Liu, Yanran Ding
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)