生成式机器人策略的零样本反应式避障
Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies
浏览论文内容
中文总结 AI 辅助
提出NUDGE,一种无需训练的零样本避障方法,通过注入符号距离场梯度到扩散或流匹配策略中,支持多种动作参数化,实时反应式避障且保持任务分布。
中文摘要 AI 辅助
我们提出NUDGE(通过可微几何的轻推更新),这是一种无需训练的避障程序,可集成到任何基于扩散或流匹配的机器人策略中,包括扩散策略和视觉-语言-动作模型。我们的方法在推理时将符号距离场(一种返回每个点到最近障碍物距离的函数)的梯度注入策略,以引导其远离障碍物。它通过可微的关节轨迹解码器支持任何常见的动作参数化,从绝对或相对关节位姿到末端执行器位姿。实验表明,NUDGE保留了策略的任务分布,并能实时反应式运行。
英文摘要
We propose NUDGE (Nudge Update via Differentiable GEometry), a training-free obstacle-avoidance procedure that can be incorporated in any robot policy based on diffusion or flow matching, including diffusion policies and vision-language-action models. Our work injects gradients from a signed distance field, a function returning each point's distance to the nearest obstacle, into the policy at inference time to steer it away from obstacles. It supports any common action parameterization, from absolute or relative joint poses to end-effector poses, through a differentiable joint-trajectory decoder. Experiments show that NUDGE preserves the policy's task distribution and runs reactively in real time.
发表机构
- Rice University(莱斯大学)
- Ken Kennedy Institute at Rice University(莱斯大学肯·肯尼迪研究所)
机构由 AI 辅助整理,请以论文原文为准。