先轻推再推动：基于触觉探测的物理感知导航
Nudge Before You Push: Physics-Aware Navigation via Tactile Probing
浏览论文内容
中文总结 AI 辅助
提出TANav，通过触觉轻推测量阻力估计质量，结合重复巡逻规划，减少漏推和边界违规，并在仿真和实物实验中验证有效性。
中文摘要 AI 辅助
视觉上相同的容器可能隐藏着需要不同处理决策的负载。我们提出了TANav，它通过一次短暂的轻推来测量推动阻力，以在站点定义的处理边界下进行导航。TacPhys将力序列（可选地结合RGB-D和运动学数据）读取为用于推动授权的质量估计。一种重复巡逻规划器权衡探测和路径成本，在有用时请求第二次接触，并在多次访问中重用观测结果。在仿真中，TacPhys接近仅基于阻力的贝叶斯参考，并在可比较的低风险工作点上，相对于峰值力阈值方法，将漏推率从28.7%降低到5.5%。在重复巡逻仿真中，TANav恢复了Oracle路径节省的90%，相对于始终绕行，人类干预次数减少了一半以上，并且相对于仅RGB-D探测，边界违规率从4.3%降低到2.9%。在带有霍尔阵列指尖的四足机械臂上，离线零样本平均绝对误差（MAE）在2.82千克以内的容器上为0.28-1.07千克。在3千克下的力上升校准给出了93.5%的合并离线准确率（非立方体情节为86.4%）；一个单独的原始峰值规则在未见过的盒子上给出了20次在线决策中15次正确的结果。
英文摘要
Visually identical containers can conceal loads that require different handling decisions. We present TANav, which uses a brief nudge to measure push resistance for navigation under a site-defined handling boundary. TacPhys reads the force sequence, with optional RGB-D and kinematics, into a mass estimate for push authorization. A repeated-patrol planner weighs probe and route costs, requests a second contact when useful, and reuses observations across visits. In simulation, TacPhys approaches a resistance-only Bayes reference and reduces missed pushes from 28.7% to 5.5% relative to peak-force thresholding at comparable low-risk operating points. In repeated-patrol simulation, TANav recovers 90% of the oracle's path saving, more than halves human interventions relative to always-detour, and reduces boundary violations from 4.3% to 2.9% relative to RGB-D-only probing. On a quadruped manipulator with a Hall-array fingertip, offline zero-shot MAE is 0.28-1.07 kg on containers up to 2.82 kg. Force-rise calibration at 3 kg gives 93.5% pooled offline accuracy (86.4% on non-cube episodes); a separate raw-peak rule gives 15 of 20 correct online decisions on unseen boxes.
发表机构
- University of Florida（佛罗里达大学）
- Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。
