ForceHarness让冻结模型利用力反馈
AI 总结
ForceHarness论文提出一套系统,使冻结的API多模态前沿模型无需示范或微调即可利用力反馈完成机器人操作。该系统以自终止力原语处理快速接触反馈,并通过物理转换层把力轨迹转换为带不确定性的物理量。论文称,在未配备腕部力传感器的真实机械臂上,GPT-6 Astra的零样本成功率从3.3%升至90.0%,在ForceBench和HiddenPhys仿真中分别提升17.5和34.3个百分点。
深度见解
论文报告的结果显示,在不依赖任务示范或微调的情况下,引入力反馈可能显著扩展冻结多模态模型处理接触密集型操作任务的能力。
Computer Science > Robotics
arXiv:2611.21099 (cs)
[Submitted on 16 Nov 2026]
Title:ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models
Authors:Ke Sun, Kevin Yuchen Ma, Yike Zhang, Yanzhe Chen, Mike Zheng Shou
View a PDF of the paper titled ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models, by Ke Sun and 4 other authors