发表机构
Carnegie Mellon University; Autel US; Northeastern University（卡内基梅隆大学; Autel US; 东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
KPI提出一个可提示内核，通过轨迹源发送的契约调整全身跟踪器的刚度等参数，实现无需任务特定代码的物理交互，并在绞盘、开门等任务中验证。
AI 中文摘要
人形机器人现在能够以显著的通用性行走、平衡和伸手：一个全身跟踪策略可以跟随来自人类或端到端策略的参考。这种通用性体现在轨迹中，而单独的轨迹携带的关于其应产生的交互的信息有限：在接触时，执行控制器决定机器人的行为。单任务策略通常通过在仿真中联合优化轨迹和控制器来实现硬交互；通用栈通常假设预设或手动选择的控制器。我们提出KPI，一个在轨迹源和未修改的全身跟踪器之间进行物理交互的可提示内核。轨迹源不是发送任务前固定的控制器，而是发送一个契约：按方向跟踪、顺从或保持力范围。根据跟踪误差和力估计，内核在接触频率下调整手臂的刚度、阻尼、参考和前馈。我们通过一个代理框架演示KPI：从一条指令，视觉语言代理编写参考轨迹和契约，无需任务特定代码。我们演示了指令驱动的绞盘操作、开门和箱体运输，以及脚本化表面交互实验。在绞盘演示中，人形机器人能够转动曲柄将第二个机器人完全吊离地面。
英文摘要
Humanoids now walk, balance and reach with remarkable generality: one whole-body tracking policy follows references from a human, or from an end-to-end policy. That generality travels in the trajectory, and a trajectory alone carries limited information about the interaction it should produce: at contact, the executing controller determines how the robot behaves. Single-task policies usually reach hard interactions by optimising trajectory and controller together in simulation; general stacks usually assume a preset or hand-chosen controller. We present KPI, a promptable kernel for physical interaction between the trajectory source and an unmodified whole-body tracker. Instead of a controller fixed before the task, the trajectory source sends a contract: per direction, track, comply, or hold a force range. From tracking error and a wrench estimate, the kernel adapts the arms' stiffness, damping, reference and feedforward toward it at contact rate. We demonstrate KPI through an agentic framework: from one instruction, a vision-language agent writes both the reference trajectory and the contract, with no task-specific code. We demonstrate instruction-driven winch operation, door opening, and box transport, alongside scripted surface-interaction experiments. In the winch demonstration, the humanoid is able to turn a crank to hoist a second robot fully off the ground.
CommentsProject website: https://kpi-robot.github.io/
