[
    {
        "id": "osp-25658",
        "type": "article-journal",
        "title": "KPI: A Promptable Kernel for Physical Interaction on Humanoids",
        "author": [
            {
                "family": "Wang",
                "given": "Yikai"
            },
            {
                "family": "Zhu",
                "given": "Honghao"
            },
            {
                "family": "Hu",
                "given": "Xiao"
            },
            {
                "family": "Zhang",
                "given": "Hao"
            },
            {
                "family": "Wang",
                "given": "Zelin"
            },
            {
                "family": "Yeung",
                "given": "Yip Fun"
            },
            {
                "family": "Zhao",
                "given": "Ding"
            },
            {
                "family": "Sun",
                "given": "Lingfeng"
            }
        ],
        "URL": "https://omanscience.com/en/articles/kpi-a-promptable-kernel-for-physical-interaction-on-humanoids",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "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."
    }
]