Skip to content
Preprint

KPI: A Promptable Kernel for Physical Interaction on Humanoids

Sep 2026 · 0 citations · 41 references
Computer Science

TL;DR

KPI, a promptable kernel for physical interaction between the trajectory source and an unmodified whole-body tracker, is presented and demonstrated through an agentic framework: from one instruction, a vision-language agent writes both the reference trajectory and the contract, with no task-specific code.

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.

View source

Similar papers

#artificial intelligence Preprint Aug 2026

GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction

GigaBrain-WBC-0.5, the first Behavior World Model for humanoid whole-body control, is presented, which trains a causal Transformer to jointly predict its next action, next state, and the distribution over its next latent behavior command, so the network that acts also models how the environment shapes what it can do ne...

Zi-Yang Cheng, Tian-Shu Tang, Jin-Xi Lan et al. · 1 citation
Sep 2026

CEER2: Directional and Tunable End-Effector and Root Compliance for Humanoid Loco-Manipulation

Humanoids are increasingly capable of tracking complex whole-body motions, but physical interaction introduces a different challenge. When a robot makes contact with a person or the environment, it needs to respond to external forces while preserving the motion needed for the task. This response can vary across directi...

Xin-Yuan Luo, Chun-Yuan Yang, Bo-Yuan Chen et al. · 0 citations
Preprint Oct 2026

I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement Learning

I-BFM is introduced, to the authors' knowledge the first BFM for humanoid-object interaction, rather than relying on task-specific policies or reference tracking, and learns a shared representation of the coupled dynamics among the humanoid, objects, and their contacts using forward-backward representations and unsuper...

Zi-Qi Han, Yi-Tang Li, Jun Sun et al. · 0 citations
Preprint Oct 2026

Learning Reflexive Behavior for Contact-Rich Manipulation

During contact-rich manipulation, interactions between a robot and its environment carry information about local geometry: a surface prevents penetration, a bore guides a peg. A controller that exploits these interactions can comply with environmental constraints while preserving task intent. Robot-earning systems comm...

Quan Nguyen, Yunho Kim, Joonho Lee · 0 citations
Preprint Aug 2026

LAC: Linear and Angular Compliance for Humanoid Whole-body Control

LAC is presented, a general whole-body controller that simultaneously realizes commanded Linear and Angular Compliance for wrenches applied to the upper body and monotonic modulation over the full range of both stiffness commands, and applicability to teleoperated loco-manipulation tasks.

Yang Liu, Zhongkai Gu, Wei Zhu et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.