FLoRe teaches humanoids where to move and how hard to push, from human demos
HaozhiQ · x · 2026-11-05
A new work introduces FLoRe: Learning Force-Reactive Humanoid Loco-Manipulation. Using human demonstrations collected without a robot, the policy learns to predict both actions and forces for each hand, while a hybrid compliance whole-body controller tracks these commands as the robot walks and balances. Multiple researchers note that a force-aware pipeline can unblock many hard loco-manipulation problems, with force sensors acting as new "eyes" for sensing physics and guiding the policy.
More from Embodied
- XR Blocks team runs talk, demos and 'World as a Canvas' workshop at UIST 2026 — DuRuofei · 2026-11-05
- YC-backed Ishiki Labs launches Fern, a robotics sim platform that builds high-fidelity sims from 3 teleop episodes — ycombinator · 2026-11-05
- First method to estimate empowerment from offline data for intrinsically motivated exploration — Berkeley/Princeton — ben_eysenbach · 2026-11-05
- GCRL and unsupervised skill learning unified via control-maximization — NeurIPS Oral from Eysenbach and Dayan — ben_eysenbach · 2026-11-05
- Aformic raises $6.95M seed round with $34M in robot purchase orders — MatthewChang · 2026-11-05
- Tau Robotics humanoid cleans an apartment on camera: 'not our bots' — kyliebytes · 2026-11-05