ForceBand: Learning Forceful Manipulation with sEMG
2026-06-24 • Robotics
Robotics
AI summaryⓘ
The authors created ForceBand, a wrist device that reads muscle signals to estimate how much force each finger applies when manipulating objects. They collected a large dataset combining video, muscle signals, motion data, and fingertip forces to train a model that predicts finger forces from muscle activity. This lets users record demonstrations with just the ForceBand and video, making it easier to teach robots to handle objects with the right amount of force. Their tests show ForceBand predicts forces more accurately than video alone and helps robots successfully complete tasks needing careful force control.
surface electromyography (sEMG)force predictionrobot manipulationmultimodal datasetfinger force estimationIMU (Inertial Measurement Unit)robot policy learningegocentric videocalibrationforce-sensitive manipulation
Authors
Botao He, Zhi Wang, Linna Kuang, Ishaan Ghosh, Jitendra Malik, Cornelia Fermuller, Tingfan Wu, Jiayuan Mao, Ruoshi Liu, Haozhi Qi, Yiannis Aloimonos
Abstract
Human demonstrations are a scalable data source for learning robot manipulation policies. However, common sources of human demonstration data, such as motion-capture trajectories and internet videos, capture mostly motion and appearance while missing the contact forces that are critical for force-sensitive manipulation. In this paper, we introduce ForceBand, a low-cost wrist-worn sEMG system that turns human muscle activity into force-enriched demonstrations. We first collect a 10-hour multimodal dataset containing egocentric video, sEMG, IMU, and fingertip force measurements across diverse actions and objects. Using this dataset, we pre-train an EMG2Force model that predicts per-finger forces from sEMG and IMU signals. After a short user-specific calibration, users can collect target-task demonstrations using only ForceBand and video; EMG2Force then labels these demonstrations with per-finger force traces, producing force-augmented demonstrations for robot policy learning. Experiments show that ForceBand recovers fine-grained fingertip interactions with over 50% lower force prediction error than vision-based baselines and achieves an 87% success rate on pick, squeeze, and place tasks that require object-specific force control across objects with diverse shapes, sizes, and weights. Project website: https://forceband-emg.github.io