ROJun 5

Simulation-Driven Imitation Learning for Biosignals-Free Shared-Autonomy Prosthetic Grasping

arXiv:2606.0738913.3
Originality Incremental advance
AI Analysis

This work addresses the scalability bottleneck of imitation learning for prosthetic control by replacing costly human demonstrations with simulated data, enabling effective policy learning for upper-limb prosthetics.

The paper presents a simulation framework that automatically generates diverse reach-to-grasp demonstrations for training imitation learning policies for biosignals-free shared-autonomy prosthetic grasping. The learned policy achieves over 90% grasp success in realistic settings, surpassing baseline methods and showing strong generalization.

Biosignals-free shared-autonomy control of upper-limb prosthetic hands aims to enable natural and low-effort manipulation without relying on EMG or other physiological signals. Recent imitation-learning-based approaches have shown promising results, but their scalability is limited by the cost and variability of collecting large amounts of real-world human demonstration data. In this work, we present a scalable simulation framework that automatically generates diverse reach-to-grasp demonstrations from a wrist-mounted virtual camera. The framework combines physically feasible grasp synthesis, natural reaching trajectories retargeting, and reach--grasp--lift execution in procedurally generated indoor environments. It records wrist-view observations, proprioception, and actions to build a large-scale demonstration dataset for imitation learning. Through extensive simulation benchmarks, we evaluate object and scene generalization and compare several representative state-of-the-art imitation learning methods. Results show that the simulated demonstrations are sufficiently rich and consistent for effective policy learning. In three realistic settings, the learned sim-to-real policy achieves over 90\% grasp success, surpasses baseline methods, and exhibits stronger generalization, highlighting the promise of simulation-driven training for biosignals-free shared-autonomy prosthetic grasping. The demonstrations are available at \href{https://sites.google.com/view/sim-prosthetic-grasp/home}{https://sites.google.com/view/sim-prosthetic-grasp/home}.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes