SOURCE-LINKED INTELLIGENCE

Energy-Regularized Imitation Learning for Force- and Work-Aware Robotic Manipulation

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

This paper studies energy-aware manipulation as a physically grounded learning problem. We define a joint-space mechanical-work proxy from joint torque and angular displacement, and train a differentiable energy predictor that estimates this work from robot states and actions. The predictor converts a non-differentiable simulator-side physical quantity into a differentiable regularizer for fine-tuning a pretrained manipulation policy. We instantiate the framework with RVT-2 on RLBench and evaluate 12 manipulation tasks involving object contact, articulated motion, placement, pushing, and sweep

Read original source ↗ Open in workspace

recordType

paper

region

Global