Skip to content
Preprint

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

Sep 2026 · 0 citations · 25 references
Computer Science

TL;DR

The results show that work-aware policy optimization can suppress physically inefficient motion without requiring an explicit differentiable dynamics model.

Abstract

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 sweeping. The proposed fine-tuning reduces the average mechanical work from 208.8J to 204.4J (i.e., 2.1% reduction), while the mean task success rate also increases slightly from 86.2% to 86.9%. These results show that work-aware policy optimization can suppress physically inefficient motion without requiring an explicit differentiable dynamics model.

View source

Similar papers

Preprint Sep 2026

Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control

While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly represent actions as target positions or poses. Even methods that incorporate force sensing either use it solely as an observation or, when predicting forces as part of th...

Johannes Hechtl, Yannik Blei, Simon Ball et al. · 0 citations
Preprint Sep 2026

Impedance Cloning: Learning Equilibrium Point Parameters for Contact-Rich Manipulation

Contact-rich manipulation requires robots to regulate force against surfaces whose geometry deviates unpredictably from training conditions. Trajectory-based imitation learning, which reproduces observable outputs, breaks down under such shifts. We propose Impedance Cloning, which instead imitates the biomechanical pri...

Hayato Takahashi, Ryoga Oishi, Yukio Kasuga et al. · 0 citations

Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation

PA-RL, a reinforcement-learning framework that uses artificial potential fields as the action representation, is proposed and is the only method to reach a 100% evaluation success rate within the allotted training time, while the best baseline reaches 92.6%.

Xin-Yu Liu, Gokhan Solak, Arash Ajoudani · 0 citations
Open access Sep 2026

Robust Task Generalization for Dual-Arm Learning from Demonstration

A Movement Primitive learning algorithm based on Gaussian Processes, combined with real-time zero-shot adaptation through Pathwise Conditioning, which encapsulates the predictive uncertainty of the demonstrated movement using heteroscedastic GPs and utilizes an update via Matheron's rule to instantaneously adjust the t...

Adrián Prados, L. Lishan, Alberto Mendez et al. · 0 citations
Preprint Aug 2026

Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL

This work uses Sample-based Model Predictive Control entirely in simulation as an automated, rapidly tunable expert to generate massive offline datasets and validate the robustness of this sim-to-real framework by successfully deploying complex loco-manipulation skills across different morphologies.

Martin Schuck, Maks Sorokin, S. Manni et al. · 1 citation

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