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.
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
This work proposes Online Residual Policy Adaptation (ORPA), a framework that enables immediate, feedback-driven correction of robot actions without modifying the underlying policy parameters.
Muhammad A. Muttaqien, Tomohiro Motoda, Ryo Hanai et al.· 1 citation
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
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%.
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.· Jornadas de Automática· 0 citations
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.