This paper introduces an energy-aware approach to robotic manipulation by defining a joint-space mechanical-work proxy based on joint torque and angular displacement. A differentiable energy predictor is trained to estimate this work from robot states and actions, enabling it to serve as a regularizer that fine‑tunes a pretrained manipulation policy. Applied to RVT‑2 on RLBench, the method reduces average mechanical work from 208.8 J to 204.4 J (a 2.1 % drop) while slightly improving task success from 86.2 % to 86.9 % across 12 manipulation tasks.
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 differenti...
arXiv:2607. 11874v1 Announce Type: cross Abstract: Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them.
Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation?
arXiv:2607. 00033v1 Announce Type: cross Abstract: Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging.
The paper introduces PA‑RL, a reinforcement‑learning framework that uses artificial potential fields as the action representation for contact‑rich robotic manipulation. Instead of directly commanding motion, the policy adjusts potential‑field parameters, which a Cartesian impedance controller then executes, decoupling task strategy from low‑level control. In peg‑in‑hole experiments, PA‑RL achieved a 100% success rate in simulation, outperformed baselines in torque and acceleration variation, and transferred to a real robot without fine‑tuning.
Model-free reinforcement learning can acquire contact-rich robotic manipulation skills through trial-and-error interaction, but it often requires the policy to learn both task strategy and low-level m...
arXiv:2506. 04147v5 Announce Type: replace-cross Abstract: Building capable household and industrial robots requires mastering the control of versatile, high-degree-of-freedom (DoF) systems such as mobile manipulators.
While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution speeds. Imitation learning policies are inherently limited by hardware constraints and the speed of the operator during data collection.
The paper introduces ORPA, a framework that adds a lightweight, feedback-conditioned module to a pretrained robotic manipulation policy, enabling real‑time residual adjustments in joint space without retraining the base policy. ORPA allows immediate correction of execution errors and distribution shifts, improving success rates and recovery on precision‑sensitive tasks compared to baseline policies and rule‑based inverse kinematics. The method is evaluated on the ALOHA platform, showing its effectiveness in real‑time deployment scenarios.
arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.
arXiv:2608. 09138v1 Announce Type: cross Abstract: While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution speeds.
arXiv:2512. 16861v2 Announce Type: replace-cross Abstract: Long-horizon manipulation has been a long-standing challenge in the robotics community.