TL;DR
P2R tracks task-relevant object points in task demonstrations and policy rollouts, and matches them to compare the desired and achieved object trajectories to generate reward scores, which effectively computes dense rewards from a single video.
This recipe for loco-manipulation generalist policies is replicated and extended to multi-object training, a first step toward loco-manipulation generalist policies at this data scale.
This work introduces ZimaBlue, a scalable framework for learning generalizable World Action Models (WAMs) from large-scale video, and adopts an asynchronous Slow-Fast dual-system architecture to make generative WAMs practical for real-time control.
This work introduces RoboReel: a unified benchmark for evaluating models that learn policies from human videos, and develops four test suites to evaluate the models' performance on multiple axes, including the robustness to visual distractors and the ability to complete long-horizon tasks.
This work presents RobotMover, a complete learning-based system for large-object manipulation that leverages human–object interaction demonstrations to train robot control policies and achieves strong performance in terms of capability, robustness, and controllability, outperforming both learned and teleoperation basel...
CHOREO, a framework for training-free composition of heterogeneous humanoid skills, demonstrates that executable trajectories provide a scalable interface for accumulating and composing pretrained humanoid capabilities.
This work introduces Dream2Reward, which learns a language-conditioned successful latent transition field from positive demonstrations that provides stronger success-failure separation and more informative feedback on low-quality behavior than progress-based alternatives.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
