Learning Contextual Motion Constraints for Object Rearrangement Exploration
Learning Contextual Motion Constraints for Object Rearrangement Exploration
This research presents MoCo-Net, a two-stream neural network designed to predict the continuous motion ranges of articulated parts and generate obstacle heatmaps from partial-view point cloud observations. By jointly modeling intrinsic joint limits and extrinsic obstacles, the system improves feasible motion range prediction and obstacle recognition, enabling better generalization to novel objects and scenes. The resulting compact configuration space allows customized planners to efficiently explore rearrangement actions in cluttered environments.
The paper introduces MoCo-Net, a two-stream neural network that predicts motion ranges and obstacle heatmaps for articulated objects in cluttered scenes to improve rearrangement exploration.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2611.12072v1 Announce Type: new Abstract: The motion of an articulated part in cluttered surroundings is constrained not only by an object's intrinsic joint limits but also by extrinsic obstacles. However, existing approaches primarily consider object articulation properties alone. Here we present Motion Constraint Prediction Network (MoCo-Net), a two-stream neural network that jointly predicts the continuous m
Open source S2
Source：arXiv Robotics — research abstracts · arxiv.org