Learning Motion Feasibility from Point Clouds in Cluttered Environments
For robotic manipulation in cluttered scenes, this work provides a fast and accurate feasibility prediction method that avoids costly planning attempts, addressing a key bottleneck in task and motion planning.
This paper tackles the problem of predicting motion feasibility for a 7-DOF manipulator in cluttered environments directly from raw RGB-D observations, introducing a large-scale benchmark with 2.7M labels. Their best model, GRASPFC-PTX, achieves an AUROC of 0.996 on novel objects and is significantly faster than sampling-based motion planners.
Motion feasibility prediction plays a central role in robotics, particularly in task and motion planning and manipulation. A major bottleneck for this problem in cluttered environments is that infeasible planning attempts by Sampling-based motion planners (SBMPs) can incur substantial computational cost. Also existing approaches for infeasibility certification are limited to low-dimensional configuration spaces and often assume simplified geometric environments represented by primitive objects with known parameters. We study the complementary problem of learning motion feasibility prediction directly from raw RGB-D observations for a 7-DOF manipulator operating in realistic cluttered scenes. We introduce the first large-scale benchmark for this setting, comprising 2.7M grasp feasibility labels over 88 scanned objects and 190 cluttered tabletop scenes. We benchmark three representative classifier families spanning MLP- based, volumetric-CNN, and point-cloud-based Transformer architectures under matched training conditions. Our best model, GRASPFC-PTX (a point-cloud transformer), achieves an AUROC of 0.996 on Novel objects while providing predictions significantly faster than SBMPs.