Skip to content
arXiv cs.RO·· 2 days agoAI score71

Auditing Grasp Feasibility Predictors with Planner-Verified Counterfactual Tests

Summary

The study proposes a planner-verified counterfactual (CF) test: holding the grasp pose fixed, a solid obstacle is inserted into the approach corridor and its points are added to the model input, after which the planner re-derives the label, flipping it from feasible to infeasible. Across eight predictors spanning point clouds, voxels, depth, and object tokens, CF-pair AUROC falls from 0.920-0.996 in natural scenes to near chance (0.470-0.504), and this flip holds across four planners, two robotic arms, and a real-object obstacle.

This page provides a summary and source link only. Read the full article at the source.

Source: arXiv cs.RO · arxiv.org

Grasping and manipulationRobot models and learningData and simulationResearch papersBenchmarks and evaluations#Research#Grasping and manipulation#Robot models and learning#Evaluations and benchmarks#Data and simulation