Pose accuracy is not grasp reliability: residual pose posteriors improve simulated robotic grasp planning
Overview
The authors propose building a pose posterior from estimator errors on annotated frames to score grasps across sampled poses and physics scenarios.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“arXiv:2609.13235v2 Announce Type: replace Abstract: Model-based robotic grasping estimates an object's six-dimensional (6D) pose and plans on its mesh as if that pose were exact. We show that this assumption reduces simulated grasp success even when the pose passes the standard accuracy test. We built LM-Grasp, a benchmark of 15{,}800 real LINEMOD RGB-D images with grasp outcomes simulated on scanned meshes. Foundati”
Exact source · revision 1Source owner not reported
Reported quantity · percent: 0.796 other · Basis not reported
“imulated success rises from 0.796 to 0.984. Among test scenes assigned singleton-success conformal prediction sets, observed held-out precision is 0.972, compared with 0.904 for the point-estimate planner; these are empirical precision estimates, not conditional guarantees. On occluded LM-O scenes never used for tuning, posterior planning closes 66\% of the gap to the annotated pose.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalPose accuracy is not grasp reliability: residual pose posteriors improve simulated robotic grasp planning
The authors propose building a pose posterior from estimator errors on annotated frames to score grasps across sampled poses and physics scenarios.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).