Kinematic Constraint-Referenced Evaluation for Articulated Object Manipulation

arXiv:2610.37550v1 Announce Type: cross Abstract: Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We introduce Constraint-Referenced Strategy (CRS), which projects the commanded end-effector twist onto the object's joint axis, separating progress along the joint from off-constraint waste. CRS requires a joint model and a joint-following scripted controller derived from it, but no recorded demonstration or learned judge. On 74 simulated articulated objects, success registers three transfer failures as lower rates but attributes none, while the two CRS channels give each a distinct signature. A door-trained behavior-cloning policy opens drawers in 59 of 110 episodes, and in these passes it commands about 40imes the off-axis rotation of a drawer-trained policy's passes (1.27 vs. 0.032~rad/s). Relative to a scripted controller scored with the same axis, CRS verdicts are unchanged under joint-axis errors up to 30^irc; absolute thresholds tolerate about 8^irc.

Related

• Outcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies
• GSAM: A Generalizable and Safe Robotic Framework for Articulated Object Manipulation
• Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies
• From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation

Source: arXiv cs.AI | 2026-10-28