CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs
2026-08-03 • Robotics
RoboticsArtificial IntelligenceMachine Learning
AI summaryⓘ
The authors introduce CoWAM, a system that helps two-handed robot policies work together better by selectively changing their actions only when necessary. CoWAM uses 'coordination contracts' that check if actions are safe, synchronized, and compatible to avoid collisions. It avoids unnecessary changes, only intervening when it improves the robot's performance or when the original action is not allowed. Tested on eight tasks, CoWAM improved coordination success and reduced harmful interventions compared to other methods. This shows that careful rules can help robots coordinate actions more reliably.
World Action Modelsbimanual robot policiesaction-conditioned predictioncoordination contractssynchronizationcollision avoidancepolicy interventionclosed-loop successselective interventionrobot coordination
Authors
Shuaijun Liu, Qifu Wen, Shuyang Hao, Qi Luo, Chenglong Zhang, Feiyang You, Chengyu Wu, Ningxin Su
Abstract
World Action Models (WAMs) augment robot policies with action-conditioned predicted futures, but a plausible future alone does not justify changing the action that a bimanual policy would execute. We present CoWAM, a selective intervention layer that expresses synchronization, role compatibility, and collision convergence as coordination contracts. Each contract combines typed admissibility checks with event-conditioned verification and calibrated intervention gates. CoWAM preserves the nominal action unless an alternative satisfies every active obligation and provides a clear, low-risk improvement; when the nominal action is also inadmissible, it invokes a predefined abstention fallback. To separate selector quality from proposal quality, all methods operate on identical candidate pools and commit their decisions before shared oracle labeling. Across eight simulated bimanual tasks, CoWAM improves coordination-valid selection by 16.7 percentage points over the contract-only variant and raises closed-loop success by 9.6 percentage points over the strongest selective baseline, while keeping harmful interventions below 1%. Together, these results establish coordination contracts as an effective interface for conservative policy intervention with predicted world-action evidence across coordination-rich bimanual tasks.