Search papers, labs, and topics across Lattice.
This paper introduces a closed-loop framework that integrates a Joint Probability Tree (JPT) with a Causal Circuit to enhance the safety and efficiency of robot action testing and failure recovery. By employing causal diagnosis upon rejection of proposed actions, the method identifies the specific parameters causing failures and suggests corrective actions that maximize the likelihood of passing tests. Experimental results in a ROS2 simulation show that the framework can reduce failed attempts by up to 37%, while also providing interpretable causal reports to support operator oversight.
Causal diagnosis transforms robot action testing from a blind resampling process into a targeted, efficient strategy that reduces failures by over a third.
Safe physical AI for robot actions are required not only likely to succeed but tested to be safe before execution. In practice, however, formal testing of motion parameters is computationally expensive, and the cost scales poorly with the dimensionality of the action space. When a proposed action is rejected by a tester, the naive response is to resample blindly until a passing candidate is found. This is wasteful, uninformative, and offers no convergence. We argue that rejection should instead trigger causal diagnosis: a principled identification of which action parameter caused the failure and what corrective value maximises the probability of passing testing under the interventional probability distribution. We propose a closed-loop framework that couples a Joint Probability Tree (JPT) with a Causal Circuit derived from a Marginal-Deterministic Variable Tree, enabling exact polytime computation without retraining, or additional data collection. The framework validates tractability of all interventional queries before the robot begins operating, and out-of-support candidates are detected and excluded from correction automatically. We perform experiments in a ROS2 simulation environment, and the framework demonstrates complementary roles across quality of distribution: under a high-quality JPT, the Causal Circuit reduces failed attempts by 10.3% and under a degraded JPT, it reduces total failed attempts by 37%. Every rejected plan produces a structured, interpretable causal report naming the primary cause variable, its observed value, and the recommended corrective region, supporting operator oversight and autonomous recovery without a separately trained failure model.
