Robot Pouring: Identifying Causes of Spillage and Selecting Alternative Action Parameters Using Probabilistic Actual Causation

2025-02-13

AI Summary

This work addresses liquid spilling during robotic pouring tasks. We propose a failure attribution and adaptive replanning method grounded in probabilistic actual causality reasoning. First, we construct an action–state causal graph, learn its structure from simulation data, and quantify the actual causal effect of each action parameter—such as tilt angle, pouring velocity, and container orientation—on spilling using the Halpern–Pearl framework. Based on this causal analysis, we generate executable corrective strategies. To our knowledge, this is the first systematic application of probabilistic actual causality models to robotic manipulation failure analysis, enabling a closed-loop decision pipeline: phenomenon identification → causal attribution → strategy optimization. Experiments demonstrate that our method accurately identifies primary spilling causes, reduces spilling rate by 76%, and achieves 89% agreement with human expert judgments in recommended strategies.

Technology Category

• Intelligent Robots: Manipulation
• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

In everyday life, we perform tasks (e.g., cooking or cleaning) that involve a large variety of objects and goals. When confronted with an unexpected or unwanted outcome, we take corrective actions and try again until achieving the desired result. The reasoning performed to identify a cause of the observed outcome and to select an appropriate corrective action is a crucial aspect of human reasoning for successful task execution. Central to this reasoning is the assumption that a factor is responsible for producing the observed outcome. In this paper, we investigate the use of probabilistic actual causation to determine whether a factor is the cause of an observed undesired outcome. Furthermore, we show how the actual causation probabilities can be used to find alternative actions to change the outcome. We apply the probabilistic actual causation analysis to a robot pouring task. When spillage occurs, the analysis indicates whether a task parameter is the cause and how it should be changed to avoid spillage. The analysis requires a causal graph of the task and the corresponding conditional probability distributions. To fulfill these requirements, we perform a complete causal modeling procedure (i.e., task analysis, definition of variables, determination of the causal graph structure, and estimation of conditional probability distributions) using data from a realistic simulation of the robot pouring task, covering a large combinatorial space of task parameters. Based on the results, we discuss the implications of the variables' representation and how the alternative actions suggested by the actual causation analysis would compare to the alternative solutions proposed by a human observer. The practical use of the analysis of probabilistic actual causation to select alternative action parameters is demonstrated.

Problem

• Identify causes of robot pouring spillage
• Select alternative actions using probabilistic causation
• Model causal relationships in robotic tasks

Innovation

• Probabilistic actual causation analysis
• Causal graph and probabilities
• Alternative action parameter selection