COBRA-PPM: a causal Bayesian reasoning architecture using probabilistic programming for robot manipulation under uncertainty

Conference item

Manipulation tasks require robots to reason about cause and effect when interacting with objects. Yet, many data-driven approaches lack causal semantics and thus only consider correlations. We introduce COBRA-PPM, a novel causal Bayesian reasoning architecture that combines causal Bayesian networks and probabilistic programming to perform interventional inference for robot manipulation under uncertainty. We demonstrate its capabilities through high-fidelity Gazebo-based experiments on an exemplar block stacking task, where it: (1) predicts manipulation outcomes with high accuracy (Pred Acc: 88.6%); and (2) performs greedy next-best action selection with a 94.2% task success rate. We further demonstrate sim2real transfer on a domestic robot, showing effectiveness in handling real-world uncertainty from sensor noise and stochastic actions. Our generalised and extensible framework supports a wide range of manipulation scenarios and lays a foundation for future work at the intersection of robotics and causality.

Authors: Cannizzaro, R; Groom, M; Routley, J; Ness, R; Kunze, L

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Host title: 2025 European Conference on Mobile Robots (ECMR)
• Publication date: 2025-09-18
• Acceptance date: 2025-06-23
• Event title: European Conference on Mobile Robots (ECMR 2025)
• Event location: Padua, Italy
• Event website: https://ecmr2025.dei.unipd.it/
• Event start date: 2025-09-02
• Event end date: 2025-09-05
• DOI: 10.1109/ecmr65884.2025.11163313
• EISSN: 2767-8733
• ISSN: 2639-7919
• EISBN: 9798331527051
• ISBN: 9798331527068
• Language: English
• Keywords: uncertainty; service robots; stacking; stochastic processes; programming; probabilistic logic; robot sensing systems; cognition; Bayes methods; tuning