Physics-Based Causal Reasoning for Safe & Robust Next-Best Action Selection in Robot Manipulation Tasks

arXiv:2403.14488v1 Announce Type: cross
Abstract: Safe and efficient object manipulation is a key enabler of many real-world robot applications. However, this is challenging because robot operation must be robust to a range of sensor and actuator uncertainties. In this paper, we present a physics-informed causal-inference-based framework for a robot to probabilistically reason about candidate actions in a block stacking task in a partially observable setting. We integrate a physics-based simulation of the rigid-body system dynamics with a causal Bayesian network …

abstract actuator applications arxiv causal cs.ai cs.lg cs.ro framework however inference key manipulation next object paper physics physics-informed reasoning robot robot manipulation robust sensor stat.ap tasks type world