Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning

arXiv:2310.03325v2 Announce Type: replace-cross
Abstract: Visual planning simulates how humans make decisions to achieve desired goals in the form of searching for visual causal transitions between an initial visual state and a final visual goal state. It has become increasingly important in egocentric vision with its advantages in guiding agents to perform daily tasks in complex environments. In this paper, we propose an interpretable and generalizable visual planning framework consisting of i) a novel Substitution-based Concept Learner (SCL) that abstracts …

arxiv causal concept cs.ai cs.cv cs.lg planning reasoning symbolic reasoning transition type visual