Plan recognition as planning revisited
Shirin Sohrabi, Anton Riabov, et al.
IJCAI 2016
Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We propose Latplan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), Latplan learns a complete propositional PDDL action model of the environment. Later, when a pair of images representing the initial and the goal states (planning inputs) is given, Latplan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. We evaluate Latplan using image-based versions of 6 planning domains: 8-puzzle, 15-Puzzle, Blocksworld, Sokoban and Two variations of LightsOut.
Shirin Sohrabi, Anton Riabov, et al.
IJCAI 2016
Tathagata Chakraborti, Vatche Isahagian, et al.
AAAI 2023
Oktie Hassanzadeh, Debarun Bhattacharjya, et al.
AAAI 2020
Tengfei Ma, Patrick Ferber, et al.
AAAI 2020