Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks.
Tom SilverRohan ChitnisAidan CurtisJoshua B. TenenbaumTomás Lozano-PérezLeslie Pack KaelblingPublished in: CoRR (2020)
Keyphrases
- neural network
- pattern recognition
- graph structure
- d objects
- graph representation
- back propagation
- graph matching
- multilayer perceptron
- random walk
- directed graph
- feed forward
- complex objects
- neural network model
- causal graph
- graph model
- weighted graph
- data objects
- object tracking
- artificial neural networks
- moving objects
- learning algorithm
- planning problems
- np complete
- partial occlusion
- object model
- search algorithm
- spanning tree
- graph partitioning
- genetic algorithm