A fully convolutional network trained on past path-planning examples predicts cost-to-go heuristics that reduce the number of cells explored by a greedy path planner in 2D grid worlds.
Learning motion planning assumptions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fully Convolutional Search Heuristic Learning for Rapid Path Planners
A fully convolutional network trained on past path-planning examples predicts cost-to-go heuristics that reduce the number of cells explored by a greedy path planner in 2D grid worlds.