Trailblazer trains a neural network with a differentiable A* planner to produce off-road costmaps directly from overhead imagery and LiDAR, claiming robust real-world navigation without manual tuning.
In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Trailblazer: Learning offroad costmaps for long range planning
Trailblazer trains a neural network with a differentiable A* planner to produce off-road costmaps directly from overhead imagery and LiDAR, claiming robust real-world navigation without manual tuning.