Neural Weighted A*: Learning Graph Costs and Heuristics with Differentiable Anytime A*
This addresses the challenge of data-driven planning for navigation tasks, offering a flexible trade-off between accuracy and efficiency, though it is incremental by combining existing differentiable algorithms with new learning objectives.
The paper tackles the problem of learning both graph costs and heuristics for path planning by proposing Neural Weighted A*, a differentiable anytime planner that trains end-to-end on raw images, outperforming baselines in accuracy and efficiency.
Recently, the trend of incorporating differentiable algorithms into deep learning architectures arose in machine learning research, as the fusion of neural layers and algorithmic layers has been beneficial for handling combinatorial data, such as shortest paths on graphs. Recent works related to data-driven planning aim at learning either cost functions or heuristic functions, but not both. We propose Neural Weighted A*, a differentiable anytime planner able to produce improved representations of planar maps as graph costs and heuristics. Training occurs end-to-end on raw images with direct supervision on planning examples, thanks to a differentiable A* solver integrated into the architecture. More importantly, the user can trade off planning accuracy for efficiency at run-time, using a single, real-valued parameter. The solution suboptimality is constrained within a linear bound equal to the optimal path cost multiplied by the tradeoff parameter. We experimentally show the validity of our claims by testing Neural Weighted A* against several baselines, introducing a novel, tile-based navigation dataset. We outperform similar architectures in planning accuracy and efficiency.