Path Planning using Neural A* Search

TL;DR

Neural A* introduces a differentiable, end-to-end trainable neural network that reformulates A* search for path planning, achieving superior accuracy and efficiency over existing data-driven methods, and can predict realistic human trajectories from natural images.

Contribution

The paper presents Neural A*, a novel differentiable reformulation of A* search combined with neural encoding, enabling effective learning and superior path planning performance.

Findings

Outperforms state-of-the-art data-driven planners in accuracy and efficiency.

Successfully predicts realistic human trajectories from natural images.

Demonstrates the effectiveness of differentiable search in neural network training.

Abstract

We present Neural A*, a novel data-driven search method for path planning problems. Despite the recent increasing attention to data-driven path planning, machine learning approaches to search-based planning are still challenging due to the discrete nature of search algorithms. In this work, we reformulate a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end trainable neural network planner. Neural A* solves a path planning problem by encoding a problem instance to a guidance map and then performing the differentiable A* search with the guidance map. By learning to match the search results with ground-truth paths provided by experts, Neural A* can produce a path consistent with the ground truth accurately and efficiently. Our extensive experiments confirmed that Neural A* outperformed state-of-the-art data-driven planners in terms of the search optimality and efficiency trade-off. Furthermore, Neural A* successfully predicted realistic human trajectories by directly performing search-based planning on natural image inputs. Project page: https://omron-sinicx.github.io/neural-astar/