[Reproducibility Report] Path Planning using Neural A* Search

TL;DR

This reproducibility report verifies the Neural A* path planning method, reproduces its results, and explores several extensions like stochasticity, hyperparameter training, and different network architectures.

Contribution

It provides a verified reproduction of Neural A* and investigates the impact of various modifications and extensions on its performance.

Findings

Reproduced original results successfully.

Extensions like dropout and GANs affect path planning performance.

Training hyperparameters as trainable improves model adaptability.

Abstract

The following paper is a reproducibility report for "Path Planning using Neural A* Search" published in ICML2 2021 as part of the ML Reproducibility Challenge 2021. The original paper proposes the Neural A* planner, and claims it achieves an optimal balance between the reduction of node expansions and path accuracy. We verify this claim by reimplementing the model in a different framework and reproduce the data published in the original paper. We have also provided a code-flow diagram to aid comprehension of the code structure. As extensions to the original paper, we explore the effects of (1) generalizing the model by training it on a shuffled dataset, (2) introducing dropout, (3) implementing empirically chosen hyperparameters as trainable parameters in the model, (4) altering the network model to Generative Adversarial Networks (GANs) to introduce stochasticity, (5) modifying the encoder from Unet to Unet++, (6) incorporating cost maps obtained from the Neural A* module in other variations of A* search.