[Re] Differentiable Spatial Planning using Transformers

TL;DR

This paper reproduces and verifies a differentiable spatial planning method using Transformers, demonstrating its effectiveness and analyzing its stability with complex obstacle maps, while also highlighting reproducibility challenges.

Contribution

It reproduces and validates the original Transformer-based spatial planning approach and explores its robustness with increased obstacle complexity.

Findings

Transformer-based planner outperforms prior models

Planning accuracy remains stable with increased obstacle complexity

Reproduction faced resource and communication challenges

Abstract

This report covers our reproduction effort of the paper 'Differentiable Spatial Planning using Transformers' by Chaplot et al. . In this paper, the problem of spatial path planning in a differentiable way is considered. They show that their proposed method of using Spatial Planning Transformers outperforms prior data-driven models and leverages differentiable structures to learn mapping without a ground truth map simultaneously. We verify these claims by reproducing their experiments and testing their method on new data. We also investigate the stability of planning accuracy with maps with increased obstacle complexity. Efforts to investigate and verify the learnings of the Mapper module were met with failure stemming from a paucity of computational resources and unreachable authors.