Lightweight Neural Path Planning

TL;DR

This paper introduces a lightweight neural path planning architecture designed for resource-constrained robots, achieving significant reductions in model size and computation while maintaining effective navigation performance.

Contribution

The authors develop a novel lightweight neural network with a dual input and hybrid sampler, optimized for low-resource robotic systems, and provide a new dataset for training.

Findings

Nearly tenfold reduction in model size

Five times lower computational cost

Faster planning convergence with fewer iterations

Abstract

Learning-based path planning is becoming a promising robot navigation methodology due to its adaptability to various environments. However, the expensive computing and storage associated with networks impose significant challenges for their deployment on low-cost robots. Motivated by this practical challenge, we develop a lightweight neural path planning architecture with a dual input network and a hybrid sampler for resource-constrained robotic systems. Our architecture is designed with efficient task feature extraction and fusion modules to translate the given planning instance into a guidance map. The hybrid sampler is then applied to restrict the planning within the prospective regions indicated by the guide map. To enable the network training, we further construct a publicly available dataset with various successful planning instances. Numerical simulations and physical experiments demonstrate that, compared with baseline approaches, our approach has nearly an order of magnitude fewer model size and five times lower computational while achieving promising performance. Besides, our approach can also accelerate the planning convergence process with fewer planning iterations compared to sample-based methods.