Lightweight Neural Path Planning

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.

Authors

• Jinsong Li
• Shaochen Wang
• Ziyang Chen
• Zhen Kan
• Jun Yu 0001

Keywords

• Training
• Navigation
• Computer architecture
• Numerical simulation
• Path planning
• Planning
• Numerical models
• Numerical Simulations
• Numerical Experiments
• Model Size
• Feature Fusion
• Physical Experiments
• Succession Planning
• Feature Fusion Module
• Sampling-based Methods
• Neural Network
• Objective Function
• Convolutional Neural Network
• End Point
• Deep Neural Network
• Regional State
• Computational Resources
• Generative Adversarial Networks
• Learning-based Methods
• Inference Time
• Optimal Path
• Rapidly-exploring Random Tree
• Feasible Path
• Environment Map
• Max-pooling Operation
• Promising Regions
• Conv Layer
• Conditional Variational Autoencoder
• Graph-based Methods
• Mobile Robot
• Storage Space