Path Planning in Support of Smart Mobility Applications using Generative Adversarial Networks

TL;DR

This paper explores using Generative Adversarial Networks to improve path planning for smart mobility, demonstrating high accuracy and reliability in indoor navigation scenarios with crowd-sourced data.

Contribution

It introduces a GAN-based architecture for path recommendation that leverages crowd data to generate accurate navigation paths for various mobility applications.

Findings

Path accuracy up to 99%

Generated path quality score of 89%

Effective in indoor wayfinding applications

Abstract

This paper describes and evaluates the use of Generative Adversarial Networks (GANs) for path planning in support of smart mobility applications such as indoor and outdoor navigation applications, individualized wayfinding for people with disabilities (e.g., vision impairments, physical disabilities, etc.), path planning for evacuations, robotic navigations, and path planning for autonomous vehicles. We propose an architecture based on GANs to recommend accurate and reliable paths for navigation applications. The proposed system can use crowd-sourced data to learn the trajectories and infer new ones. The system provides users with generated paths that help them navigate from their local environment to reach a desired location. As a use case, we experimented with the proposed method in support of a wayfinding application in an indoor environment. Our experiments assert that the generated paths are correct and reliable. The accuracy of the classification task for the generated paths is up to 99% and the quality of the generated paths has a mean opinion score of 89%.