One-Shot Learning of Visual Path Navigation for Autonomous Vehicles

TL;DR

This paper introduces a one-shot learning approach for autonomous vehicle path navigation, enabling vehicles to learn new routes from a single example without retraining, thus addressing data scarcity issues.

Contribution

The paper proposes a novel deep neural network that incorporates one-shot learning for image-to-steering navigation, allowing autonomous vehicles to learn new paths from minimal data.

Findings

Vehicle can navigate unseen paths after a single demonstration

The system performs well in both in-vehicle and offline tests

Different neural network architectures are compared for effectiveness

Abstract

Autonomous driving presents many challenges due to the large number of scenarios the autonomous vehicle (AV) may encounter. End-to-end deep learning models are comparatively simplistic models that can handle a broad set of scenarios. However, end-to-end models require large amounts of diverse data to perform well. This paper presents a novel deep neural network that performs image-to-steering path navigation that helps with the data problem by adding one-shot learning to the system. Presented with a previously unseen path, the vehicle can drive the path autonomously after being shown the path once and without model retraining. In fact, the full path is not needed and images of the road junctions is sufficient. In-vehicle testing and offline testing are used to verify the performance of the proposed navigation and to compare different candidate architectures.