One-Shot Learning of Visual Path Navigation for Autonomous Vehicles
This addresses the data problem for autonomous vehicles by reducing reliance on large datasets, though it is incremental as it builds on existing end-to-end deep learning models.
The paper tackles the challenge of data scarcity in autonomous driving by introducing a deep neural network that enables one-shot learning for visual path navigation, allowing a vehicle to autonomously drive a previously unseen path after being shown it once, with in-vehicle and offline tests verifying performance.
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.