End-to-End Steering for Autonomous Vehicles via Conditional Imitation Co-Learning

TL;DR

This paper introduces conditional imitation co-learning (CIC), an advanced end-to-end autonomous driving model that improves generalization to unseen environments by learning relationships between specialist branches and using hybrid loss functions.

Contribution

The work proposes CIC with a co-learning matrix and hybrid loss to enhance generalization in end-to-end autonomous driving models, addressing limitations of previous CIL approaches.

Findings

62% improvement in success rate in unseen environments

Enhanced generalization through co-learning matrix and hybrid loss

Effective modeling of steering as classification with spatial considerations

Abstract

Autonomous driving involves complex tasks such as data fusion, object and lane detection, behavior prediction, and path planning. As opposed to the modular approach which dedicates individual subsystems to tackle each of those tasks, the end-to-end approach treats the problem as a single learnable task using deep neural networks, reducing system complexity and minimizing dependency on heuristics. Conditional imitation learning (CIL) trains the end-to-end model to mimic a human expert considering the navigational commands guiding the vehicle to reach its destination, CIL adopts specialist network branches dedicated to learn the driving task for each navigational command. Nevertheless, the CIL model lacked generalization when deployed to unseen environments. This work introduces the conditional imitation co-learning (CIC) approach to address this issue by enabling the model to learn the relationships between CIL specialist branches via a co-learning matrix generated by gated hyperbolic tangent units (GTUs). Additionally, we propose posing the steering regression problem as classification, we use a classification-regression hybrid loss to bridge the gap between regression and classification, we also propose using co-existence probability to consider the spatial tendency between the steering classes. Our model is demonstrated to improve autonomous driving success rate in unseen environment by 62% on average compared to the CIL method.