CCIL: Context-conditioned imitation learning for urban driving

TL;DR

This paper introduces CCIL, a novel context-conditioned imitation learning method for urban driving that improves trajectory prediction by using a perturbed coordinate system and outperforms existing approaches on large-scale datasets.

Contribution

The paper proposes a new imitation learning framework that conditions on context and employs a perturbed coordinate system to enhance urban driving performance.

Findings

Significantly outperforms state-of-the-art methods on Lyft and nuPlan datasets.

Effectively addresses covariate shift in behavior cloning.

Demonstrates improved trajectory prediction accuracy in complex urban scenarios.

Abstract

Imitation learning holds great promise for addressing the complex task of autonomous urban driving, as experienced human drivers can navigate highly challenging scenarios with ease. While behavior cloning is a widely used imitation learning approach in autonomous driving due to its exemption from risky online interactions, it suffers from the covariate shift issue. To address this limitation, we propose a context-conditioned imitation learning approach that employs a policy to map the context state into the ego vehicle's future trajectory, rather than relying on the traditional formulation of both ego and context states to predict the ego action. Additionally, to reduce the implicit ego information in the coordinate system, we design an ego-perturbed goal-oriented coordinate system. The origin of this coordinate system is the ego vehicle's position plus a zero mean Gaussian perturbation, and the x-axis direction points towards its goal position. Our experiments on the real-world large-scale Lyft and nuPlan datasets show that our method significantly outperforms state-of-the-art approaches.