PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving

TL;DR

PLUTO is a novel imitation learning framework for autonomous driving that combines a new model architecture, auxiliary loss, and contrastive learning with data augmentation to achieve state-of-the-art performance on real-world benchmarks.

Contribution

The paper introduces a comprehensive framework that significantly advances imitation learning-based planning by integrating a new model architecture, auxiliary loss, and contrastive learning techniques.

Findings

Achieves state-of-the-art closed-loop performance on nuPlan dataset

Surpasses existing learning-based and rule-based planners

Demonstrates effective behavior regulation and interaction understanding

Abstract

We present PLUTO, a powerful framework that pushes the limit of imitation learning-based planning for autonomous driving. Our improvements stem from three pivotal aspects: a longitudinal-lateral aware model architecture that enables flexible and diverse driving behaviors; An innovative auxiliary loss computation method that is broadly applicable and efficient for batch-wise calculation; A novel training framework that leverages contrastive learning, augmented by a suite of new data augmentations to regulate driving behaviors and facilitate the understanding of underlying interactions. We assessed our framework using the large-scale real-world nuPlan dataset and its associated standardized planning benchmark. Impressively, PLUTO achieves state-of-the-art closed-loop performance, beating other competing learning-based methods and surpassing the current top-performed rule-based planner for the first time. Results and code are available at https://jchengai.github.io/pluto.