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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, Jie, Chen, Yingbing, Chen, Qifeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909177600802816
author Cheng, Jie
Chen, Yingbing
Chen, Qifeng
author_facet Cheng, Jie
Chen, Yingbing
Chen, Qifeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_14327
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving
Cheng, Jie
Chen, Yingbing
Chen, Qifeng
Robotics
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.
title PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving
topic Robotics
url https://arxiv.org/abs/2404.14327