Generalizing Motion Planners with Mixture of Experts for Autonomous Driving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Qiao, Wang, Huimin, Zhan, Jiahao, Nie, Fan, Wen, Xin, Xu, Leimeng, Zhan, Kun, Jia, Peng, Lang, Xianpeng, Zhao, Hang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913566905335808
author Sun, Qiao
Wang, Huimin
Zhan, Jiahao
Nie, Fan
Wen, Xin
Xu, Leimeng
Zhan, Kun
Jia, Peng
Lang, Xianpeng
Zhao, Hang
author_facet Sun, Qiao
Wang, Huimin
Zhan, Jiahao
Nie, Fan
Wen, Xin
Xu, Leimeng
Zhan, Kun
Jia, Peng
Lang, Xianpeng
Zhao, Hang
contents Large real-world driving datasets have sparked significant research into various aspects of data-driven motion planners for autonomous driving. These include data augmentation, model architecture, reward design, training strategies, and planner pipelines. These planners promise better generalizations on complicated and few-shot cases than previous methods. However, experiment results show that many of these approaches produce limited generalization abilities in planning performance due to overly complex designs or training paradigms. In this paper, we review and benchmark previous methods focusing on generalizations. The experimental results indicate that as models are appropriately scaled, many design elements become redundant. We introduce StateTransformer-2 (STR2), a scalable, decoder-only motion planner that uses a Vision Transformer (ViT) encoder and a mixture-of-experts (MoE) causal Transformer architecture. The MoE backbone addresses modality collapse and reward balancing by expert routing during training. Extensive experiments on the NuPlan dataset show that our method generalizes better than previous approaches across different test sets and closed-loop simulations. Furthermore, we assess its scalability on billions of real-world urban driving scenarios, demonstrating consistent accuracy improvements as both data and model size grow.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15774
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalizing Motion Planners with Mixture of Experts for Autonomous Driving
Sun, Qiao
Wang, Huimin
Zhan, Jiahao
Nie, Fan
Wen, Xin
Xu, Leimeng
Zhan, Kun
Jia, Peng
Lang, Xianpeng
Zhao, Hang
Robotics
Computer Vision and Pattern Recognition
Large real-world driving datasets have sparked significant research into various aspects of data-driven motion planners for autonomous driving. These include data augmentation, model architecture, reward design, training strategies, and planner pipelines. These planners promise better generalizations on complicated and few-shot cases than previous methods. However, experiment results show that many of these approaches produce limited generalization abilities in planning performance due to overly complex designs or training paradigms. In this paper, we review and benchmark previous methods focusing on generalizations. The experimental results indicate that as models are appropriately scaled, many design elements become redundant. We introduce StateTransformer-2 (STR2), a scalable, decoder-only motion planner that uses a Vision Transformer (ViT) encoder and a mixture-of-experts (MoE) causal Transformer architecture. The MoE backbone addresses modality collapse and reward balancing by expert routing during training. Extensive experiments on the NuPlan dataset show that our method generalizes better than previous approaches across different test sets and closed-loop simulations. Furthermore, we assess its scalability on billions of real-world urban driving scenarios, demonstrating consistent accuracy improvements as both data and model size grow.
title Generalizing Motion Planners with Mixture of Experts for Autonomous Driving
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.15774