TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xing, Zebin, Yang, Pengxuan, Wang, Linbo, Zhang, Yichen, Hu, Yiming, Zheng, Yupeng, Wang, Junli, Gao, Yinfeng, Li, Guang, Ma, Kun, Chen, Long, Xia, Zhongpu, Zhang, Qichao, Ye, Hangjun, Zhao, Dongbin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908699051687936
author Xing, Zebin
Yang, Pengxuan
Wang, Linbo
Zhang, Yichen
Hu, Yiming
Zheng, Yupeng
Wang, Junli
Gao, Yinfeng
Li, Guang
Ma, Kun
Chen, Long
Xia, Zhongpu
Zhang, Qichao
Ye, Hangjun
Zhao, Dongbin
author_facet Xing, Zebin
Yang, Pengxuan
Wang, Linbo
Zhang, Yichen
Hu, Yiming
Zheng, Yupeng
Wang, Junli
Gao, Yinfeng
Li, Guang
Ma, Kun
Chen, Long
Xia, Zhongpu
Zhang, Qichao
Ye, Hangjun
Zhao, Dongbin
contents Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous work has demonstrated that models can achieve better planning performance when provided with a prior distribution of possible trajectories. However, these approaches often overlook two critical aspects: 1) The appropriate trajectory prior can vary significantly across different driving scenarios. 2) Their trajectory evaluation mechanism lacks policy-driven refinement, remaining constrained by the limitations of one-stage supervised training. To address these issues, we explore improvements in two key areas. For problem 1, we employ MoE to apply different trajectory priors tailored to different scenarios. For problem 2, we utilize Reinforcement Learning to fine-tune the trajectory scoring mechanism. Additionally, we integrate models with different perception backbones to enhance perceptual features. Our integrated model achieved a score of 51.08 on the navsim ICCV benchmark, securing third place.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07135
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning
Xing, Zebin
Yang, Pengxuan
Wang, Linbo
Zhang, Yichen
Hu, Yiming
Zheng, Yupeng
Wang, Junli
Gao, Yinfeng
Li, Guang
Ma, Kun
Chen, Long
Xia, Zhongpu
Zhang, Qichao
Ye, Hangjun
Zhao, Dongbin
Computer Vision and Pattern Recognition
Artificial Intelligence
Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous work has demonstrated that models can achieve better planning performance when provided with a prior distribution of possible trajectories. However, these approaches often overlook two critical aspects: 1) The appropriate trajectory prior can vary significantly across different driving scenarios. 2) Their trajectory evaluation mechanism lacks policy-driven refinement, remaining constrained by the limitations of one-stage supervised training. To address these issues, we explore improvements in two key areas. For problem 1, we employ MoE to apply different trajectory priors tailored to different scenarios. For problem 2, we utilize Reinforcement Learning to fine-tune the trajectory scoring mechanism. Additionally, we integrate models with different perception backbones to enhance perceptual features. Our integrated model achieved a score of 51.08 on the navsim ICCV benchmark, securing third place.
title TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.07135