@article{Kuang2026, 
author = {Senyun Kuang and Yushu Gao and Shijie Cong and Yang Liu and Yintao Wei},
title = {TrafficPerceiver: A multimodal large language model with reinforcement learning for unified challenging traffic scene perception},
year = {2026},
journal = {Communications in Transportation Research},
volume = {6},
number = {1},
pages = {9640008},
keywords = {reinforcement learning (RL), traffic scene perception, multimodal large language model (MLLM), instruction-guided perception},
url = {https://www.sciopen.com/article/10.26599/COMMTR.2026.9640008},
doi = {10.26599/COMMTR.2026.9640008},
abstract = {Understanding traffic scenes under diverse and challenging conditions is critical for intelligent transportation systems (ITSs). Existing methods primarily focus on ideal scenarios and often lack the ability to perform fine-grained perception or respond to human instructions. To address these limitations, we propose TrafficPerceiver, a unified multimodal framework based on a multimodal large language model (MLLM) that jointly supports both image understanding and target-oriented segmentation. To enhance the model’s performance under adverse conditions such as rain, fog, and motion blur, we introduce a reinforcement learning (RL) optimization strategy based on group-relative policy optimization (GRPO), which encourages interpretable, instruction-following behavior. Additionally, we construct the challenging traffic scene understanding (CTSU) dataset, a large-scale dataset tailored to challenging traffic environments, with dense annotations for both segmentation and instruction-response tasks. Extensive experiments on both the DRAMA-ROLISP and CTSU datasets demonstrate that TrafficPerceiver achieves state-of-the-art performance in both understanding and segmentation tasks.}
}