RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Baihui, Feng, Chengjian, Huang, Zhijian, yan, Feng, Zhong, Yujie, Ma, Lin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913977807667200
author Xiao, Baihui
Feng, Chengjian
Huang, Zhijian
yan, Feng
Zhong, Yujie
Ma, Lin
author_facet Xiao, Baihui
Feng, Chengjian
Huang, Zhijian
yan, Feng
Zhong, Yujie
Ma, Lin
contents Collecting real-world data for rare high-risk scenarios, long-tailed driving events, and complex interactions remains challenging, leading to poor performance of existing autonomous driving systems in these critical situations. In this paper, we propose RoboTron-Sim that improves real-world driving in critical situations by utilizing simulated hard cases. First, we develop a simulated dataset called Hard-case Augmented Synthetic Scenarios (HASS), which covers 13 high-risk edge-case categories, as well as balanced environmental conditions such as day/night and sunny/rainy. Second, we introduce Scenario-aware Prompt Engineering (SPE) and an Image-to-Ego Encoder (I2E Encoder) to enable multimodal large language models to effectively learn real-world challenging driving skills from HASS, via adapting to environmental deviations and hardware differences between real-world and simulated scenarios. Extensive experiments on nuScenes show that RoboTron-Sim improves driving performance in challenging scenarios by around 50%, achieving state-of-the-art results in real-world open-loop planning. Qualitative results further demonstrate the effectiveness of RoboTron-Sim in better managing rare high-risk driving scenarios. Project page: https://stars79689.github.io/RoboTron-Sim/
format Preprint
id arxiv_https___arxiv_org_abs_2508_04642
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case
Xiao, Baihui
Feng, Chengjian
Huang, Zhijian
yan, Feng
Zhong, Yujie
Ma, Lin
Robotics
Computer Vision and Pattern Recognition
Collecting real-world data for rare high-risk scenarios, long-tailed driving events, and complex interactions remains challenging, leading to poor performance of existing autonomous driving systems in these critical situations. In this paper, we propose RoboTron-Sim that improves real-world driving in critical situations by utilizing simulated hard cases. First, we develop a simulated dataset called Hard-case Augmented Synthetic Scenarios (HASS), which covers 13 high-risk edge-case categories, as well as balanced environmental conditions such as day/night and sunny/rainy. Second, we introduce Scenario-aware Prompt Engineering (SPE) and an Image-to-Ego Encoder (I2E Encoder) to enable multimodal large language models to effectively learn real-world challenging driving skills from HASS, via adapting to environmental deviations and hardware differences between real-world and simulated scenarios. Extensive experiments on nuScenes show that RoboTron-Sim improves driving performance in challenging scenarios by around 50%, achieving state-of-the-art results in real-world open-loop planning. Qualitative results further demonstrate the effectiveness of RoboTron-Sim in better managing rare high-risk driving scenarios. Project page: https://stars79689.github.io/RoboTron-Sim/
title RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.04642