# RoboRacer Arena：用于自主赛车的规格驱动赛道构建

> 原文链接：https://robotics.hellobike.com/papers/2026-08-24-2608-23040
> 频道：papers | 更新日期：2026-08-24 | 标签：arxiv, cs.RO
> 核心摘要：RoboRacer Arena以自然语言规格驱动生成、验证赛道并构建Isaac Sim环境，在地图生成、资产转换和物理竞速中验证。

# RoboRacer Arena：用于自主赛车的规格驱动赛道构建

::: v-pre
> 原文链接：[RoboRacer Arena: Specification-Driven Track Construction for Autonomous Racing](https://arxiv.org/abs/2608.23040)（arXiv 2608.23040 · 发布日期：2026-08-24）

**RoboRacer Arena: Specification-Driven Track Construction for Autonomous Racing**

RoboRacer Arena以自然语言规格驱动生成、验证赛道并构建Isaac Sim环境，在地图生成、资产转换和物理竞速中验证。

## 核心要点

- 学习式自主赛车需要多样训练环境，但新赛道构建将几何设计、验证与仿真资产生成耦合在一起。
- 该流程从自然语言需求出发，以种子覆盖引导构造闭环布局，验证占据地图并自动生成Isaac Sim环境。
- 同一接口支持记录地图和缩放赛道，形成包含130条赛道的初始参考集合。
- 评估中其有效地图生成率在受测流程预算内最高，8个基准地图每个少于2.5秒转为仿真资产。

**验证范围与局限**：验证覆盖仿真资产生成和RoboRacer物理平台实验，物理实验为最高四倍名义训练速度下连续十圈。

## 英文摘要 (Abstract)

Learning-based autonomous racing relies on diverse training environments, yet constructing a new track requires geometric design, validation, and simulation-asset generation. This coupling makes track geometry difficult to vary systematically during policy training and evaluation. To address this limitation, we present RoboRacer Arena, a specification-driven pipeline that exposes track geometry as an explicit experimental variable. Starting from natural-language requirements, a seeded coverage-guided constructor generates closed-loop layouts, validates the exported occupancy maps, and automatically builds the corresponding Isaac Sim environments. The same interface admits recorded maps and scaled circuits, yielding an initial reference collection of 130 tracks. Across our evaluation, RoboRacer Arena achieves the highest valid-map generation rate among the tested construction procedures under their respective computational budgets and converts eight benchmark maps into simulation assets in less than 2.5 seconds each. We further reconstruct the RoboRacer vehicle as a CAD and USD asset and use it for parallel residual-policy training and deployment on the physical platform. In physical experiments, policies trained with RoboRacer Arena complete ten consecutive laps at command settings up to four times the nominal training speed. These results demonstrate that explicit track requirements can be connected to validated simulation assets and physical evaluation within a reproducible autonomous-racing workflow.

作者：Mihaela-Larisa Clement, Agnes Poks, Ezio Bartocci
:::

## 原始参考来源 (Sources)

- [arXiv 2608.23040：RoboRacer Arena: Specification-Driven Track Construction for Autonomous Racing](https://arxiv.org/abs/2608.23040)