RoboRacer Arena: Specification-Driven Track Construction for Autonomous Racing
RoboRacer Arena: Specification-Driven Track Construction for Autonomous Racing
RoboRacer Arena is a specification-driven pipeline that enables systematic variation of track geometry during policy training and evaluation. Starting from natural-language requirements, the system generates closed-loop layouts, validates occupancy maps, and automatically builds Isaac Sim environments. It achieves high valid-map generation rates and enables physical testing of trained policies, demonstrating the connection between explicit track requirements and validated simulation assets.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S4
- Control
- Reported autonomousOpen source S5
Reported numbers
time per map conversion
<2.5 seconds
View original evidence
converts eight benchmark maps into simulation assets in less than 2.5 seconds each
Open source S4laps completed
10
View original evidence
policies trained with RoboRacer Arena complete ten consecutive laps
Open source S5command settings speed
≤4
number of tracks
130
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ation, 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 experi
Open source S4
ments, 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.
Open source S5
e 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 evalu
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org