Verti-Arena: A Controllable and Standardized Indoor Testbed for Multi-Terrain Off-Road Autonomy
Haiyue Chen, Aniket Datar, Tong Xu, Francesco Cancelliere, Harsh Rangwala, Madhan Balaji Rao, Daeun Song, David Eichinger, Xuesu Xiao
TL;DR
Verti-Arena tackles the lack of controllable, standardized real-world testbeds for off-road autonomy by delivering a configurable indoor platform with diverse terrains and vertical variation. It provides a detailed geometry and semantics design, an obstacle layout, and a mechanism to shuffle terrain layouts, plus an eight-camera motion-capture system for ground-truth data collection and a ROS 2-based data pipeline. The work also offers a web-based interface for remote standardized experiments and reports that kinodynamics are terrain-dependent, emphasizing the need for terrain-aware models in perception, planning, and learning. Overall, Verti-Arena enables safe, repeatable, and scalable benchmarking for perception, control, and learning in off-road autonomy.
Abstract
Off-road navigation is an important capability for mobile robots deployed in environments that are inaccessible or dangerous to humans, such as disaster response or planetary exploration. Progress is limited due to the lack of a controllable and standardized real-world testbed for systematic data collection and validation. To fill this gap, we introduce Verti-Arena, a reconfigurable indoor facility designed specifically for off-road autonomy. By providing a repeatable benchmark environment, Verti-Arena supports reproducible experiments across a variety of vertically challenging terrains and provides precise ground truth measurements through onboard sensors and a motion capture system. Verti-Arena also supports consistent data collection and comparative evaluation of algorithms in off-road autonomy research. We also develop a web-based interface that enables research groups worldwide to remotely conduct standardized off-road autonomy experiments on Verti-Arena.