Benchmark GSL Algorithms with ease in complex environments
Gas Source Localization (GSL) is a challenging field of research within the robotics community, with high-stakes search-and-rescue applications. Existing methods vary widely and each has its own strengths and weaknesses. Comparisons of different methods are limited due to the lack of a broadly adopted and standardized testing methodology. Existing GSL evaluations vary in environment size, wind conditions, and gas simulation fidelity. They also lack photo-realistic rendering for the integration of obstacle avoidance. In this paper, we propose GSL-Bench, a benchmarking suite that can evaluate the performance of existing GSL algorithms. GSL-Bench features high-fidelity graphics and gas simulation, featuring NVIDIA's Isaac Sim and OpenFOAM computational fluid dynamics software (CFD). Realism is further increased by simulating relevant gas and wind sensors. Scene generation is simplified with the introduction of AutoGDM+, capable of procedural environment generation, CFD and particle-based gas dispersion simulation. To illustrate GSL-Bench's capabilities, three algorithms are compared in six warehouse settings of increasing complexity: E. Coli, dung beetle and a random walker. Our results demonstrate GSL-Bench's ability to provide valuable insights into algorithm performance.
The inclusion of pre-generated environments and implementation of GSL algorithms with Python aid accessibility of GSL-Bench.
With GSL-Bench, the user is only required to supply their GSL algorithm. The included waypoint logic and obstacle avoidance ensure every algorithm to work even in combination with complex environments. However, please note that users can make their own real-time 'on-board' obstacle avoidance with the help of the sensors available in Isaac Sim.
Photorealistic visuals, Turbulent CFD and Filament-Based Gas Dispersion
Visual realism ensures compatibility with visual obstacle avoidance methods
Gas Dispersion is modelled according to the validated filament-based dispersion model by Farrel et al. with GADEN
GSL-Bench comes with three indoor environment types of varying complexity
Indoor environment without obstacles
Features storage racks
Features storage racks, forklifts and piles
GSL-Bench automatically outputs various results
Coming soon...