Benchmarking Visual Localization for Autonomous Navigation
This provides a tool for evaluating visual localization methods in realistic autonomous navigation scenarios, though it is incremental as it builds on existing simulation and localization techniques.
The authors introduced a simulator-based benchmark to study how variables like time of day and weather affect visual localization in autonomous navigation, finding major variation in method suitability.
This work introduces a simulator-based benchmark for visual localization in the autonomous navigation context. The dynamic benchmark enables investigation of how variables such as the time of day, weather, and camera perspective affect the navigation performance of autonomous agents that utilize visual localization for closed-loop control. The experimental part of the paper studies the effects of four such variables by evaluating state-of-the-art visual localization methods as part of the motion planning module of an autonomous navigation stack. The results show major variation in the suitability of the different methods for vision-based navigation. To the authors' best knowledge, the proposed benchmark is the first to study modern visual localization methods as part of a complete navigation stack. We make the benchmark available at https://github.com/lasuomela/carla_vloc_benchmark.