Acoustic Simultaneous Localization and Mapping for Autonomous Driving

The current technology employed for autonomous driving has provided us with satisfactory performance and results. However, some of the most commonly used sensors, such as LiDAR and cameras, are typically high-priced and often require tremendous amount of computational power to process the collected data. In many cases, the adverse weather and night-time conditions hinder the performance of vision-based sensors. In this paper, we propose an alternative approach for enhancing the current sensing methodologies by utilizing acoustic signatures of moving objects. This approach makes use of a microphone array to collect and process acoustic signatures captured for simultaneous localization and mapping (SLAM). Rather than using numerous sensors to gather information of the surrounding environment of the ego vehicle, this method investigates the benefits of considering the sound waves of different objects around the ego vehicle and offers a cost-effective approach for SLAM.