A Persistent and Context-aware Behavior Tree Framework for Multi Sensor Localization in Autonomous Driving
This work addresses localization failures in autonomous driving, which is critical for safety, but it appears incremental as it builds on existing behavior tree and sensor fusion methods.
The paper tackles the problem of robust and persistent localization for autonomous vehicles in diverse urban environments by proposing a behavior tree framework that monitors localization health and triggers intelligent responses like sensor switching and loss recovery, with experimental validation on a dataset collected over 18 months.
Robust and persistent localisation is essential for ensuring the safe operation of autonomous vehicles. When operating in large and diverse urban driving environments, autonomous vehicles are frequently exposed to situations that violate the assumptions of algorithms, suffer from the failure of one or more sensors, or other events that lead to a loss of localisation. This paper proposes the use of a behavior tree framework that can monitor the performance of localisation health metrics and triggers intelligent responses such as sensor switching and loss recovery. The algorithm presented selects the best available sensor data at given time and location, and can perform a series of actions to react to adverse situations. The behavior tree encapsulates the system-level logic to give commands that make up the intelligent behaviors, so that the localisation "actuators" (data association, optimisation, filters, etc) can perform decoupled actions without needing context. Experimental results to validate the algorithms are presented using the University of Sydney Campus dataset which was taken weekly over an 18 month period. A video showing the online localisation process can be found here: https://youtu.be/353uKqXLV5g