Aurrigo has introduced new software designed to enhance the performance of its airside autonomous vehicles in extreme wet weather conditions.
The company, which specialises in smart airside solutions, has developed a rainfall algorithm that allows its Auto-DollyTug® to distinguish between raindrops and physical objects while operating in precipitation levels of up to 50mm per hour.
Alongside software advancements, Aurrigo has also improved the protective housing for its LiDAR sensors, ensuring the vehicles can function effectively in conditions that would typically halt manual operations.
The technology has undergone rigorous testing in both controlled simulated rainfall and real-world heavy rain conditions, with performance validated through observational assessments and rain meter readings.
Simon Brewerton, Chief Technical Officer at Aurrigo International plc said:Traditionally, very heavy rain has presented a significant problem for autonomous vehicles, particularly for LiDAR detection and navigation. AVs using this technology rely on the reflection feedback of laser beams for localisation and object recognition and, in intense weather, the scattering and absorption of laser beams by raindrops can lead to distorted signals, compromising the vehicle’s ability to accurately perceive its surroundings.
The first stage of the solution was to design the latest Auto-DollyTug® with better casing protection for the LiDARs, which we duly did. However, the big ‘Eureka’ moment for us and the sector is the algorithm we have trained to strike a balance between the removal of raindrops and retaining the ability to detect real obstacles. This means that airlines and airport operators have complete confidence that, even in extreme rain conditions, our autonomous dollies will operate efficiently.
The new software incorporates two key features. First, it applies rain filtering across five spatial zones around the vehicle, adjusting the intensity of filtering based on proximity. Second, it compensates for variations in scan properties between filtered and unfiltered data, ensuring low-lying obstacles and reflective surfaces are accurately detected.
This upgrade required adjustments to field height settings and the inclusion of near-field low-profile detection in the algorithm.
Heavy rain often disrupts manual ground operations at airports, particularly in regions like Singapore, where frequent CAT5 lightning risks require personnel to halt work for safety reasons. Autonomous vehicles, unaffected by these risks, could support a fully automated aircraft turnaround process, covering baggage and cargo handling, catering, water services, and refuelling.
