Unreliable Pedestrian Detection & Driver Alerting in Advanced Driver Assist Systems
Vehicles with advanced driving assist systems that automatically steer, accelerate and brake are popular, but associated with increased driver distraction. This distraction coupled with unreliable autonomous system performance leads to vehicles that may be at higher risk for striking pedestrians. To this end, this study tested three consumer vehicles in each of two model classes in a pedestrian crossing scenario. In 120 trials, one model never detected the pedestrian, nor alerted the driver. In 123 trials, the other model vehicles almost always detected the pedestrian, but 35% of trials, alerted the driver too late. These cars were not consistent internally or with one another in pedestrian detection and response, and only sparingly sounded any warnings. These vehicles also detected the pedestrian earlier if there were no established lane lines, suggesting that in well-marked areas, typically the case in pedestrians may be at increased risk of a possible conflict. This research demonstrates that vehicle behaviors and warnings can significantly vary in pedestrian detection, potentially catching drivers off guard. These results indicate industry needs to do more testing, regulators should reevaluate the self-certification approval process, and that more fundamental work is needed in academia around the performance and quality of neural networks.
Read more at https://ieeexplore.ieee.org/document/10399802
Comments