dRISK, a London and Pasadena-based firm that has been operating in stealth mode until now, revealed today its commercial launch and the use of its edge case retraining tool to achieve a 6x performance increase in time to detect high-risk occurrences for autonomous vehicles (AVs).
Whereas semi-autonomous and autonomous vehicles do not always detect high-risk events in time to react (oncoming cars peeking into lanes from behind other vehicles, vehicles running red lights concealed by other vehicles), dRISK's tools for retraining AVs to recognize edge cases represent a significant step forward in the ability to retrain autonomous vehicles to outperform humans in even the most difficult driving scenarios. On April 12, 2021, the results were formally announced at NVIDIA's GTC conference. Visit our official website for more information.
To write a review, you must login first.