How To Train Your Self-Driving Car? Use Edge Cases | The Extra Mile, With dRISK скачать в хорошем качестве

How To Train Your Self-Driving Car? Use Edge Cases | The Extra Mile, With dRISK

dRISK is an autonomous vehicle training company that is creating a “map” of dangerous scenarios for driverless algorithms to learn from. The U.K. startup says it believes that the best way to train a self-driving algorithm is to expose it to edge cases - some of the weirdest and most bizarre encounters on our roads. CEO Chess Stetston told me he believes that training these algorithms on the hardest cases, meant that the simple easy driving scenarios were solved too. To find out more about the company, the technology and where selfdriving technology is headed, I sat down for a chat with Chess. This interview has been edited for length and clarity. 0:00 Introducing dRISK 2:40 How are driverless car companies training their algorithms? 4:41 dRISK’s dataset: A million hours of CCTV and thousands of accident reports 8:55 Do autonomous vehicles have to pass a driving test? 11:55 Will driverless vehicles always need to train on real roads? 14:20 When will self-driving cars become a reality? The Extra Mile is a series of extended interview discussions with the guests that feature in my videos. You can see the full feature here:    • How Do Driverless Cars Prove They Are Safe...   I'm George Downs, a WSJ video journalist fascinated by how technology is changing how we get from A to B. If you're interested in the future of mobility or how modern transportation can impact our lives– from EVs to eVTOLs, and beyond – then don't forget to subscribe. #dRisk #AI #GeorgeDowns