Post by Michael DeKort

Self-driving tech supplier Mobileye targets U.S. robotaxi launch in 2027 Seen Waymo's scaling issues? Do not confuse some capabilites, hype and rigged data for good anough Mobileye will expose itself too Google me, the IEEE Barus Ethics Award and 60 Minutes-I work with SAE and I do my homework No one in the industry is using a viable development approach. Don’t confuse some capabilities and cherry-picked data for good enough. No one can spend the lives, money or time to get near L4. (Which is why we see performance issues and misleading data) Each needs to be resolved to reach L4: -No AGI/GL, inference etc. Results in an untenable pattern recognition effort. Also, "pixel" or micro level classification is often wrong when only a few pixels are in contention - Use and sacrifice of needless human Guinea pigs. How are crashes learned and tested? And it is virtually impossible to regain situational awareness in time critical disengagement scenarios like crashes. - Relying on the real-world vs simulation for most development - Use of inadequate gaming sim tech and sensor modelling - 360 deg fused sensor design needs to be=Cameras, LiDARs and imaging radars each classifying, localizing and tracking to proper operation through the ODD, especially as conditions degrade. Cristen (CJ) Haddad do the homework https://lnkd.in/g2-V-G_J #driverlesscars #driverlesscars #driverless #autonomousvehicles #selfdrivingcars #autonomous #autonomousdriving #selfdriving #adas #autonomousvehicle #driverlessvehicles #autonomouscar #nhtsa #ntsb #waymo #artificialintelligence #machinelearning #deeplearning #waymo #tesla #elonmusk