Talking Autonomy: How Ghost is Designing Autonomy for Scale скачать в хорошем качестве

Talking Autonomy: How Ghost is Designing Autonomy for Scale

Ghost Autonomy co-founder and CTO Volkmar Uhlig gives a high-level overview of our strategy and highlights the distinct technology choices that make Ghost's approach unique: 1. Instead of relying on classic image recognition for obstacles, we use a new form of physics-based AI 2. Instead of using a complex sensor stack with dozens of LiDAR, radar, camera, and ultrasonic sensors, we rely on scalable HD cameras and radar, using advanced AI to analyze their raw outputs 3. Instead of localizing our vehicle to HD Maps, we drive first-person based upon the world we observe from our sensors, and re-compute our drive path 30 times per second 4. And instead of deploying a supercomputer-on-wheels or locking ourselves to specialty ASICs, we use low-power, low-cost SoC compute, capable of enabling the software-defined, ever-evolving car Thank you for watching Talking Autonomy, a series of short tech talks that explain the key elements of our work at Ghost. Subscribe and stay tuned for new episodes as we continue exploring the core technologies behind the Ghost Autonomy Engine and sharing insights from the founders, engineers, designers, mathematicians, and even the policy-makers who are responsible for bringing Ghost’s self-driving technology to the roads. Connect with Ghost and learn more: Ghost Autonomy Engine on the web: https://www.ghostautonomy.com/platform KineticFlow vision neural network: https://www.ghostautonomy.com/kinetic... Follow Ghost on Twitter:   / ghostautonomy   Follow Ghost on LinkedIn:   / ghostautonomy   #selfdriving #AI #autonomous #GhostAutonomy #computervision