Talking Autonomy: Optimizing for Low-Power Compute

In this episode, Ghost Autonomy co-founder and CTO Volkmar Uhlig discusses another key opinionated hardware choice: optimizing our software for scalable, low-power SoC compute.

While Ghost is primarily an AI software company, our reference hardware design enables us to deliver a safe and functional end-to-end system with the ideal balance of computing power, reliability, power consumption, and cost. Let's focus on the compute. In today's market, some vendors opt for specialty ASICs. The ASIC approach can yield attractive economics and power dynamics but sacrifices the flexibility and openness required in the software-defined car era. On the other end of the spectrum, some vendors are engaged in a race for TOPS as they build supercomputers-on-wheels, which results in inherent cost and energy consumption tradeoffs. In this video, Volkmar explains why Ghost has chosen a different path. By optimizing software for scalable SoC compute, Ghost is achieving high performance with low power consumption and low cost dynamics while preserving the ultimate flexibility in the continuous evolution of our software.

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