Latest / The Edge Computing Podcast with Fexingo: Local Compute, CDNs, and Distributed Infrastructure
Edge Computing Cuts the Latency Self-Driving Cars Can't Afford
Episode 135 of The Edge Computing Podcast explains why autonomous vehicles are the ultimate edge devices. Lucas and Luna break down the compute requirements inside a Level 4 self-driving car: processing a terabyte of sensor data per hour with latencies under 10 milliseconds. They explore how specialized edge chips like NVIDIA's Xavier and Qualcomm's Snapdragon Ride handle real-time perception, planning, and control, and why offloading to the cloud is impossible at 70 miles per hour. The episode also covers 5G V2X edge for cooperative perception and the redundancy needed for safety-critical…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.