Car manufacturers are currently racing to be the first to implement Level 4 autonomous vehicles.
Standing in Argo AI’s way are two major technical challenges:
Bryan Salesky, CEO of Argo AI, is focusing on the first problem.
“Salesky, along with many others in the field, say perception is the stickier problem, because it’s important for the autonomous vehicle to not only detect relevant objects, but to predict what those objects like a car, pedestrian, or bicyclist are going to do. Once it has the correct and robust information, making a decision is relatively easy.”
To overcome this challenge, Argo AI is training deep neural nets to solve the specific problems that autonomous vehicles are likely to encounter, then tying them into a larger network. This strategy avoids the extensive research and computing power necessary for a deep learning approach, currently being pursued by Drive.ai and Nvidia.
Read the full article here.