Why Tesla thinks vision is enough for autonomous driving

While most self-driving car companies have been using a combination of computer vision and lidar sensors, Tesla has been a vocal champion for the pure vision-based approach to autonomous driving.

And in this year’s Conference on Computer Vision and Pattern Recognition (CVPR), its chief AI scientist Andrej Karpathy explained why.

Speaking at CVPR 2021 Workshop on Autonomous Driving, Karpathy, who has been leading Tesla’s self-driving efforts in the past years, detailed how the company is developing deep learning systems that only need video input to make sense of the car’s surroundings. He also explained why Tesla is in the best position to make vision-based self-driving cars a reality.

Karpathy spoke about Tesla’s data gathering and labeling strategy, its deep learning architecture, and its vertical integration.

Read the full article on TechTalks.

For more on self-driving cars:

• Why deep learning won’t give us level 5 self-driving cars

• From general AI to self-driving cars, why we need to invent the impossible

• The consolidation of the self-driving car market

• If a driverless car were to take a life, whose should it be?