TECHNOLOGY'S AND ARTIFICIAL INTELLIGENCE

ARTIFICIAL INTELLIGENCE IN TESLA CARS 

The current AI technologies that Tesla is using in it's cars are based on unsupervised machine learning. Tesla's most recently AI tools haave not been made public yet. The new AI is supposed to upgrade the company cars to new levels of autonomy (level 5). Revealed in 2019 , this new AI hardware has already been performing better than competitors.  The company has collaborated with Nvidia to optimise their AI Integrated Chips.  However,  some of Nvidia best minds came together with Tesla to create AI chips smart enough to power cars with complete self driving capabilities.  With this new AI , Tesla is aiming at setting a benchmark for mass-market automation for cars.

 

• AI Integrated Chips : Tesla aims to create AI Integrated chips that will enable cars to navigate through freeways and even traffic. Approximately 6 billion transistors constitute the circuit of each Tesla chip. These Tesla chips are 21 times faster than the original Nvidia chips and 20%cheaper too. They have 32 megabytes of high speed SRAM memory on the chip because of which fetching data is faster and easier compared to DRAM. Tesla AI chips have been optimised to perform 36 trillion operations per second and runs ar 2GHs. For better performance,  Tesla automobile systemshave two AI chips . Both the chips make separate assessment of the traffic and denger situation around the cars. The assessments are then matched and the car is guided accordinglyif the outputsare the same. If there is ambiguity in the outputs obtained from the chips, then revaluation is done until a safe and suitable decision is taken. Thus, dual chip will enable better control over the navigation in self-driving Tesla cars. 

 Tesla Full Self Driving :