fully autonomous electric car uses artificial intelligence to drive itself on the road
A self-driving electric car uses artificial intelligence imaging and scanning to drive around highways and cities. The Japanese electric car developer Turing has unveiled its driverless EV whose car concept lets AI makes driving decisions while it cruises on the road.
The camera on board, alongside sensors and dynamic maps, of the car design gathers the views it receives while driving. Based on the information detected, the car operates the steering wheel on its own and drives itself on public roads without the passengers’ help.
images courtesy of Turing
Turning to AI has always been the car's concept, and in 2022, the technology team was able to pool a driving data base amounting to 500 hours for its AI-driven system. For the car design, Turing works with the design group Nichinan to adopt Stable Diffusion, a deep learning and text-to-image modeling.
The team decides to combine static images with digital modeling, CG rendering, full-color 3D printing scale models, driving animations, and augmented reality data. The design outcome results in a bean-shaped model that slopes at the front to make a rounder look, swings its doors up, and splits its windscreen into three views.
‘Combining artificial intelligence and car design, this project, in which experts in human intelligence and digital work worked together, proves the amazing power and speed of AI design,’ says Yoshiichi Saruwatari, the Design and Engineering Division General Manager and Director of Nichinan. Turing plans to complete a small-scale production plant with a scale of 100 units and 10,000 acquired hours of driving data in 2023 and to achieve production of 10,000 fully autonomous EVs by 2030.
Turing plans to beat Tesla with its fully autonomous and self-driving electric car
While breakthroughs have shone upon Turing, the design team recognizes the amount of time they need to invest to reach the full potential of their project. They are informed that fully automated driving requires human recognition and judgment ability.
They believe that it is necessary to create a large-scale, deep-learning model for their electric car to realize fully automated driving. ‘We have already built a considerable amount of driving database, but we plan to grow it exponentially in the future. In the future, we will create a system that can acquire driving data from vehicles sold by Turing,’ says the design team.
the team combines static images with digital modeling, CG rendering, 3D printing scale models, and AR data
Turing aims to mass produce its fully autonomous driving electric car and even claims to realize its mission of overtaking Tesla. ‘If hardware and software get along well, we can make better cars from Japan. I will turn this wonderful misunderstanding into a reality with my friends,’ says Turing co-founder and CEO Kazunari Yamamoto. ‘I decided that my next challenge in life would be to create an automaker that surpasses Tesla.’
Turing Co-Founder and CTO Shunsuke Aoki echoes the statement of Yamamoto on bringing their fully autonomous electric car to life. ‘I have devoted much of my life to self-driving cars and academic research. When I returned to Japan, I thought about the question, ‘What kind of work can I be proud of for future generations?’ And I decided to create a mass production of fully automated driving EV with Mr. Yamamoto,’ he says.
the team also uses AI to tweak the car's design