Toyota wants to develop self-driving cars with cameras instead of lidars

Toyota’s Woven Planet division is developing a system for self-driving cars without expensive sensors, such as lidar. Instead, the technology should use cameras, as Tesla does.

Woven Planet, a Toyota subsidiary that develops new technology, Reuters news agency That it can use relatively inexpensive cameras to collect data about things like traffic. This data can then be used to develop an autonomous driving system. The company says such data is important for developing such systems, but it is too expensive and scalable to collect data from a fleet of cars equipped with expensive lidar sensors.

The company claims that the new camera system is up to 90 percent cheaper than the sensors it has used before, saying it can be installed relatively easily in large numbers of passenger cars.

Tesla uses a similar method, in which the company collects data based on camera images from Tesla cars. The fully self-driving option from Tesla is currently available on a subscription basis, but it’s still in beta. CEO Elon Musk said Tesla could achieve fully autonomous driving with cameras this year. However, the company previously missed the deadlines that Musk had expected for this.

The Toyota division notes that for now it will continue to release self-driving cars equipped with lidar and other sensors, since this is the best and safest way, according to the company, to deploy automated taxis and other self-driving cars on the road. Woven Planet notes that autonomous camera-based systems could catch up in the long run, but says it doesn’t know how long that will take.