By Hyunjoo Jin

San Francisco (Reuters) – Toyota Woven Planet (NYSE:) Motor has joined Tesla Inc (NASDAQ:) Inc as it tries to improve self-driving technology using inexpensive sensors like lidars.

Woven Planet informed Reuters that low-cost cameras are used to gather data and train the self-driving vehicle’s system effectively. This is a breakthrough it claims will lead to lower costs and greater scale.

It said that gathering diverse data from a large fleet of vehicles is crucial to develop a reliable self-driving vehicle system. However, this is expensive and difficult to scale up to allow for testing autonomous cars with high-end sensors.

Tesla is betting on camera data to track over 1,000,000 vehicles to help develop automated driving technology. Alphabet (NASDAQ) added lidars and expensive sensors to only a few vehicles.

We need lots of data. It’s insufficient to only have a few data points from a fleet of highly-priced autonomous vehicles.” Michael Benisch (Vice President of Engineering at Woven Planet), stated this in an interview for Reuters.

Benisch, an ex-engineering director at, stated that they are not trying to unlock Toyota’s advantages. Lyft Toyota’s autonomous division (NASDAQ:), which was acquired by Toyota last year.

Woven Planet’s cameras are 90% more affordable than previous sensors and can easily be fitted in passenger vehicle fleets.

The company claimed that using the majority of data from low cost cameras raised its system’s performance to levels comparable to those obtained when training was done exclusively with high-cost data.

Toyota would use several sensors like radars and lidars to deploy robotaxis on the roads. This is currently the most safest and best way to create robotaxis.

He said that it was possible for camera technology to catch up with more sophisticated sensors in the future, but this could take many, many decades.

“The real question might be about how and when it takes to achieve safety and reliability. It’s not something we can yet know.

Tesla CEO Elon Musk stated that it will achieve complete autonomy with cameras in this year’s Tesla after missing several targets.