Several companies are in the process of building fully autonomous driving cars, and one of the key players in the competition is Owen Planet Holdings Inc., a subsidiary of Toyota Motor Corporation. The Tokyo-based technology company has recently revealed that it will use only camera methods to develop self-driving projects, such as electric and self-driving car giant Tesla Inc.
During an interview with a media outlet, Bona Planet stated that it would be able to use the camera to collect data and efficiently train its self-driving system. The tech firm believes that vision-oriented technology is a “breakthrough” and that it will help reduce costs and increase the level of technology.
The company added that using a large fleet of vehicles to collect various driving data is crucial for developing a reliable self-driving car system, but testing autonomous vehicles alone with expensive sensors is not costly and measurable. In addition, it was stated that despite the new vision-oriented approach, Bona Planet would still use the data collected from other sensors, such as radar and leader, for long-term deployment as well as training.
“We need a lot of data,” said Michael Benish, VP of Bona Planet’s engineering. And having a small amount of data that can be collected from a small fleet of very expensive autonomous vehicles is not enough, “he added.” Rather, we are trying to show that we can unlock the advantage that Toyota and a large automaker will have Amount of data access, but with much less fidelity. “
Tesla Inc., which is currently one of the foremost runners in electric mobility and self-driving technology, has been installing camera systems in its cars for a long time. American automakers are relying on cameras to collect data from more than 1 million vehicles on the road to create its automated driving technology.
During an earnings call last year, Musk said the only camera-approach for self-driving cars would help Tesla. He said, “When your vision works, it works better than the best ones because it has eight cameras, it has three eyes on the back of your head, one on the side of your head and three eyes at different focal lengths looking forward. That’s the decent thing to do, and it should end there. I have no question that with a clear vision solution, we can create a car that is dramatically safer than the average person, “he once said, adding that LiDAR was a” crunch “.
Bona Planet uses cameras that are 90% less expensive than the sensors used before and can be easily placed in a passenger car fleet. The Tokyo-based company claims that incorporating most of the data from low-cost cameras has improved the system’s performance to the same level as when it was fully trained on high-value sensor data.
However, Benish added that Toyota would continue to employ a number of sensors, such as leaders and radars, to deploy robotics and other autonomous vehicles on the road, as it seemed at the time the best and safest strategy.