Cost is always a major factor to sell your dreams. Self-driving technology is no doubt a costly affair to maintain. The complete need for a variety of sensors like lidars and radar raises the price comparatively higher than the traditional market price.
However, the way Tesla is venturing into AVs with cameras, Toyota is also heading on the same path. As per Toyota Motor Corp unit Woven Planet, “it is able to use cameras to collect data and effectively train its self-driving system, a “breakthrough” that it hopes will help drive down costs and scale up the technology.” Stated Reuters.
The major struggle or the hurdles faced by the AV manufacturers is the accumulation of the driving data for a robust self-driving car system. The use of a variety of sensors is expensive and leads the cost of the vehicle to rise high. Without mastering another solution for a safe and efficient way of using the data can lead to autonomous vehicles become a costly sector.
The woven planet is using cameras that are 90% cheaper than the sensors. As per Michael Benisch, VP of Engineering at Woven Planet, former engineering director at Lyft’s self-driving division, “We need a lot of data. And it’s not sufficient to just have a small amount of data that can be collected from a small fleet of very expensive autonomous vehicles.”
He also mentioned in Reuters, “ Rather, we’re trying to demonstrate that we can unlock the advantage that Toyota and a large automaker would have, which is access to a huge corpus of data, but with a much lower fidelity.”
One of the advantages of a low-cost camera is the ability not to compromise the available data and the system’s performance. The same thing you achieve with expensive sensor data. Toyota is also expanding its capabilities in the robotaxi and autonomous ride-hailing fleet.