The rise of self-driving software development within the last couple of years has forced automakers to narrow down the key elements of this new technology.
One autonomous aspect most competitors have leached on to is LIDAR, which is a laser sensor that is considered an essential component for driverless vehicles. LIDAR stands for light detection and ranging, and it has been embedded into self-driving cars operated by companies like General Motors and Alphabet’s Waymo.
Despite the reliance on LIDAR amongst most automakers engaging in self-driving technology, Tesla‘s CEO, Elon Musk, still doesn’t believe it’s necessary.
His views on this matter have been highly debated amongst experts within the field, and even Tesla employees disagree that vehicles can be fully autonomous without LIDAR sensors.
“We have to solve passive optical image recognition extremely well in order to be able to drive in any environment and in any conditions,” Musk said. “At the point where you’ve solved it really well, what is the point in having active optical, which means LiDAR. In my view, it’s a crutch that will drive companies to a local maximum that they will find very hard to get out of.”
Musk stands by Tesla’s strategy of achieving “full autonomy” by only using cameras, radar and ultrasonic sensors. The strongest argument in favor of Musk’s belief is that the best current drivers – humans – lack LIDAR sensors and depend primarily on standard passive optical sensing when driving.
For now, Tesla is focusing on what it believes is a much bigger issue: passive optical recognition.
The electric automotive company is banking on cameras as the key hardware component for its long-term autonomous vehicle development project. Camera sensors are seen as the key for its driverless technology due to their high-pixel resolution and how cost efficient they are.
However, Tesla recently faced a high-profile split from its main camera supplier, Mobileye, in 2016 after a fatal accident that involved a Tesla driver who was using the car’s autopilot system.
Tesla introduced its second-generation autopilot system in October 2016, when the company replaced the computer vision technology that was powered by Mobileye’s technology with its own vision system called “Tesla Vision.”
Many experts believe that the new autopilot version is still missing a lot of the functionality from the original version powered by Mobileye.
Despite expert doubts, Musk is still confident that Tesla can become fully autonomous due to the company’s “sophistical neutral net,” which he says will ultimately be able to “see through” adverse weather conditions, such as rain, fog, dust and snow.
“Perhaps I’m wrong, in which case I’ll look like a fool,” Musk said. “But I’m quite certain that I’m not.”