In May 2021, Tesla announced that it would be replacing the ultrasonic sensors in its Model 3 and Model Y vehicles with Tesla Vision cameras. The cameras, which are already used for Autopilot and Full Self-Driving features, will now also be used to detect and interpret the environment around the vehicles.
According to Tesla, the camera-based system is more reliable and efficient than the ultrasonic sensors, which were originally used to detect nearby objects and obstacles. Tesla also claims that the new camera-based system will be able to detect objects in more challenging situations, such as when there is rain, fog, or snow.
The move to camera-based sensors is part of Tesla’s larger effort to develop fully autonomous driving technology. The company believes that cameras, combined with artificial intelligence and machine learning algorithms, will be the key to achieving this goal. However, it is important to note that the new camera-based system is still undergoing testing and is not yet fully operational in all Tesla vehicles.
Tesla made the news earlier this year after it announced that it was scrapping its future radar tech, relying only on a camera-based system called Tesla Vision.
More recently, Tesla announced that all Model 3 and Model Y models built for North America, Europe, the Middle East, and Taiwan will no longer be built with ultrasonic sensors. These models used to be equipped with camera systems, radar, and 12 ultrasonic sensors but will now rely solely on the camera system.
The transition to cars without radar and ultrasonic sensors will not have an impact on existing safety ratings, and the existing fleet will still benefit from over-the-air (OTA) updates as they already have a camera system in place.
On the downside, some of the features will be temporarily limited or inactive. These systems include Park Assist, Autopark, Summon, and Smart Summon. Once these features can perform the same way they did with radar and the ultrasonic sensors, they will be made available again via OTA updates.
All other available Autopilot, Enhanced Autopilot, and Full Self-Driving capability features will be active at delivery.
“Given the incremental improvements already achieved with Tesla Vision, and our roadmap of future Autopilot improvements and abilities, we are confident that this is the best strategy for the future of Autopilot and the safety of our customers,” Tesla said in a statement.
Along with removing the ultrasonic sensors, Tesla has launched its vision-based occupancy network, as used in the infamous Full Self-Driving Beta (FSDB). It replaces the inputs the car would have received from the sensors.
“With today’s software, this approach gives Autopilot high-definition spatial positioning, longer range visibility, and the ability to identify and differentiate between objects. As with many Tesla features, our occupancy network will continue to improve rapidly over time,” said Tesla.
It will be interesting to see how the move over to the camera-based system works out, as Tesla has been in the news several times due to Autopilot and FSDB.
Autopilot is under federal investigation, and FSDB has been a mixed bag. One week the system is hampered by larger stop signs, and the following week it saves a distracted driver from getting mowed down.
Toyota and Tesla both agree that a camera-based system is a reliable and efficient method for detecting and interpreting a vehicle’s environment. However, most other automobile manufacturers still rely on radar and LiDAR technology.
Mercedes-Benz has been particularly vocal about its autonomous driving efforts and has already achieved Level 3 autonomy, which is higher than any Tesla vehicle currently available for purchase. Mercedes-Benz believes that multiple systems are necessary in autonomous driving technology, even if only to act as fail-safes.
In other words, if the camera system were to fail for any reason, Mercedes-Benz believes that radar, LiDAR, and sensors should be in place to act as a backup, ensuring that the vehicle can still operate safely. While the camera-based system may be reliable, it is important to have additional redundancies in place to ensure the safety of passengers and other drivers on the road.
Mercedes-Benz’s approach to autonomous driving is indicative of the industry-wide effort to create a comprehensive and reliable autonomous driving system. While there are different approaches being taken, the ultimate goal is to create a system that is safe, efficient, and reliable, one that will ultimately transform the way we travel on our roads and highways.