Tesla will probably return radars to cars for Full Self-Driving starting next year

Partially autonomous driving from Tesla with the paradoxical name Autopilot and the more advanced Full Self-Driving is the source of many controversies. We’ve had some odd accidents here, such as the infamous crashes into white trucks or police cars. “Nonetheless”, Musk decided to throw out basically all conceivable sensors from his cars and autonomous driving will only use cameras. LiDAR a long time ago evaluated as meaningless, the radars then disappeared from the cars in May 2021 and the ultrasound this fall. But according to FCC filings, Tesla will be in its cars starting next month reinstall the radars. So has Elon Musk changed his mind about radars? Yes and no. The whole matter is quite complicated, so let’s look at it in more detail. When we look at the whole problem from several points of view, we find that it is not as clear-cut as it may seem at first glance. Here we find many reasons to think that Tesla may have made a good or a bad decision to cancel radar in the past.

Almost all manufacturers except Tesla are trying to add different types of sensors and use cameras, ultrasonic sensors, radars and lidar to provide as many inputs as possible for the autonomous driving system. Tesla, on the other hand, is the only one taking them away. So the question is, does she see something different in the Tesla issue that others overlook, or is she just foolishly trying to be different? When almost everyone does it, there’s usually a reason for it, but does that necessarily mean it’s good? A lot of breakthroughs in technology happened because someone tried to find a different way. How it is here, it’s hard to say yet. Intuitively, it seems that Tesla is the one choosing the wrong path here and going senselessly against the current. It is an indisputable fact that Tesla cars account for 70% of accidents with ADAS systems that are investigated by the NHTSA agency, but on the other hand, these data do not take into account the number of cars and the number of kilometers driven, so in the end we have no idea whether Teslas really crash into the car and mileage more often than other systems. Statistics will publish this very important detail in the future.

A great deal of debate broke out about removing radar from cars. We all know cases where Teslas have crashed into white semi-trailers or cars with beacons. And here we come to a paradoxical situation. Radars stopped being fitted to Tesla cars in May 2021, but most of these methods happened before that date, so they happened to cars equipped with radars (and the remaining ones just after that transition). It can be seen that the mere presence of a radar does not guarantee that a car will “see” a car with a beacon. On the contrary, it doesn’t seem that the number of these accidents has increased dramatically recently, when all new (and today, after the updates, probably also old) Teslas on the roads only drive with a camera system.

The first such isolated accident occurred in January 2018, but basically the vast majority happened between December 2019 and September 2021, a total of there are 16 of them and the last investigated accident is almost a year old, from January 2022. As we can see, after the launch of the radars and the transition to a purely camera system, these “lighthouse” accidents rather stopped, which contradicts what we would probably expect. So why such a turn and Tesla wants to install radars again? Many people, including Musk, argue that even humans use only their eyes and brain to drive, so the cameras and evaluation system should be able to handle it as well. Man has nothing like radar, and yet he drives. On the other hand, the latter could supply additional information to the system, and most likely also information that a person is not able to perceive by himself. But there is one “but”.

Tesla car accident


When Musk announced the removal of radar from cars, he made an argument that may not sound intuitive. According to him, the radar made the whole system more error prone. However, it is well known that the more measurements you have, even if they are imprecise, the more accurate the result you will usually get by averaging them. You know this system, for example, from cameras and telephones, where noise is reduced by multi-exposure. Multiple noisy photos are taken, they are overlapped, and the noise is largely eliminated. Something like that should intuitively work here as well. A few inaccurate (eg noisy) measurements from the cameras, a few inaccurate measurements from the radar, and in theory we should have a great idea of ​​what’s in front of the car.

And here Elon Musk suddenly told us that it’s worse? This doesn’t make much sense at first glance. However, from my own experience of working on 3D reconstruction from stereo cameras, I can say that pairing classic cameras with depth cameras, which should theoretically improve it, does not necessarily lead to a more accurate result. Exactly opposite. An additional sensor can work in such a way that it improves detection in some situations, but at the same time quite often “breaks” something that already worked without it. It often happens that the next type of sensors will bring correct data where the original solution did not work (where the sensor did not see it correctly), but on the contrary, it reports wrong data where the original system did not have a problem. And now it’s a question of whether the benefit is greater than the downside. And it looks like that was the reason Musk had the radars removed. While this certainly helped some situations, according to him, the implication was that it actually made many situations worse (it worsened the signal-to-noise ratio). After all, it also corresponds to my experience with adding sensors, which did not always lead to what we would intuitively expect.

While Musk has fully condemned lidar in the past, he has not been so critical of radar, saying even then that while existing radar makes the situation worse with its noise, cameras combined with high-resolution radar should be better than a purely camera solution. The problem was that, according to him, such a sufficiently high-quality radar did not exist, so he preferred a solution without radars, which was more reliable than with it. Now, however, it seems that Tesla finally has a radar with high resolution and low noise available, so we will probably see it already in cars assembled from January of this year. However, you should not use the new component in practice yet. This will come with the next software versions that will be ready for this sensor. In any case, it does not change the fact that autonomous driving depends primarily on the computing part, i.e. understanding what the sensor actually sees.


Source: Svět hardware by www.svethardware.cz.

*The article has been translated based on the content of Svět hardware by www.svethardware.cz. If there is any problem regarding the content, copyright, please leave a report below the article. We will try to process as quickly as possible to protect the rights of the author. Thank you very much!

*We just want readers to access information more quickly and easily with other multilingual content, instead of information only available in a certain language.

*We always respect the copyright of the content of the author and always include the original link of the source article.If the author disagrees, just leave the report below the article, the article will be edited or deleted at the request of the author. Thanks very much! Best regards!