[Street] Tesla’s self-driving device reportedly has trouble seeing motorcycles, and here’s why

In the United States, in July 2022, two deaths of motorcyclists in road accidents involved Teslas. These vehicles are believed to have collided with the motorcycles while having the autonomous driving device activated. In both cases, the Teslas – which were different models – rammed the motorcycles from behind. Both crashes happened at night and both involved cruiser-type motorcycles with low, close-set taillights.

Why are these motorcycle details important? In this video, FortNine’s Ryan lays out a very logical theory as to why the automatic self-driving device may not have seen the motorcycles in these two life cases. To be clear, this is just a theory and the National Highway Traffic Safety Administration (NHTSA) and other relevant authorities are still investigating both crashes.

That said, this theory seems pretty solid. Tesla vehicles rely on a combination of multiple cameras and radars for the self-driving device to calculate the safe distance to vehicles and other objects around a given Tesla. However, Tesla phased out its use of speed cameras in its model lineup over time, using only its Tesla Vision camera system. The most recent such change occurred in February 2022, when Tesla removed the radars from its Model S and Model X, according to InsideEV.

Several motorcycle OEMs have developed radar adaptive cruise control over the past few years, with these devices now being offered by manufacturers on their most high-end models. While the systems may work slightly differently, the idea is the same: all rely on radar to help motorcycles maintain a safe distance from surrounding vehicles. On motorcycles, this is not yet fully autonomous driving, but this system performs some of the same functions, and relies on the proven accuracy of radar.

But then why not use this combination of radars and cameras on the Tesla? As Ryan points out, while Tesla (and most companies) don’t directly state that the company primarily wants to make money selling its products, and therefore save as many parts as possible on a vehicle, the businesses are, after all, businesses. Therefore, the idea that they want to make a profit should not be new and should probably be considered an implicit factor in all their decision-making.

The location of these taillights on the two motorcycles involved — a Yamaha V-Star and a Harley-Davidson Sportster — is important if both cars were relying on Tesla Vision to tell them where the next vehicle was on the highway. Tesla Vision relies on a system of multiple cameras and Artificial Intelligence, which interprets the visual data collected by the cameras.

At night, it is difficult to distinguish the silhouettes of vehicles, but the taillights are there to help make our job easier. If the AI ​​was perceiving those close taillights as being distant car headlights instead of a much closer motorbike, this is the likely source of the problem. If a radar had been present, in addition to these cameras, the problem could perhaps have been avoided, but we cannot know for sure.

What we do know is that two bikers died and NHTSA data released in June 2022 revealed that “Tesla vehicle data analysis proves that the advanced driver assistance system, Autopilot, was turned off approximately one second before impact,” according to the Washington Post. This observation comes from the analysis of 273 previous accidents involving Tesla’s self-driving device.

Pending the development of a technical solution by Tesla, the best solution – provisional – to avoid this kind of problem while being a motorcyclist, and driving on a highway at night with a car approaching behind is to move from side to side. the other of its way. Indeed, this movement will alert the AI ​​to the presence of a vehicle much closer than expected.

Leave a Comment