Tesla to make more use of radar for Autopilot
Tesla said at the weekend there are dozens of small refinements to version 8 of its software but the most significant upgrade to Autopilot will be the use of more advanced signal processing to create a picture of the world using the onboard radar. The radar was added to all Tesla vehicles in October 2014 as part of the Autopilot hardware but was only meant to be a supplementary sensor to the primary camera and image processing system.
"After careful consideration, we now believe it can be used as a primary control sensor without requiring the camera to confirm visual image recognition," Tesla said in a post on its website.
"This is a non-trivial and counter-intuitive problem, because of how strange the world looks in radar. Photons of that wavelength travel easily through fog, dust, rain and snow, but anything metallic looks like a mirror. The radar can see people, but they appear partially translucent. Something made of wood or painted plastic, though opaque to a person, is almost as transparent as glass to radar.
"On the other hand, any metal surface with a dish shape is not only reflective, but also amplifies the reflected signal to many times its actual size. A discarded soda can on the road, with its concave bottom facing towards you can appear to be a large and dangerous obstacle, but you would definitely not want to slam on the brakes to avoid it.
"Therefore, the big problem in using radar to stop the car is avoiding false alarms. Slamming on the brakes is critical if you are about to hit something large and solid, but not if you are merely about to run over a soda can. Having lots of unnecessary braking events would at best be very annoying and at worst cause injury."
Software 8.0 unlocks access to six times as many radar objects with the same hardware with a lot more information per object, the automaker said.
The software has to assemble those radar snapshots, which take place every tenth of a second, into a 3D 'picture' of the world. It is hard to tell from a single frame whether an object is moving or stationary or to distinguish spurious reflections. By comparing several contiguous frames against vehicle velocity and expected path, the car can tell if something is real and assess the probability of collision.
When the car is approaching an overhead highway road sign positioned on a rise in the road or a bridge where the road dips underneath, this often looks like a collision course. The navigation data and height accuracy of the GPS are not enough to know whether the car will pass under the object or not. By the time the car is close and the road pitch changes, it is too late to brake.
This is where fleet learning comes in handy. Initially, the vehicle fleet will take no action except to note the position of road signs, bridges and other stationary objects, mapping the world according to radar. The car computer will then silently compare when it would have braked to the driver action and upload that to the Tesla database. If several cars drive safely past a given radar object, whether Autopilot is turned on or off, then that object is added to the geocoded whitelist.
When the data shows that false braking events would be rare, the car will begin mild braking using radar, even if the camera doesn't notice the object ahead. As the system confidence level rises, the braking force will gradually increase to full strength when it is approximately 99.99% certain of a collision. This may not always prevent a collision entirely, but the impact speed will be dramatically reduced to the point where there are unlikely to be serious injuries to the vehicle occupants.
"The net effect of this, combined with the fact that radar sees through most visual obscuration, is that the car should almost always hit the brakes correctly even if a UFO were to land on the freeway in zero visibility conditions," Tesla claimed.
A Tesla will also be able to bounce the radar signal under a vehicle in front - using the radar pulse signature and photon time of flight to distinguish the signal - and still brake even when trailing a car that is opaque to both vision and radar. The car in front might hit the UFO in dense fog, but the Tesla will not.
Tesla founder Elon Musk told reporters on a conference call the improvements to Autopilot might have prevented an accident in May that took the life of an Ohio man when his Model S car driving in Autopilot crashed into a tractor-trailer.
The improvements include changes that require drivers to refrain from taking their hands off the steering wheel for long periods and that more precise use of radar to recognise potential obstacles in the road.
According to a New York Times report, Musk said he believed the upgrades would have prevented the accident.
"These things cannot be said with absolute certainty, but we believe it is very likely that, yes, it would have," he said. The new version of Autopilot, with its improved radar, "would see a large metal object across the road" and be able to determine that the object is not an overpass or overhead road sign that poses no threat, he said. "Impact probability would be assessed as high and it would probably brake."
Musk reportedly added Tesla had explained the coming improvements to the National Highway Traffic Safety Administration which is investigating the crash to determine if it resulted from any safety defect in Autopilot.
"They appear pretty happy with these changes," he said. "The reaction was quite positive, but I don't really want to speak for them."
Musk also suggested that the improvements could negate the possibility of the safety agency's calling for a recall, the NYT said. "The word 'recall' does not make sense because this will be an over-the-air update," Musk said, and owners will not be required to bring their cars to Tesla for the upgrade.
The upgraded version of Autopilot, known as Version 8, will give drivers more frequent warnings to put their hands on the steering wheel at moderate and higher speeds. If a driver is warned three times within an hour to put his hands on the wheel, the Autosteer feature will not resume unless the driver stops the car, shuts off the engine and then restarts it.
In stop-and-go traffic, at speeds under eight miles an hour, drivers can still keep their hands off the wheel almost indefinitely, Musk said. At speeds up to 45 miles an hour, they will be warned after a few minutes, and more frequently if the road turns or curves, or if there are other cars on the road ahead.
"I think it will be a dramatic improvement in the safety of vehicles," Musk told the NYT. He added, however, that technology advances are unlikely to eliminate road accidents completely.
"Perfect safety is really an impossible goal," he said. "There won't ever be zero fatalities. There won't ever be zero injuries."