Tesla releases the details of its new radar processing technology: point cloud, 2-car ahead tracking & more

Fred Lambert | Sep 11 2016 - 3:02 pm PT

Tesla and Elon Musk released the much-anticipated blog post about Autopilot improvements under its upcoming v8.0 software update. They confirmed a few features we revealed over the last few months like disabling Autosteer after ignoring alerts and the capacity to take highway exit, but we also now have a lot more details about improvements to the radar processing technology of the Autopilot.

Musk said that Tesla took advantage of upgraded drivers from Bosch, its radar supplier, and managed to reinvent the processing of the input to make the radar a primary sensor within the Autopilot hardware suite.

The radar is currently only supplementary to the front-facing camera and image processing, but it will now become the primary sensor in a separate channel from image processing with the upcoming v8.0. Musk expects the wide release within the next 1 to 2 weeks.

We will update with comments made by Musk during a press conference this afternoon:

But in the meantime, here’s the blog post:

Upgrading Autopilot: Seeing the World in Radar

While there are dozens of small refinements with Version 8 of our software, described in addendum below, 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 suite, 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. This is a non-trivial and counter-intuitive problem, because of how strange the world looks in radar. Photons of that wavelength travel easy 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.

The first part of solving that problem is having a more detailed point cloud. Software 8.0 unlocks access to six times as many radar objects with the same hardware with a lot more information per object.

The second part consists of assembling 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.

The third part is a lot more difficult. 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.

Taking this one step further, 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.

Additional Autopilot Release Notes

TACC braking max ramp rate increased and latency reduced by a factor of five

Now controls for two cars ahead using radar echo, improving cut-out response and reaction time to otherwise-invisible heavy braking events

Will take highway exit if indicator on (8.0) or if nav system active (8.1). Available in the United States initially

Car offsets in lane when overtaking a slower vehicle driving close to its lane edge

Interface alerts are much more prominent, including flashing white border on instrument panel

Improved cut-in detection using blinker on vehicle ahead

Reduced likelihood of overtaking in right lane in Europe

Improved auto lane change availability

Car will not allow reengagement of Autosteer until parked if user ignores repeated warnings

Automatic braking will now amplify user braking in emergencies

In manual mode, alerts driver if about to leave the road and no torque on steering wheel has been detected since Autosteer was deactivated

With further data gathering, car will activate Autosteer to avoid collision when probability ~100%

Curve speed adaptation now uses fleet-learned roadway curvature

Approximately 200 small enhancements that aren’t worth a bullet point