Tesla has announced a raft of updates in Autopilot 8.0, the latest version of its autonomous driving system. And the big change is a switch from reliance on cameras to radar.

The update can be applied to all Tesla Model S and Model X cars built since October 2014, which are fitted with radar sensors at the front. While radar can ‘see’ further in bad weather than cameras, it had previously only been a backup system due to the problem of avoiding ‘false positives’.

While radar is highly effective at detecting an object in the distance, determining the exact nature of that object can be problematic. Metallic surfaces become mirrors, people become partially translucent, and wooden and painted plastic surfaces become virtually see-through. Adding a curve can make an object appear smaller or larger than it actually is, too.

The net result could be lots of unnecessary braking events in response to objects that pose no danger to the car. But Tesla has solved the problem in the update by increasing the size of the radar ‘cloud’, thereby gathering more information about an object. Comparing that information with the car’s movement allows the system to determine how likely an impact is.

‘Fleet learning’ has been added to the system, as well, to build up a database of every signpost, overhead gantry and bridge on the road network. In that way, Autopilot will know if the bridge that appears to be directly in the car’s path is actually over a depression in the road, or a signpost is just beyond a crest.

The radar sensor is also able to ‘bounce’ its beam under a car directly in front in order to see what’s going on in front of it, reducing response time to any emergency situations that develop.

Object detection is now so effective, Tesla claims, that “the car should almost always hit the brakes correctly even if a UFO were to land on the freeway in zero visibility conditions.”Leaving the driver free to marvel that, you know, a UFO has just landed on the road.

Other updates include more prominent warnings, including a flashing white border around the instrument panel, whether or not Autopilot is engaged; the ability to take a highway exit when the indicators are used or the navigation activated; greater lane offset when overtaking, and more than 200 other items that improve Autopilot’s user-friendliness and safety margin.

At a press conference, Tesla CEO Elon Musk was asked if Autopilot 8.0 would have prevented the recent fatal in crash in Florida involved a Model S running with Autopilot engaged. "We believe it would have," Musk replied. But he added: "I do want to emphasize that this does not mean perfect safety. Perfect safety is really an impossible goal. It is about improving the probability of safety. That's really all you can accomplish."

Autopilot 8.0 will be rolled out within the next couple of weeks.

Source: InsideEV

Got a tip for us? Email: tips@motor1.com
Hide press releaseShow press release

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 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.

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