Tesla Motors had finally unveiled its Autopilot 2.0 features – the list is really astonishing and in some details looks more like fantastic. Actually there are more than 200 major and minor improvements – let us tell you about the most significant.

tesla_model_s_night-1

Unsurprisingly, the Autopilot upgrade aims at increasing safety. Tesla autonomous driving has already had a strong effect on the public roads safety – the very first fatal accident involving autopilot happened only after autonomous electric cars total mileage reached 120 million miles. This, actually, means that the autopilot drives about two times safer than the average driver – since there is one fatal crash per 60 million miles in the world according to the statistics. However, the Autopilot 2.0 is going to be available in one or two weeks, and the upgrade would be capable of eliminating a number of potential accidents.

img_2469

The biggest part of the upgrade is the radar’s new role. Tesla Model S and Model X with autopilot suite have that radar onboard since late 2014, but it previously served as the supporting unit, complementing the main camera and the image processing system. Now it became the main part of the whole system: the radar allows Tesla to “see” through the rain, snow, dust or fog up to absolutely zero visibility. Though there was an obstacle in the radar’s perception of different objects – for example, the human in its eye is partially translucent, while the wood and plastic are glass-like completely transparent. Moreover, dish-shaped objects reflect and amplify the radar signal: for example, the radar sees the soda can bottom many times bigger than it is, thus implementing the emergency braking – which may result serious accidents and injuries. Tesla Motors have made the enourmous amount of work to eliminate such false positives. After all, the radar make the snapshots of the area around the car each tenth of a second making a 3D map, comparing the objects position with the speed and predicted direction of a Tesla, thus always assessing the probability of an accident.

tesla-autopilot-performs-surpris

Additionally, each and every Tesla with autopilot will use the data gathered from the whole Tesla fleet to a higher extent. Now the autopilot would act more confident passing the potentially dangerous points based on multiple facts of safe driving from other cars. When the gathered data shows rare false braking events, the car would begin with mild braking, transitioning to the emergency braking when it’s about 100% certain about the collision.

“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 Motors.

maxresdefault

Furthermore, a Tesla would also be able to bounce the radar signal under the vehicle in front. This allows the autopilot to sense the dangerous event two cars forward – and still brake even when trailing a car that is opaque to both vision and radar.


Totally, there are more than 200 improvements the Autopilot would get in firmware 8.0. Here is the list of the most important notes from the Tesla blog post:

 

  • 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.