New sensing system for Tesla autopilot

Electric automotive company Tesla has announced in a blog that it will be upgrading its autopilot system for autonomous cars. The main change will be using radar as the primary control sensor, though it will be developing more fleet learning capabilities to improve safety.

In the blog posted on its website on Sunday, Tesla said: “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.”

Fleet learning is where all the data collected from all the vehicles in the fleet of autonomous cars is used to build a picture of how best to deal with different sorts of road conditions and situations. In this way all cars will collectively learn how to drive better.

The changes come after a Tesla driver was killed in May when the car he was driving hit a truck. In this case it is believed that the autopilot camera was unable to spot the white truck trailer against the bright sky. Technical experts think that the radar will be a better sensor in respect of other vehicles, and can cut out the question of whether the camera can ‘see’ an obstacle before brakes and other safety measures are applied.

While self driving vehicles are the next great step in technology, it is still an awful lot to ask a computer when people don’t always drive perfectly as it is. Where the driver can be blamed for a silly accident, a computer has to be perfect or this will feed back to its developer…