False positives (with a driverless auto identifying, for example, a road sign as an obstacle) are more easily avoided with radar when compared to camera systems, by measuring the density of objects as well as their distance from the vehicle.
Advertisement
Electric carmaker Tesla recently announced that it is upgrading the autopilot software to use more advanced radar technology.
Tesla has come under fire in recent months, following the death of a driver who crashed when Autopilot failed to detect a lorry.
Tesla CEO Elon Musk insists that the Autopilot update is not a case of issues being fixed but it’s instead the next natural step in Tesla’s continual improvement of its products.
The Tesla Software Update 8.0 is planned for release in the next few weeks, with Tesla promising over 200 enhancements, including improved auto lane change and Autosteer to avoid collision.
Speaking in an online press conference to launch the software update he said: “It’s not going from bad to good, it’s going from good to great”.
The administration has been investigating the matter to find out if the accident has taken place from any safety defect in the Autopilot.
With the latest update, the system would have identified a “large metal object across the road”, Musk said.
“When the data shows that false braking events would be rare, the vehicle will begin mild braking using radar, even if the camera doesn’t notice the object ahead”.
Overall, the new measures should result in the auto hitting the brakes appropriately “even if a UFO were to land on the freeway in zero visibility conditions”, Tesla said. Some said Apple would have been Tesla’s only true competitor in the field.
“It’s really about improving the probability of safety”.
“We are able to process that echo by using the unique signature of each radar pulse as well as the time of flight of the photon to determine that what we are seeing is in fact an echo in front of the auto that’s in front of you”.
Advertisement
Tesla has been facing mounting criticism for whether the feature lulls drivers into a false sense of security and whether the company rolled out the technology – which is still in the public beta-testing phase – too quickly.
