Tesla CEO, Elon Musk has revealed the car company is working on an aggressive autonomous driving mode dubbed ‘Mad Max’. The revelation came to light after a Tesla fan made a mockup of a Tesla truck on the set of a Mad Max film which he tweeted at Musk.
Tesla Semi Truck in Mad Max Mode https://t.co/hL5v9rikhW— Elon Musk (@elonmusk) June 24, 2018
Musk then shared an image of the center display of a Tesla vehicle with Autopilot on ‘development mode’, which allows Tesla to test out new features. The display shows three options for ‘blind spot threshold’ as standard, aggressive or ‘Mad Max’.
It’s real pic.twitter.com/L9h3F86Guo— Elon Musk (@elonmusk) June 25, 2018
LA Freeway mode too much even for Tesla
The CEO then went on to joke that Tesla considered having an ‘LA Freeway’ mode, but that would be too ‘loco’. Changing lanes can be a difficult task for autonomous cars, as they often have systems that require them to keep a certain distance from other cars, making a risky maneuver like changing lanes impossible.
We considered going beyond Mad Max to “LA Freeway” level, but that’s too loco— Elon Musk (@elonmusk) June 25, 2018
To combat these developers are building autonomous driving software that is more like the way humans drive - aggressively. Tesla is no different and seems to be taking the challenge to the extreme.
It’s a tough call. Reality is that it will be pretty easy to bully a self-driving car, as it will always yield. Will prob have a manual override that requires continuous press for hardcore lane changes.— Elon Musk (@elonmusk) June 25, 2018
The Mad Max feature is not yet available to current Tesla owners. Changing lanes is possible in a Tesla in Autopilot mode, however, the action needs to be initiated by the driver who takes responsibility for checking the lanes around them first.
Musk has promised full autonomous driving mode will be ready for Teslas by the end of next year, but said the Tesla 9 software update due in August will already have some ‘full self-driving features’.
MIT is also developing autonomous driving technology based on the way human drivers aggressively overtake or change lanes when needed.
MIT looks to lighten data load
The CSAIL lab is looking at ways autonomous cars can be more efficient when given fewer data. Currently, most current lane-change algorithms are based on detailed statistical models that force the car to act very conservatively - in many cases avoiding changing lanes all together.
The new MIT algorithm actually gives the cars less information allowing them to make decisions faster and allows them to act more aggressively. Lead author of the recently published paper on the MIT algorithm, Alyssa Pierson asks, “What can we do with as little information as possible?'" going on to question, "how can we have an autonomous vehicle behave as a human driver might behave?"
The new algorithm works by adjusting allowable buffer zones around the car. Giving the car less data allows the car to adjust this zone on the fly, and gives permission to the car to drive in different styles such as aggressive or conservative.
“The optimization solution will ensure navigation with lane changes that can model an entire range of driving styles, from conservative to aggressive, with safety guarantees,” says Daniela Rus, director of CSAIL.
So it seems that freeway driving might just be as crazy in an autonomous car as it is now, but hopefully, it will be a hell of a lot safer.
Via: Elon Musk/Twitter