New Tesla UI Patent Suggests Cybertruck Can See Terrain, Include Facial Recognition, Adjust Mirrors To Face Movement, & Have Range Over 600 Miles (Possibly)

0
33

Tesla recently filed a patent for a context sensitive user interface for enhanced vehicle operation and Twitter user @AMuchBetterFace noted that one of the images filed in the patent showed a range of 610 miles. If the range on the Cybertruck is over 600, this is incredibly mind-blowing. This is well above the 500+ miles shown for the Cybertruck Tri Motor on the Tesla website at the moment. That aside, this patent is packed with juicy gold nuggets, so let’s dive into it.

610 miles of range for Tesla Cybertruck @elonmusk? pic.twitter.com/UxRyHAJBFQ

— AMuchVaccinatedFace (@AMuchBetterFace) May 27, 2021

The new patent relates to user interfaces and particularly to user interfaces for vehicle operation. One key aspect of the filing is that the UI tries to anticipate whether the driver or passenger is interacting with it. It swaps the buttons to the passenger side if they are trying to interact with it, and vice versa if the driver seems to be trying to do so — most likely using an internal camera to detect whether or not the driver or passenger is using it.

Air Conditioning & Heat Tracking

One cool feature is that the Cybertruck will automatically know where to blow cool or warm air when you’re in the vehicle. You won’t have to adjust the vents — they will adjust to you. The flowchart above shows that the Cybertruck will be able to identify the passenger in the vehicle as it blows either cool air or heat. It will also determine the location of a portion of the person’s body and adjust the output of the air or heat based on tracking of location.

Terrain, Towing, & Camper Mode

A couple of other things included in the patent filing include the UI interface of a driving view while the vehicle is towing a trailer, is in camper mode, or is towing a truck trailer.

The Cybertruck will also be able to display the terrain when driving off-road as illustrated by Figure 7B, which shows an example.

Mirrors & Eye Tracking

The flow chart above shows that Tesla has engineered a way for the mirrors to automatically adjust to the driver. First, it will identify the passenger in the vehicle and determine the location of a portion of their face. Then it will adjust the mirrors based on the tracking of that part of the passenger’s face.

Topographic Data

Tesla may be able to combine topographic data with vision from the cameras to create a visualization of the terrain on the Cybertruck’s screen. The patent gave an example of this:

“For example, the vehicle may be parked while off-roading. In this example, the autonomous visualization may include a graphical representation of a terrain surrounding the vehicle. For example, sensor information (e.g., images) may be obtained of the terrain. Map information may be used to inform the topographical information. For example, a topographical map may be accessed for location of the vehicle.

“The user interface 500 may thus include a representation of the terrain based on the topographical map. Optionally, sensor information and the topographical map may be combined. As an example, the topographical map is used to determine a shape associated with the location of the vehicle.”

It noted that sensor information can help form the shape or other fine-grained information. An example of this is the sensor information indicating a portion of the terrain more sharply sloped than indicated on the topographical map. This would help a driver who is driving off-road.

Automatically Detect Off-Roading

According to the filing, the Cybertruck may be able to automatically detect when the vehicle goes off-road. This is based on a variety of things such as angle changes, vibration, slipping of the tires. Sensor information may also be used to determine which type of surface the vehicle is driving on and if it’s rocky or sandy.

The system may also use the location of the vehicle to determine whether or not it is off-road. An example of this is a map indicating that the vehicle is outside of known roads or on roads associated with off-roading.

Wireless Communication Between Trailer & Truck

The filing noted that the Cybertruck may be able to detect a trailer behind the truck. This could mean that the vehicle will be able to communicate wirelessly between truck and trailer. The filing stated that information could be presented from the cameras or sensors in the truck, enabling it to detect a trailer is near.

The filing also stated that “The information may also be presented based on a truck trailer providing wireless communications to the vehicle.”

Facial Recognition

This part of the filing indicates the Cybertruck will be able to track passengers with facial recognition. As hinted above, one thing is that it will be able to track passengers to determine where their body is in order to blow cool or warm air.

The filing noted that in some aspects of the system, the vehicle may identify which vehicle passenger — the driver or side passenger — will provide user input to the display.

Once the Cybertruck determines who the person is, it will present a customized UI. An example is switching the icons from the left to the right side of the display. It may also use facial recognition techniques to learn vehicle passengers. This is for the personalization of their preferred settings and/or profile information. A great example of this is adjusting the mirrors, air conditioning, steering wheel, and so on.

Imagine going to your car and it recognizes you based on what its internal camera sees — it knows who you are and adjusts your settings without you having to press a button. This is pretty wild!

Deep Learning & Passenger Recognition

The Cybertruck will also be able to tell when the passenger has entered the vehicle by using infrared emitters or projectors. If those beams are interrupted, it may realize that someone is sitting in the seat. It can also use machine learning techniques to identify a person based on images by using convolutional neural networks.

The vehicle’s system will be able to store any information that it can use to identify a passenger’s face, and this includes using deep learning techniques. An example of this is looking at your face using one of the cameras outside of the vehicle and encoding your face in an example face space that the model previously learned. However, there will be only a limited number of images of your face used to uniquely identify you or your passenger.

Once you or the passenger adjusts the mirrors, seats, and other preferences, these can be stored in the system, which will associate you or the passenger with those preferences. It can store the preferences in a way that, when you enter the vehicle, it welcomes you like a long-lost friend.

Facial Recognition — Tesla Is Being Careful About Privacy & Security

Although to some, facial recognition may seem scary or like an invasion of privacy, Tesla is being very careful in regards to protecting privacy.

The filing noted that in every situation in which facial recognition is used, these are opt-in messages, meaning the driver can opt in or out of using this feature. Also, the information may be stored locally on the vehicles while also being encrypted.

Twitter user @AMuchBetterFace, who shared the patent with me, pointed out that Tesla is taking a page out of Apple’s book in regards to handling biometric data.

“This is taking a cue from how Apple handles biometric data like FaceID and TouchID,”  he said.

Appreciate CleanTechnica’s originality? Consider becoming a CleanTechnica Member, Supporter, Technician, or Ambassador — or a patron on Patreon.

 

 

Have a tip for CleanTechnica, want to advertise, or want to suggest a guest for our CleanTech Talk podcast? Contact us here.

LEAVE A REPLY

Please enter your comment!
Please enter your name here