May 26, 2024


Cream of Techno

UltraSense uses machine learning to make better touch controls in cars

4 min read
UltraSense uses machine learning to make better touch controls in cars

Check out all the on-demand sessions from the Intelligent Security Summit here.

UltraSense Systems announced it has created new touch-control sensors for cars that are more accurate because they use machine learning.

The new In-Plane sensing automotive technology has the ability to enable multi-mode sensing and human-machine interface (HMI) control in the plane of the SmartSurface (or A-Surface). This drastically reduces the size and weight of the sensors, reducing the number of parts and complexity. It also enables modern designs and configurations.

And it helps deal with one of the worst things about touch controls: accidental activations. No one wants to tap a screen and miss the button they’re trying to hit, or make a phone call from their pocket.

This translates to advantages in sustainability and recyclability. It increases driving range and enables modern designs and new user experiences that were not possible before such as supporting controls for retractable steering wheels that require elegant slim form factors, the company said.


Intelligent Security Summit On-Demand

Learn the critical role of AI & ML in cybersecurity and industry specific case studies. Watch on-demand sessions today.

Watch Here

San Jose, California-based UltraSense said In-Plane sensing is a major step towards the ability to deliver a full HMI experience by enabling the thinnest possible space. This is more than a capacitive ITO (indium tin oxide) layer, but as defined by offering sensor fusion and enabling multimode sensing, processing and algorithms, feedback control: illumination, audio, haptics, and secure connectivity.

UltraSense said this is a recipe for transformational changes in reducing the size of existing automotive module depth.  Combined with the TouchPoint family of HMI controllers, InPlane sensing enables designs that support all types of Smart Surface HMI interactions through the broadest set of materials, beyond capacitive plastic and glass, the company said. Smart Surfaces can now operate through natural materials such as wood and leather to metal and other soft surfaces. 

UltraSense Systems uses machine learning to do more accurate touch sensing.

“Traditional interface modules were measured in inches of thickness, with In-plane sensing we are talking
about millimeters of surface thickness, with full solid-state HMI controller capabilities, of multi-modal sensing and feedback control of lighting, audio and haptics,” said Mo Maghsoudnia, CEO of UltraSense, in a statement. “InPlane sensing principles combined with our TouchPoint family of HMI controllers deliver the thinnest HMI operating through the broadest range of materials. This technology is applicable for HMI experiences for automotive interior and exteriors, industrial, and consumer applications.” 

TouchPoint HMI controllers offer multi-mode sensing (CapForce, UltraForce, TapForce), processing and AI machine learning algorithms, feedback control to drive Illumination, audio and haptics, and secure connectivity options.

UltraSense is a global company headquartered in Silicon Valley with offices in Taiwan, China, Korea, Japan, and Europe. The company investors include Robert Bosch Ventures, Artiman Ventures, Abies Ventures, Sony Innovation, Sparx Group and Asahi Kasei.

UltraSense said its HMI controller delivers higher accuracy than one sense (ie Capacitive alone), helping to eliminate “accidental activations.” The sensor can also sense through the broadest range of materials, whereas capacitive can sense through plastic and glass. Automakers are looking to differentiate and see if sensors can work with luxury materials like metal, and natural materials such as wood or leather.

I asked how the tech works. A large number of the founding leadership team came from MEMS gyro/accelerometer leader InvenSense, which was acquired by TDK. Their MEMS technology powers the majority of cellphones today.

UltraSense responded that dual-mode sensing using Cap and Force can improve accuracy at a touchpoint significantly (usability scoring increases from 88% to 94%.) With machine learning and local processing, the company can improve accuracy further, (usability scoring increasing beyond 96% approaching 99%). This further removes “accidental activations”.

As an example, steering wheel buttons for a driver who holds the wheel at 10 o’clock and 2, or 9 o’clock and 3, cover most conditions. But one automaker encountered the “trucker’s pose.” While on long drives, such drivers hold the wheel at the spokes and the palms accidentally activate the buttons with their palms. Ultrasense ML technology can identify and remove that scenario of accidental activations.

The sensors also have integrated processing to deliver “zero latency” required for good sensing-feedback interactions (think of a foreign film where the mouth and the voice tracks are mismatched). This is like the effect that is happening with haptic response in the car, where the MCU is a centralized MCU that is multi-tasking that introduces random latency, resulting in double-presses or impressions that something isn’t working. An integrated local processor eliminates this situation.

It also has feedback control of illumination, audio, and haptic feedback, which provides the best control with zero latency, the company said.

The company has under 100 employees, and it was founded in 2018. UltraSense has been integrated into consumer devices such as the LG Velvet and Rollable phones and with CASE (Connected, Autonomous, Shared Vehicle, Electrified) automotive initiatives.

VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.

Copyright © All rights reserved. | Newsphere by AF themes.