Machine learning improves ultrasound buttons

Machine learning improves ultrasound buttons
New Products |
UltraSense Systems Inc. (San Jose, Calif.) has announced a follow up generation of its multi-mode touch sensing technology called TouchPoint Edge.
By Peter Clarke

Share:

UltraSense has developed an ultrasound actuator/sensor that can be attached to the inside surface of an enclosure to create a touch user interface. The MEMS-based technology operates at megahertz frequencies. It sends and receives pressure wave signals through 5mm of aluminium or glass and so can detect strength of tap and avoids the need for cut outs or openings in the enclosure.

UltraSense has added an embedded, always-on Neural Touch Engine (NTE) to differentiate intended touches from possible unintended false touches. This now provides TouchPoint with the input accuracy of a mechanical button, the company claims.

TouchPoint Edge is a fully integrated system-on-a-chip (SoC) which replicates the touch input of mechanical buttons by directly sensing up to eight standalone UltraSense ultrasound plus force sensing TouchPoint P transducers.

TouchPoint Edge has the ability to remove mechanical buttons from the steering wheel, center and overhead console controls for HVAC and lighting, door panels for seating and window controls and even embedded into soft surfaces like leather or even in foam seating. Other applications include appliance touch panels, smart locks, security access control panels and elevator button panels.

TouchPoint Edge learns a user’s press with respect to the surface material. The data set is then used to train the neural network to learn and discern the user’s press pattern.

TouchPoint Edge features:

Neural Touch Engine for processing Machine Learning and Convolutional Neural Net

Open interface allows for non-proprietary and even non-touch sensors inputs (e.g., inertial, piezo, position, force, etc.) to be processed by the Neural Touch Engine

Direct drive and sense of eight multi-mode TouchPoint P standalone transducers

Embedded MCU and ALU for algorithm processing and sensor post processing

Integrated analog front end (AFE)

Configurable power management and frame rate

I2C and UART serial interfaces

Two GPIO for direct connect to haptic, LED, PMIC, etc.

-40C to +105C operating range

3.5mm x 3.5mm x 0.49mm WLCSP package size

TouchPoint P sensor features:

Multi-mode standalone piezo transducer for ultrasound + strain sensing

-40C to +105C operating range

2.6mm x 1.4mm x 0.49mm QFN package

TouchPoint Edge evaluation kits using TouchPoint P transducers samples will be generally available in 1Q22.

Related links and articles:

www.ultrasensesys.com

News articles:

Analog, MEMS and Sensor startups to follow in 2021

Former InvenSense executives launch MEMS ultrasound interface startup

Ultrasound sensor good for 3D echolocation

Startup Chirp Microsystems to become part of TDK’s InvenSense


Linked Articles
eeNews Analog
10s