UltraSense Systems Brings Neural Processing to Smart Surfaces with New Generation of Multimode Sensing Solutions

TouchPoint Edge is a fully integrated system-on-a-chip (SoC) that mimics tactile input from mechanical buttons by directly sensing up to eight stand-alone force-sensing and ultrasonic-sensing UltraSense UltraSense transducers TouchPoint P. TouchPoint Edge also uses a Neural Touch Built-in, always-on Engine (NTE) to discern intentional keystrokes from possible unintentional false keystrokes, eliminating corner cases and providing the typing precision of a mechanical button.

Smart surfaces will further change the way we interact with products in the years to come. The definition of smart surfaces is a solid surface with lower lighting to show the user where to touch. The UI / UX paradigm shift started with the smartphone over a decade ago with the removal of the mechanical keyboard to simply press the keyboard on a capacitive screen. However, not all smart surfaces will be a capacitive screen. The UltraSense system’s first-generation sensor, TouchPoint Z, continues the paradigm shift by cost-effectively removing mechanical buttons and improving the user experience (UX) in smartphones, electric toothbrushes, home appliances and automotive interior ceiling lights.

TouchPoint Edge takes the experience to the next level in applications that use many mechanical buttons. For example, the automotive cockpit has many use cases, including the removal of mechanical steering wheel buttons, center console and overhead controls for HVAC and lighting, door panels for seats and controls. window and even integrated into soft surfaces like leather or even foam seats to create new user interfaces where mechanical buttons could not be implemented before. Other applications include device touch panels, smart locks, security access control panels, elevator button panels, and a host of other applications.

“In just three years from the first funding, we have been able to develop, qualify and deliver to OEM and ODM a fully integrated virtual button solution for smart surfaces,” said Mo Maghsoudnia, CEO of UltraSense Systems. “We are the only multi-mode sensor solution for smart surfaces designed from the ground up to integrate neural touch processing into everything from battery-powered devices to consumer / industrial IoT products and now to large-scale automotive. “

Human-machine interfaces are very subjective and extremely complex under a solid surface to replicate a mechanical button press. It is more than an applied force greater than a threshold to trigger pressure on a surface. When a user applies force to a mechanical button, the user applies a time varying force curve where the mechanical button reacts with a lot of non-linearity due to friction, hysteresis, air gaps and spring properties to name a few. As a result, a simple piezoresistive or MEMS strain sensor with certain algorithms and one or two trigger threshold levels cannot efficiently and accurately recreate the user experience of a mechanical button and eliminate false triggers.

TouchPoint Edge, with multimode sensing and built-in Neural Touch Engine, processes on-chip machine learning and neural network algorithms, so user intent can be learned. As with TouchPoint Z, TouchPoint Edge captures the unique pattern of the user’s press in relation to the surface material. The dataset is then used to train the neural network to learn and discern the user’s pressure pattern, unlike traditional algorithms which accept a single force threshold. Once TouchPoint Edge is trained and optimized for a user’s pressure pattern, the most natural button press response can be recognized. Additionally, the unique sensor array design of the TouchPoint P transducer allows for the capture of unique multichannel data sets in a small, localized area, as a mechanical button would be located, dramatically improving the performance of the neural network to be replicated. at the touch of a button. The Neural Touch Engine enhances the user experience and is further enhanced by being closely associated with TouchPoint P’s proprietary sensor design to deliver optimum performance. Finally, the integration of the Neural Touch Engine with TouchPoint Edge is a game-changer in terms of system efficiency, where neural processing can be performed 27 times faster with 80% less energy compared to unloading the same setup. system on an external ultra-low power microcontroller.

“The challenges of replacing traditional mechanical buttons with sensor-based solutions require technologies such as solid surface illumination, ultrasonic or capacitive sensing, and force sensing,” said Nina Turner, research director of IDC. “But these sensors alone can lead to false positives. The integration of machine learning built into these touch sensors brings a new level of intelligence to the touch sensor market and would be beneficial in a wide range of devices and markets. . ”

Main features of TouchPoint Edge

  • Neural Touch Engine for Machine Learning and Convolutional Neural Network Processing
  • The open interface allows non-proprietary and even non-touch sensor inputs (e.g. inertial, piezo, position, force, etc.) to be processed by the Neural Touch Engine
  • Direct drive and sensing of eight stand-alone, multimode TouchPoint P transducers
  • Integrated MCU and ALU for algorithm processing and sensor post-processing
  • Integrated analog front-end (AFE)
  • Configurable power management and frame rate
  • I2Serial C and UART interfaces
  • Two GPIOs for direct connection to haptics, LEDs, PMICs, etc.
  • -40C to + 105C operating range
  • WLCSP enclosure size 3.5mm x 3.5mm x 0.49mm

Main features of TouchPoint P

  • Autonomous multimode piezo transducer for ultrasound + strain detection
  • -40C to + 105C operating range
  • 2.6mm x 1.4mm x 0.49mm QFN Case

TouchPoint Edge evaluation kits using TouchPoint P transducers will be sampled to select customers next month with production samples available in Q1 2022.

About UltraSense Systems

Founded in 2018 and based in San jose, california, UltraSense Systems is changing the UI / UX paradigm in smartphones, consumer / industrial IoT, home devices and automotive by creating multi-mode tactile sensing solutions to enable smart surfaces with precise, highly localized, and wireless interfaces. button. Its TouchPoint product line enables customers to deliver transparent touchscreen HMIs on hard and soft surfaces, including metals, glass, plastics, wood and leather. The company has moved to $ 24 million to date with investors such as Robert Bosch Ventures, Artiman Ventures, Abies Ventures, Sony Innovation Fund and Asahi Kasei Corporation.

Nicole conley
[email protected]

SOURCE UltraSense Systems

Comments are closed.