Apple files patent for Hand Gestures that could go beyond AssistiveTouch so as to control other devices like an HMD, Macs & more
Today the U.S. Patent Office published a patent application of Apple's that relates to electrodes that can be used to determine two forms of physiological signals. It would appear that this patent is describing a system that is a deeper form of AssistiveTouch where gestures could be used with an HMD, Macs, Apple TV and more.
Many types of input can be provided for performing operations in a computing system, such as buttons or keys, mice, trackballs, joysticks, touch sensor panels, touch screens and the like. In addition, other types of input such as audio input (e.g., voice commands), accelerometer input (e.g., device motion, shaking, etc.) and user gestures can also be provided as inputs.
In particular, a person's physical motions, such as eye gaze, body movement and the like can be detected and tracked over time as inputs to a computing system.
Hand gestures, in particular, can be detected by touch or proximity sensors in a touch sensing panel. However, these sensors generally have limited detection range, and therefore the hand gestures must be performed in close proximity to the panel.
Some computing systems can include circuitry to detect cardiac characteristics of a user of the computing systems. Attempting to integrate circuitry to sense hand gestures in addition to detecting cardiac characteristics often requires computing systems that are complex to manufacture and unwieldy.
Examples of in Apple's patent are directed to electrodes that can be formed in a backside of a device that can be configured to detect posing and movement of a hand of a user of the device and can be configured to detect a heartbeat of the user. This could be performed on Apple Watch and possibly future fitness trackers.
In some examples, the device can configure sensing circuitry to measure the electrodes to detect electromyography (EMG) signals, which is the electrical activity that results from the contraction of muscles. In some examples, the device configures the electrodes to detect EMG signals that are produced by activity of the flexor and extensor muscles and tendons in the forearm, wrist, and/or hand of a user. The EMG signals can be routed to processing circuitry in the housing of the wrist-worn device.
These EMG signals can be processed to identify hand movements such as hand flexion, extension, pronation, supination, radial deviation, ulnar deviation, finger pinching, and finger movement, and recognize gestures and/or poses associated with those hand movements. In some examples, the device can be configured to detect electrocardiogram (ECG) signals, which is the electrical activity that results from palpitations of a heart of the user.
In some examples, the device configures sensing circuitry to measure the electrodes to detect ECG signals produced by activity of the heart of the user. The ECG signals can be routed to processing circuitry housed in the device to determine a heart rate (HR) of the user.
In some examples, the device further includes pose detection circuitry such as one or more inertial measurement units (IMUs). The IMUs can be configured to supplement pose and/or movement detection determined using EMG signals. In some examples, the device can detect a quality of a measurement associated with the EMG signals, such as a conductance between electrodes detecting the EMG signals, and/or an amount of noise coupling to the EMG signals. In some examples, when the quality of the measurement is suboptimal, the device can detect pose and/or gestures using signals detected by the pose detection circuitry and forgo consideration of the EMG signals in detecting the pose and/or gestures.
Apple notes that hand gestures via Apple Watch could be used in a computer system to moving an object such as a cursor or pointer, scrolling or panning, adjusting control settings, opening a file or document, viewing a menu, making a selection, executing instructions, operating a peripheral device connected to the host device, answering a telephone call, placing a telephone call, terminating a telephone call, changing the volume or audio settings, storing information related to telephone communications such as addresses, frequently dialed numbers, received calls, missed calls, logging onto a computer or a computer network, permitting authorized individuals access to restricted areas of the computer or computer network, loading a user profile associated with a user's preferred arrangement of the computer desktop, permitting access to web content, launching a particular program, encrypting or decoding a message, and/or the like.
It is understood that the output from the digital signal processor DSP can be used to perform one or more operations at an electronic device and/or at additional or alternative devices in communication with an electronic device such as other wearable (e.g., head-mounted) devices, laptop computers, desktops, media set-top boxes, and the like.
Apple has been working on this project for years. Back in 2023, Patently Apple posted a report titled "Apple patent reveals smart-bands with embedded micro-machined ultrasonic transducers to detect touch, biometrics, hand-gestures+." One set of images from that patent is presented below.
A Few of Apple's Inventors for Today's Patent
- Chia-Yeh Lee: Hardware Engineer
- Seulki Lee: Health Sensing EE – Wearable Healthcare Electronics
- Dave Fernandes: Applied ML Researcher