Abstract: There are provided methods and devices for enabling touchscreen device interactions using a virtual joystick. In response to detecting a touch input detected at or near a display of the touchscreen device, touch contact information including a centroid and a contact shape of the touch input may be generated. A speed and a direction associated with an interactive element on the display may be determined, by a model, based on the touch contact information. The interactive element may be controlled on the display, based on the speed and the direction. The disclosed methods and devices may enable improved user interaction with touchscreen devices having limited interaction space, for example, by more accurately distinguishing small-scale micromovements as touch inputs.

Abstract: Systems and methods are disclosed for providing a virtual mouse for a computing device have a touchscreen. A first placement region of the touchscreen may be determined. The first placement region may then be determined to contain a first portion of at least one touch target. The first portion of the at least one touch target may then be deactivated. A virtual mouse may then be activated at the first placement region.

Abstract: Systems and methods are disclosed for providing a virtual mouse for a computing device have a touchscreen. A first placement region of the touchscreen may be determined. The first placement region may then be determined to contain a first portion of at least one touch target. The first portion of the at least one touch target may then be deactivated. A virtual mouse may then be activated at the first placement region.

Abstract: Systems and methods are disclosed for providing a virtual mouse for a computing device have a touchscreen. A first placement region of the touchscreen may be determined. The first placement region may then be determined to contain a first portion of at least one touch target. The first portion of the at least one touch target may then be deactivated. A virtual mouse may then be activated at the first placement region.

Abstract: In various examples, the present disclosure describes methods and systems for generating hand state predictions. A hand state prediction system includes a machine learning-based model, such as a neural network model, that is trained to convert inertial motion measurements and surface contact data into predictions of a corresponding hand gesture or gripping posture. For each window of data sampled, motion data and contact data are obtained, processed and fused to generate a fused prediction. The hand state prediction system can operate in continuous mode to automatically detect a start and an end of a hand action, or a user can designate a start and an end of a hand action. A hand state prediction is generated by a multimodal classifier by processing the fused prediction. Instructions represented by a hand action can be acted upon through a command action performed by a computing device or a computer application.

Abstract: In various examples, the present disclosure describes methods and systems for generating hand state predictions. A hand state prediction system includes a machine learning-based model, such as a neural network model, that is trained to convert inertial motion measurements and surface contact data into predictions of a corresponding hand gesture or gripping posture. For each window of data sampled, motion data and contact data are obtained, processed and fused to generate a fused prediction. The hand state prediction system can operate in continuous mode to automatically detect a start and an end of a hand action, or a user can designate a start and an end of a hand action. A hand state prediction is generated by a multimodal classifier by processing the fused prediction. Instructions represented by a hand action can be acted upon through a command action performed by a computing device or a computer application.

Abstract: A method, a feedback-enabled device and a computer-readable memory are provided, for generating haptic feedback. The actuators of a tactile surface are vibrated for producing vibration bursts based on a sequence of an adaptive friction grain signal. The adaptive friction grain signal comprises a plurality of grains corresponding to the vibration bursts, each grain being defined by an amplitude. The adaptive friction grain signal has a grain density that is variable over the sequence.

Abstract: A method, a feedback-enabled device and a computer-readable memory are provided, for generating haptic feedback. The actuators of a tactile surface are vibrated for producing vibration bursts based on a sequence of an adaptive friction grain signal. The adaptive friction grain signal comprises a plurality of grains corresponding to the vibration bursts, each grain being defined by an amplitude. The adaptive friction grain signal has a grain density that is variable over the sequence.