# US 12,112,001 B1 · Preventing false activations based on don/doff detection for assistant systems > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,112,001 B1 - Document ID: US12112001B1 - Status: Granted - Kind: B1 - Application number: 18/183,816 - Filed: 2023-03-14 - Published: 2024-09-19 - Granted: 2024-10-08 - Earliest claimed: 2023-03-14 - Assignees: Meta Platforms, Inc. - Applicants: Meta Platforms, Inc. - Inventors: Rongzhou Shen; Amy Lawson Bearman; Shijun Sun; Qian Fang; Riza Kazemi - Web page: https://patentgrep.com/patent/US12112001B1 ## CPC - G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)} - G06F 3/04186: {Touch location disambiguation} - G06F 1/163: {Wearable computers, e.g. on a belt} - G06F 1/1694: {the I/O peripheral being a single or a set of motion sensors for pointer control or gesture input obtained by sensing movements of the portable computer} - G06F 1/3231: Monitoring the presence, absence or movement of users - G06F 1/3287: by switching off individual functional units in the computer system - G06F 3/012: {Head tracking input arrangements} - G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)} - G06F 3/017: {Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883)} - G06F 3/044: by capacitive means - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract In one embodiment, a method includes receiving touch inputs from a user corresponding to an activation trigger for an assistant system executing on a head-mounted device at the head-mounted device, accessing signals from inertial measurement unit (IMU) sensors of the head-mounted device by the head-mounted device, determining that the user is either donning or doffing the head-mounted device by an on-device don/doff detection model and based only on the signals from the IMU sensors, and overriding the activation trigger to prevent an activation of the assistant system responsive to the received touch inputs. ## Claims ### Claim 1 A method comprising, by a head-mounted device: receiving, at the head-mounted device, one or more touch inputs from a user corresponding to an activation trigger for an assistant system executing on the head-mounted device; accessing, by the head-mounted device, one or more signals from one or more inertial measurement unit (IMU) sensors of the head-mounted device; determining, by an on-device don/doff detection model and based only on the one or more signals from the one or more IMU sensors, that the user is either donning or doffing the head-mounted device; and overriding the activation trigger to prevent an activation of the assistant system responsive to the received one or more touch inputs. ### Claim 2 (depends on 1) The method of claim 1, further comprising: receiving, at the head-mounted device, one or more additional touch inputs from the user corresponding to the activation trigger for the assistant system executing on the head-mounted device; accessing, by the head-mounted device, one or more additional signals from the one or more IMU sensors of the head-mounted device; determining, by the on-device don/doff detection model and based only on the one or more additional signals from the one or more IMU sensors, that the user is neither donning nor doffing the head-mounted device; and activating the assistant system responsive to the received one or more additional touch inputs. ### Claim 3 (depends on 2) The method of claim 2, w further comprising determining that the head-mounted device is on the user's head. ### Claim 4 (depends on 3) The method of claim 3, further comprising determining, based on a detection of an eye gaze of the user that the user is engaged with one or more displays of the head-mounted device. ### Claim 5 (depends on 1) The method of claim 1, wherein the one or more touch inputs comprise one or more of tapping the head-mounted device, holding the head-mounted device, or swiping the head-mounted device. ### Claim 6 (depends on 1) The method of claim 1, wherein the one or more touch inputs are received at a capacitive touch area of the head-mounted device. ### Claim 7 (depends on 1) The method of claim 1, wherein the one or more touch inputs last longer than a threshold time. ### Claim 8 (depends on 1) The method of claim 1, wherein the don/doff detection model executes in the one or more IMU sensors. ### Claim 9 (depends on 1) The method of claim 1, wherein the don/doff detection model is based on one or more finite state machines. ### Claim 10 (depends on 9) The method of claim 9, further comprising: detecting, by the one or more finite state machines, one or more don/doff events; and setting, by the one or more finite state machines based on the one or more don/doff events, a state variable in a state module within a microcontroller unit of the head-mounted device. ### Claim 11 (depends on 10) The method of claim 10, wherein the state variable comprises one or more of don, doff, or normal. ### Claim 12 (depends on 10) The method of claim 10, wherein determining the user is either donning or doffing the head-mounted device is further based on the state variable, and wherein the state variable comprises one or more don or doff. ### Claim 13 (depends on 1) The method of claim 1, wherein the head-mounted device is associated with a controller. ### Claim 14 (depends on 1) The method of claim 1, wherein the one or more signals from the one or more IMU sensors are sampled at a frequency not greater than 26 Hz. ### Claim 15 (depends on 1) The method of claim 1, wherein the on-device don/doff detection model is based on one or more neural networks that are operable to learn contexts and track relationships in sequential data associated with the one or more signals from the one or more IMU sensors. ### Claim 16 (depends on 1) The method of claim 1, wherein a size of the on-device don/doff detection model is no greater than 1 MB. ### Claim 17 One or more computer-readable non-transitory non-volatile storage media embodying software that is operable when executed to: receive, at the head-mounted device, one or more touch inputs from a user corresponding to an activation trigger for an assistant system executing on the head-mounted device; access, by the head-mounted device, one or more signals from one or more inertial measurement unit (IMU) sensors of the head-mounted device; determine, by an on-device don/doff detection model and based only on the one or more signals from the one or more IMU sensors, that the user is either donning or doffing the head-mounted device; and override the activation trigger to prevent an activation of the assistant system responsive to the received one or more touch inputs. ### Claim 18 A system comprising: one or more processors; and a non-transitory non-volatile memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to: receive, at the head-mounted device, one or more touch inputs from a user corresponding to an activation trigger for an assistant system executing on the head-mounted device; access, by the head-mounted device, one or more signals from one or more inertial measurement unit (IMU) sensors of the head-mounted device; determine, by an on-device don/doff detection model and based only on the one or more signals from the one or more IMU sensors, that the user is either donning or doffing the head-mounted device; and override the activation trigger to prevent an activation of the assistant system responsive to the received one or more touch inputs.