# US 12,179,784 B2 · Detection of health conditions in vehicle occupants > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,179,784 B2 - Document ID: US12179784B2 - Status: Granted - Kind: B2 - Application number: 18/164,956 - Filed: 2023-02-06 - Published: 2024-08-08 - Granted: 2024-12-31 - Earliest claimed: 2023-02-06 - Assignees: GM Global Technology Operations LLC - Applicants: GM Global Technology Operations LLC - Inventors: Jacob Alan Bond; Joseph F. Szczerba - Web page: https://patentgrep.com/patent/US12179784B2 ## CPC - B60W 50/14: Means for informing the driver, warning the driver or prompting a driver intervention - B60W 40/08: related to drivers or passengers - B60W 40/10: related to vehicle motion - G06N 20/00: Machine learning - G06V 20/593: {Recognising seat occupancy} - G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands - G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) - B60W 2040/0863: {due to erroneous selection or response of the driver} - B60W 2050/146: {Display means} - B60W 2420/403: Image sensing, e.g. optical camera - B60W 2510/202: Steering torque - B60W 2540/10: Accelerator pedal position - B60W 2540/12: Brake pedal position - B60W 2540/18: Steering angle - B60W 2540/221: Physiology, e.g. weight, heartbeat, health or special needs - B60W 2556/45: External transmission of data to or from the vehicle - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A system for detecting a health condition of an occupant of a vehicle includes a plurality of vehicle sensors and a controller in electrical communication with the plurality of vehicle sensors. The controller is programmed to perform a plurality of measurements using the plurality of vehicle sensors determine a health risk probability based at least in part on the plurality of measurements. The health risk probability is a probability that the occupant of the vehicle has the health condition. The controller is further programmed to notify the occupant of the vehicle in response to determining that the health risk probability is greater than or equal to a predetermined health risk threshold. ## Claims ### Claim 1 A system for detecting a health condition of an occupant of a vehicle, the system comprising: a plurality of vehicle sensors including at least one control sensor and at least one reference sensor, wherein the at least one control sensor is configured to measure a control input provided to the vehicle by the occupant, and wherein the at least one reference sensor is configured to measure a movement of the vehicle; and a controller in electrical communication with the plurality of vehicle sensors, wherein the controller is programmed to: perform a plurality of measurements using the plurality of vehicle sensors, wherein the plurality of measurements includes a plurality of control measurements performed using the at least one control sensor and a plurality of vehicle movement measurements performed using the at least one reference sensor; determine a plurality of occupant control inputs based at least in part on the plurality of control measurements and the plurality of vehicle movement measurements; determine a health risk probability based at least in part on the plurality of occupant control inputs, wherein the health risk probability is a probability that the occupant of the vehicle has the health condition; and notify the occupant of the vehicle in response to determining that the health risk probability is greater than or equal to a predetermined health risk threshold. ### Claim 2 (depends on 1) The system of claim 1, wherein to determine the health risk probability, the controller is further programmed to: determine the health risk probability using a machine learning algorithm, wherein the machine learning algorithm is trained to determine the health risk probability based on a plurality of model input data, and wherein the plurality of model input data includes at least the plurality of occupant control inputs. ### Claim 3 (depends on 2) The system of claim 2, further including an automated driving system in electrical communication with the controller, wherein to determine the health risk probability, the controller is further programmed to: generate a plurality of expected control inputs using the automated driving system; and determine the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of expected control inputs. ### Claim 4 (depends on 2) The system of claim 2, further including a vehicle communication system in electrical communication with the controller, wherein to determine the health risk probability, the controller is further programmed to: establish a connection with a mobile device using the vehicle communication system; retrieve a plurality of mobile device health data from the mobile device using the vehicle communication system; and determine the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is further trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of mobile device health data. ### Claim 5 (depends on 4) The system of claim 4, wherein the controller is further programmed to: establish a connection with a remote server using the vehicle communication system; transfer the plurality of model input data to the remote server using the vehicle communication system, wherein the machine learning algorithm is executed by the remote server using the plurality of model input data; and receive the health risk probability from the remote server using the vehicle communication system. ### Claim 6 (depends on 2) The system of claim 2, wherein the plurality of vehicle sensors includes an occupant movement sensor, and wherein to determine the health risk probability, the controller is further programmed to: perform a plurality of occupant movement measurements using the occupant movement sensor; and determine the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is further trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of occupant movement measurements. ### Claim 7 (depends on 6) The system of claim 6, wherein the occupant movement sensor is a camera, and wherein to perform the plurality of occupant movement measurements, the controller is further programmed to: capture a plurality of videos of the occupant using the camera; determine a plurality of occupant induced movements in the plurality of videos of the occupant; and determine the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is further trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of occupant induced movements. ### Claim 8 (depends on 2) The system of claim 2, further including a display in electrical communication with the controller, wherein to determine the health risk probability, the controller is further programmed to: record a plurality of touch accuracies of a plurality of occupant interactions with the display; and determine the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is further trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of touch accuracies of the plurality of occupant interactions with the display. ### Claim 9 (depends on 2) The system of claim 2, wherein the controller is further programmed to: label the model input data as positive diagnosis model input data in response to determining that the health risk probability is greater than or equal to the predetermined health risk threshold; train the machine learning algorithm using the positive diagnosis model input data in response to labeling the model input data as positive diagnosis model input data; label the model input data as negative diagnosis model input data in response to determining that the health risk probability is less than the predetermined health risk threshold; and train the machine learning algorithm using the negative diagnosis model input data in response to labeling the model input data as negative diagnosis model input data. ### Claim 10 A method for detecting a health condition of an occupant of a vehicle, the method comprising: performing a plurality of measurements using a plurality of vehicle sensors, wherein the plurality of measurements includes a plurality of control measurements and a plurality of vehicle movement measurements; determining a plurality of occupant control inputs based at least in part on the plurality of control measurements and the plurality of vehicle movement measurements; determining a health risk probability based at least in part on the plurality of occupant control inputs, wherein the health risk probability is a probability that the occupant of the vehicle has the health condition; and notifying the occupant of the vehicle in response to determining that the health risk probability is greater than or equal to a predetermined health risk threshold. ### Claim 11 (depends on 10) The method of claim 10, wherein determining the health risk probability further comprises: determining the health risk probability using a machine learning algorithm, wherein the machine learning algorithm is trained to determine the health risk probability based on a plurality of model input data, and wherein the plurality of model input data includes at least the plurality of occupant control inputs. ### Claim 12 (depends on 11) The method of claim 11, wherein determining the health risk probability further comprises: generating a plurality of expected control inputs using an automated driving system; and determining the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of expected control inputs. ### Claim 13 (depends on 12) The method of claim 12, wherein determining the health risk probability further comprises: establishing a connection with a mobile device using a vehicle communication system; retrieving a plurality of mobile device health data from the mobile device using the vehicle communication system; and determining the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is further trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of mobile device health data. ### Claim 14 (depends on 13) The method of claim 13, wherein determining the health risk probability further comprises: capturing a plurality of videos of the occupant using a camera; determining a plurality of occupant induced movements in the plurality of videos of the occupant; and determining the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is further trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of occupant induced movements. ### Claim 15 (depends on 14) The method of claim 14, wherein determining the health risk probability further comprises: recording a plurality of touch accuracies of a plurality of occupant interactions with a display; and determining the health risk probability using the machine learning algorithm, wherein the machine learning algorithm is further trained to determine the health risk probability based on the plurality of model input data, and wherein the plurality of model input data further includes the plurality of touch accuracies of the plurality of occupant interactions with the display. ### Claim 16 A system for detecting a health condition of an occupant of a vehicle, the system comprising: a plurality of vehicle sensors; an automated driving system; a vehicle communication system; and a controller in electrical communication with the plurality of vehicle sensors, wherein the controller is programmed to: perform a plurality of control measurements using the plurality of vehicle sensors; perform a plurality of occupant movement measurements using the plurality of vehicle sensors; generate a plurality of expected control inputs using the automated driving system; retrieve a plurality of mobile device health data from a mobile device using the vehicle communication system; determine a health risk probability based at least in part on the plurality of control measurements, the plurality of occupant movement measurements, the plurality of expected control inputs, and the plurality of mobile device health data, wherein the health risk probability is a probability that the occupant of the vehicle has the health condition; and notify the occupant of the vehicle in response to determining that the health risk probability is greater than or equal to a predetermined health risk threshold. ### Claim 17 (depends on 16) The system of claim 16, further comprising: a display in electrical communication with the controller; and wherein the controller is further programmed to: record a plurality of touch accuracies of a plurality of occupant interactions with the display; and determine a health risk probability based at least in part on the plurality of control measurements, the plurality of occupant movement measurements, the plurality of expected control inputs, the plurality of mobile device health data, and the plurality of touch accuracies, wherein the health risk probability is a probability that the occupant of the vehicle has the health condition.