# US 12,759,458 B2 · Pedestrian alert system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,759,458 B2 - Document ID: US12759458B2 - Status: Granted - Kind: B2 - Application number: 18/895,495 - Filed: 2024-09-25 - Published: 2026-03-26 - Granted: 2026-10-13 - Earliest claimed: 2024-09-25 - Assignees: GM Global Technology Operations LLC - Applicants: GM Global Technology Operations LLC - Inventors: Seokju Yong; Sungdae Kim; Yeongman Jo; Gaurav Talwar; Bongbum Back; Jenna Hansen - Web page: https://patentgrep.com/patent/US12759458B2 ## CPC - B60Q 9/008: {for anti-collision purposes} - G01S 13/931: of land vehicles - G01S 17/931: of land vehicles - G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads - G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands - B60Q: ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A system for alerting pedestrians to a vehicle includes a sensing system having at least one imaging sensor in communication with a controller. The controller includes a processor and a memory. The memory stores a pedestrian detection module and a pedestrian alert module. The pedestrian detection module including instructions configured to cause the processor to identify a pedestrian in an output of the at least one imaging sensor using image analysis and instructions configured to cause the processor to respond to an identified pedestrian by determining a reduced sensory state of the pedestrian. The system generates an ambient environment model based on an output of the at least one imaging sensor and a connection to at least one external data source. The pedestrian alert module causes the processor to generate a pedestrian alert that contrasts with the ambient environment model. An external alert system implements the pedestrian alert. ## Claims ### Claim 1 A system for alerting pedestrians to a presence of a vehicle, the system comprising: a sensing system including at least one imaging sensor in communication with a controller; the controller including a processor and a memory, the memory storing a pedestrian detection module and a pedestrian alert module; the pedestrian detection module including instructions configured to cause the processor to identify a pedestrian in an output of the at least one imaging sensor using image analysis; the pedestrian alert module including instructions configured to cause the processor to respond to an identified pedestrian by determining a reduced sensory state of the pedestrian, generate an ambient environment model based on an output of the at least one imaging sensor, a weather detection system, a lumens sensor, and a connection to at least one external data source, the at least one data source including a database correlating a time of day and location of the vehicle with an expected ambient lighting condition, wherein the ambient environment model includes a model of ambient lighting conditions surrounding the vehicle; the pedestrian alert module further including instructions configured to determine at least one alert type, based on the reduced sensory state of the pedestrian, and at least one of an initial visual data and an initial audio data, the at least one alert type including a visual alert; the pedestrian alert module further including instructions configured to cause the processor to generate a pedestrian alert of the at least one alert type, the pedestrian alert configured to contrast with the ambient environment model, wherein the pedestrian alert includes a pattern comprising one of directional indicators and motion, and wherein the pattern contrasts the ambient lighting conditions surrounding the vehicle; an external alert system configured to implement the pedestrian alert external to the vehicle, the external alert system including a visual alert system, and implementation of the pedestrian alert external to the vehicle comprising projecting the pattern, such that the pattern is displayed on at least one surface of the external environment. ### Claim 2 (depends on 1) The system of claim 1, wherein the external alert system includes an audio alert system; the audio alert system including a speaker; and wherein causing the alert system to implement the pedestrian alert includes activating at least one of the audio alert system and the visual alert system. ### Claim 3 (depends on 2) The system of claim 2, wherein the audio alert system has an audio output that is adjustable in at least amplitude and frequency. ### Claim 4 (depends on 2) The system of claim 2, wherein the visual alert system has a visual output that is adjustable in at least color and brightness. ### Claim 5 (depends on 2) The system of claim 2, wherein the external alert system includes an olfactory alert system, the olfactory alert system includes a blower, and the blower has an olfactory output that is adjustable in at least scent. ### Claim 6 (depends on 2) The system of claim 2, wherein the external alert system includes a tactile air alert system and the tactile air alert system includes an airflow generator. ### Claim 7 (depends on 1) The system of claim 1, wherein determining the reduced sensory state of the pedestrian includes identifying one of a distracted state of the pedestrian and a detectable disability of the pedestrian and wherein the at least one alert type includes an audio alert in response to the pedestrian having a distracted state. ### Claim 8 (depends on 1) The system of claim 1, wherein determining the reduced sensory state of the pedestrian includes identifying one of a distracted state of the pedestrian and a detectable disability of the pedestrian and wherein the at least one alert type includes a visual alert in response to identifying a hearing impairment of the pedestrian. ### Claim 9 (depends on 1) The system of claim 1, wherein determining the reduced sensory state of the pedestrian includes identifying one of a distracted state of the pedestrian and a detectable disability of the pedestrian and wherein the at least one alert type includes an audio alert in response to identifying a vision impairment of the pedestrian. ### Claim 10 (depends on 1) The system of claim 1, wherein determining the reduced sensory state of the pedestrian includes identifying one of a distracted state of the pedestrian and a detectable disability of the pedestrian includes identifying a detectable disability having an impairment above a minimum threshold and wherein the at least one alert type omits a corresponding one of the audio alert, visual alert, olfactory alert, and the tactile air impact alert. ### Claim 11 (depends on 1) The system of claim 1, wherein the sensing system includes at least one ranging sensor and the at least one ranging sensor including at least one of a light and distance ranging (LiDAR) sensor and a radio and distance ranging (RADAR) sensor; and wherein generating the pedestrian alert is based at least in part on a range output received by the processor from the at least one ranging sensor. ### Claim 12 (depends on 1) The system of claim 1, wherein generating the pedestrian alert of the determined at least one alert type comprises providing the ambient environment model and a set of reward/weight penalties to a weighted machine learning algorithm. ### Claim 13 (depends on 12) The system of claim 12, wherein the set of reward/weight penalties are received from a remote computing system. ### Claim 14 (depends on 13) The system of claim 13, wherein the pedestrian alert module is further configured to cause the processor to isolate a response of the pedestrian to the pedestrian alert and provide the response of the pedestrian to the remote computing system. ### Claim 15 (depends on 1) The system of claim 1, wherein generating the pedestrian alert of the at least one alert type comprises applying the ambient environment model to a rules-based alert model. ### Claim 16 (depends on 1) The system of claim 1, wherein the olfactory alert system comprises an olfactory blower having a scent repository and a compressed gas portion, the scent repository storing at least one aromatic chemical. ### Claim 17 (depends on 16) The system of claim 16, wherein the scent repository stores a plurality of distinct aromatic chemicals, and wherein generating a pedestrian alert of the at least one alert type includes selecting one of a distinct aromatic chemical from the plurality of distinct aromatic chemicals and a combination of distinct aromatic chemicals from the plurality of distinct aromatic chemicals, and implementing the pedestrian alert comprises dispersing the selected one of the distinct aromatic chemical from the plurality of distinct aromatic chemicals and the combination of distinct aromatic chemicals from the plurality of distinct aromatic chemicals using compressed gas from the compressed gas portion. ### Claim 18 (depends on 1) The system of claim 1, wherein the ambient environment model includes a time of day, a weather state, an ambient sound profile, an ambient lighting profile, a speed of the vehicle, and a direction of travel of the vehicle. ### Claim 19 A method for alerting a pedestrian to the presence of a vehicle, the method comprising: receiving a set of images from a vehicle sensor system at a controller and identifying a pedestrian in the set of images using image analysis performed by the controller; determining a reduced sensory state of the pedestrian using the controller; receiving, at the controller, a set of ambient conditions from the vehicle sensor system and generating an ambient environment model, the vehicle sensor system including a weather detection system and a lumens sensor, and wherein generating the ambient environment model includes generating a model of ambient lighting conditions surrounding the vehicle based at least in part on at least one external data source including a database correlating a time of day and location of the vehicle with an expected ambient lighting condition; determining at least one alert type corresponding to the reduced sensory state, wherein the at least one alert type includes a visual alert; generating a pedestrian alert based on the at least one alert type and an ambient environment model using a pedestrian alert module, wherein the pedestrian alert contrasts an ambient environment defined by the ambient environment model, and wherein the pedestrian alert includes a pattern comprising one of directional indicators and motion, and wherein the pattern contrasts the ambient lighting conditions surrounding the vehicle; and implementing the pedestrian alert using at least one external alerting system of the vehicle by at least comprising projecting the pattern such that the pattern is displayed on at least one surface of the external environment. ### Claim 20 (depends on 19) The method of claim 19, wherein the pedestrian alert module is a weighted machine learning algorithm, and wherein a set of rewards/weight penalties for the weighted machine learning algorithm is retrieved from a remote computing system.