# US 12,214,782 B2 · Ensemble of narrow AI agents for intersection assistance > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,214,782 B2 - Document ID: US12214782B2 - Status: Granted - Kind: B2 - Application number: 17/817,935 - Filed: 2022-08-05 - Published: 2023-02-09 - Granted: 2025-02-04 - Earliest claimed: 2021-08-05 - Assignees: Autobrains Technologies Ltd - Applicants: Autobrains Technologies Ltd - Inventors: Igal Raichelgauz - Web page: https://patentgrep.com/patent/US12214782B2 ## CPC - B60W 30/0956: {the prediction being responsive to traffic or environmental parameters} - G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames} - B60W 30/18154: {Approaching an intersection} - G06V 10/762: using clustering, e.g. of similar faces in social networks - G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)} - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - 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 20/54: of traffic, e.g. cars on the road, trains or boats - 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 - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method for intersection assistance, the method may include obtaining sensed information regarding an environment of the vehicle; determining an occurrence of an intersection related situation, based on the sensed information; generating one or more intersection driving related decisions; wherein the generating comprises processing, by one or more narrow AI agents of a group of narrow AI agents, at least one out of (a) at least a first part of the sensed information, and (b) an outcome of a pre-processing of at least a second part of the sensed information; and responding to the one or more intersection driving related decisions; wherein the responding comprises at least one out of (a) executing the one or more intersection driving related decisions, and (b) suggesting executing the one or more intersection driving related decisions. ## Claims ### Claim 1 A method for intersection assistance, the method comprises: obtaining sensed information regarding an environment of the vehicle; determining an occurrence of an intersection related situation, based on the sensed information; generating one or more intersection driving related decisions; wherein the generating comprises processing, by one or more narrow AI agents of a group of narrow AI agents, at least one out of (a) at least a first part of the sensed information, and (b) an outcome of a pre-processing of at least a second part of the sensed information; and responding to the one or more intersection driving related decisions; wherein the responding comprises at least one out of (a) executing the one or more intersection driving related decisions, and (b) suggesting executing the one or more intersection driving related decisions; wherein the narrow AI agents of the group are generated by: obtaining multiple videos obtained during driving sessions; identifying, in the multiple videos intersection related video segments of intersection related situations; clustering, by applying an unsupervised learning process, the intersection related video segments to video segment clusters, such that different video segment clusters are associated with different intersection related situations; generating, per each video segment cluster, one or more driving patterns clusters indicative of driving patterns of a vehicle at the presence of corresponding intersection related situations; and allocating different narrow AI agents of the group of narrow AI agents to different combinations of (a) an intersection related situation, and (b) a driving pattern of a single driving pattern cluster. ### Claim 2 (depends on 1) The method according to claim 1 wherein the responding comprises determining a safety parameter related to a passage through intersection. ### Claim 3 (depends on 1) The method according to claim 1 wherein the responding comprising determining a manner of passage through the intersection. ### Claim 4 (depends on 1) The method according to claim 1 comprising selecting the one or more narrow AI agents based on the intersection related situation. ### Claim 5 (depends on 1) The method according to claim 1 wherein the one or more narrow AI agents are all members of the group. ### Claim 6 (depends on 1) The method according to claim 1 comprising generating the group of narrow AI agents. ### Claim 7 (depends on 6) The method according to claim 6 further comprising training the different narrow AI agents of the group. ### Claim 8 (depends on 7) The method according to claim 7 wherein the training is based, at least in part, on telemetry information. ### Claim 9 A non-transitory computer readable medium for intersection assistance, the non-transitory computer readable medium comprises: obtaining sensed information regarding an environment of the vehicle; determining an occurrence of an intersection related situation, based on the sensed information; generating one or more intersection driving related decisions; wherein the generating comprises processing, by one or more narrow AI agents of a group of narrow AI agents, at least one out of (a) at least a first part of the sensed information, and (b) an outcome of a pre-processing of at least a second part of the sensed information; and responding to the one or more intersection driving related decisions; wherein the responding comprises at least one out of (a) executing the one or more intersection driving related decisions, and (b) suggesting executing the one or more intersection driving related decisions; wherein the narrow AI agents of the group are generated by: obtaining multiple videos obtained during driving sessions; identifying, in the multiple videos, intersection related video segments of intersection related situations; clustering, by applying an unsupervised learning process, the intersection related video segments to video segment clusters, such that different video segment clusters are associated with different intersection related situations; generating, per each video segment cluster, one or more driving patterns clusters indicative of driving patterns of a vehicle at the presence of corresponding intersection related situations; and allocating different narrow AI agents of the group of narrow AI agents to different combinations of (a) an intersection related situation, and (b) a driving pattern of a single driving pattern cluster. ### Claim 10 (depends on 9) The non-transitory computer readable medium according to claim 9 wherein the responding comprises determining a safety parameter related to a passage through intersection. ### Claim 11 (depends on 9) The non-transitory computer readable medium according to claim 9 wherein the responding that stores instructions for determining a manner of passage through the intersection. ### Claim 12 (depends on 9) The non-transitory computer readable medium according to claim 9 that stores instructions for selecting the one or more narrow AI agents based on the intersection related situation. ### Claim 13 (depends on 9) The non-transitory computer readable medium according to claim 9 wherein the one or more narrow AI agents are all members of the group. ### Claim 14 (depends on 10) The non-transitory computer readable medium according to claim 10 that stores instructions for generating the group of narrow AI agents. ### Claim 15 (depends on 14) The non-transitory computer readable medium according to claim 14 further that stores instructions for training the different narrow AI agents of the group. ### Claim 16 (depends on 15) The non-transitory computer readable medium according to claim 15 wherein the training is based, at least in part, on telemetry information.