# US 11,443,644 B2 · System and method of guiding a plurality of agents for complete coverage of an inspection area > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,644 B2 - Document ID: US11443644B2 - Status: Granted - Kind: B2 - Application number: 16/700,149 - Filed: 2019-12-02 - Published: 2021-04-15 - Granted: 2022-09-13 - Earliest claimed: 2019-10-11 - Assignees: Wipro Limited - Applicants: Wipro Limited - Inventors: Gyanesh Dwivedi; Vinod Pathangay - Web page: https://patentgrep.com/patent/US11443644B2 ## CPC - G08G 5/26: Transmission of traffic-related information between aircraft and ground stations - G08G 5/55: for a single aircraft - G05D 1/0027: {involving a plurality of vehicles, e.g. fleet or convoy travelling (fleet control of land vehicles from a control room G05D1/0297; traffic control systems for road vehicles G08G1/00; for marine craft G08G3/00; for aircraft G08G5/00)} - G05D 1/0202: {specially adapted to aircraft} - G05D 1/0297: {by controlling means in a control room} - G05D 1/104: {involving a plurality of aircrafts, e.g. formation flying (traffic control systems for aircraft G08G5/00)} - G08G 5/22: located on the ground - G08G 5/32: for flight plan preparation - G08G 5/56: for two or more aircraft - G08G 5/57: for unmanned aircraft - B64U 2101/26: for manufacturing, inspections or repairs - B64U 2101/30: for imaging, photography or videography - B64U 2101/70: for use inside enclosed spaces, e.g. in buildings or in vehicles - B64U 2201/102: adapted for flying in formations - G08G 5/59: in accordance with predefined flight zones, e.g. to avoid prohibited zones - G08G 5/80: Anti-collision systems - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - B64U: UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR ## Abstract Disclosed herein is a system and a method of guiding a plurality of agents 106 for complete coverage of the inspection area 102. The system and the method provide navigational instructions to navigate the plurality of agents 106 across the plurality of signalling unit 104 for traversing the inspection area 102. The plurality of signalling units 104 are communicatively coupled with the multi-agent visual navigation system for transmitting navigational instructions to the plurality of agents 106 based on pass-by information associated with the plurality of agents 106 obtained at the plurality of signalling units 104 and the pre-determined proximity associated with each pair of the plurality of signalling units. The navigational instructions are provided to the plurality of agents 106 at the plurality of signalling units 106 for subsequent navigation of the plurality of agents 106 across the plurality of signalling units 104 for complete coverage of the inspection area 102. ## Claims ### Claim 1 A method of guiding a plurality of agents for complete coverage of an inspection area, where the method comprises: providing, by a multi-agent visual navigation system, first navigational instructions to the plurality of agents to reach a corresponding signalling unit of a plurality of signalling units associated with the inspection area; upon reaching the corresponding signalling unit by an agent of the plurality of agents, recording, by the multi-agent visual navigation system, pass-by information associated with the agent at the corresponding signalling unit of the plurality of signalling units, wherein the recording of the pass-by information comprises: recording of pass-by event of the agent by capturing agent identity (ID) from the agent, and recording a corresponding time-stamp for the agent; and receiving path information associated with the agent at the corresponding signalling unit, wherein the path information comprises at least one of one or more previously traversed signalling units by the agent, previously received navigational instructions, details of designated signalling unit, and time-stamps associated with the one of one or more previously traversed signalling units by the agent; determining, by the multi-agent visual navigation system, second navigational instructions for the agent of the plurality of agents to traverse a proximal signalling unit of the plurality of signalling units, wherein determining the second navigational instructions for the agent comprises predicting the proximal signalling unit to be traversed by the agent based on pass-by information associated with the plurality of agents obtained at the plurality of signalling units and a pre-determined proximity associated with each pair of the plurality of signalling units; and providing, by the multi-agent visual navigation system, the second navigational instructions to the plurality of agents at the corresponding signalling unit for subsequent traversal of each of the proximal signalling units of the plurality of signalling units by at least one agent of the plurality of agents. ### Claim 2 (depends on 1) The method as claimed in claim 1, wherein the pass-by information associated with the plurality of agents obtained at the corresponding signalling unit comprises the pass-by information associated with the agent recorded at the corresponding signalling unit, pass-by information associated with the plurality of agents obtained from the plurality of signalling units, and time-stamp for each traversal. ### Claim 3 (depends on 1) The method as claimed in claim 1, wherein determining the second navigational instructions for the agent comprises using a pre-trained reinforcement learning model. ### Claim 4 (depends on 1) The method as claimed in claim 1, wherein the pre-determined proximity associated with each pair of the plurality of signalling units comprises adjacency information for each of the plurality of signalling units and relative distance between each pair of the plurality of signalling units. ### Claim 5 (depends on 1) The method as claimed in claim 1, wherein providing the second navigational instructions to the plurality of agents comprises displaying visual instructions at the plurality of signalling units to be captured by the plurality of agents for on-board processing. ### Claim 6 A multi-agent visual navigation system for guiding a plurality of agents for complete coverage of an inspection area, the multi-agent navigation system comprises: a plurality of signalling units configured with display; a memory communicatively coupled with at least one processor, storing instructions which on execution causes the processor to: provide first navigational instructions to the plurality of agents to reach a corresponding signalling unit of the plurality of signalling units associated with the inspection area; record pass-by information associated with an agent at the corresponding signalling unit of the plurality of signalling units upon reaching the corresponding signalling unit by the agent of the plurality of agents, wherein the pass-by information is recorded by: recording of pass-by event of the agent by capturing agent identity (ID) from the agent, and recording a corresponding time-stamp for the agent; and receiving path information associated with the agent at the corresponding signalling unit, wherein the path information comprises at least one of one or more previously traversed signalling units by the agent, previously received navigational instructions, details of designated signalling unit, and time-stamps associated with the one of one or more previously traversed signalling units by the agent; determine second navigational instructions for the agent of the plurality of agents to traverse a proximal signalling unit of the plurality of signalling units for complete coverage of the inspection area, wherein determining second navigational instructions for the agent comprises predicting the proximal signalling unit to be traversed by the agent based on pass-by information associated with the plurality of agents obtained at the plurality of signalling units and a pre-determined proximity associated with the plurality of signalling units; provide the second navigational instructions to the plurality of agents at the corresponding signalling unit for subsequent traversal of each of the proximal signalling units of the plurality of signalling units by at least one agent of the plurality of agents. ### Claim 7 (depends on 6) The multi-agent visual navigation system as claimed in claim 6, wherein the pass-by information associated with the plurality of agents obtained at the corresponding signalling unit comprises the pass-by information associated with the agent recorded at the corresponding signalling unit, pass-by information associated with the plurality of agents obtained from the plurality of signalling units, and time-stamp for each traversal. ### Claim 8 (depends on 6) The multi-agent visual navigation system as claimed in claim 6, wherein the second navigational instructions for the agent are determined using pre-trained reinforcement learning model. ### Claim 9 (depends on 6) The multi-agent visual navigation system as claimed in claim 6, wherein the pre-determined proximity associated with each pair of the plurality of signalling units comprises adjacency information for each of the plurality of signalling units and relative distance between each pair of the plurality of signalling units. ### Claim 10 (depends on 6) The multi-agent visual navigation system as claimed in claim 6, to provide the second navigational instructions to the plurality of agents, the instructions on execution causes the processor to display visual instructions at the plurality of signalling units to be captured by the plurality of agents for on-board processing. ### Claim 11 A non-transitory computer readable medium storing processor-executable instructions for: providing first navigational instructions to the plurality of agents to reach a corresponding signalling unit of a plurality of signalling units associated with the inspection area; upon reaching the corresponding signalling unit by an agent of the plurality of agents, recording pass-by information associated with the agent at the corresponding signalling unit of the plurality of signalling units, wherein the recording of the pass-by information comprises: recording of pass-by event of the agent by capturing agent identity (ID) from the agent, and recording a corresponding time-stamp for the agent; and receiving path information associated with the agent at the corresponding signalling unit, wherein the path information comprises at least one of one or more previously traversed signalling units by the agent, previously received navigational instructions, details of designated signalling unit, and time-stamps associated with the one of one or more previously traversed signalling units by the agent; determining second navigational instructions for the agent of the plurality of agents to traverse a proximal signalling unit of the plurality of signalling units, wherein determining the second navigational instructions for the agent comprises predicting the proximal signalling unit to be traversed by the agent based on pass-by information associated with the plurality of agents obtained at the plurality of signalling units and a pre-determined proximity associated with each pair of the plurality of signalling units; and providing the second navigational instructions to the plurality of agents at the corresponding signalling unit for subsequent traversal of each of the proximal signalling units of the plurality of signalling units by at least one agent of the plurality of agents. ### Claim 12 (depends on 11) The non-transitory computer readable medium of the claim 11, wherein the pass-by information associated with the plurality of agents obtained at the corresponding signalling unit comprises the pass-by information associated with the agent recorded at the corresponding signalling unit, pass-by information associated with the plurality of agents obtained from the plurality of signalling units, and time-stamp for each traversal. ### Claim 13 (depends on 11) The non-transitory computer readable medium of the claim 11, wherein determining the second navigational instructions for the agent comprises using a pre-trained reinforcement learning model. ### Claim 14 (depends on 11) The non-transitory computer readable medium of the claim 11, wherein the pre-determined proximity associated with each pair of the plurality of signalling units comprises adjacency information for each of the plurality of signalling units and relative distance between each pair of the plurality of signalling units. ### Claim 15 (depends on 11) The non-transitory computer readable medium of the claim 11, wherein the processor-executable instructions are further for displaying visual instructions at the plurality of signalling units to be captured by the plurality of agents for on-board processing.