# US 10,481,610 B2 · Method and device for controlling an autonomous vehicle using location based dynamic dictionary > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,481,610 B2 - Document ID: US10481610B2 - Status: Granted - Kind: B2 - Application number: 15/719,643 - Filed: 2017-09-29 - Published: 2019-02-21 - Granted: 2019-11-19 - Earliest claimed: 2017-08-18 - Assignees: Wipro Limited - Applicants: Wipro Limited - Inventors: Balaji Govindaraj; Bharath Kumar Muthupandian; Sujatha Jagannath; Ramachandra Budihal - Web page: https://patentgrep.com/patent/US10481610B2 ## CPC - G05D 1/0246: {using a video camera in combination with image processing means} - B60W 60/001: {Planning or execution of driving tasks} - G05D 1/00: Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots (drive control systems specially adapted for autonomous road vehicles B60W60/00) - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 20/582: {of traffic signs} - G06V 30/153: {using recognition of characters or words} - G08G 1/09623: {Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle (G08G1/0967 takes precedence)} - B60W 2420/403: Image sensing, e.g. optical camera - B60W 2555/20: Ambient conditions, e.g. wind or rain - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - 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}) ## Abstract A method and device are described for controlling a vehicle using a location based dynamic dictionary. The method includes receiving, by a navigation device, an image from an image sensing device associated with the autonomous vehicle, wherein the image sensing device captures the image at a location of the autonomous vehicle. The method includes extracting, by the navigation device, navigation content from the image. The method further includes identifying, by the navigation device, the navigation content from the image by comparing the navigation content from the image with a dynamic dictionary. The dynamic dictionary is created based on the location of the autonomous vehicle. The method further includes controlling, by the navigation device, the autonomous vehicle based on the navigation content. ## Claims ### Claim 1 A method of controlling an autonomous vehicle, the method comprising: receiving, by a navigation device, an image from an image sensing device associated with the autonomous vehicle, wherein the image sensing device partially captures the image at a current location of the autonomous vehicle due to conditions that include one of motion blurring of the image, low lighting conditions, and weather conditions; extracting, by the navigation device, navigation content from the partially-captured image; regenerating, by the navigation device, the navigation content by comparing the navigation content from the partially-captured image with each one of look-up entries in a dynamic dictionary, wherein the dynamic dictionary is dynamically created based on surrounding location data within a pre-defined radius from the current location of the autonomous vehicle; and controlling, by the navigation device, the autonomous vehicle based on the regenerated navigation content. ### Claim 2 (depends on 1) The method as claimed in claim 1, wherein extracting the navigation content from the partially-captured image comprises isolating the navigation content in the image. ### Claim 3 (depends on 1) The method as claimed in claim 1, wherein the navigation content comprises at least one of alphabets, numeric digits and symbols. ### Claim 4 (depends on 1) The method as claimed in claim 1, wherein the dynamic dictionary comprises text data associated with the current location of the autonomous vehicle, the surrounding location data retrieved from external sources, and historical location data. ### Claim 5 (depends on 1) The method as claimed in claim 1, further comprising, updating the dynamic dictionary associated with the current location of the autonomous vehicle based on the navigation content. ### Claim 6 (depends on 1) The method as claimed in claim 1, wherein comparing the navigation content from the partially-captured image with the dynamic dictionary comprises pattern matching the navigation content with the dynamic dictionary. ### Claim 7 (depends on 1) The method as claimed in claim 1, further comprising determining a confidence score based on comparing the navigation content from the partially-captured image with the dynamic dictionary. ### Claim 8 A navigation device, to control an autonomous vehicle based on a dynamic dictionary, the navigation device comprising: a processor; and a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to: receive an image from an image sensing device associated with the autonomous vehicle, wherein the image sensing device partially captures the image at a current location of the autonomous vehicle due to conditions that include one of motion blurring of the image, low lighting conditions, and weather conditions; extract navigation content from the partially-captured image; regenerate the navigation content by comparing the navigation content from the partially-captured image with each one of look-up entries in a dynamic dictionary, wherein the dynamic dictionary is dynamically created based on surrounding location data within a pre-defined radius from the current location of the autonomous vehicle; and control the autonomous vehicle based on the regenerated navigation content. ### Claim 9 (depends on 8) The navigation device of claim 8, wherein extracting the navigation content from the partially-captured image comprises isolating the navigation content in the image. ### Claim 10 (depends on 8) The navigation device of claim 8, wherein the navigation content comprises at least one of numeric digits, alphabets, and symbols. ### Claim 11 (depends on 8) The navigation device of claim 8, wherein the dynamic dictionary comprises text data associated with the current location of the autonomous vehicle, the surrounding location data retrieved from external sources, and historical location data. ### Claim 12 The navigation system of device 8, further comprising, updating the dynamic dictionary associated with the current location of the autonomous vehicle based on the navigation content. ### Claim 13 (depends on 8) The navigation device of claim 8, wherein comparing the navigation content from the partially-captured image with the dynamic dictionary comprises pattern matching the navigation content with the dynamic dictionary. ### Claim 14 (depends on 8) The navigation device of claim 8, further comprising determining a confidence score based on comparing the navigation content from the partially-captured image with the dynamic dictionary. ### Claim 15 A non-transitory computer-readable storage medium having stored thereon, a set of computer-executable instructions for causing a computer comprising one or more processors to perform steps comprising: receiving an image from an image sensing device associated with the autonomous vehicle, wherein the image sensing device partially captures the image at a current location of the autonomous vehicle due to conditions that include one of motion blurring of the image, low lighting conditions, and weather conditions; extracting navigation content from the partially-captured image; regenerating the navigation content by comparing the navigation content from the partially-captured image with each one of look-up entries in a dynamic dictionary, wherein the dynamic dictionary is dynamically created based on surrounding location data within a pre-defined radius from the current location of the autonomous vehicle; and controlling the autonomous vehicle based on the regenerated navigation content. ### Claim 16 (depends on 1) The method as claimed in claim 1, wherein regenerating, by the navigation device, the navigation content by comparing the navigation content from the partially-captured image with a dynamic dictionary, comprises: performing pattern matching of the navigation content extracted from the partially-captured image with each one of the look-up entries in the dynamic dictionary; identifying a content of the dynamic dictionary, which has a common pattern as that of the navigation content extracted from the partially-captured image, based on the pattern matching; and regenerating the navigation content by updating, removing and/or adding of at least one portion of the navigation content extracted from the partially-captured image, based on the identified content of the dynamic dictionary. ### Claim 17 (depends on 1) The method as claimed in claim 1, wherein, in the dynamic dictionary, the surrounding location data encompassed within the pre-defined radius is indexed in an increasing order based on the distance of each of the surrounding location data from the center of the current location of the autonomous vehicle.