# US 11,307,302 B2 · Method and device for estimating an absolute velocity of an obstacle, and non-volatile computer-readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,307,302 B2 - Document ID: US11307302B2 - Status: Granted - Kind: B2 - Application number: 16/521,112 - Filed: 2019-07-24 - Published: 2020-03-12 - Granted: 2022-04-19 - Earliest claimed: 2018-09-07 - Assignees: Baidu Online Network Technology (Beijing) Co., Ltd. - Applicants: Baidu Online Network Technology (Beijing) Co., Ltd. - Inventors: Chongchong Li - Web page: https://patentgrep.com/patent/US11307302B2 ## CPC - G01S 13/58: Velocity or trajectory determination systems; Sense-of-movement determination systems - G01S 13/931: of land vehicles - G01S 13/726: {Multiple target tracking} - G01S 2013/932: {using own vehicle data, e.g. ground speed, steering wheel direction} - 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 ## Abstract A method and system for estimating an absolute velocity of an obstacle are provided. The method can include measuring an absolute velocity of a motor vehicle at a current moment t1 by an integrated navigation device, and storing the measured absolute velocity of the motor vehicle at the current moment t1 in a data table, obtaining a relative velocity of the obstacle relative to the motor vehicle at a second moment t2 by a millimeter wave radar; adjusting the relative velocity of the obstacle at the second moment t2 to a relative velocity of the obstacle at the current moment t1, and obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after an adjustment. ## Claims ### Claim 1 A method for estimating an absolute velocity of an obstacle, comprising: measuring an absolute velocity of a motor vehicle at a current moment t1 by an integrated navigation device, and storing the measured absolute velocity of the motor vehicle at the current moment t1 in a data table; obtaining a relative velocity of the obstacle relative to the motor vehicle at a second moment t2 by a millimeter wave radar; adjusting the relative velocity of the obstacle at the second moment t2 to a relative velocity of the obstacle at the current moment t1; and obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting; wherein adjusting the relative velocity of the obstacle at the second moment t2 to the relative velocity of the obstacle at the current moment t1 comprises: obtaining respective hypothetical absolute velocities of multiple types of obstacles at the current moment t1 by adding relative velocities of the multiple types of obstacles at the second moment t2 to the absolute velocity of the motor vehicle at the current moment t1, wherein the multiple types of obstacles are in a scene in which the obstacle is located; determining the multiple types of obstacles having similar hypothetical absolute velocities and the greatest number in the scene at the current moment t1, as a type of reference obstacles; and averaging the hypothetical absolute velocities of the reference obstacles, to obtain an average error amount; and obtaining the relative velocity of the obstacle at the current moment t1 after the adjusting by subtracting the average error amount from the relative velocity of the obstacle at the second moment t2. ### Claim 2 (depends on 1) The method of claim 1, wherein obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting comprises: obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting, in a case that the number of the reference obstacles is greater than a first threshold and/or the average error amount is less than a second threshold. ### Claim 3 A method for estimating an absolute velocity of an obstacle, comprising: measuring an absolute velocity of a motor vehicle at a current moment t1 by an integrated navigation device, and storing the measured absolute velocity of the motor vehicle at the current moment t1 in a data table; obtaining a relative velocity of the obstacle relative to the motor vehicle at a second moment t2 by a millimeter wave radar; adjusting the relative velocity of the obstacle at the second moment t2 to a relative velocity of the obstacle at the current moment t1; and obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting; wherein obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting comprises: obtaining respective hypothetical absolute velocities of multiple types of obstacles at the current moment t1 by adding relative velocities of the multiple types of obstacles at the second moment t2 to the absolute velocity of the motor vehicle at the current moment t1, wherein the multiple types of obstacles are in a scene in which the obstacle is located; determining the multiple types of obstacles having similar hypothetical absolute velocities at the current moment t1, as multiple types of reference obstacles; and averaging the hypothetical absolute velocities of the reference obstacles, to obtain an average error amount; determining the number of each type of the reference obstacles detected by the millimeter wave radar and a detection period of the millimeter wave radar between adjacent detections, in a case that the number of each type of the reference obstacles is less than a first threshold and/or the average error amount is greater than a second threshold; and obtaining, for each type of the reference obstacles, a function relationship among the number of reference obstacles, the detection period and a time difference t2−t1, wherein the time difference t2−t1 is a difference between the second moment t2 and the current moment t1. ### Claim 4 (depends on 3) The method of claim 3, further comprising: adjusting time data of the millimeter wave radar at the second moment t2 to time data of the millimeter wave radar at the current moment t1 according to the number of the reference obstacles detected by the millimeter wave radar and the detection period of the millimeter wave radar, to obtain the relative velocity of the obstacle at the current moment t1 after the adjusting; looking up the absolute velocity of the motor vehicle at the current moment t1 in the data table, and obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the reference obstacles at the current moment t1 after the adjusting. ### Claim 5 A system for estimating an absolute velocity of an obstacle, comprising: one or more processors; a storage device for storing one or more programs; wherein the one or more programs are executed by the one or more processors to enable the one or more processors to measure an absolute velocity of a motor vehicle at a current moment t1, and to store the measured absolute velocity of the motor vehicle at the current moment t1 in a data table; obtain a relative velocity of the obstacle relative to the motor vehicle at a second moment t2; adjust the relative velocity of the obstacle at the second moment t2 to a relative velocity of the obstacle at the current moment t1; and obtain the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting; wherein the one or more programs are executed by the one or more processors to enable the one or more processors to: obtain respective hypothetical absolute velocities of multiple types of obstacles at the current moment t1 by adding relative velocities of the multiple types of obstacles at the second moment t2 to the absolute velocity of the motor vehicle at the current moment t1, wherein the multiple types of obstacles are in a scene in which the obstacle is located; determine the multiple types of obstacles having similar hypothetical absolute velocities and the greatest number in the scene at the current moment t1, as a type of reference obstacles; and averaging the hypothetical absolute velocities of the reference obstacles, to obtain an average error amount; and obtain the relative velocity of the obstacle at the current moment t1 after the adjusting by subtracting the average error amount from the relative velocity of the obstacle at the second moment t2. ### Claim 6 (depends on 5) The system of claim 5, wherein the one or more programs are executed by the one or more processors to enable the one or more processors to: obtain the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting, in a case that the number of the reference obstacles is greater than a first threshold and/or the average error amount is less than a second threshold. ### Claim 7 A system for estimating an absolute velocity of an obstacle, comprising: one or more processors; a storage device for storing one or more programs; wherein the one or more programs are executed by the one or more processors to enable the one or more processors to: measure an absolute velocity of a motor vehicle at a current moment t1, and to store the measured absolute velocity of the motor vehicle at the current moment t1 in a data table; obtain a relative velocity of the obstacle relative to the motor vehicle at a second moment t2; adjust the relative velocity of the obstacle at the second moment t2 to a relative velocity of the obstacle at the current moment t1; and obtain the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting; obtain respective hypothetical absolute velocities of multiple types of obstacles at the current moment t1 by adding relative velocities of the multiple types of obstacles at the second moment t2 to the absolute velocity of the motor vehicle at the current moment t1, wherein the multiple types of obstacles are in a scene in which the obstacle is located; determine the multiple types of obstacles having similar hypothetical absolute velocities at the current moment t1, as multiple types of reference obstacles; and averaging the hypothetical absolute velocities of the reference obstacles, to obtain an average error amount; determine the number of each type of the reference obstacles detected by a millimeter wave radar and a detection period of the millimeter wave radar between adjacent detections, in a case that the number of each type of the reference obstacles is less than a first threshold and/or the average error amount is greater than a second threshold; and obtain, for each type of the reference obstacles, a function relationship among the number of reference obstacles, the detection period and a time difference t2−t1, wherein the time difference t2−t1 is a difference between the second moment t2 and the current moment t1. ### Claim 8 (depends on 7) The system of claim 7, wherein the one or more programs are executed by the one or more processors to enable the one or more processors to: adjust time data of the millimeter wave radar at the second moment t2 to time data of the millimeter wave radar at the current moment t1 according to the number of the reference obstacles detected by the millimeter wave radar and the detection period of the millimeter wave radar, to obtain the relative velocity of the obstacle at the current moment t1 after the adjusting; and look up the absolute velocity of the motor vehicle at the current moment t1 in the data table, and obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the reference obstacles at the current moment t1 after the adjusting. ### Claim 9 A non-transitory computer-readable storage medium having computer programs stored thereon, wherein the computer programs, when executed by a processor, cause the processor to perform operations of: measuring an absolute velocity of a motor vehicle at a current moment t1 by an integrated navigation device, and storing the measured absolute velocity of the motor vehicle at the current moment t1 in a data table; obtaining a relative velocity of the obstacle relative to the motor vehicle at a second moment t2 by a millimeter wave radar; adjusting the relative velocity of the obstacle at the second moment t2 to a relative velocity of the obstacle at the current moment t1; and obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting; wherein when the computer programs, executed by a processor, cause the processor to adjust the relative velocity of the obstacle at the second moment t2 to the relative velocity of the obstacle at the current moment t1, the computer programs, executed by a processor, cause the processor to specifically perform operations of: obtaining respective hypothetical absolute velocities of multiple types of obstacles at the current moment t1 by adding relative velocities of the multiple types of obstacles at the second moment t2 to the absolute velocity of the motor vehicle at the current moment t1, wherein the multiple types of obstacles are in a scene in which the obstacle is located; determining the multiple types of obstacles having similar hypothetical absolute velocities and the greatest number in the scene at the current moment t1, as a type of reference obstacles; and averaging the hypothetical absolute velocities of the reference obstacles, to obtain an average error amount; and obtaining the relative velocity of the obstacle at the current moment t1 after the adjusting by subtracting the average error amount from the relative velocity of the obstacle at the second moment t2. ### Claim 10 A non-transitory computer-readable storage medium having computer programs stored thereon, wherein the computer programs, when executed by a processor, cause the processor to perform operations of: measuring an absolute velocity of a motor vehicle at a current moment t1 by an integrated navigation device, and storing the measured absolute velocity of the motor vehicle at the current moment t1 in a data table; obtaining a relative velocity of the obstacle relative to the motor vehicle at a second moment t2 by a millimeter wave radar; adjusting the relative velocity of the obstacle at the second moment t2 to a relative velocity of the obstacle at the current moment t1; and obtaining the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting; wherein when the computer programs, executed by a processor, cause the processor to obtain the absolute velocity of the obstacle at the current moment t1 by adding the absolute velocity of the motor vehicle at the current moment t1 to the relative velocity of the obstacle at the current moment t1 after the adjusting, the computer programs, executed by a processor, cause the processor to specifically perform operations of: obtaining respective hypothetical absolute velocities of multiple types of obstacles at the current moment t1 by adding relative velocities of the multiple types of obstacles at the second moment t2 to the absolute velocity of the motor vehicle at the current moment t1, wherein the multiple types of obstacles are in a scene in which the obstacle is located; determining the multiple types of obstacles having similar hypothetical absolute velocities at the current moment t1, as multiple types of reference obstacles; and averaging the hypothetical absolute velocities of the reference obstacles, to obtain an average error amount; determining the number of each type of the reference obstacles detected by the millimeter wave radar and a detection period of the millimeter wave radar between adjacent detections, in a case that the number of each type of the reference obstacles is less than a first threshold and/or the average error amount is greater than a second threshold; and obtaining, for each type of the reference obstacles, a function relationship among the number of reference obstacles, the detection period and a time difference t2−t1, wherein the time difference t2−t1 is a difference between the second moment t2 and the current moment t1.