# US 12,179,755 B2 · Trajectory generation device and trajectory generation method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,179,755 B2 - Document ID: US12179755B2 - Status: Granted - Kind: B2 - Application number: 17/705,290 - Filed: 2022-03-26 - Published: 2022-10-06 - Granted: 2024-12-31 - Earliest claimed: 2021-03-29 - Assignees: Honda Motor Co., Ltd. - Applicants: Honda Motor Co., Ltd. - Inventors: Yuji Yasui - Web page: https://patentgrep.com/patent/US12179755B2 ## CPC - B60W 30/0956: {the prediction being responsive to traffic or environmental parameters} - B60W 60/0011: {involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles} - B60W 50/0097: {Predicting future conditions} - B60W 60/0027: {using trajectory prediction for other traffic participants} - B60W 60/00276: {for two or more other traffic participants} - G05B 17/02: electric - B60W 2050/0028: {Mathematical models, e.g. for simulation} - B60W 2554/4029: Pedestrians - 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 - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) ## Abstract A trajectory generation device 1 determines first to third predicted trajectories by using model formulas (1) to (20) that model a trajectory of a host vehicle 3 on the basis of peripheral information of an information detection device 4, calculates a risk potential R_p_mi_vj_v_r by using the first to third predicted trajectories, and determines moving average values P_c1 to P_c3 so that the risk potential R_p_mi_vj_v_r decreases. In a case where the moving average values P_c1 and P_c2 have the same sign, the first predicted trajectory is determined while reflecting the moving average value P_c2 for correcting the second predicted trajectory. ## Claims ### Claim 1 A trajectory generation device that generates one future trajectory of a mobile body, the trajectory generation device comprising at least one processor and a memory comprising instructions, that when executed by the at least one processor, cause the at least one processor to implement: a surrounding situation recognizer that recognizes a surrounding situation of the mobile body; a predicted trajectory generator that generates a plurality of predicted trajectories by dividing the one future trajectory of the mobile body into a plurality of trajectories as the plurality of predicted trajectories, by using a plurality of trajectory models that models a trajectory of the mobile body, on a basis of a result of recognition of the surrounding situation by the surrounding situation recognizer; an interference degree parameter calculator that calculates a plurality of interference degree parameters representing a degree of interference of an interference object around the mobile body with the mobile body by using the plurality of predicted trajectories; a correction amount determiner that determines a plurality of amounts of correction for respectively correcting the plurality of predicted trajectories to cause the degree of interference represented by the plurality of interference degree parameters to be decreased; and a controller that controls the mobile body to travel along the plurality of predicted trajectories, wherein the predicted trajectory generator generates the plurality of predicted trajectories by using the plurality of trajectory models and the plurality of amounts of correction on the basis of the result of recognition of the surrounding situation, and in a case where two of the amounts of correction for correcting two of the predicted trajectories adjacent to each other are determined to correct the two predicted trajectories in an identical direction, the predicted trajectory generator generates one of the predicted trajectories closer to a current position of the mobile body out of the two predicted trajectories while reflecting one of the amounts of correction for correcting one of the predicted trajectories farther from the current position of the mobile body. ### Claim 2 (depends on 1) The trajectory generation device according to claim 1, wherein in a case where the two of the amounts of correction are determined to correct the two predicted trajectories in directions different from each other, the predicted trajectory generator generates one of the predicted trajectories closer to the current position of the mobile body independently of one of the amounts of correction for correcting one of the predicted trajectories farther from the current position of the mobile body. ### Claim 3 (depends on 2) The trajectory generation device according to claim 2, wherein the one of the predicted trajectories closer to the current position of the mobile body is generated in a state of being divided into a plurality of predicted trajectories shorter than the one of the predicted trajectories farther from the current position of the mobile body. ### Claim 4 (depends on 3) The trajectory generation device according to claim 3, wherein the mobile body includes the surrounding situation recognizer, the predicted trajectory generator, the interference degree parameter calculator, and the correction amount determiner. ### Claim 5 (depends on 3) The trajectory generation device according to claim 3, wherein the mobile body is a second mobile body other than a first mobile body including the surrounding situation recognizer, the predicted trajectory generator, the interference degree parameter calculator, and the correction amount determiner, and the predicted trajectory generator generates the plurality of predicted trajectories by using a past position of the second mobile body, the plurality of trajectory models, and the plurality of amounts of correction. ### Claim 6 (depends on 5) The trajectory generation device according to claim 5, wherein the predicted trajectory generator generates one of the predicted trajectories closer to the current position of the mobile body to cause a difference to be reduced between a time series of the past position of the mobile body and a time series of a plurality of estimated positions on a trajectory when the one of the predicted trajectories closer to the current position of the mobile body is extended to a past position side of the mobile body along the one of the predicted trajectories. ### Claim 7 (depends on 2) The trajectory generation device according to claim 2, wherein the mobile body includes the surrounding situation recognizer, the predicted trajectory generator, the interference degree parameter calculator, and the correction amount determiner. ### Claim 8 (depends on 2) The trajectory generation device according to claim 2, wherein the mobile body is a second mobile body other than a first mobile body including the surrounding situation recognizer, the predicted trajectory generator, the interference degree parameter calculator, and the correction amount determiner, and the predicted trajectory generator generates the plurality of predicted trajectories by using a past position of the second mobile body, the plurality of trajectory models, and the plurality of amounts of correction. ### Claim 9 (depends on 8) The trajectory generation device according to claim 8, wherein the predicted trajectory generator generates one of the predicted trajectories closer to the current position of the mobile body to cause a difference to be reduced between a time series of the past position of the mobile body and a time series of a plurality of estimated positions on a trajectory when the one of the predicted trajectories closer to the current position of the mobile body is extended to a past position side of the mobile body along the one of the predicted trajectories. ### Claim 10 (depends on 1) The trajectory generation device according to claim 1, wherein one of the predicted trajectories closer to the current position of the mobile body is generated in a state of being divided into a plurality of predicted trajectories shorter than one of the predicted trajectories farther from the current position of the mobile body. ### Claim 11 (depends on 10) The trajectory generation device according to claim 10, wherein the mobile body includes the surrounding situation recognizer, the predicted trajectory generator, the interference degree parameter calculator, and the correction amount determiner. ### Claim 12 (depends on 10) The trajectory generation device according to claim 10, wherein the mobile body is a second mobile body other than a first mobile body including the surrounding situation recognizer, the predicted trajectory generator, the interference degree parameter calculator, and the correction amount determiner, and the predicted trajectory generator generates the plurality of predicted trajectories by using a past position of the second mobile body, the plurality of trajectory models, and the plurality of amounts of correction. ### Claim 13 (depends on 12) The trajectory generation device according to claim 12, wherein the predicted trajectory generator generates one of the predicted trajectories closer to the current position of the mobile body to cause a difference to be reduced between a time series of the past position of the mobile body and a time series of a plurality of estimated positions on a trajectory when the one of the predicted trajectories closer to the current position of the mobile body is extended to a past position side of the mobile body along the one of the predicted trajectories. ### Claim 14 (depends on 1) The trajectory generation device according to claim 1, wherein the mobile body includes the surrounding situation recognizer, the predicted trajectory generator, the interference degree parameter calculator, and the correction amount determiner. ### Claim 15 (depends on 1) The trajectory generation device according to claim 1, wherein the mobile body is a second mobile body other than a first mobile body including the surrounding situation recognizer, the predicted trajectory generator, the interference degree parameter calculator, and the correction amount determiner, and the predicted trajectory generator generates the plurality of predicted trajectories by using a past position of the second mobile body, the plurality of trajectory models, and the plurality of amounts of correction. ### Claim 16 (depends on 15) The trajectory generation device according to claim 15, wherein the predicted trajectory generator generates one of the predicted trajectories closer to the current position of the mobile body to cause a difference to be reduced between a time series of the past position of the mobile body and a time series of a plurality of estimated positions on a trajectory when the one of the predicted trajectories closer to the current position of the mobile body is extended to a past position side of the mobile body along the one of the predicted trajectories. ### Claim 17 (depends on 1) The trajectory generation device according to claim 1, wherein the predicted trajectory generator generates the plurality of predicted trajectories by dividing the one future trajectory of the mobile body into a plurality of consecutive trajectories. ### Claim 18 A trajectory generation method for generating one future trajectory of a mobile body by a calculation processing device, the trajectory generation method comprising: a surrounding situation recognition step of recognizing a surrounding situation of the mobile body; a predicted trajectory generation step of generating a plurality of predicted trajectories by dividing the one future trajectory of the mobile body into a plurality of trajectories as the plurality of predicted trajectories, by using a plurality of trajectory models that models a trajectory of the mobile body, on a basis of a result of recognition of the surrounding situation by the surrounding situation recognition step; an interference degree parameter calculation step of calculating a plurality of interference degree parameters representing a degree of interference of an interference object around the mobile body with the mobile body by using the plurality of predicted trajectories; a correction amount determination step of determining a plurality of amounts of correction for respectively correcting the plurality of predicted trajectories to cause the degree of interference represented by the plurality of interference degree parameters to be decreased; and a controlling step of controlling the mobile body to travel along the plurality of predicted trajectories, executed by the calculation processing device, wherein in the predicted trajectory generation step, the plurality of predicted trajectories is generated by using the plurality of trajectory models and the plurality of amounts of correction on the basis of the result of recognition of the surrounding situation, and in a case where two of the amounts of correction for correcting two of the predicted trajectories adjacent to each other are determined to correct the two predicted trajectories in an identical direction, one of the predicted trajectories closer to a current position of the mobile body out of the two predicted trajectories is generated while reflecting one of the amounts of correction for correcting one of the predicted trajectories farther from the current position of the mobile body.