# US 11,442,467 B2 · Method and system for generating a trajectory for navigating an autonomous vehicle > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,442,467 B2 - Document ID: US11442467B2 - Status: Granted - Kind: B2 - Application number: 16/690,296 - Filed: 2019-11-21 - Published: 2020-10-01 - Granted: 2022-09-13 - Earliest claimed: 2019-03-29 - Assignees: Wipro Limited - Applicants: Wipro Limited - Inventors: Manas Sarkar; Balaji Sunil Kumar - Web page: https://patentgrep.com/patent/US11442467B2 ## CPC - G05D 1/0278: {using satellite positioning signals, e.g. GPS} - B60W 60/0011: {involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles} - G01C 21/3476: {using point of interest [POI] information, e.g. a route passing visible POIs} - G05D 1/0219: {ensuring the processing of the whole working surface} - G05D 1/0223: {involving speed control of the vehicle (vehicle fittings for automatically controlling, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator B60K31/00)} - B60W 2554/60: Traversable objects, e.g. speed bumps or curbs - B60W 2555/60: Traffic rules, e.g. speed limits or right of way - B60W 2556/50: of positioning data, e.g. GPS [Global Positioning System] data - 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 - G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S) ## Abstract Disclosed subject matter relates to field of vehicle navigation system that performs a method of generating trajectory for navigating an autonomous vehicle. A trajectory generating system associated with autonomous vehicle detects Points of Interest (POIs) for a selected segment which is at predefined distance from current position of autonomous vehicle, in real-time. Further, features of each of the POIs are determined and first level trajectory is generated for selected segment based on features of POIs proximal to selected segment. Furthermore, the trajectory generating system generates second level trajectory for portions of first level trajectory from current position of autonomous vehicle by modifying each portion based on real-time environment data. First level trajectory in present disclosure enables trajectory generating system to effectively plan the second level trajectory such that, sudden change in velocity or direction of autonomous vehicle is eliminated, when autonomous vehicle encounters infrastructure conditions present in the selected segment. ## Claims ### Claim 1 A computer-implemented method of generating a trajectory for navigating an autonomous vehicle, the method comprising: detecting, by a trajectory generating system that comprises a processor and is associated with the autonomous vehicle, one or more Points of Interest (POIs) for a selected segment, on a pre-generated navigation path, in real-time, wherein the selected segment is at a predefined distance from a current position of the autonomous vehicle, and wherein the pre-generated navigation path is generated based on a source point and a destination point; determining, by the trajectory generating system, an impact of the one or more POIs on navigation of the autonomous vehicle; determining, by the trajectory generating system, features of each of the one or more POIs based on the impact of the one or more POIs on the navigation of the autonomous vehicle, wherein the features comprise at least one of one or more parameter values and a priority value corresponding to the one or more parameter values; detecting, by the trajectory generating system, a previous segment prior to the selected segment, wherein the previous segment has a previously generated trajectory; generating, by the trajectory generating system, a first level trajectory for the selected segment at an end portion of the previously generated trajectory based on the features of each of the one or more POIs for the selected segment, in real-time, wherein the first level trajectory comprises a velocity-acceleration plan that acts as a threshold velocity and a threshold acceleration set for the autonomous vehicles and wherein the first level trajectory is generated for the selected segment when the autonomous vehicle is navigating through the previously generated trajectory for the previous segment; acquiring, by the trajectory generating system, real-time environment data indicating a real-time situation along the selected segment; determining, by the trajectory generating system, one or more portions of the first level trajectory which is visible for Field Of View (FOV) of one or more sensors associated with the autonomous vehicle; generating, by the trajectory generating system, a second level trajectory for the one or more portions of the first level trajectory beginning from the current position of the autonomous vehicle, by modifying each of the one or more portions of the first level trajectory based on the real-time environment data; and transmitting, by the trajectory generating system, the second level trajectory to a navigation module associated with the trajectory generating system to determine a command velocity for navigating the autonomous vehicle. ### Claim 2 (depends on 1) The method as claimed in claim 1, wherein the first level trajectory is generated by mapping the features of each of the one or more POIs with a pretrained decision tree. ### Claim 3 (depends on 1) The method as claimed in claim 1, wherein an end portion of the first level trajectory is extended based on one or more locations of the one or more POIs when the second level trajectory is being generated in front of the autonomous vehicle, wherein an extended segment of the first level trajectory is a subsequent first level trajectory on the pre-generated navigation path. ### Claim 4 (depends on 1) The method as claimed in claim 1, wherein the one or more POIs are detected using a map database associated with the trajectory generating system, comprising a plurality of annotated vectors related to infrastructure information. ### Claim 5 (depends on 1) The method as claimed in claim 1, wherein the one or more POIs comprise at least one of sign boards, symbols and images related to infrastructure information along the pre-generated navigation path. ### Claim 6 (depends on 1) The method as claimed in claim 1, wherein the priority value is directly proportional to the impact of the one or more POIs on the navigation of the autonomous vehicle. ### Claim 7 (depends on 1) The method as claimed in claim 1, wherein the priority value is pre-determined based on the impact of the one or more POIs on the navigation of the autonomous vehicle, and the one or more parameter values are determined using a map database associated with the trajectory generating system. ### Claim 8 (depends on 1) The method as claimed in claim 1, wherein each of the one or more POIs is associated with corresponding one or more parameters. ### Claim 9 (depends on 1) The method as claimed in claim 1, wherein the second level trajectory is generated by modifying the velocity-acceleration plan of the first level trajectory based on the real-time environment data in such a way that a velocity and an acceleration of the second level trajectory do not exceed the threshold velocity and the threshold acceleration of the first level trajectory, respectively. ### Claim 10 A trajectory generating system for generating a trajectory for navigating an autonomous vehicle, the trajectory generating system comprising: a processor; and a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, cause the processor to: detect one or more Points of Interest (POIs) for a selected segment, on a pre-generated navigation path, in real-time, wherein the selected segment is at a predefined distance from a current position of the autonomous vehicle, and wherein the pre-generated navigation path is generated based on a source point and a destination point; determine an impact of the one or more POIs on navigation of the autonomous vehicle; determine features of each of the one or more POIs based on the impact of the one or more POIs on the navigation of the autonomous vehicle, wherein the features comprise at least one of one or more parameter values and a priority value corresponding to the one or more parameter values; detect a previous segment prior to the selected segment, wherein the previous segment has a previously generated trajectory; generate a first level trajectory for the selected segment at an end portion of the previously generated trajectory based on the features of each of the one or more POIs for the selected segment, in real-time, wherein the first level trajectory comprises a velocity-acceleration plan that acts as a threshold velocity and a threshold acceleration set for the autonomous vehicle, and wherein the first level trajectory is generated for the selected segment when the autonomous vehicle is navigating through the previously generated trajectory for the previous segment; acquire real-time environment data indicating a real-time situation along the selected segment; determine one or more portions of the first level trajectory which is visible for Field Of View (FOV) of one or more sensors associated with the autonomous vehicle; generate a second level trajectory for one or more portions of the first level trajectory beginning from the current position of the autonomous vehicle, by modifying each of the one or more portions of the first level trajectory based on the real-time environment data; and transmit the second level trajectory to a navigation module associated with the trajectory generating system to determine a command velocity for navigating the autonomous vehicle. ### Claim 11 (depends on 10) The trajectory generating system as claimed in claim 10, wherein the processor generates the first level trajectory by mapping the features of each of the one or more POIs with a pretrained decision tree. ### Claim 12 (depends on 10) The trajectory generating system as claimed in claim 10, wherein the processor extends an end portion of the first level trajectory based on one or more locations of the one or more POIs when the second level trajectory is being generated in front of the autonomous vehicle, wherein an extended segment of the first level trajectory is a subsequent first level trajectory on the pre-generated navigation path. ### Claim 13 (depends on 10) The trajectory generating system as claimed in claim 10, wherein the processor detects the one or more POIs using a map database associated with the trajectory generating system, comprising a plurality of annotated vectors related to infrastructure information. ### Claim 14 (depends on 10) The trajectory generating system as claimed in claim 10, wherein the one or more POIs comprise at least one of sign boards, symbols and images related to infrastructure information along the pre-generated navigation path. ### Claim 15 (depends on 10) The trajectory generating system as claimed in claim 10, wherein the priority value is directly proportional to the impact of the one or more POIs on the navigation of the autonomous vehicle. ### Claim 16 (depends on 10) The trajectory generating system as claimed in claim 10, wherein the priority value is pre-determined based on the impact of the one or more POIs on the navigation of the autonomous vehicle, and the processor determines the one or more parameter values using a map database associated with the trajectory generating system. ### Claim 17 (depends on 10) The trajectory generating system as claimed in claim 10, wherein each of the one or more POIs is associated with corresponding one or more parameters. ### Claim 18 A non-transitory computer readable medium including instructions stored thereon that when processed by at least one processor cause a trajectory generating system to perform operations comprising: detecting one or more Points of Interest (POIs) for a selected segment, on a pre-generated navigation path, in real-time, wherein the selected segment is at a predefined distance from a current position of an autonomous vehicle, and wherein the pre-generated navigation path is generated based on a source point and a destination point; determining an impact of the one or more POIs on navigation of the autonomous vehicle; determining features of each of the one or more POIs based on the impact of the one or more POIs on the navigation of the autonomous vehicle, wherein the features comprise at least one of one or more parameter values and a priority value corresponding to the one or more parameter values; detecting a previous segment prior to the selected segment, wherein the previous segment has a previously generated trajectory; generating a first level trajectory for the selected segment at an end portion of the previously generated trajectory based on the features of each of the one or more POIs for the selected segment, in real-time, wherein the first level trajectory comprises a velocity-acceleration plan that acts as a threshold velocity and a threshold acceleration set for the autonomous vehicle, and wherein the first level trajectory is generated for the selected segment when the autonomous vehicle is navigating through the previously generated trajectory for the previous segment; acquiring real-time environment data indicating a real-time situation along the selected segment; determining one or more portions of the first level trajectory which is visible for Field Of View (FOV) of one or more sensors associated with the autonomous vehicle; generating a second level trajectory for one or more portions of the first level trajectory beginning from the current position of the autonomous vehicle, by modifying each of the one or more portions of the first level trajectory based on the real-time environment data; and transmitting the second level trajectory to a navigation module associated with the trajectory generating system to determine a command velocity for navigating the autonomous vehicle.