# US 12,767,129 B2 · Systems and methods for smooth lane positioning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,767,129 B2 - Document ID: US12767129B2 - Status: Granted - Kind: B2 - Application number: 18/410,073 - Filed: 2024-01-11 - Published: 2025-07-17 - Granted: 2026-10-20 - Earliest claimed: 2024-01-11 - Assignees: TORC Robotics, Inc. - Applicants: Torc Robotics, Inc. - Inventors: Akshay Pai Raikar; Joseph R. Fox-Rabinovitz - Web page: https://patentgrep.com/patent/US12767129B2 ## CPC - B60W 30/12: Lane keeping - B60W 60/001: {Planning or execution of driving tasks} - B60W 2552/53: Road markings, e.g. lane marker or crosswalk - 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 ## Abstract An autonomy computing system for an autonomous vehicle traveling through a lane width irregularity includes at least one memory storing executable instructions defining a lane positioning module and at least one processor. The processor, upon executing the lane positioning module, is configured to: detect the lane width irregularity; select a lane marking to be used as a guide through the lane width irregularity; and maintain a predefined distance from the lane marking through the lane width irregularity. ## Claims ### Claim 1 An autonomy computing system for an autonomous vehicle traveling through a lane width irregularity, the autonomy computing system comprising: at least one memory storing executable instructions defining a lane positioning module; and at least one processor, wherein the at least one processor, upon executing the lane positioning module, is configured to: detect the lane width irregularity; select a lane marking to be used as a guide through the lane width irregularity by selecting the lane marking between a left lane marking and a right lane marking having a lower curvature; and maintain a predefined distance from the lane marking through the lane width irregularity. ### Claim 2 (depends on 1) The autonomy computing system of claim 1, wherein, prior to identifying the lane width irregularity, the lane positioning module maintains a center position between a left lane marking and a right lane marking. ### Claim 3 (depends on 2) The autonomy computing system of claim 2, wherein the at least one processor is further configured to detect the lane width irregularity by: computing curvatures for each of the left lane marking and the right lane marking; and determining a difference between the curvatures exceeds a predetermined threshold. ### Claim 4 (depends on 1) The autonomy computing system of claim 1, wherein the lane marking includes a solid lane marking indicating an outer lane marking of a roadway. ### Claim 5 (depends on 1) The autonomy computing system of claim 1, wherein the at least one processor is further configured to identify the autonomous vehicle has passed the lane width irregularity by detecting a constant lane width. ### Claim 6 (depends on 1) The autonomy computing system of claim 1, wherein the at least one processor is further configured to detect the lane width irregularity by measuring a lane width exceeding a predetermined threshold. ### Claim 7 A method of lane positioning of an autonomous vehicle travelling through a lane width irregularity, the method comprising: detecting the lane width irregularity by: computing curvatures for each of a left lane marking and a right lane marking; and determining a difference between the curvatures exceeds a predetermined threshold; selecting a lane marking to be used as a guide through the lane width irregularity; and maintaining a predefined distance from the lane marking through the lane width irregularity. ### Claim 8 (depends on 7) The method of claim 7 further comprising, prior to identifying the lane width irregularity, maintaining a center position between a left lane marking and a right lane marking. ### Claim 9 (depends on 8) The method of claim 8, wherein selecting the lane marking comprises selecting the lane marking among the left lane marking and the right lane marking having a lower curvature. ### Claim 10 (depends on 7) The method of claim 7, wherein the lane marking includes a solid lane marking indicating an outer lane marking of a roadway. ### Claim 11 (depends on 7) The method of claim 7, further comprising identifying the autonomous vehicle has passed the lane width irregularity by detecting a constant lane width. ### Claim 12 (depends on 7) The method of claim 7, wherein detecting the lane width irregularity comprises measuring a lane width exceeding the predetermined threshold. ### Claim 13 An autonomous vehicle configured to travel on a roadway, the autonomous vehicle comprising: a plurality of sensors configured to detect a first lane marking and a second lane marking on the roadway; at least one memory configured to store executable instructions defining a lane positioning module; at least one processor coupled to the at least one memory and configured, upon executing the executable instructions, to: detect a lane width irregularity based on the first lane marking and the second lane marking; select a lane marking among the first lane marking and the second lane marking to be used as a guide through the lane width irregularity by selecting the lane marking between the first lane marking and the second lane marking having a lower curvature; and maintain a predefined distance from the lane marking throughout the lane width irregularity. ### Claim 14 (depends on 13) The autonomous vehicle of claim 13, wherein, prior to identifying the lane width irregularity, the lane positioning module maintains a center position between the first lane marking and the second lane marking. ### Claim 15 (depends on 14) The autonomous vehicle of claim 14, wherein the at least one processor is further configured to detect the lane width irregularity by: computing curvatures for each of the first lane marking and the second lane marking; and determining a difference between the curvatures exceeds a predetermined threshold. ### Claim 16 (depends on 13) The autonomous vehicle of claim 13, wherein the lane marking includes a solid lane marking indicating an outer lane marking of a roadway. ### Claim 17 (depends on 13) The autonomous vehicle of claim 13, wherein the at least one processor is further configured to identify the autonomous vehicle has passed the lane width irregularity by detecting a constant lane width.