# US 2020/0401147 A1 · Methods and Systems for Autonomous Vehicle Motion Deviation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401147 A1 - Document ID: US20200401147A1 - Status: Published application - Kind: A1 - Application number: 16/654,469 - Filed: 2019-10-16 - Published: 2020-12-24 - Earliest claimed: 2019-06-21 - Assignees: Uatc, LLC - Applicants: Uatc, LLC - Inventors: Edward Henry Lim; Eric Michael Perko - Web page: https://patentgrep.com/patent/US20200401147A1 ## CPC - G05D 1/0214: {in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13)} - B60W 30/18163: {Lane change; Overtaking manoeuvres} - B60W 60/0011: {involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles} - B60W 60/0015: {specially adapted for safety} - G05D 1/0088: {characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00)} - G08G 1/167: {Driving aids for lane monitoring, lane changing, e.g. blind spot detection} - B60W 2520/10: Longitudinal speed - B60W 2554/20: Static objects - B60W 2554/4026: Cycles - B60W 2554/4029: Pedestrians - B60W 2554/4041: Position - B60W 2555/60: Traffic rules, e.g. speed limits or right of way - G05D 1/0276: {using signals provided by a source external to the vehicle (involving a plurality of vehicles G05D1/0287; automatically controlling vehicle speed responsive to externally generated signals B60K31/0058)} - 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 - 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 The present disclosure is directed to deviating from a planned path for an autonomous vehicle. In particular, a computing system comprising one or more computing devices physically located onboard an autonomous vehicle can identify one or more boundaries at least in part defining a lane in which the autonomous vehicle is traveling along a path of a planned route. Responsive to identifying one or more obstructions ahead of the autonomous vehicle along the path, the computing system can: determine one or more deviations from the path that would result in the autonomous vehicle avoiding the obstruction(s) and at least partially crossing at least one of the one or more boundaries; and generate, based at least in part on the deviation(s), a motion plan instructing the autonomous vehicle to deviate from the path such that it avoids the obstruction(s) and continues traveling along the planned route. ## Claims ### Claim 1 A computer-implemented method for autonomous vehicle control, the method comprising: identifying, by a computing system comprising one or more computing devices, one or more boundaries at least in part defining a lane in which an autonomous vehicle is traveling along a path of a planned route; and responsive to identifying, by the computing system, one or more obstructions ahead of the autonomous vehicle along the path: determining, by the computing system, one or more deviations from the path that would result in the autonomous vehicle avoiding the one or more obstructions and at least partially crossing at least one of the one or more boundaries; generating, by the computing system and based at least in part on the one or more deviations, a motion plan comprising a location plan and a velocity plan for the autonomous vehicle, the motion plan instructing the autonomous vehicle to deviate from the path by instructing the autonomous vehicle to avoid the one or more obstructions, to cross at least partially the at least one of the one or more boundaries, and to continue traveling along the planned route; determining, by the computing system, whether one or more safety conditions that evaluate characteristics of the motion plan or an environment in which the autonomous vehicle is travelling are satisfied; and responsive to determining that the one or more safety conditions are satisfied, causing, by the computing system, the autonomous vehicle to execute the motion plan to avoid the one or more obstructions. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, comprising: responsive to determining that the one or more safety conditions are not satisfied, causing, by the computing system, the autonomous vehicle to execute an alternative motion plan instructing the autonomous vehicle to remain within the one or more boundaries at least in part defining the lane in which the autonomous vehicle is travelling. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the one or more safety conditions require one or more of: an absence of actors in an adjacent lane in which traffic travels in an opposing direction from traffic in the lane in which the autonomous vehicle is traveling; an absence of actors in one or more driveways providing entry to a travelway including the lane; a minimum visibility distance in front of the autonomous vehicle; the motion plan to include complete re-entry of the autonomous vehicle into the lane within a threshold period of time following the autonomous vehicle at least partially crossing the at least one of the one or more boundaries; an absence of pedestrians or bicyclists in the travelway including the lane; the motion plan to include a minimum amount of signal time in which a turn signal of the autonomous vehicle can be operated prior to the autonomous vehicle at least partially crossing the at least one of the one or more boundaries; and the motion plan to maintain the autonomous vehicle at greater than a minimum velocity throughout the motion plan. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the one or more deviations would result in only a limited portion of the autonomous vehicle crossing the at least one of the one or more boundaries. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the one or more deviations would result in the autonomous vehicle in its entirety crossing the at least one of the one or more boundaries. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the at least one of the one or more boundaries delineates the lane in which the autonomous vehicle is traveling from: an adjacent shoulder of a travelway including the lane; an adjacent lane in which traffic travels in a common direction with traffic in the lane in which the autonomous vehicle is traveling; or an adjacent lane in which traffic travels in an opposing direction from traffic in the lane in which the autonomous vehicle is traveling. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein determining the one or more deviations comprises determining the one or more deviations provide a minimum clearance distance between the autonomous vehicle and the one or more obstructions. ### Claim 8 (depends on 7) The computer-implemented method of claim 7, comprising determining, by the computing system and based at least in part on a current speed of the autonomous vehicle, the minimum clearance distance between the autonomous vehicle and the one or more obstructions. ### Claim 9 (depends on 7) The computer-implemented method of claim 7, comprising: determining, by the computing system, a classification for at least one of the one or more obstructions; and determining, by the computing system and based at least in part on the classification, the minimum clearance distance between the autonomous vehicle and the one or more obstructions. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein determining the one or more deviations comprises: determining a plurality of different alternative deviations that would each result in the autonomous vehicle avoiding the one or more obstructions and at least partially crossing at least one of the one or more boundaries; and selecting, from amongst the plurality of different alternative deviations and based at least in part on predetermined logic for selecting amongst available alternative deviations, the one or more deviations. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, wherein: the method comprises determining, by the computing system, a classification for at least one of the one or more obstructions; and selecting the one or more deviations comprises selecting the one or more deviations based at least in part on the classification. ### Claim 12 (depends on 10) The computer-implemented method of claim 10, wherein: the method comprises, for each deviation of the plurality of different alternative deviations, determining, by the computing system and in accordance with a predetermined cost function, a total cost associated with the deviation; and selecting the one or more deviations comprises selecting the one or more deviations based at least in part on one or more of their respective associated total costs determined in accordance with the predetermined cost function. ### Claim 13 (depends on 1) The computer-implemented method of claim 1, wherein determining the one or more deviations comprises determining the one or more deviations would not result in the autonomous vehicle crossing the at least one of the one or more boundaries by more than a threshold distance. ### Claim 14 (depends on 13) The computer-implemented method of claim 13, comprising: determining, by the computing system, a classification for at least one of the one or more obstructions; and determining, by the computing system and based at least in part on the classification, the threshold distance. ### Claim 15 (depends on 1) The computer-implemented method of claim 1, wherein determining the one or more deviations comprises determining at least one deviation that would result in the autonomous vehicle at least partially crossing the at least one of the one or more boundaries such that one or more sensors of the autonomous vehicle can generate data representing a scene otherwise at least partially occluded by at least one of the one or more obstructions. ### Claim 16 (depends on 1) The computer-implemented method of claim 1, wherein the one or more obstructions comprise one or more of: a stationary inanimate object in the lane; a stationary vehicle in the lane; a cyclist in the lane; a pedestrian in the lane; or a travelway-surface condition of at least a portion of the lane. ### Claim 17 (depends on 1) The computer-implemented method of claim 1, comprising: determining, by the computing system, a geometric planning problem associated with the autonomous vehicle traveling along the path; and determining, by the computing system and based at least in part on the one or more deviations, at least one boundary constraint of the geometric planning problem. ### Claim 18 (depends on 1) The computer-implemented method of claim 1, comprising: determining, by the computing system, a location of the autonomous vehicle on the planned route; and determining, by the computing system and based at least in part on one or more preconfigured rules, that the one or more deviations are permissible at the location. ### Claim 19 An autonomous vehicle comprising: one or more processors; and a memory storing instructions that when executed by the one or more processors cause the autonomous vehicle to perform operations comprising: identifying one or more obstructions ahead of the autonomous vehicle along a path of a planned route; and responsive to identifying the one or more obstructions: determining one or more deviations from the path that would result in the autonomous vehicle avoiding the one or more obstructions and at least partially crossing at least one of one or more boundaries defining a lane in which the autonomous vehicle is traveling along the path; generating, based at least in part on the one or more deviations, a motion plan instructing the autonomous vehicle to deviate from the path such that it avoids the one or more obstructions, at least partially crosses the at least one of the one or more boundaries, and continues traveling along the planned route; evaluating one or more safety conditions that evaluate characteristics of the motion plan or an environment in which the autonomous vehicle is travelling; and when the one or more safety conditions are satisfied, executing the motion plan. ### Claim 20 One or more non-transitory computer-readable media comprising instructions that when executed by a computing system comprising one or more computing devices physically located onboard an autonomous vehicle cause the computing system to perform operations comprising: identifying one or more obstructions ahead of the autonomous vehicle; and responsive to identifying the one or more obstructions: determining one or more deviations, from a planned path of the autonomous vehicle, that would result in the autonomous vehicle avoiding the one or more obstructions and at least partially crossing at least one of one or more boundaries defining a lane in which the autonomous vehicle is traveling along the planned path; evaluating one or more safety conditions that evaluate characteristics of the one or more deviations or an environment in which the autonomous vehicle is travelling; and when the one or more safety conditions are satisfied, executing one of the one or more deviations.