# US 12,594,961 B2 · Method and system for dynamically curating autonomous vehicle policies > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,594,961 B2 - Document ID: US12594961B2 - Status: Granted - Kind: B2 - Application number: 18/654,579 - Filed: 2024-05-03 - Published: 2024-08-29 - Granted: 2026-04-07 - Earliest claimed: 2020-07-01 - Assignees: May Mobility, Inc. - Applicants: May Mobility, Inc. - Inventors: Stuart Fairley; Asheesh Ranjan; Melinda Kothbauer; Sajan Patel; Tom Voorheis; Jeff Sterniak; Edwin B. Olson - Web page: https://patentgrep.com/patent/US12594961B2 ## CPC - B60W 60/0011: {involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles} - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 20/00: Machine learning - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G06V 20/582: {of traffic signs} - G08G 1/0112: {from the vehicle, e.g. floating car data [FCD]} - G08G 1/0116: {from roadside infrastructure, e.g. beacons} - B60W 2420/403: Image sensing, e.g. optical camera - B60W 2420/408: Radar; Laser, e.g. lidar - G06N 3/04: Architecture, e.g. interconnection topology - 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 - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - 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 A system for dynamic policy curation includes a computing system and interfaces with an autonomous agent. A method for dynamic policy curation includes collecting a set of inputs; processing the set of inputs; and determining a set of available policies based on processing the set of inputs. Additionally or alternatively, the method can include any or all of: selecting a policy; implementing a policy; and/or any other suitable processes. ## Claims ### Claim 1 A system for controlling an autonomous vehicle, the system comprising: a computing subsystem of an autonomous vehicle, wherein the computing subsystem: determines a set of position data for the autonomous vehicle; retrieves a set of autonomous vehicle policies from a set of candidate autonomous vehicle policies based on the set of position data, wherein retrieving the set of autonomous vehicle policies comprises mapping the set of position data to a set of available autonomous vehicle policies associated with a bound region defined in a map; and selects an autonomous vehicle policy from the set of autonomous vehicle policies by evaluating each of the set of autonomous vehicle policies; and a control subsystem, wherein the control subsystem controls a movement of the autonomous vehicle according to the selected autonomous vehicle policy. ### Claim 2 (depends on 1) The system of claim 1, wherein evaluating each of the set of autonomous vehicle policies comprises determining a score for each of the autonomous vehicle policies. ### Claim 3 (depends on 1) The system of claim 1, wherein retrieving the set of autonomous vehicle policies comprises weighting each of a set of inputs, the set of inputs comprising: the set of position data, a set of sensor data, and a set of rules. ### Claim 4 (depends on 3) The system of claim 3, wherein the set of rules comprises the map, the map defining a plurality of sets of policies available within each of a plurality of separate map regions. ### Claim 5 (depends on 3) The system of claim 3, wherein the set of inputs further comprises a set of human operator inputs. ### Claim 6 (depends on 1) The system of claim 1, wherein retrieving the set of autonomous vehicle policies comprises: determining a first set of autonomous vehicle policies from the set of candidate autonomous vehicle policies; and refining the first set of autonomous vehicle policies based on a set of supplementary data sources. ### Claim 7 (depends on 1) The system of claim 1, wherein the computing subsystem is further configured to characterize a state of the autonomous vehicle, wherein retrieving the set of autonomous vehicle policies is further based on the characterized state. ### Claim 8 (depends on 7) The system of claim 7, wherein the characterized state is associated with a health status of one or more subsystems of the autonomous vehicle. ### Claim 9 (depends on 1) The system of claim 1, wherein the computing subsystem is further configured to reduce a number of autonomous vehicle policies contained within the set of autonomous vehicle policies based on a restriction in computing resources available to the computing subsystem. ### Claim 10 (depends on 1) The system of claim 1, wherein retrieving the set of autonomous vehicle policies comprises implementing a set of probabilistic methods to predict the set of autonomous vehicle policies based on the set of position data. ### Claim 11 A method for controlling an autonomous vehicle, the method comprising, at an autonomous vehicle computing subsystem: receiving a set of sensor data from a set of sensors onboard the autonomous vehicle; determining a location of the autonomous vehicle; based on the location and a set of maps, determining a set of electable autonomous vehicle policies, wherein the map prescribes multiple sets of policy selection rules; selecting an autonomous vehicle policy from the set of electable autonomous vehicle policies, wherein a control subsystem of the autonomous vehicle maneuvers the vehicle according to the selected autonomous vehicle policy. ### Claim 12 (depends on 11) The method of claim 11, wherein determining the set of electable autonomous vehicle policies comprises, based on the multiple sets of policy selection rules, selecting the set of electable autonomous vehicle policies from a plurality of candidate autonomous vehicle policies available at a database in communication with the autonomous vehicle computing subsystem. ### Claim 13 (depends on 11) The method of claim 11, further comprising: receiving a second set of sensor data; and refining the set of electable autonomous vehicle policies based on the second set of sensor data. ### Claim 14 (depends on 11) The method of claim 11, further comprising characterizing a state of the autonomous vehicle, wherein selecting the set of electable policies is further based on the characterized state. ### Claim 15 (depends on 11) The method of claim 11, further comprising refining the set of electable policies based on a set of situational information. ### Claim 16 (depends on 15) The method of claim 15, wherein the set of situational information comprises at least one of: a time of day, a set of traffic conditions, or a set of weather conditions. ### Claim 17 (depends on 15) The method of claim 15, wherein the set of situational information comprises a confidence associated with one or more of the set of sensors onboard the autonomous vehicle. ### Claim 18 (depends on 11) The method of claim 11, wherein the method is performed at each decision-making step of the autonomous vehicle, continuously along a route traversal of the autonomous vehicle. ### Claim 19 (depends on 11) The method of claim 11, wherein determining the set of electable autonomous vehicle policies is further based on a set of aggregated historical data from a fleet of autonomous vehicles. ### Claim 20 A system for controlling an autonomous vehicle, the system comprising: a computing subsystem of an autonomous vehicle, wherein the computing subsystem: determines a set of position data for the autonomous vehicle; retrieves a set of autonomous vehicle policies from a set of candidate autonomous vehicle policies based on the set of position data, wherein retrieving the set of autonomous vehicle policies comprises weighting each of a set of inputs, the set of inputs comprising: the set of position data; a set of sensor data; and a set of rules, the set of rules comprising a map, the map defining a plurality of sets of policies available within each of a plurality of separate map regions; and selects an autonomous vehicle policy from the set of autonomous vehicle policies by evaluating each of the set of autonomous vehicle policies; and a control subsystem, wherein the control subsystem controls movement of the autonomous vehicle according to the selected autonomous vehicle policy.