Granted Patent B2

US 12,594,961 · App. 18/654,579 · Granted Apr 7, 2026

Inventors: Stuart Fairley (Ann Arbor, MI); Asheesh Ranjan (Ann Arbor, MI); Melinda Kothbauer (Ann Arbor, MI); Sajan Patel (Ann Arbor, MI); Tom Voorheis (Ann Arbor, MI); Jeff Sterniak (Ann Arbor, MI); Edwin B. Olson (Ann Arbor, MI)

Assignee: May Mobility, Inc.

B60W60/0011G06N20/00G06V20/56B60W2420/403B60W2420/408

Abstract

Claims (41)

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.

2 . 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.

3 . 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.

4 . 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.

5 . The system of claim 3 , wherein the set of inputs further comprises a set of human operator inputs.

6 . 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.

7 . 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.

8 . The system of claim 7 , wherein the characterized state is associated with a health status of one or more subsystems of the autonomous vehicle.

9 . 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.

10 . 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.

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.

12 . 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.

13 . 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.

14 . 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.

15 . The method of claim 11 , further comprising refining the set of electable policies based on a set of situational information.

16 . 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.

17 . 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.

18 . 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.

19 . 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.

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.

Assignments (2)

Continuity (6)

References Cited (318)