# US 2022/0026910 A1 · Initial Trajectory Generator for Motion Planning System of Autonomous Vehicles

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0026910 A1
- Document ID: US20220026910A1
- Status: Published application
- Kind: A1
- Application number: 17/498,378
- Filed: 2021-10-11
- Published: 2022-01-27
- Earliest claimed: 2018-05-11
- Assignees: Uatc, LLC
- Applicants: Uatc, LLC
- Inventors: Chenggang Liu; Moslem Kazemi; David McAllister Bradley; Tianyu Gu; Michael Lee Phillips
- Web page: https://patentgrep.com/patent/US20220026910A1

## CPC

- B60W 60/0011: {involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles}
- B60W 60/0027: {using trajectory prediction for other traffic participants}
- B60W 60/00276: {for two or more other traffic participants}
- G01C 21/3461: {Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types or segments such as motorways, toll roads or ferries}
- G05D 1/0217: {in accordance with energy consumption, time reduction or distance reduction criteria}
- B60W 2552/53: Road markings, e.g. lane marker or crosswalk
- B60W 2554/20: Static objects
- B60W 2554/4026: Cycles
- B60W 2554/4029: Pedestrians
- B60W 2720/103: Speed profile
- 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)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES

## Abstract

Generally, the present disclosure is directed to systems and methods that include or otherwise leverage an iterative solver as part of optimizing a motion plan for an autonomous vehicle (AV). In particular, a scenario generator within a motion planning system can include a warm start generator configured to determine an initial trajectory that respects the dynamics of the autonomous vehicle and that closely tracks a speed profile determined by a constraint solver and one or more nominal paths determined by a route selector. A decision validator can analyze speed profiles and nominal paths to identify potential inconsistencies and validate a decision before optimization and execution. An initial trajectory can be further optimized by an iterative solver to determine an optimized trajectory for execution as a motion plan for the autonomous vehicle.

## Claims

### Claim at position 1

-20. (canceled)

### Claim 21

An autonomous vehicle control system for an autonomous vehicle, the autonomous vehicle control system comprising:
an initial trajectory generator configured to determine an initial trajectory that includes location and speed information over time for travel of the autonomous vehicle along one or more nominal paths;
wherein the one or more nominal paths comprise one or more predetermined potential paths for travel of the autonomous vehicle based on a common pattern of vehicle travel along one or more lanes of a roadway;
an optimization planner configured to determine an optimized trajectory based at least in part on the initial trajectory; and
a vehicle controller configured to control motion of the autonomous vehicle based at least in part on the optimized trajectory.

### Claim 22 (depends on 21)

An autonomous vehicle control system as in claim 21, wherein the optimization planner comprises an iterative solver configured to identify a motion plan that optimizes a total cost associated with the motion plan.

### Claim 23 (depends on 22)

An autonomous vehicle control system as in claim 22, wherein the iterative solver comprises a gain controller configured to determine one or more gains associated with a lateral command and one or more gains associated with a longitudinal command.

### Claim 24 (depends on 21)

An autonomous vehicle control system as in claim 21, wherein the initial trajectory generator is configured to determine a validation parameter by evaluating the initial trajectory relative to a dynamics equation for the autonomous vehicle for evaluating whether the initial trajectory is implementable by the autonomous vehicle.

### Claim 25 (depends on 24)

An autonomous vehicle control system as in claim 24, wherein the optimization planner is configured to determine the optimized trajectory after the validation parameter is determined to meet one or more predetermined validation criteria.

### Claim 26 (depends on 25)

An autonomous vehicle control system as in claim 25, wherein the initial trajectory generator is configured to transmit a notification signal when the validation parameter is determined to not meet the one or more predetermined validation criteria.

### Claim 27 (depends on 21)

An autonomous vehicle control system as in claim 21, wherein the initial trajectory generator is configured to generate the initial trajectory by translating a current driving speed and a current steering angle of the autonomous vehicle forward in time.

### Claim 28 (depends on 21)

An autonomous vehicle control system as in claim 21, comprising a constraint solver configured to:
generate a constraint for one or more objects of interest having a predetermined manner of interaction with the one or more nominal paths; and
determine a plurality of speed profiles for a corresponding plurality of candidate maneuvers for implementation by the autonomous vehicle, wherein at least one of the plurality of speed profiles is determined to satisfy the plurality of constraints associated with travel by the autonomous vehicle.

### Claim 29 (depends on 28)

An autonomous vehicle control system as in claim 28, wherein the one or more objects of interest comprise at least one of: (i) a vehicle, (ii) a pedestrian, (iii) a bicycle, (iv) a traffic light, (v) a stop sign, (vi) a crosswalk, or (vii) a speed zone.

### Claim 30

A method, comprising:
determining an initial trajectory that includes location and speed information over time for travel of an autonomous vehicle along one or more nominal paths;
wherein the one or more nominal paths comprise one or more predetermined potential paths for travel of the autonomous vehicle based on a common pattern of vehicle travel along one or more lanes of a roadway;
determining an optimized trajectory based at least in part on the initial trajectory, wherein the optimized trajectory is iteratively determined to identify a motion plan that optimizes a total cost associated with the motion plan; and
controlling motion of the autonomous vehicle based at least in part on the optimized trajectory.

### Claim 31 (depends on 30)

A method as in claim 30, wherein determining the optimized trajectory comprises determining one or more gains associated with a lateral command and one or more gains associated with a longitudinal command.

### Claim 32 (depends on 30)

A method as in claim 30, further comprising determining a validation parameter by evaluating the initial trajectory relative to a dynamics equation for the autonomous vehicle for evaluating whether the initial trajectory is implementable by the autonomous vehicle, and wherein determining the optimized trajectory is implemented after the validation parameter is determined to meet one or more predetermined validation criteria.

### Claim 33 (depends on 30)

A method as in claim 30, wherein determining an initial trajectory comprises translating a current driving speed and a current steering angle of the autonomous vehicle forward in time as the initial trajectory.

### Claim 34 (depends on 30)

A method as in claim 30, comprising:
generating a constraint for one or more objects of interest having a predetermined manner of interaction with the one or more nominal paths, wherein the one or more objects of interest comprise at least one of: (i) a vehicle, (ii) a pedestrian, (iii) a bicycle, (iv) a traffic light, (v) a stop sign, (vi) a crosswalk, or (vii) a speed zone; and
determining a plurality of speed profiles for a corresponding plurality of candidate maneuvers for implementation by the autonomous vehicle, wherein at least one of the plurality of speed profiles is determined to satisfy the plurality of constraints associated with travel by the autonomous vehicle.

### Claim 35 (depends on 34)

A method as in claim 34, comprising:
determining a selected maneuver from the plurality of candidate maneuvers, the selected maneuver being associated with the one or more nominal paths for travel, and the initial trajectory being based on a selected maneuver and a speed profile associated with the selected maneuver.

### Claim 36 (depends on 35)

A method as in claim 35, wherein determining the selected maneuver comprises:
generating a score for at least one candidate maneuver in the plurality of candidate maneuvers, wherein the score is determined based on one or more costs, discounts or rewards associated with aspects of a candidate maneuver; and
determining the selected maneuver from the plurality of candidate maneuvers based at least in part on the score for the at least one candidate maneuver in the plurality of candidate maneuvers.

### Claim 37

An autonomous vehicle, comprising:
one or more processors; and
one or more non-transitory computer-readable media that store instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, the operations comprising:
determining an initial trajectory that includes location and speed information over time for travel of an autonomous vehicle along one or more nominal paths;
wherein the one or more nominal paths comprise one or more predetermined potential paths for travel of the autonomous vehicle based on a common pattern of vehicle travel along one or more lanes of a roadway;
determining an optimized trajectory based at least in part on the initial trajectory, wherein the optimized trajectory is determined by an iterative solver configured to identify a motion plan that optimizes a total cost associated with the motion plan; and
controlling motion of the autonomous vehicle based at least in part on the optimized trajectory.

### Claim 38 (depends on 37)

An autonomous vehicle as in claim 37, wherein determining an initial trajectory comprises translating a current driving speed and a current steering angle of the autonomous vehicle forward in time as the initial trajectory.

### Claim 39 (depends on 37)

An autonomous vehicle as in claim 37, wherein determining the optimized trajectory comprises determining one or more gains associated with a lateral command and one or more gains associated with a longitudinal command.

### Claim 40 (depends on 37)

An autonomous vehicle as in claim 37, the operations comprising:
generating a constraint for one or more objects of interest having a predetermined manner of interaction with the one or more nominal paths;
determining a plurality of speed profiles for a corresponding plurality of candidate maneuvers for implementation by the autonomous vehicle; and
determining a selected maneuver from the plurality of candidate maneuvers, the selected maneuver being associated with the one or more nominal paths for travel, and the initial trajectory being based on a selected maneuver and a speed profile associated with the selected maneuver.
