# US 2023/0399026 A1 · State Identification For Road Actors With Uncertain Measurements Based On Compliant Priors

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

- Number: US 2023/0399026 A1
- Document ID: US20230399026A1
- Status: Published application
- Kind: A1
- Application number: 17/835,824
- Filed: 2022-06-08
- Published: 2023-12-14
- Earliest claimed: 2022-06-08
- Assignees: Ford Global Technologies, LLC
- Applicants: Ford Global Technologies, LLC
- Inventors: Randall SCHUR; Alexander METZ; Kevin WYFFELS
- Web page: https://patentgrep.com/patent/US20230399026A1

## CPC

- B60W 60/0027: {using trajectory prediction for other traffic participants}
- B60W 40/04: Traffic conditions
- B60W 2554/4041: Position
- B60W 2554/4042: Longitudinal speed
- B60W 2555/60: Traffic rules, e.g. speed limits or right of way
- B60W 2556/40: High definition maps
- 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

Disclosed herein are system, method, and computer program product embodiments for state identification for road actors with uncertain measurements based on compliant priors. The perception system of an autonomous vehicle (AV) may detect an object with an uncertain kinematic state based on sensor information received from a sensing device associated with the AV. A first, second, and third distribution of velocity values may be generated based on the sensor information, map information, and a kinematic state for each additional object of a plurality of additional objects in proximity to the detected object with the uncertain kinematic state, respectively. A velocity value for the detected object with the uncertain kinematic state may be generated based on a comparison of the first, second, and third distributions of velocity values. The AV may perform a driving maneuver based on the velocity value for the detected object.

## Claims

### Claim 1

A method comprising:
detecting, based on sensor information received from a sensing device associated with a vehicle, an object with an uncertain kinematic state;
generating, based on the sensor information, a first distribution of velocity values;
generating, based on map information, a second distribution of velocity values;
generating, based on a kinematic state for each additional object of a plurality of additional objects in proximity to the detected object, a third distribution of velocity values;
generating a velocity value for the object, the velocity value being based on a comparison of the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values; and
performing, based on the velocity value for the detected object, a driving maneuver.

### Claim 2 (depends on 1)

The method of claim 1, wherein the generating the first distribution of velocity values comprises:
in response to the uncertain kinematic state of the detected object, extracting from the sensor information, an indication of position for the detected object and an indication of velocity for the detected object;
generating, based on the indicated position and the indicated velocity, a trajectory for the detected object; and
identifying, from the trajectory for the detected object, the first distribution of velocity values.

### Claim 3 (depends on 1)

The method of claim 1, wherein the map information indicates at least one of a speed limit for a route or an instruction for the route, wherein the generating the second distribution of velocity values comprises:
identifying that the detected object is located on the route; and
generating, based on an assumption that the detected object will move along the route during a time window and at least one of the speed limit for the route or the instruction for the route, the second distribution of velocity values.

### Claim 4 (depends on 1)

The method of claim 1, wherein the generating the third distribution of velocity values comprises:
detecting, based on the sensor information, the plurality of additional objects;
removing, from the plurality of additional objects, any additional object with a respective uncertain kinematic state;
removing, from remaining additional objects of the plurality of additional objects, any objects that comprise at least one of a stationary state or an object type that is different from an object type of the object; and
generating, based on a respective velocity indicated for each additional object of the remaining additional objects, the third distribution of velocity values.

### Claim 5 (depends on 1)

The method of claim 1, wherein the proximity to the detected object comprises at least one of a spatial proximity or a temporal proximity.

### Claim 6 (depends on 1)

The method of claim 1, wherein the comparison of the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values comprises evaluating an amount of statistical uncertainty associated with each of the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values.

### Claim 7 (depends on 1)

The method of claim 1, wherein the uncertain kinematic state of the detected object is based on at least one of: oversegmentation associated with the sensor information, false information associated with the sensor information, occlusion of the detected object, or an amount of geometric features of the detected object.

### Claim 8

A computing system comprising:
a memory of a vehicle configured to store instructions;
a processor of the vehicle, coupled to the memory, configured to process the stored instructions to:
detect, based on sensor information received from a sensing device associated with the vehicle, an object with an uncertain kinematic state;
generate, based on the sensor information, a first distribution of velocity values;
generate, based on map information, a second distribution of velocity values;
generate, based on a kinematic state for each additional object of a plurality of additional objects in proximity to the detected object, a third distribution of velocity values;
generate a velocity value for the object, the velocity value being based on a comparison of the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values; and
perform, based on the velocity value for the detected object, a driving maneuver.

### Claim 9 (depends on 8)

The system of claim 8, wherein the processor configured to generate the first distribution of velocity values is further configured to:
in response to the uncertain kinematic state of the detected object, extract from the sensor information, an indication of position for the detected object and an indication of velocity for the detected object;
generate, based on the indicated position and the indicated velocity, a trajectory for the detected object; and
identify, from the trajectory for the detected object, the first distribution of velocity values.

### Claim 10 (depends on 8)

The system of claim 8, wherein the map information indicates at least one of a speed limit for a route or an instruction for the route, wherein the processor configured to generate the second distribution of velocity values is further configured to:
identify that the detected object is located on the route; and
generate, based on an assumption that the detected object will move along the route during a time window and at least one of the speed limit for the route or the instruction for the route, the second distribution of velocity values.

### Claim 11 (depends on 8)

The system of claim 8, wherein the processor configured to generate the third distribution of velocity values is further configured to:
detect, based on the sensor information, the plurality of additional objects;
remove, from the plurality of additional objects, any additional object with a respective uncertain kinematic state;
remove, from remaining additional objects of the plurality of additional objects, any objects that comprise at least one of a stationary state or an object type that is different from an object type of the object; and
generate, based on a respective velocity indicated for each additional object of the remaining additional objects, the third distribution of velocity values.

### Claim 12 (depends on 8)

The system of claim 8, wherein the proximity to the detected object comprises at least one of a spatial proximity or a temporal proximity.

### Claim 13 (depends on 8)

The system of claim 8, wherein the processor configured to compare the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values is further configured to evaluate an amount of statistical uncertainty associated with each of the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values.

### Claim 14 (depends on 8)

The system of claim 8, wherein the uncertain kinematic state of the detected object is based on at least one of: oversegmentation associated with the sensor information, false information associated with the sensor information, occlusion of the detected object, or an amount of geometric features of the detected object.

### Claim 15

A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
detecting, based on sensor information received from a sensing device associated with a vehicle, an object with an uncertain kinematic state;
generating, based on the sensor information, a first distribution of velocity values;
generating, based on map information, a second distribution of velocity values;
generate, based on a kinematic state for each additional object of a plurality of additional objects in proximity to the detected object, a third distribution of velocity values;
generate a velocity value for the object, the velocity value being based on a comparison of the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values; and
performing, based on the velocity value for the detected object, a driving maneuver.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the generating the first distribution of velocity values comprises:
in response to the uncertain kinematic state of the detected object, extracting from the sensor information, an indication of position for the detected object and an indication of velocity for the detected object;
generating, based on the indicated position and the indicated velocity, a trajectory for the detected object; and
identifying, from the trajectory for the detected object, the first distribution of velocity values.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the map information indicates at least one of a speed limit for a route or an instruction for the route, wherein the generating the second distribution of velocity values comprises:
identifying that the detected object is located on the route; and
generating, based on an assumption that the detected object will move along the route during a time window and at least one of the speed limit for the route or the instruction for the route, the second distribution of velocity values.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the generating the third distribution of velocity values comprises:
detecting, based on the sensor information, the plurality of additional objects;
removing, from the plurality of additional objects, any additional object with a respective uncertain kinematic state;
removing, from remaining additional objects of the plurality of additional objects, any objects that comprise at least one of a stationary state or an object type that is different from an object type of the object; and
generating, based on a respective velocity indicated for each additional object of the remaining additional objects, the third distribution of velocity values.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the proximity to the detected object comprises at least one of a spatial proximity or a temporal proximity.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the comparison of the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values comprises evaluating an amount of statistical uncertainty associated with each of the first distribution of velocity values, the second distribution of velocity values, and the third distribution of velocity values.
