# US 2023/0055066 A1 · Driver command prediction

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

- Number: US 2023/0055066 A1
- Document ID: US20230055066A1
- Status: Published application
- Kind: A1
- Application number: 17/406,729
- Filed: 2021-08-19
- Published: 2023-02-23
- Earliest claimed: 2021-08-19
- Assignees: GM Global Technology Operations LLC
- Applicants: GM Global Technology Operations LLC
- Inventors: Ehsan Asadi; Seyedeh Asal Nahidi; SeyedAlireza Kasaiezadeh Mahabadi; Kausalya Singuru; Bakhtiar B. Litkouhi; Isaac Tabatschnic
- Web page: https://patentgrep.com/patent/US20230055066A1

## CPC

- B60W 50/10: Interpretation of driver requests or demands
- B60W 40/06: Road conditions
- B60W 50/0097: {Predicting future conditions}
- B60W 50/06: Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot
- G05B 13/027: {using neural networks only}
- B60W 2050/0029: {Mathematical model of the driver}
- B60W 2050/0088: {Adaptive recalibration}
- 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
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)

## Abstract

A driver command predictor includes a controller, multiple sensors, and a command prediction unit. The controller is configured to command an adjustment of multiple motion vectors of a vehicle relative to a roadway in response to multiple actual driver commands and multiple future driver commands. The actual driver commands are received at a current time. The future driver commands are received at multiple update times. The update times range from the current time to a future time. The sensors are configured to generate sensor data that determines multiple actual states of the vehicle in response to the motion vectors as commanded. The command prediction unit is configured to generate the future driver commands at the update times in response to a driver model. The driver model operates on the actual driver commands and the actual states to predict the future driver commands at the update times.

## Claims

### Claim 1

A driver command predictor comprising:
a controller configured to command an adjustment of one or more motion vectors of a vehicle relative to a roadway in response to a plurality of actual driver commands and a plurality of future driver commands, wherein the plurality of actual driver commands are received at a current time, the plurality of future driver commands are received at a plurality of update times, and the plurality of update times range from the current time to a future time;
a plurality of sensors configured to generate a plurality of sensor data that determines a plurality of actual states of the vehicle in response to the one or more motion vectors as commanded; and
a command prediction unit configured to generate the plurality of future driver commands at the plurality of update times in response to a driver model, wherein the driver model operates on the plurality of actual driver commands and the plurality of actual states to predict the plurality of future driver commands at the plurality of update times.

### Claim 2 (depends on 1)

The driver command predictor according to claim 1, further comprising:
one or more information devices configured to generate road information, wherein the driver model operates on the road information to generate the plurality of future driver commands at the plurality of update times. 3 The driver command predictor according to claim 1, wherein the driver model is a deep learning model.

### Claim 4 (depends on 3)

The driver command predictor according to claim 3, wherein the deep learning model is configured to generate a plurality of desired states of the vehicle based on the plurality of actual driver commands and a plurality of vehicle dynamic properties.

### Claim 5 (depends on 4)

The driver command predictor according to claim 4, wherein the command prediction unit generates the plurality of future driver commands to conform the plurality of desired states to the plurality of actual states.

### Claim 6 (depends on 1)

The driver command predictor according to claim 1, wherein the command prediction unit is further configured to:
generate a plurality of results by a comparison of the plurality of future driver commands to the plurality of actual driver commands; and
update the driver model based on the plurality of results.

### Claim 7 (depends on 1)

The driver command predictor according to claim 1, wherein the controller treats the plurality of actual driver commands as a plurality of constants between the current time and the future time.

### Claim 8 (depends on 1)

The driver command predictor according to claim 1, wherein the controller comprises:
a driver command interpreter configured to generate a plurality of intermediate commands in response to the plurality of actual driver commands and the plurality of future driver commands; and
a model predictive controller that commands the adjustment of the one or more motion vectors of the vehicle at the plurality of update times in response to the plurality of intermediate commands and the plurality of future driver commands.

### Claim 9 (depends on 1)

The driver command predictor according to claim 1, wherein the future time is in a range of 100 milliseconds to 500 milliseconds after the current time.

### Claim 10

A method for driver command prediction comprising:
commanding an adjustment of one or more motion vectors of a vehicle relative to a roadway in response to a plurality of actual driver commands and a plurality of future driver commands, wherein the plurality of actual driver commands are received by a circuit at a current time;
generating a plurality of sensor data that determines a plurality of actual states of the vehicle in response to the one or more motion vectors as commanded; and
generating the plurality of future driver commands at a plurality of update times in response to a driver model, wherein the plurality of update times range from the current time to a future time, and the driver model operates on the plurality of actual driver commands and the plurality of actual states to predict the plurality of future driver commands at the plurality of update times.

### Claim 11 (depends on 10)

The method according to claim 10, further comprising:
generating road information, wherein the driver model operates on the road information to generate the plurality of future driver commands at the plurality of update times.

### Claim 12 (depends on 10)

The method according to claim 10, wherein the driver model is a deep learning model.

### Claim 13 (depends on 12)

The method according to claim 12, wherein the deep learning model is configured to generate a plurality of desired states of the vehicle based on the plurality of actual driver commands and a plurality of vehicle dynamic properties.

### Claim 14 (depends on 13)

The method according to claim 13, wherein the plurality of future driver commands are generated to conform the plurality of desired states to the plurality of actual states.

### Claim 15 (depends on 10)

The method according to claim 10, further comprising:
generating a plurality of results by a comparison of the plurality of future driver commands to the plurality of actual driver commands; and
updating the driver model based on the plurality of results.

### Claim 16 (depends on 10)

The method according to claim 10, wherein the plurality of actual driver commands are treated as a plurality of constants between the current time and the future time.

### Claim 17

A vehicle comprising:
a plurality of driver controls configured to generate a plurality of actual driver commands; and
a driver command predictor configured to:
command an adjustment of one or more motion vectors of the vehicle relative to a roadway in response to the plurality of actual driver commands and a plurality of future driver commands, wherein the plurality of actual driver commands are received at a current time;
generate a plurality of sensor data that determines a plurality of actual states of the vehicle in response to the one or more motion vectors as commanded; and
generate the plurality of future driver commands at a plurality of update times in response to a driver model, wherein the plurality of update times range from the current time to a future time, and the driver model operates on the plurality of actual driver commands and the plurality of actual states to predict the plurality of future driver commands at the plurality of update times.

### Claim 18 (depends on 17)

The vehicle according to claim 17, wherein the driver command predictor further comprises:
one or more information devices configured to generate road information, wherein the driver model operates on the road information to generate the plurality of future driver commands at the plurality of update times.

### Claim 19 (depends on 18)

The vehicle according to claim 18, wherein:
the driver model is a deep learning model; and
the deep learning model is configured to generate a plurality of desired states of the vehicle based on the plurality of actual driver commands and a plurality of vehicle dynamic properties.

### Claim 20 (depends on 19)

The vehicle according to claim 19, wherein the driver command predictor generates the plurality of future driver commands to conform the plurality of desired states to the plurality of actual states.
