# US 12,005,914 B2 · Method and system for driving condition-agnostic adaptation of advanced driving assistance systems

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

- Number: US 12,005,914 B2
- Document ID: US12005914B2
- Status: Granted
- Kind: B2
- Application number: 17/651,923
- Filed: 2022-02-22
- Published: 2023-08-24
- Granted: 2024-06-11
- Earliest claimed: 2022-02-22
- Assignees: Mitsubishi Electric Research Laboratories, Inc.
- Applicants: Mitsubishi Electric Research Laboratories, Inc.
- Inventors: Marcel Menner; Stefano Di Cairano; Karl Berntorp; Ziyi Ma
- Web page: https://patentgrep.com/patent/US12005914B2

## CPC

- B60W 50/087: {where the control system corrects or modifies a request from the driver}
- B60W 50/10: Interpretation of driver requests or demands
- B60W 30/09: Taking automatic action to avoid collision, e.g. braking and steering
- B60W 30/12: Lane keeping
- B60W 30/16: Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
- B60W 50/0098: {Details of control systems ensuring comfort, safety or stability not otherwise provided for}
- B60W 2050/0075: {Automatic parameter input, automatic initialising or calibrating means}
- B60W 2050/0088: {Adaptive recalibration}
- B60W 2554/408: Traffic behavior, e.g. swarm
- B60W 2556/05: Big data
- B60W 2556/45: External transmission of data to or from the vehicle
- B60W 2556/50: of positioning data, e.g. GPS [Global Positioning System] data
- 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

A vehicle includes an advanced driver-assistance system (ADAS) configured to intervene in an operation of the control system by complementing or overriding the driving input in response to detecting a driving condition dependent on a calibration parameter indicative of a preference of execution of the driving maneuver. The ADAS is calibrated based on a crowd-local distribution function of the calibration parameter indicative of a distribution of the preference of execution of the driving maneuver by other drivers of other vehicles at a specific location or a specific environment in response to detecting that the vehicle approaches the specific location or the specific environment.

## Claims

### Claim 1

A vehicle, comprising:
a control system configured to accept a driving input from a driver of a vehicle and transform the driving input into actuation of wheels of the vehicle to perform a driving maneuver;
an advanced driver-assistance system (ADAS) configured to intervene in an operation of the control system by complementing or overriding the driving input in response to detecting a driving condition dependent on a calibration parameter indicative of a preference of execution of the driving maneuver;
a receiver configured to receive over a wireless channel a crowd-local distribution function of the calibration parameter indicative of a distribution of the preference of execution of the driving maneuver by other drivers of other vehicles at a specific location or a specific environment; and
a processor configured to adapt the calibration parameter of the ADAS based on the crowd-local distribution function of the calibration parameter in response to detecting that the vehicle approaches the specific location or the specific environment.

### Claim 2 (depends on 1)

The vehicle of claim 1, wherein the processor is configured to adapt the calibration parameter of the ADAS based on a quantile value of the crowd-local distribution function.

### Claim 3 (depends on 2)

The vehicle of claim 2, wherein to adapt the calibration parameter, the processor is configured to:
quantized values of the crowd-local distribution function according to a quantile resolution of quantile values; and
select a quantized value of the crowd-local distribution function corresponding to the quantile value; and
update the calibration parameter based on the selected quantized value.

### Claim 4 (depends on 3)

The vehicle of claim 3, wherein the quantized values of the crowd-local distribution function are formed by averaging values of the crowd-local distribution function falling within a corresponding quantization partition.

### Claim 5 (depends on 2)

The vehicle of claim 2, wherein to adapt the calibration parameter, the processor is configured to:
determine a difference between a value of the crowd-local distribution function indicated by the quantile value and a median value of the crowd-local distribution function; and
shift values of the crowd-local distribution function in a direction indicated of a sign of the difference with a step indicated by a value of the difference.

### Claim 6 (depends on 2)

The vehicle of claim 2, further comprising:
an input device configured to accept input from the driver specifying the quantile value on a predetermined scale defining a resolution of the adaptation of the calibration parameter, wherein to adapt the calibration parameter the processor is configured to:
select a value of the calibration parameter corresponding to a range identified by partitioning the crowd-local distribution function into a set of groups according to the resolution of adaptation and selecting the value of the calibration parameter corresponding to an average value in the group identified by the quantile value.

### Claim 7 (depends on 1)

The vehicle of claim 1, wherein the crowd-local distribution function is computed using two or more other crowd-local distribution functions.

### Claim 8 (depends on 1)

The vehicle of claim 1, wherein the calibration parameter of the ADAS is adapted gradually such that the interventions of the ADAS are gradually increasing based on the crowd-local distribution.

### Claim 9 (depends on 1)

The vehicle of claim 1, wherein the calibration parameter of the ADAS is adapted such that the interventions of the ADAS are gradually increasing based on the crowd-local distribution and a confidence level of the crowd-local distribution.

### Claim 10 (depends on 1)

The vehicle of claim 1, wherein
the receiver is further configured to receive over a wireless channel a crowd-global distribution function of the calibration parameter indicative of a distribution of the preference of execution of the driving maneuver by different drivers of different vehicles at various locations or environments;
the processor is further configured to
collect driving inputs at corresponding driving conditions for performing the driving maneuver at various locations or environments of operation of the vehicle;
construct, from the driving inputs at driving conditions, an ego-global distribution function of the calibration parameter indicative of a distribution of the preference of execution of the driving maneuver by the driver of the vehicle at the various locations or environments;
compare the ego-global distribution function with the crowd-global distribution function to determine a ranking of the preference of execution of the driving maneuver by the driver of the vehicle at various locations or environments with respect to the different drivers of different vehicles at different locations or environments;
adjust the crowd-local distribution function of the calibration parameter according to the determined ranking to produce an ego-local distribution function of the calibration parameter for the specific locality;
adjust the calibration parameter of the ADAS based on the ego-local distribution function of the calibration parameter in response to detecting that the vehicle approaches the specific location or the specific environment.

### Claim 11 (depends on 10)

The vehicle of claim 10, wherein the calibration parameter of the ADAS is adapted such that the interventions of the ADAS are gradually increasing based on the ego-local distribution.

### Claim 12 (depends on 10)

The vehicle of claim 10, wherein the calibration parameter of the ADAS is adapted such that the interventions of the ADAS are gradually increasing based on the ego-local distribution and a confidence level of the ego-local distribution.

### Claim 13 (depends on 1)

The vehicle of claim 1, wherein the crowd-local distribution function is given by an analytical cumulative distribution function.

### Claim 14 (depends on 1)

The vehicle of claim 1, wherein the crowd-local distribution function is given by an empirical cumulative distribution function.

### Claim 15 (depends on 1)

The vehicle of claim 1, wherein the crowd-local distribution function is computed using data collected from other vehicles at the specific location or the specific environment.

### Claim 16 (depends on 1)

The vehicle of claim 1, further comprising:
a transmitter configured to transmit the driving input indicative of the calibration parameter over the wireless channel to update the crowd-local distribution function of the calibration parameter.

### Claim 17 (depends on 1)

The vehicle of claim 1, wherein the ADAS includes an automatic emergency braking (AEB) system, and the calibration parameter indicates one or a combination of a distance to a stopping line when the AEB starts to intervene or complement the driving input commanding the control system to brake the vehicle and a ratio between an extent of braking and a distance to a stopping line.

### Claim 18 (depends on 1)

The vehicle of claim 1, wherein the ADAS includes adaptive cruise control (ACC) system, and the calibration parameter indicates a target distance to be kept from a leading vehicle driving ahead of the vehicle.

### Claim 19

A method for controlling a vehicle, comprising:
accepting a driving input from a driver of a vehicle and transforming the driving input into actuation of wheels of the vehicle to perform a driving maneuver;
receiving over a wireless channel a crowd-local distribution function of the calibration parameter indicative of a distribution of the preference of execution of the driving maneuver by other drivers of other vehicles at a specific location or a specific environment;
adapting a calibration parameter of an advanced driver-assistance system (ADAS) based on the crowd-local distribution function of the calibration parameter in response to detecting that the vehicle approaches the specific location or the specific environment; and
complementing or overriding the driving input using the ADAS calibrated with the calibration parameter indicative of a preference of execution of the driving maneuver.