DE-102024139718-A1 - Methods for adapting the reactions of an advanced driver assistance system

DE102024139718A1DE 102024139718 A1DE102024139718 A1DE 102024139718A1DE-102024139718-A1

Abstract

A method for adapting the response of a vehicle equipped with an advanced driver assistance system (ADAS), which includes the collection of telemetry data. The telemetry data includes impact and near-impact events relative to a map. The method further includes the collection of environmental data and the analysis of the telemetry data in relation to the environmental data to determine impact risk factors. The impact risk factors correlate with an increased risk of impact. The method further includes the identification of areas of increased impact risk based on the impact risk factors. The method further includes the determination of the location of the ADAS-equipped vehicle relative to the map and the collection of vehicle data from one or more sensors. The method further includes the calculation of an increased risk of vehicle impact (IRVCI) based on the location of the ADAS-equipped vehicle and the collected vehicle data. The method further includes the adaptation of the response of the ADAS-equipped vehicle based on the IRVCI.

Inventors

Michael John Aprile
Michael G. Carpenter
Chad T. Zagorski
Shawn F. Granda
Donald K. Grimm

Assignees

GM Global Technology Operations LLC

Dates

Publication Date: 20260513
Application Date: 20241223
Priority Date: 20241113

Claims (10)

A method for adapting the response of a vehicle equipped with an advanced driver assistance system (ADAS), comprising: collecting telemetry data from a multitude of remote vehicles, wherein the telemetry data includes impact and near-impact events with respect to locations on a map; collecting environmental data of the locations on the map, wherein the environmental data indicates inherent properties of the locations, including road curvature, road gradient, road surface, visibility, and weather conditions; performing an analysis of the telemetry data with respect to the environmental data of the locations to determine impact risk factors that correlate with an increased risk of impact; determining areas of increased risk of impact based on the impact risk factors; determining a location of the ADAS-equipped vehicle with respect to the map; collecting vehicle data from one or more sensors mounted on the ADAS-equipped vehicle, wherein the vehicle data includes vehicle load, trailer status, tire pressure, tire wear, tire temperature, and any spare tires fitted. Calculating an increased risk of a vehicle impact index (IRVCI) based on the location of the ADAS-equipped vehicle in relation to areas of increased impact risk and vehicle data; and adjusting the response of the ADAS-equipped vehicle based on the IRVCI.
Procedure according to Claim 1 , furthermore, the comprehensive collection of telemetry data from a cloud.
Procedure according to Claim 1 , furthermore, comprehensively classifying telemetry data as impact events when distant vehicles collide.
Procedure according to Claim 1 , furthermore, including the classification of telemetry data as near-collision events when remote vehicles activate alarms indicating a near-collision.
Procedure according to Claim 1 , furthermore, including the classification of telemetry data as near-collision events when remote vehicles activate automatic vehicle reactions indicating a near-collision.
Procedure according to Claim 1 , where the impact risk factors include road curvature, traffic patterns and intersection configurations.
Procedure according to Claim 1 , furthermore, comprehensively locating the impact risk factors relative to the map.
Procedure according to Claim 1 , furthermore, including the adjustment of the reaction time control of the vehicle equipped with ADAS.
Procedure according to Claim 1 , furthermore, comprehensively the adjustment of the reaction aggressiveness of the vehicle equipped with ADAS.
A method for adapting the response of a vehicle equipped with an advanced driver assistance system (ADAS), comprising: Generating a driver profile, wherein the driver profile is based on collected driving habits and collected driving preferences, the driver's driving habits including vehicle speed, vehicle acceleration, vehicle deceleration, and steering inputs over a period of time; Calculating a historical aggressiveness metric (D-HAM) of the driver by comparing the driving habits with a statistical mean; Collecting vehicle data from one or more sensors mounted on the ADAS-equipped vehicle, wherein the vehicle data includes vehicle load, trailer status, tire pressure, tire wear, tire temperature, and any spare tires mounted; Collecting environmental data from locations on a map, wherein the environmental data includes inherent properties of the locations, including road curvature, road gradient, road surface, visibility, and weather conditions; Collecting real-time vehicle inputs from the driver, including speed, acceleration, deceleration, and steering inputs relative to the map; Performing an analysis of vehicle and environmental data to determine impact risk factors when vehicle inputs deviate from the D-HAM; Calculating a predicted driver aggressiveness metric (D-PAM) from the impact risk factors based on deviation from the D-HAM; and Adjusting the response of the ADAS-equipped vehicle based on the D-PAM.

Description

Introduction This description refers generally to an advanced driver assistance system (ADAS). More specifically, this description refers to a system and method that adapts the reactions of a vehicle equipped with ADAS. Vehicles are equipped with ADAS to enhance vehicle and road safety. ADAS-equipped vehicles include sensors that collect data about the vehicle's surroundings. This data is processed to generate an alarm or an automatic vehicle response. While ADAS generates alarms and automatic vehicle responses, it does not adjust the timing of these alarms or responses to environmental factors or a driver's driving habits and preferences. While current ADAS-equipped vehicles fulfill their intended purpose, there is therefore a need for a new and improved system and procedure to adapt the reactions of the ADAS-equipped vehicle based on environmental, system, and personalization factors. Description A method for adapting the response of a vehicle equipped with an advanced driver assistance system (ADAS) is provided, outlining several aspects. The method involves collecting telemetry data from a large number of remote vehicles. This telemetry data includes impact and near-impact events related to locations on a map. The method also includes collecting environmental data for these locations on the map. This environmental data indicates inherent properties of the locations, including road curvature, gradient, surface, visibility, and weather conditions. Furthermore, the method involves analyzing the telemetry data in relation to the environmental data to determine impact risk factors that correlate with an increased risk of impact. Based on these risk factors, the method further includes identifying areas of increased impact risk. Finally, the method involves determining the location of the ADAS-equipped vehicle relative to the map. The procedure further includes collecting vehicle data from one or more sensors mounted on the ADAS-equipped vehicle. This vehicle data includes vehicle load, trailer status, tire pressure, tire wear, tire temperature, and whether a spare tire is fitted. The procedure further includes calculating an increased risk of vehicle crash index (IRVCI) based on the location of the ADAS-equipped vehicle in relation to areas with increased impact risk and the vehicle data. The procedure further includes adjusting the response of the ADAS-equipped vehicle based on the IRVCI. In an additional aspect of the present description, the procedure also includes the collection of telemetry data from a cloud. In another aspect of the present description, the procedure also includes classifying the telemetry data as impact events when distant vehicles collide. In another aspect of the present description, the procedure further includes classifying the telemetry data as near-collision events when the remote vehicles activate alarms indicating a near-collision. In another aspect of the present description, the procedure further includes classifying the telemetry data as near-collision events when the remote vehicles activate automatic vehicle reactions that indicate a near-collision. Another aspect of the present description includes impact risk factors such as road curvature, traffic patterns, and intersection configurations. In another aspect of the present description, the procedure also includes locating the impact risk factors relative to the map. In another aspect of the present description, the procedure also includes adjusting the reaction time control of the ADAS-equipped vehicle. In another aspect of the present description, the procedure also includes adjusting the reaction aggressiveness of the ADAS-equipped vehicle. According to several aspects, a procedure for adjusting a response of one with a The procedure involves generating a driver profile for a vehicle equipped with an advanced driver assistance system (ADAS). This profile is based on collected driving habits and preferences. The driver's driving habits include vehicle speed, acceleration, deceleration, and steering inputs over time. The procedure further involves calculating the driver's historical aggressiveness metric (D-HAM) by comparing these driving habits to a statistical mean. The procedure also involves collecting vehicle data from one or more sensors mounted on the ADAS-equipped vehicle. This vehicle data includes vehicle load, trailer status, tire pressure, tire wear, tire temperature, and any spare tires mounted. Finally, the procedure involves collecting environmental data from locations on a map. This environmental data indicates the inherent properties of these locations, including road curvature, gradient, surface finish, visibility, and weather conditions. The procedure further includes collecting real-time vehicle inputs from the driver. These inputs include speed, acceleration, deceleration, and steering inputs in relation to the map. The procedure also includes analyzing the vehicle and environmental data to determin