Method for determining driving comfort, control unit and motor vehicle

Abstract

A method for determining driving comfort in a motor vehicle is provided, in which an AI is used to determine driving comfort by evaluating sensor data from the vehicle's sensors, where the sensor data includes optical signals. Since not only the interior climate but also, or alternatively, optically detectable influences occurring only during driving, especially vibrations, are considered as effects on subjectively perceived driving comfort, a high level of driving comfort is achieved. By coupling this with acoustic and mechanical sensors, driving comfort can be evaluated using all sensory input.

Description

[0001] The invention relates to a method by which driving comfort can be determined when driving a motor vehicle, as well as such a control device and such a motor vehicle.

[0002] US 2018 / 0134116 A1 describes a system in which climate conditions in the interior of a motor vehicle are measured and, depending on the results of a trained AI that detects the well-being of a vehicle occupant, are changed to improve the well-being of the vehicle occupant.

[0003] There is a constant need to improve comfort when driving a motor vehicle.

[0004] The purpose of the invention is to demonstrate measures that enable a high level of comfort when driving in a motor vehicle.

[0005] The problem is solved according to the invention by a method with the features of claim 1, a control device with the features of claim 7, and a motor vehicle with the features of claim 8. Preferred embodiments of the invention are specified in the dependent claims and the following description, each of which can individually or in combination represent an aspect of the invention, the scope of protection being determined by the claims.

[0006] One aspect of the invention relates to a method for determining driving comfort when driving a motor vehicle, in which an AI is provided for determining driving comfort by evaluating sensor data from a sensor system of the motor vehicle, wherein the sensor data includes optical signals.

[0007] This allows for the creation of a system for evaluating the driving comfort of a motor vehicle using AI, in particular a neural network. The AI ​​is specifically designed to learn the relationship between input data and / or measurement data and a subjective assessment. Optical input data, such as camera images and / or LiDAR, can also be used to evaluate driving comfort. Since not only the interior climate but also, or alternatively, optically detectable influences occurring during the journey, especially vibrations, are considered as effects on subjectively perceived driving comfort, a high level of comfort while driving a motor vehicle is made possible.

[0008] Ride comfort can be assessed using artificial intelligence (AI). It has been recognized that ride comfort is generally evaluated subjectively based on all human sensory channels, particularly haptics, acoustics, and / or visual perception. The human eye is the most important sensory organ in this regard, and incorrect synchronization between sensory channels can lead to motion sickness and thus discomfort. This can therefore be avoided through the automated integration of visual aspects for ride comfort analysis. In particular, an analysis of visual aspects is planned for evaluating ride comfort characteristics related to vibrations in the range of approximately 1-500 Hz, as such frequencies can occur, for example, during roll, pitch, and / or road edge crossings.The shift from a subjective assessment of ride comfort to an objective one can be achieved using AI, particularly neural networks, preferably with supervised learning strategies. This involves learning the relationship between objective parameters and subjective assessment, in order to then apply this knowledge to previously unseen data, especially to predict subjective assessments. This can utilize AI or neural networks that, in a vehicle, already process acceleration signals, microphone measurements, damper forces, engine speeds, and anthropometric data, and can now additionally receive information processed via optical channels.

[0009] Since visual impressions influence human expectations and thus perception, they should be taken into account. For example, when driving over an edge, the edge to be crossed might be very high, so that it can be visually perceived before crossing it. The occupant might then expect a correspondingly harsh jolt. However, if the edge is not very high but still results in a strongly perceived jolt, then this does not correspond to expectations and is therefore perceived as uncomfortable.

[0010] The optical signals that can be used to assess ride comfort can be of a variety of nature. Suitable optical signals that can be detected by vehicle sensors include, in particular, camera images in RGB, infrared, 3D (depth camera), LiDAR, stereo camera, and panoramic camera.

[0011] In particular, the AI ​​uses optical signals to determine the current and / or future vibration behavior of the vehicle and / or a vehicle occupant, and uses this information to determine ride comfort. This allows the vehicle's vibration behavior to be considered as an impact on ride comfort.

[0012] Preferably, the AI ​​determines the vibration behavior of a vehicle's roll, pitch, and / or edge crossing. Such various vibration phenomena can have different effects on ride comfort.

[0013] It is particularly preferred that, in addition to optical signals, the sensor data includes acoustic and / or mechanical signals, in particular acceleration signals, microphone measurements, damping forces, engine speeds, and / or anthropometric data. This allows non-optical data to also be considered for evaluating ride comfort. All of this data (optical, mechanical, anthropometric, etc.) together serve as input data for the AI, enabling a more detailed simulation of human perception across all sensory channels.

[0014] In particular, the AI ​​is designed to be trained, and / or trained, by observing occupant behavior to subjectively assess ride comfort. This allows counterintuitive effects on the subjective perception of ride comfort, such as those caused by unmet occupant expectations, to be learned and taken into account through machine learning based on the observed occupant behavior.

[0015] Preferably, an AI-generated parameter for driving comfort is made available to at least one driver assistance system and / or at least one comfort system of the vehicle, particularly as a control input for a control system. The driving comfort determined by the AI, especially in a quantified form, can thus be easily used as information for the automated improvement of comfort.

[0016] Another aspect concerns a control unit for regulating driving comfort while driving a motor vehicle with the aid of at least one controlled driver assistance system and / or comfort system, whereby an AI designed to carry out the procedure, which can be developed and further refined as described above, is provided. Since not only the interior climate, but also, or alternatively, optically detectable influences occurring only during driving, in particular vibrations, are taken into account as effects on the subjectively perceived driving comfort, a high level of comfort while driving a motor vehicle is made possible.

[0017] Another aspect concerns a motor vehicle with a control unit that can be designed and further developed as described above. Since not only the interior climate, but also, or alternatively, optically detectable influences occurring only during driving, especially vibrations, are taken into account as effects on the subjectively perceived driving comfort, a high level of comfort while driving a motor vehicle is made possible.

[0018] Particularly preferred is a sensor system that outputs optical signals, comprising a camera, a LiDAR system, a stereo camera, and / or a panoramic camera. Such a sensor system may already be installed in the vehicle, so that the existing optical signals can easily be used additionally to determine driving comfort.

[0019] In particular, the optical signals contain data in the form of camera images in RGB, infrared and / or 3D. This allows a wide spectrum of optical signals to be covered and used. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] US 2018 / 0134116 A1

[0002]

Claims

[1] Method for determining ride comfort when driving a motor vehicle, in which An AI is provided to determine driving comfort by evaluating sensor data from the vehicle's sensors. the sensor data includes optical signals. [2] Method according to claim 1, wherein the AI ​​determines a current and / or future vibration behavior of the motor vehicle and / or a vehicle occupant from the optical signals and takes this into account for determining driving comfort. [3] Method according to 2, in which the AI ​​determines the vibration behavior of a roll, pitch and / or edge crossing of the motor vehicle. [4] Method according to any one of claims 1 to 3, wherein in addition to the optical signals the sensor data comprise acoustic signals and / or mechanical signals, in particular acceleration signals, microphone measurements, damping forces, motor speeds and / or anthropometric data. [5] Method according to any one of claims 1 to 4, wherein the AI ​​was and / or is trained by observing occupant behavior to subjectively assess the driving comfort by the vehicle occupant. [6] Method according to any one of claims 1 to 5, wherein a parameter generated by the AI ​​for driving comfort is made available to at least one driver assistance system of the motor vehicle and / or at least one comfort system of the motor vehicle, in particular as a control variable of a control system. [7] Control device for regulating driving comfort when driving a motor vehicle with the aid of at least one controlled driver assistance system and / or comfort system, wherein an AI designed to carry out the method according to one of claims 1 to 6 is provided. [8] Motor vehicle with a control device according to claim 1. [9] Motor vehicle according to claim 8, wherein optical signal output sensor technology is provided, the sensor technology comprising a camera, a LiDAR system, a stereo camera and / or a panoramic camera. [10] Motor vehicle according to claim 9, wherein the optical signals include data in the form of camera images in RGB, infrared and / or 3D.