EP3688661A1 - Kommunikationsfluss von verkehrsteilnehmer in richtung eines automatisiert fahrenden fahrzeug - Google Patents
Kommunikationsfluss von verkehrsteilnehmer in richtung eines automatisiert fahrenden fahrzeugInfo
- Publication number
- EP3688661A1 EP3688661A1 EP18772739.1A EP18772739A EP3688661A1 EP 3688661 A1 EP3688661 A1 EP 3688661A1 EP 18772739 A EP18772739 A EP 18772739A EP 3688661 A1 EP3688661 A1 EP 3688661A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- control command
- vehicle
- sign
- road user
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q1/00—Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor
- B60Q1/26—Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor the devices being primarily intended to indicate the vehicle, or parts thereof, or to give signals, to other traffic
- B60Q1/50—Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor the devices being primarily intended to indicate the vehicle, or parts thereof, or to give signals, to other traffic for indicating other intentions or conditions, e.g. request for waiting or overtaking
- B60Q1/507—Arrangement of optical signalling or lighting devices, the mounting or supporting thereof or circuits therefor the devices being primarily intended to indicate the vehicle, or parts thereof, or to give signals, to other traffic for indicating other intentions or conditions, e.g. request for waiting or overtaking specific to autonomous vehicles
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01F—ADDITIONAL WORK, SUCH AS EQUIPPING ROADS OR THE CONSTRUCTION OF PLATFORMS, HELICOPTER LANDING STAGES, SIGNS, SNOW FENCES, OR THE LIKE
- E01F9/00—Arrangement of road signs or traffic signals; Arrangements for enforcing caution
- E01F9/20—Use of light guides, e.g. fibre-optic devices
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/161—Decentralised systems, e.g. inter-vehicle communication
- G08G1/163—Decentralised systems, e.g. inter-vehicle communication involving continuous checking
Definitions
- the invention relates to a training evaluation device for a vehicle according to claim 1, a method for training an artificial neural network according to claim 6 and a computer program product according to claim 8 for its execution, a deployment evaluation device for an automated operation vehicle according to claim 9, a driver assistance system according to claim 12, A use of a driver assistance system according to claim 16, a method for recognizing a meaning of a sign of a road user and for signaling a vehicle response to a recognized meaning of this sign according to claim 17 and a computer program product according to claim 19 for its execution.
- the invention has the object to realize a communication flow from a road user to an automated moving vehicle, so that the road user has further eye contact with the vehicle to independently analyze their behavior, assess and thus calms down and safely perceive further locomotion in traffic to be able to.
- a training evaluation device for a vehicle having the features of claim 1 a method for training an artificial neural network with the features of claim 6 and a computer program product having the features of claim 8 for its execution, an insert evaluation device for an automatically operable A vehicle having the features of claim 9, a driver assistance system having the features of claim 12, a use of a driver assistance system having the features of claim 16, a method of recognizing a meaning of a sign of a road user and signaling a vehicle response to a recognized meaning of that sign the features of claim 17 and a computer program product having the features of claim 19 for its execution.
- the training evaluation apparatus for a vehicle has a first input interface for obtaining a sign of a road user, and a second input interface for receiving a driver control command corresponding to the sign, the training evaluating device executing an artificial neural network with detection of the vehicle Signal and the driver control command to receive a vehicle control command in the supply of the artificial neural network, and Adjust weighting factors such that the vehicle control command matches the driver control command for machine learning a meaning of the character.
- An evaluation device is a device that processes incoming information and outputs a result resulting from this processing.
- an electronic circuit such as a central processor unit or a graphics processor, an evaluation device.
- a training evaluation device is an evaluation device which is in a training phase or learning phase for machine learning of a behavior. After the training phase, the behavior is learned and the evaluation device can be used as auswakened to react purposefully to new information.
- a vehicle is a vehicle on land, water or in the air, in particular a road vehicle.
- An interface is a device between at least two functional units at which an exchange of logical quantities, for example data or physical quantities, for example electrical signals, takes place, either only unidirectionally or bidirectionally.
- the exchange can be analog or digital.
- the exchange can also be wired or wireless.
- a sign is in particular a sign with which a road user signals a traffic decision to another road user, for example, a further wave to request to continue.
- Road users are in particular pedestrians, motorized and non-motorized cyclists and / or other non-motorized road users.
- a driver control command is a command of a driver with which the driver controls the vehicle of which he is the driver.
- a step on an accelerator pedal or a brake pedal are driver control commands.
- Driver control commands can be processed electronically.
- An artificial neural network is an algorithm that is executed on an electronic circuit and programmed on the model of the neural network of the human brain.
- Functional units of an artificial neural network are artificial neurons whose output is generally evaluated as the value of an activation function over a weighted sum of the inputs plus a systematic error, the so-called bias.
- By testing multiple inputs with different weighting factors and / or activation functions artificial neural networks similar to the human brain are trained. The training of an artificial neural network using predetermined inputs is called machine learning.
- Food in particular forward feeding, means a summation and output by the activation function.
- a subset of machine learning is deep learning, in which a series of hierarchical layers of neurons called hidden layers are used to perform the machine learning process.
- An artificial neural network with multiple hidden layers is a deep neural network.
- Artificial intelligence refers to the purposeful reaction to new information. For example, weighting factors are adjusted by means of a backward feed, that is, an already obtained output is processed as input by the artificial neural network in order to obtain the original input as calculated output.
- a driver control command is an instruction calculated by the artificial neural network to control the vehicle, for example, an electrical voltage used to actuate a brake actuator.
- the action of other road users can be trained with artificial intelligence on a vehicle, in particular what the features of a signaling could be. If, for example, a driver of a vehicle driving towards a crosswalk recognizes, by means of a clear further rotation of a pedestrian standing at the pedestrian crossing, that the pedestrian will stop at the crosswalk and will not cross it, the driver will accelerate and drive on, instead of order to stop at the crosswalk. It clearly means that there is no conversation between the vehicle and other road users, which would hinder traffic.
- the further wave is detected by the training evaluation device by the first, the corresponding gas input by the second input interface.
- the training evaluation device uses the artificial neural network to calculate a vehicle control command and optimizes it by adjusting the weighting factors. If the training evaluation device now detects a similar situation, the training evaluation device will automatically calculate and output a corresponding vehicle control command. Based on the driver control command, the training evaluation device has learned to react purposefully to the waving.
- the training evaluation device is designed to simulate a fault movement of the vehicle, for example a stop vehicle control command in the case of a detected waving sign of the road user. This makes it possible to directly win error movements without additional sensors. With simulated error movements, an artificial neural network can learn to respond to errors.
- the first input interface is designed to obtain a visual, preferably a gesture, in particular a hand movement, and / or a facial expression, and / or an acoustic signal of the road user.
- Hand movements, facial expressions and / or acoustic sounds are the usual signs with which road users, especially non-motorized road users, communicate with drivers of vehicles.
- the first input interface is designed to obtain a detection of a size and / or a facial feature of the road user
- the artificial neural network is designed to obtain an age of the road user based on the size and / or the facial features Vehicle control command depending on the age to adjust.
- the first input interface is an interface to an environment detection sensor and / or a system of environment detection sensors, preferably an image sensor of a camera, a radar, a lidar and / or a sound sensor and / or the second input interface an interface to a vehicle Data transmission system, preferably a CAN bus.
- a vehicle Data transmission system preferably a CAN bus.
- environment detection sensors the decisions communicated by a road user by means of signs are detected and processed particularly easily. Speech recognition can be provided in particular with a sound sensor, wherein corresponding filters are preferably provided in order to filter out a speech symbol of a road user from further environmental noises.
- the CAN bus is the Controller Area Network Bus, which connects control units in a vehicle and transmits signals. Thus, a driver control command can be easily evaluated.
- the artificial neural network is a multi-layer, preferably a convolutional or a recurrent, artificial neural network.
- Convolutional artificial neural networks are characterized by a two- or three-dimensional arrangement of neurons and shared weighting factors and are used in particular for image recognition, in which the input is a gray image or an image in a three-dimensional color space and thus a two- or three-dimensional matrix.
- a recurrent, also feedback, neural network is a network which is characterized by connections of neurons of a layer to neurons of the same or a preceding layer.
- Practical applications commonly find artificial recurrent neural networks in problems that affect processing of sequences. Examples include text recognition, speech recognition and machine translation.
- the method according to the invention for training an artificial neural network comprises the following method steps:
- the artificial neural network learns a meaning of the sign.
- a vehicle control command is learned with the method according to the invention in order to purposefully react to signs of road users.
- a training evaluation device is used to carry out the method.
- the inventive computer program product is designed to be loaded into a memory of a computer and has software code sections with which the steps of the method according to the invention for training an artificial neural network are executed when the computer program product is running on the computer.
- a computer is a device for processing data that can process data by means of programmable calculation rules.
- Computer program products typically include a sequence of instructions that cause the hardware, when the program is loaded, to perform a particular procedure that results in a particular result.
- the computer program product causes a technical effect, namely, obtaining a vehicle control command.
- a memory is a medium for backing up data.
- Software is a collective term for programs and related data.
- the complement to software is hardware.
- Hardware refers to the mechanical and electronic alignment of a data processing system.
- an artificial neural network is particularly easily trained to respond to signs of road users with a corresponding vehicle control command.
- the automated vehicle operation evaluation device has an input interface for obtaining detection of a traffic participant's character, wherein the employment evaluation device is adapted to train a meaning of the character, preferably according to the artificial neural network training method of the present invention to feed artificial neural network with the detection of the character and to obtain a corresponding vehicle control command.
- the deployment evaluation device has a first output interface in order to issue the vehicle control command to the road user in order to recognize the meaning of the sign and to signal to the road user a vehicle reaction to the recognized meaning of this sign.
- An automated operable vehicle is a vehicle that has technical equipment to handle a driving task, including longitudinal and transverse guidance, the respective vehicle after activation of a corresponding automated driving function, in particular a highly or fully automated Driving function according to the standard SAE J3016, with a vehicle control device can control.
- this technical equipment is designed to correspond to the traffic guidance directed to the vehicle guidance during the automated vehicle control, that is to say during the automated operation of the vehicle.
- the technical equipment may consist in particular of sensors, control units and actuators.
- this equipment may preferably be manually overridden or deactivated by the vehicle driver at any time.
- the technical equipment may be designed to detect the necessity of autograph vehicle control by the driver and the driver to display the requirement of autograph vehicle control with sufficient time reserve before the delivery of vehicle control to the driver visually, acoustically, tactually or otherwise perceptible and on one of System description to indicate contrary use.
- Driver is also the one who activates an automated driving function and used for vehicle control, even if he does not control the vehicle in the context of the intended use of this function by hand.
- An automated operable vehicle that does not require human intervention during operation of the vehicle, other than the destination, is a fully automated vehicle. In a fully automated moving vehicle, the driver is not obliged to take over the vehicle control immediately.
- the meaning of a sign refers to the semantics and includes what someone understands by the sign.
- An environment detection sensor initially captures only one sign, without its semantic meaning. The meaning of a sign is learned.
- the deployment evaluation device recognizes the meaning of a detected character by means of an appropriately trained artificial neural network and can react purposefully with a corresponding vehicle control command.
- the deployment evaluation device advantageously signals to the road user that they have detected the sign of the road user and recognized its significance.
- the deployment evaluation device is preferably designed to signal the road user to continue driving or stopping the vehicle as a function of a detected stop sign or onward journey sign. By means of this signaling, a communication flow from a driver of the vehicle to the road user is easily replaced.
- the austician designed on a second output interface to output the vehicle control command for a vehicle control device.
- a vehicle control device is a device with which a vehicle can be controlled.
- a longitudinal and / or lateral control is a vehicle control.
- the vehicle is operated automatically.
- the driver assistance system comprises an environment detection sensor or a system of environment detection sensors for detecting a sign of a road user, an application evaluating device configured to feed an artificial neural network trained on a meaning of the sign with the detection of the sign and to obtain a vehicle control command corresponding to the sign , and a signal generator configured to signal the vehicle control command to the road user to recognize a meaning of the sign and to signal the road user to a vehicle response to a recognized meaning of that sign.
- a signal generator is a device, an assembly or a circuit that generates and preferably transmits a signal, that is, information with a specific meaning.
- the driver assistance system according to the invention can thus automatically react purposely to signs of road users and signal a corresponding reaction to the road user.
- the use evaluation device is preferably an application evaluation device according to the invention.
- the signal transmitter is designed to generate an electrical, optical and / or acoustic signal, wherein the signal transmitter is preferably in a front region and / or rear region of the vehicle, preferably on a bumper, can be arranged and preferably has a light bar.
- An optical signal can be perceived by normal-looking road users simply by eye contact with the vehicle.
- An acoustic signal for example a tone or a tone sequence with a certain frequency, can be perceived by weak-sighted, in particular blind, road users.
- An electrical signal can also be perceived tactilely.
- a light strip is a narrow, in particular long component, which has light-emitting components.
- a light bar can be easily perceived optically.
- the driver assistance system has an interface for outputting a signal of the signal transmitter to a device for increasing the traffic safety for the road user, wherein the portable device is executed, depending on the signal of the signal transmitter the road user by means of a vibration to alert the signaling of the vehicle control command.
- Portable devices also called wearables, are widely used in the fitness or wellness field and are connected to a network for exchanging data with other devices such as computers or other portable devices or mobile terminals. Portable devices are worn on the body.
- the vibration can be output via a loudspeaker as an acoustically perceptible signal.
- the portable device may be a smartphone or a smartwatch. With such a portable device in particular pedestrians and cyclists are warned in advance of driving decisions in traffic. Such a portable device is an example of a car-to-X communication application.
- a driver assistance system according to the invention is used in an automatically operable vehicle.
- the method according to the invention for recognizing a meaning of a sign of a road user and for signaling a vehicle reaction to a recognized meaning of this sign comprises the following method steps:
- the meaning of the character is automatically detected and a corresponding vehicle reaction simply signals the road user.
- an application evaluation device according to the invention or a driver assistance system according to the invention is used to carry out the method according to the invention.
- the computer program product according to the invention is designed to be loaded into a memory of a computer and has software code sections with which the steps of the method according to the invention for recognizing a meaning of a sign of a road user and for signaling a vehicle response to a recognized meaning of this sign are executed
- Computer program product on the computer is running.
- FIG. 1 shows an embodiment of a training evaluation device according to the invention
- FIG. 2 shows an embodiment of a method according to the invention for training an artificial neural network
- 5 shows an embodiment of a driver assistance system according to the invention
- 6 shows exemplary embodiments for signal transmitters of a driver assistance system according to the invention
- FIG. 7 shows an embodiment of a driver assistance system according to the invention with an exemplary embodiment of a portable device
- FIG. 8 shows an embodiment of a method according to the invention for recognizing a meaning of a sign of a road user and for signaling a vehicle reaction to a recognized meaning of this sign and
- FIG. 9 shows a further exemplary embodiment of a driver assistance system according to the invention.
- the training evaluation device 10 shown in FIG. 1 receives a sign 2 of a road user 3 via a first input interface 11.
- the sign 2 is a clear hand signal for requesting a driver of a vehicle 1 to continue traveling. This character is detected by means of an image sensor of a camera as an example of an environment detection sensor 5.
- the training evaluation device 10 receives a driver control command 4 via a second input interface 12.
- the driver control command 4 is accelerated.
- the driver of the vehicle operates a gas pedal to execute the driver control command 4.
- the pressure required for this purpose on the gas pedal can be converted into an electrical voltage, which is input by means of a vehicle data transmission system 6 via the second input interface 12 into the training evaluation device 10 and further processed there.
- the training evaluation device 10 is, for example, a graphics card processor designed specifically for automotive applications and executing an artificial neural network 13.
- the artificial neural network 13 is for example play a recurrent artificial neural network 13 in which neurons 16 of a layer are connected to neurons 16 of a preceding layer.
- the inputs, ie the inputs, of the artificial neural network 13 are the detection of the character 2 and a driver control command 4 corresponding to the character 2.
- the output, ie the output, of the artificial neural network 13 is a vehicle control command 14 calculated from the inputs. By adjusting weighting factors 15, the calculated vehicle control command 14 is optimized such that the vehicle control command 14 coincides with the driver control command 4.
- training training device 10 learns a detected character 2 a corresponding vehicle control command 14 and thus the character 2 to assign a corresponding meaning.
- the training evaluation device 10 which is arranged on the vehicle 1, detects a gesture of a road user 3 waiting at a crosswalk 9, and a corresponding driver control command 4; if there is a continue driving, gives a gas, braking in the case of a stop sign, learns the training evaluation device 10 to generate a corresponding situation-dependent vehicle control command 14. In a similar situation, the training evaluation device 10 may then purposely respond with a vehicle control command 14 without having detected a corresponding driver control command 4.
- FIG. 2 shows the method according to the invention for training an artificial neural network 13.
- the artificial neural network is thereby executed on the training evaluation device 10 shown in FIG. 1 for the vehicle 1.
- the surroundings detection sensor 5 provides the training evaluation device 10 with the sign 2 of the traffic participant 3 detected by the vehicle 1 during travel with the vehicle 1 via the first input interface 11 and the driver control command 4 corresponding to the character 2 via the second input interface 12.
- the training evaluation device 10 feeds the artificial neural network 13 with the character 2 and the driver control command 4.
- the training evaluation device 10 simulates an error movement of the vehicle 1, for example a stop signal. Vehicle control command with a detected waving sign of the road user. This makes it possible to directly win error movements without additional sensors. With simulated error movements, the artificial neural network 13 learns to respond to errors. As the output of the artificial neural network 10, the corresponding vehicle control command 14 is obtained.
- the weighting factors 15 are adjusted such that, for example, by feeding back the artificial neural network 13, the vehicle control command 14 coincides with the driver control command 4.
- the artificial neural network 13 learns the semantic meaning of the character 2.
- a computer program product 20 is shown in FIG.
- the computer program product 20 is loaded into a memory 21 of a computer 22 and executes the steps of the method for training the artificial neural network 13 there.
- FIG. 4 shows a deployment evaluator 30 that executes an artificial neural network 13 trained according to the method shown in FIG. Via an input interface 31, the service evaluation device 30 is provided with the sign 2 of the road user 3 detected by the surroundings detection sensor 5.
- the artificial neural network 13 is optimized by the arrangement of its neurons 16 and carried out in a training phase adaptation of the weighting factors 15, depending on the detected character 2 to calculate the vehicle control command corresponding to this 14 character. If the deployment evaluation device 30 detects a clear sign 2 for driving on, the deployment evaluation device 30 uses the artificial neural network 13 to calculate the corresponding vehicle control command 14 to accelerate the gas.
- the deployment evaluation device 30 outputs the vehicle control command for the road user 3 in order to signal to the road user 3 that the vehicle 1 has detected its sign 2 and will react with a corresponding driving behavior.
- the vehicle control device 40 which is also shown in FIG. 9, controls the longitudinal and / or lateral control of the vehicle 1.
- the driver assistance system 50 has a system of environment detection sensors comprising a centrally located front camera and two laterally arranged front radars.
- the driver assistance system 50 is in particular designed to process the various detected sensor raw data, that is, for example, to generate images from the camera data and to merge them into an environment model.
- a pedestrian is detected as a road user 3 at a crosswalk 9.
- the road user can also be at another crossing facility, for example a traffic light crossing.
- the surroundings detection sensors 5 also detect the sign 2 of the road user 3 for driving on the vehicle 1.
- the deployment evaluation device 30 of the driver assistance system 50 uses the artificial neural network 13 to calculate the vehicle control command 14 corresponding to the character 2.
- the driver assistance system 50 further has a signal generator 51 with which the vehicle control command 14 is signaled to the road user 3.
- the signal generator 51 thus signals the road user 3 a vehicle reaction to the recognized meaning of the character 2.
- the signal generator 51 generates and outputs a signal.
- the signal is a visually perceptible signal, for example a light signal in a particular color.
- the signal generator 51 may in particular be designed as a light strip 8, which has a plurality of lighting means, as shown in the middle embodiment of FIG.
- the light bar 8 may be a strip of light emitting diodes.
- the signal generator 51 is horizontal, that is parallel to one Road surface, aligned.
- the signal generator 51 is vertical, that is perpendicular, arranged to the surface of the road.
- the signal generator 51 is executed, the road user 3 shown in Fig. 5, a further travel of the vehicle 1, that is, for example, a gas give, with a light signal in a first color, preferably green, and a stop of the vehicle, that is, for example Brakes to signal with a light signal in a second color, preferably red.
- the driver assistance 50 of FIG. 7 has an interface 52.
- the interface 52 is a WLAN interface with which the signal of the signal generator 51 is output to a portable device 60, which is carried by the road user 3.
- a complete networking of the vehicle 1 and the weaker road user 3 is realized.
- Such networking can take place, in particular, in a cloud, in which preferably a corresponding algorithm is executed. This increases traffic safety. In particular, it is possible to warn against collisions.
- the portable device 60 is also designed, in response to the signal of the signal generator 51 to make the road user 3 aware of the signaling of the vehicle control command 14 by means of a vibration.
- the inventive method for recognizing a meaning of a character 2 of a road user 3 and for signaling a vehicle response to a recognized meaning of this character 2 is shown in Fig. 9.
- the character 2 of the traffic participant 3 is detected, for example with an environment detection sensor 5.
- an artificial neural network 13 trained on a meaning of the character 2 is supplied with this detection of the character 2.
- a vehicle control command 14 is obtained. This vehicle control command 14 is output to the road user 3.
- a computer program product 70 for carrying out the method according to the invention for recognizing a meaning of a character 2 of a road user 3 and for signaling a vehicle response to a recognized meaning of this character 2 is shown in FIG.
- the driver assistance system 50 can also be used successfully in the following situation.
- the driver assistance system 50 of the automated moving vehicle 1 recognizes the individual road user 3 and signals him by means of the signal generator 51 that it will stop.
- the road user 3 is by a unique gesture, for example, by a hand movement, the vehicle 1 to recognize that the vehicle 1 should continue. This hand movement is recognized as a character 2 with the corresponding meaning and processed by the driver assistance system 50.
- the vehicle 1 then changes the signal, and the signal generator 51 signals that the vehicle 1 will now continue.
- the driver assistance system 50 estimates the gestures on the basis of size, age and / or facial features of the road user 3. This assessment is needed to sensitively analyze children and the elderly.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Mechanical Engineering (AREA)
- Social Psychology (AREA)
- Automation & Control Theory (AREA)
- Psychiatry (AREA)
- Transportation (AREA)
- Civil Engineering (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Architecture (AREA)
- Structural Engineering (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102017217256.8A DE102017217256A1 (de) | 2017-09-28 | 2017-09-28 | Kommunikationsfluss von Verkehrsteilnehmer in Richtung eines automatisiert fahrenden Fahrzeug |
| PCT/EP2018/073318 WO2019063237A1 (de) | 2017-09-28 | 2018-08-30 | Kommunikationsfluss von verkehrsteilnehmer in richtung eines automatisiert fahrenden fahrzeug |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP3688661A1 true EP3688661A1 (de) | 2020-08-05 |
Family
ID=63637853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP18772739.1A Withdrawn EP3688661A1 (de) | 2017-09-28 | 2018-08-30 | Kommunikationsfluss von verkehrsteilnehmer in richtung eines automatisiert fahrenden fahrzeug |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US11126872B2 (de) |
| EP (1) | EP3688661A1 (de) |
| CN (1) | CN110663042B (de) |
| DE (1) | DE102017217256A1 (de) |
| WO (1) | WO2019063237A1 (de) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102017217256A1 (de) | 2017-09-28 | 2019-03-28 | Zf Friedrichshafen Ag | Kommunikationsfluss von Verkehrsteilnehmer in Richtung eines automatisiert fahrenden Fahrzeug |
| US20230356728A1 (en) * | 2018-03-26 | 2023-11-09 | Nvidia Corporation | Using gestures to control machines for autonomous systems and applications |
| US11347225B2 (en) * | 2019-02-05 | 2022-05-31 | Intel Corporation | Mechanism for conflict resolution and avoidance of collisions for highly automated and autonomous vehicles |
| DE102019208735B4 (de) * | 2019-06-14 | 2021-12-23 | Volkswagen Aktiengesellschaft | Verfahren zum Betreiben eines Fahrassistenzsystems eines Fahrzeugs und Fahrerassistenzsystem für ein Fahrzeug |
| CN113393687B (zh) * | 2020-03-12 | 2023-07-21 | 奥迪股份公司 | 驾驶辅助装置、驾驶辅助方法、车辆和介质 |
| DE102020116054A1 (de) * | 2020-06-18 | 2021-12-23 | Bayerische Motoren Werke Aktiengesellschaft | Verfahren, Vorrichtung, Computerprogramm und computerlesbares Speichermedium zum Ermitteln eines neuronalen Netzes und zum Betreiben eines Fahrzeuges |
| DE102021208422A1 (de) | 2021-08-04 | 2023-02-09 | Zf Friedrichshafen Ag | Verfahren, Computerprogramm, eingebettetes System und Fahrsystem zur Kommunikation eines Fahrzeuges mit Verkehrsteilnehmern |
| DE102023209058A1 (de) * | 2023-09-19 | 2025-03-20 | Robert Bosch Gesellschaft mit beschränkter Haftung | Hierarchische Systemarchitektur zur Steuerung eines automatisierten Fahrzeugs |
| DE102023132461A1 (de) * | 2023-11-21 | 2025-05-22 | Bayerische Motoren Werke Aktiengesellschaft | Steuerung eines Kraftfahrzeugs |
Family Cites Families (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE8205948U1 (de) * | 1982-03-04 | 1984-03-08 | Goebels, Hardo, 6800 Mannheim | Kraftfahrzeug |
| DE4305186C2 (de) | 1993-02-19 | 1996-02-01 | Gerhaher Max | Verfahren zur Reduzierung der Gefahr von Auffahrunfällen im Straßenverkehr durch eine Verzögerungswarnung und Verzögerungswarnanlage |
| US6421600B1 (en) * | 1994-05-05 | 2002-07-16 | H. R. Ross Industries, Inc. | Roadway-powered electric vehicle system having automatic guidance and demand-based dispatch features |
| DE10200002A1 (de) * | 2001-01-12 | 2002-08-22 | Zoltan Pal | E-Traffic Network e-Verkehr Netzwerk Verfahren Computergestützte über Präzision Position Information Navigation Telekommunikation Verkehrsüberwachungs-Koordinations-Operationssystem |
| US7526103B2 (en) * | 2004-04-15 | 2009-04-28 | Donnelly Corporation | Imaging system for vehicle |
| KR101035805B1 (ko) * | 2005-02-14 | 2011-05-20 | 삼성전자주식회사 | 이동체가 주행할 목적지까지 경로를 안내하는 방법 |
| US20120249797A1 (en) * | 2010-02-28 | 2012-10-04 | Osterhout Group, Inc. | Head-worn adaptive display |
| US10180572B2 (en) * | 2010-02-28 | 2019-01-15 | Microsoft Technology Licensing, Llc | AR glasses with event and user action control of external applications |
| US9994228B2 (en) * | 2010-05-14 | 2018-06-12 | Iarmourholdings, Inc. | Systems and methods for controlling a vehicle or device in response to a measured human response to a provocative environment |
| US20120126996A1 (en) * | 2010-11-19 | 2012-05-24 | Mccarthy Tom C | Hazardous vehicle alert system and method based on reaction time, distance and speed |
| DE102011111422A1 (de) * | 2011-08-23 | 2013-02-28 | Audi Ag | Multifunktionsband für ein Kraftfahrzeug |
| DE102011112577A1 (de) * | 2011-09-08 | 2013-03-14 | Continental Teves Ag & Co. Ohg | Verfahren und Vorrichtung für ein Assistenzsystem in einem Fahrzeg zur Durchführung eines autonomen oder teilautonomen Fahrmanövers |
| DE102011114888A1 (de) * | 2011-10-05 | 2013-04-11 | Gm Global Technology Operations, Llc | Verfahren zum Betreiben eines Fahrerassistenzsystems eines Kraftfahrzeugs und Fahrerassistenzsystem für ein Kraftfahrzeug |
| US9196164B1 (en) * | 2012-09-27 | 2015-11-24 | Google Inc. | Pedestrian notifications |
| DE102012022207B3 (de) * | 2012-11-13 | 2014-01-09 | Audi Ag | Verfahren zum Bereitstellen von Fahrstreckeninformationen mittels zumindest eines Kraftwagens |
| GB201305067D0 (en) * | 2013-03-19 | 2013-05-01 | Massive Analytic Ltd | Apparatus for controlling a land vehicle which is self-driving or partially self-driving |
| KR101470140B1 (ko) * | 2013-04-01 | 2014-12-05 | 현대자동차주식회사 | 주행모드 제어 시스템 및 방법 |
| US20150109148A1 (en) * | 2013-10-18 | 2015-04-23 | Elwha Llc | Pedestrian Warning System |
| US9014905B1 (en) | 2014-01-28 | 2015-04-21 | Google Inc. | Cyclist hand signal detection by an autonomous vehicle |
| US10112528B1 (en) * | 2015-07-28 | 2018-10-30 | Apple Inc. | Exterior lighting and warning system |
| US11077768B2 (en) * | 2015-07-30 | 2021-08-03 | Ford Global Technologies, Llc | Personalized range protection strategy for electrified vehicles |
| US9864918B2 (en) | 2015-11-04 | 2018-01-09 | Ford Global Technologies, Llc | Predicting vehicle movements based on driver body language |
| US20170190336A1 (en) * | 2016-01-04 | 2017-07-06 | Delphi Technologies, Inc. | Automated Vehicle Operation Based On Gesture To Pedestrian |
| US9969326B2 (en) * | 2016-02-22 | 2018-05-15 | Uber Technologies, Inc. | Intention signaling for an autonomous vehicle |
| US9913116B2 (en) * | 2016-02-24 | 2018-03-06 | Robert D. Pedersen | Multicast expert system information dissemination system and method |
| CN205396082U (zh) * | 2016-03-01 | 2016-07-27 | 西安工业大学 | 一种车辆防溜车的提醒装置 |
| DE102016114353A1 (de) * | 2016-08-03 | 2018-02-08 | Daimler Ag | Endkappe für eine beleuchtete Zierleistenanordnung sowie Zierleistenanordnung |
| US11001262B2 (en) * | 2017-01-31 | 2021-05-11 | Ford Global Technologies, Llc | Vehicle systems and methods for avoiding unintentional electrified vehicle movement and for reducing electrified vehicle noise, vibration, and harshness |
| DE102017217256A1 (de) | 2017-09-28 | 2019-03-28 | Zf Friedrichshafen Ag | Kommunikationsfluss von Verkehrsteilnehmer in Richtung eines automatisiert fahrenden Fahrzeug |
-
2017
- 2017-09-28 DE DE102017217256.8A patent/DE102017217256A1/de not_active Ceased
-
2018
- 2018-08-30 US US16/489,625 patent/US11126872B2/en active Active
- 2018-08-30 EP EP18772739.1A patent/EP3688661A1/de not_active Withdrawn
- 2018-08-30 CN CN201880016815.5A patent/CN110663042B/zh active Active
- 2018-08-30 WO PCT/EP2018/073318 patent/WO2019063237A1/de not_active Ceased
Also Published As
| Publication number | Publication date |
|---|---|
| US11126872B2 (en) | 2021-09-21 |
| WO2019063237A1 (de) | 2019-04-04 |
| US20200005056A1 (en) | 2020-01-02 |
| DE102017217256A1 (de) | 2019-03-28 |
| CN110663042A (zh) | 2020-01-07 |
| CN110663042B (zh) | 2023-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3688661A1 (de) | Kommunikationsfluss von verkehrsteilnehmer in richtung eines automatisiert fahrenden fahrzeug | |
| DE102021110309A1 (de) | Verfahren zum Modellieren eines menschlichen Fahrverhaltens zum Trainieren von Bewegungssteuerungen, die auf einem neuronalen Netzwerk basieren | |
| DE102017208728B4 (de) | Verfahren zur Ermittlung einer Fahranweisung | |
| DE102015224555A1 (de) | Verfahren zum Betreiben eines Fahrzeugs | |
| DE102019135131B4 (de) | Verfahren zur Verbesserung der Straßensicherheit | |
| EP3828758A1 (de) | Objektklassifizierungsverfahren, objektklassifizierungsschaltung, kraftfahrzeug | |
| DE102021203520B3 (de) | Verfahren zum Erzeugen eines Steuersignals für eine Querregeleinrichtung eines zumindest teilweise assistiert betriebenen Kraftfahrzeugs, sowie Assistenzsystem | |
| DE102021206297A1 (de) | Verfahren und System zum Betreiben eines wenigstens teilweise automatisierten Fahrzeugs | |
| DE102021004191A1 (de) | Verfahren zur Erkennung einer Überholabsicht und/oder Vorhersage von Einschermanövern von Fahrzeugen vor einem Ego-Fahrzeug | |
| DE10309934A1 (de) | Fahrsimulator und Verfahren zum Simulieren des Fahrzeugstands eines Fahrzeuges | |
| DE102014201037A1 (de) | Informationsübermittlung durch Oberflächenveränderung | |
| WO2019211293A1 (de) | Verfahren zum betreiben eines fahrerassistenzsystems eines egofahrzeugs mit wenigstens einem umfeldsensor zum erfassen eines umfelds des egofahrzeugs, computer-lesbares medium, system, und fahrzeug | |
| DE102021205037A1 (de) | Verfahren zum Ermitteln einer Steueraktion für eine Robotervorrichtung | |
| DE102018212266A1 (de) | Anpassung eines auswertbaren Abtastbereichs von Sensoren und angepasste Auswertung von Sensordaten | |
| DE102020212009A1 (de) | Steuervorrichtung für ein Fahrzeug | |
| DE102008038859A1 (de) | System zur Erfassung der Wahrnehmung eines Menschen | |
| WO2019115186A2 (de) | Signalisieren einer fahrentscheidung eines automatisiert betreibbaren fahrzeuges für einen verkehrsteilnehmer | |
| DE102020209987A1 (de) | Vorrichtung und Verfahren zum Verarbeiten von Umfeldsensordaten | |
| DE102018206745B4 (de) | Verfahren zum Betreiben eines Fahrzeugs mit Umfeldsensoren zum Erfassen eines Umfelds des Fahrzeugs, computerlesbares Medium, System, und Fahrzeug | |
| DE102020003692A1 (de) | Assistenzsystem zur schallabhängigen Erkennung von Objekten im Straßenverkehr und einer Warnfunktion | |
| DE102018219255A1 (de) | Trainingssystem, Datensatz, Trainingsverfahren, Auswerteeinrichtung und Einsatzsystem für ein Straßenfahrzeug zum Erfassen und Klassifizieren von Verkehrsgeräuschen | |
| DE102021004068A1 (de) | Verfahren zum Betrieb eines Assistenzsystems zur geschwindigkeitsabhängigen Abstandsregelung eines Fahrzeugs | |
| DE102022132377A1 (de) | Verfahren zum Betreiben einer automatisierten Fahrfunktion, Verfahren zum Trainieren einer künstlichen Intelligenz und Verarbeitungseinrichtung | |
| WO2023025613A1 (de) | Validieren einer fahrsteuerungsfunktion für den automatischen betrieb eines fahrzeugs | |
| DE102018219269A1 (de) | Verfahren, Computerprogrammprodukt, Detektionssystem und Verwendung des Detektionssystems zur akustischen Erfassung und/oder Zielverfolgung von Elektrofahrzeugen |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20190711 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| AX | Request for extension of the european patent |
Extension state: BA ME |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20220301 |