Classifications

• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L67/00—Network arrangements or protocols for supporting network services or applications
  • H04L67/01—Protocols
  • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B60—VEHICLES IN GENERAL
  • 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
  • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
  • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
  • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
  • G06F21/55—Detecting local intrusion or implementing counter-measures
  • G06F21/552—Detecting local intrusion or implementing counter-measures involving long-term monitoring or reporting
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
  • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
  • G06F21/55—Detecting local intrusion or implementing counter-measures
  • G06F21/554—Detecting local intrusion or implementing counter-measures involving event detection and direct action
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L63/00—Network architectures or network communication protocols for network security
  • H04L63/12—Applying verification of the received information
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
  • H04L63/00—Network architectures or network communication protocols for network security
  • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B60—VEHICLES IN GENERAL
  • 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
  • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
  • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
• • 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
  • G06N3/08—Learning methods

Definitions

• the present invention relates to an arrangement and a method for controlling a device.
• a system is known from TW 201802705, which comprises an artificial intelligence and has a first artificial intelligence module with functions for supported or self-disciplined information exchange with an open network and a second artificial intelligence module for monitoring the first artificial intelligence module, during operation the Monitoring takes place independently in a closed network alongside an information exchange process.
• This can manipulate the first artificial intelligence module by e.g. B. a hacker attack can be detected by the second artificial intelligence module.
• this does not provide a safeguard against a wrong decision by the first artificial intelligence module.
• a monitoring device which can be a predecessor version of the first non-deterministic, self-learning system or a determined system. Furthermore, data of a first measuring device are processed by the first non-deterministic, self-learning system, while data of a first and / or a second measuring device are processed by the monitoring device.
• a first measuring device and / or a second measuring device a first non-deterministic, self-learning system, the first non-deterministic, self-learning system being designed to process measurement data from the first measuring device and to output a first signal for controlling the device,
• the monitoring device being designed to process measurement data from the first measuring device and / or the second measuring device and to output a second signal which contains information about the plausibility of the first signal
• control unit which is designed to receive and process the first signal and the second signal
• the monitoring device is a second non-deterministic, self-learning system and a previous version of the first system, or
• a first measuring device is a device for recording first measurement data which contain information about the surroundings of the device.
• z. B objects in a direction of movement of the device or in the vicinity of the device, or movement data via a in one
• This first measurement data can actively z. B. by means of electromagnetic distance measurement, in particular radar or
• the detection of objects can be passive z. B. by receiving signals emitted or reflected by obstacles, for example by
• a second measuring device is a device for recording second measurement data which contain information about the surroundings of the device.
• z. B objects in a direction of movement of the device or in the vicinity of the device, or movement data via a in one
• This second measurement data can actively z. B. by means of electromagnetic distance measurement, in particular radar or
• the detection of objects can be passive z. B. by receiving signals emitted or reflected by obstacles, for example by
• a first non-deterministic, self-learning system in short the first system, is an artificial intelligence that uses in particular a neural network and was preferably trained with the help of data, that is to say with machine learning.
• a deterministic system is a system in which the transition from one state to the next subsequent state is determined. For example, the
• a non-deterministic system is a system in which the transition from one state to the next subsequent state is not determined.
• a learned neural network is a deterministic system, whereas a system is non-deterministic as long as the learning process continues.
• determinacy is to denote the degree of predetermination of a system.
• the transition from an initial state Z1 to an end state Z3 is determined.
• the transition from the initial state Z1 to an intermediate state Z2 or from an intermediate state Z2 to an end state Z3 is not determined.
• the second system is determined.
• a final state Z3 is accordingly determined from the initial state Z1 for the first system.
• An intermediate state Z2 is not determined.
• the second system is not determined. Accordingly, in this embodiment, neither a final state Z3 nor an intermediate state Z2 is determined from the initial state Z1 for the first system.
• Radius of movement of the device is located. This means that the first signal contains information to avoid contact between the device and the object. For example, it can be provided that the first signal signals an acceleration of the device in the form of a change in the direction of movement and / or in the form of a reduction in the speed of movement.
• the first measurement data of the object include
• the first signal then contains instructions for
• the device can thereby be directed to a predetermined destination.
• the measurement data include speed information.
• the first signal then contains instructions on the speed of movement of the device. For example, the device can thereby be moved at a predetermined speed.
• the measurement data comprise information about preferred movement sequences.
• the first signal then contains instructions on preferred ones
• Movements of the device For example, it can be provided that the first to control a preferred movement sequence, for. B. a change in direction is designed in combination with an acceleration.
• the measurement data comprise priority information.
• Movement sequence must adapt to that of an object, or whether an object must adapt its movement sequence to that of a device.
• the first signal controls a device, for example, in such a way that the device is brought to a standstill from a moving state. This allows an object to pass the area around the device. After passing the object, the device is brought back into a moving state from a standstill.
• a monitoring device is a device for generating and outputting a second signal, which contains information about the plausibility of the first signal.
• the monitoring device can process the same measurement data as the first system, that is to say the first measurement data.
• the monitoring device can come to a different result than the first system. For example, the
• Monitoring device detect a necessary change in the state of motion, whereas the first system does not change the necessary
• the first system Recognizes state of motion.
• the first system then outputs a first signal, which does not cause a change in the state of motion of the device.
• Monitoring device has recognized a necessary change in the state of motion.
• the monitoring device then outputs a second signal with the information about the lack of plausibility of the first signal.
• the monitoring device can process the second measurement data. Processing the second measurement data ensures additional security, since the first system, e.g. B. due to faulty first measurement data, z. B. a malfunction of the first measuring device, outputs a first signal for controlling the device, which may be faulty, but is not recognized by the monitoring device as implausible, since the monitoring device could come to the same evaluation as the first system based on the faulty first measurement data and could therefore output a second signal that indicates plausibility.
• a first faulty signal can be recognized as implausible by the second signal due to faulty first measurement data.
• the plausibility information is output as described above in the event that the monitoring device processes the first measurement data.
• the monitoring device can process both a part of the first measurement data, the complete first measurement data, and the second measurement data. Processing the first measurement data and the second measurement data ensures a further additional security, since incorrect measurement data of the first
• Measuring device or the second measuring device can lead to a second signal which does not indicate the plausibility of the first signal.
• the processing of the first measurement data and the second measurement data by the monitoring device would lead to the same result as the processing of the first measurement data by the first system.
• the second signal would then indicate that the first signal is plausible. If z. B. only the second
• Measurement data are incorrect, the processing of the first measurement data and the second measurement data by the monitoring device z. B. lead to different results. Accordingly, the second signal would not indicate the plausibility of the first signal, since at least the result from the processing of a measurement data set, e.g. B. the processing from the faulty second measurement data record does not indicate a plausibility of the first signal.
• the control unit is e.g. B. a processor.
• the monitoring device can be a second non-deterministic, self-learning system and a previous version of the first system, in short the second system.
• a second system is an artificial intelligence, which is in particular a neural network used and preferably trained with the help of data, i.e. with machine learning.
• the previous version means that the second system is an older configuration of the first system, the first system being at least different from the second system by an update and / or upgrade, that is to say at least an update and / or upgrade of the first system Systems compared to the second system was carried out.
• the second system is a downdate (downdate denotes the creation of a software version before an update is imported) and / or downgrade of the first system.
• a previous version in the sense of a neural network designates a configuration which the neural network had at an earlier point in time.
• a configuration results e.g. B. from the weighted edges of a neural network.
• a neural network can have a configuration K1 at a time t1 and a configuration K2 at a time t2.
• the time t1 lies further in the past than the time t2.
• Configuration K1 is then a previous version of configuration K2.
• the second system is determined. In another embodiment, the second system is determined.
• the second system is undetermined.
• the monitoring device can also be a deterministic system.
• the deterministic system can comprise a program code of software.
• the first non-deterministic, self-learning system is connected to an open network and is configured by it.
• An open network is a network that is used for a plurality of systems e.g. B. a plurality of first systems is accessible.
• an open network allows the integration of systems from different manufacturers that communicate with one another using uniform rules.
• the majority of the first systems send information to the open network.
• the open network stores the information e.g. B. in a data Cloud.
• Training data sets for neural networks, in particular for first systems, are generated from the data of the data cloud and then sent through the open network to the respective first systems.
• the first systems can e.g. B. configured by machine learning through these training records.
• the open network can support or independently manage the exchange of desired information between the open network and a first system.
• the open network obtains its information, which is stored in the data cloud, from external sources, e.g. B. a first system.
• the monitoring device is a local entity.
• Local instance means that the monitoring device is not connected to an open network. Manipulation by external intervention, e.g. b. through a hacker attack are not possible.
• the local entity operates in a closed network.
• a local network only allows the integration of data stations, e.g. B. computers, one or less specific groups of participants.
• the arrangement has an output device, the control unit being designed such that no plausibility of the first signal is recognized during processing of the second signal
• the output device can give a warning such. B. in the form of an acoustic signal, an optical signal, and / or a haptic signal.
• the second signal additionally contains at least one piece of information for controlling the device or complete piece of information for controlling the device.
• the second signal can be identical to the first signal.
• the second signal can e.g. B. an acceleration of the device in the form of a
• the arrangement has a consistency unit, which is designed to check the first signal and the second signal for consistency and to transmit a third signal to the control unit.
• the third signal is a measure of the consistency of the first signal and the second signal.
• the control unit is designed to use the first signal to control the device as long as a limit value is not exceeded by the third signal.
• the consistency unit is e.g. B. a processor.
• the first signal and the second signal are forwarded to the control unit by the consistency unit.
• the third signal contains information about the consistency of the first signal and the second signal.
• the third signal can be a number from 0 to 1.
• the value 0 for the third signal means that the first signal and the second signal are identical.
• the value 1 for the third signal means that the first signal and the second signal contain opposite information.
• the first signal indicates a negative acceleration
• the second signal indicates a positive acceleration.
• the opposite information can also be understood in particular if the first signal does not indicate a change in the state of motion and the second signal indicates a change in the state of motion, or vice versa.
• a value between 0 and 1 for the third signal means that the first signal and the second signal contain similar information for controlling the device.
• the first signal indicates positive acceleration and the second signal also indicates positive, but stronger, acceleration.
• the greater the difference in the displayed acceleration of the first signal and the second signal the greater the value for the third signal.
• a limit value of 0 ⁇ g ⁇ 1 this means that the first signal is used to control the device, provided that the difference between the first signal and the second signal does not exceed the limit value.
• Acceleration of one signal is no more than twice the acceleration of the other signal. that the indicated acceleration by one signal is twice as high as the indicated acceleration by the other signal.
• the first signal is then used for control as long as the acceleration of one signal is no more than twice the acceleration of the other signal.
• control unit is designed to generate a warning if the limit value is exceeded.
• a warning can e.g. B. in the form of an acoustic signal, an optical signal, and or a haptic signal.
• control unit is designed to use the second signal to control the device when the limit value is exceeded, provided that the first signal does not indicate a change in a movement state of the device and the second signal indicates a change in a movement state of the device.
• the second signal is always used to control the device, as long as the first signal and the second signal are not identical and the first signal does not indicate a change in the state of motion of the device.
• control unit is designed to initiate an emergency stop when the limit value is exceeded, provided the first signal indicates a change in a movement state of the device.
• An emergency stop is to be understood to mean that the device is brought to a standstill as quickly as possible by negative acceleration.
• this arrangement for controlling knowledge-based systems such. B. in office communication, systems for pattern analysis and recognition z. B. for facial recognition, systems for pattern prediction z. B. for sales and / or systems of robotics, in particular for autonomous control of vehicles.
• the first system and / or the second system is integrated in the device which is to be controlled.
• the first system and / or the second system is detached from the device.
• data between the individual parts of the arrangement z. B. be transmitted by radio.
• the monitoring device a second non-deterministic, self-learning system, which is a previous version of the first non-deterministic, self-learning system, or
• FIG. 3 shows a schematic representation of an embodiment of a further arrangement for controlling a motor vehicle.
• Fig. 1 shows a schematic representation of an embodiment of a
• Arrangement 17 for controlling a device 16, for example a motor vehicle, with a first measuring device 1, first measurement data 3, a first system 5, a second system 6, a first signal 7, a second signal 8, a control unit 9, an output unit 1 1, a warning 12 and a control signal 15.
• the first measuring device 1 forwards first measurement data 3 to the first system 5 and to the second system 6.
• the first system 5 outputs the first signal 7 to the control unit 9.
• the second system 6 outputs the second signal 8 to the control unit 9.
• the control unit 9 is with the output unit 1 1 connected, via which a warning 12 can be issued.
• the control unit 9 transmits a control signal 15 to the device 16.
• the first signal 7 contains information about the control of the device 16 and the second signal 8 contains information about the plausibility of the first signal 7. If the control unit 9 does not detect a plausibility of the first signal 7 by the second signal 8, the output device 11 is activated the control unit 9 causes a warning 12 to be issued. Furthermore, in particular a
• Control signal 15 which is not identical to the first signal 7 to the
• the control signal 15 contains, in particular, instructions for controlling the device in three
• Fig. 2 shows a schematic representation of an embodiment of a
• Arrangement 17 for controlling a device 16 with a first measuring device 1, a second measuring device 2, first measurement data 3, second measurement data 4, a first system 5, a second system 6, a first signal 7, a second signal 8, a control unit 9 , an open network 10, an output unit 11, a warning 12, a consistency unit 13, a third signal 14, a control signal 15.
• the first measuring device 1 forwards first measurement data 3 to the first system 5 and to the second system 6.
• the second measuring device 2 forwards second measurement data 4 to the second system 6.
• the first system 5 is connected to an open network 10.
• the first system 5 outputs the first signal 7 to the consistency unit 13 and the second system 6 outputs the second signal 8 to the consistency unit 13.
• the consistency unit 13 outputs the third signal 14 to the control unit 9.
• the consistency unit 13 forwards the first signal 7 and the second 8 to the control unit 9.
• the first signal 7 and the second signal 8 can be forwarded directly from the first system 5 and the second system 6 to the control unit 9.
• the control unit 9 is with the
• the control unit 9 transmits a control signal 15 to the device 16. Provided there is consistency between the first signal 7 and the second signal 8 by the third Signal 14 is displayed, the control signal 15 is in particular identical to the first signal 7.
• Fig. 3 shows a schematic representation of an embodiment of a
• the measuring device 1 transmits first measurement data 3 to a first system 5 and to a second system 6.
• the first system 5 processes the first measurement data 3 and forwards a first signal 7 to a consistency unit 13.
• the second system 6 processes the first measurement data 3 and outputs a second signal 8 to one
• Consistency unit 13 further.
• the consistency unit 13 checks the first signal 7 and the second signal 8 for consistency and outputs a third signal 14, which contains information on the consistency of the first signal 7 and the second signal 8, the first signal 7 and the second signal 8 to the control unit 9 further.
• the control unit 9 controls the motor vehicle on the basis of the third signal 14 and the first signal 7 or the second signal 8.
• the first system 5 consists of an open network. The first system 5 can in particular be detached from the motor vehicle. The first
• Measurement data 3 can be made by means of a communication device 18, in particular a wireless communication device, e.g. B. can be sent by radio to the first system 5.
• the first system 5 can e.g. B. by radio a first signal 7 to the
• the second system 6 is a local system and can in particular be installed in and / or on the motor vehicle.
• the consistency unit 13 is mounted in particular in and / or on the motor vehicle.
• the consistency unit 13 processes the first signal 7 and the second signal 8.
• the third signal 14 of the consistency unit 13 is used, among other things, to control the motor vehicle and can e.g. B. detect an inconsistency of the first signal 7 with the second signal 8 to an emergency braking of the motor vehicle, which by the
• Control unit 9 is initiated.
• the control signal 15 contains, in particular, information for controlling the motor vehicle for longitudinal and / or lateral control. Reference list

Landscapes

• Engineering & Computer Science (AREA)
• Computer Security & Cryptography (AREA)
• Theoretical Computer Science (AREA)
• Software Systems (AREA)
• Computer Hardware Design (AREA)
• General Engineering & Computer Science (AREA)
• Signal Processing (AREA)
• Computing Systems (AREA)
• Computer Networks & Wireless Communication (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Transportation (AREA)
• Mathematical Physics (AREA)
• Automation & Control Theory (AREA)
• Mechanical Engineering (AREA)
• Health & Medical Sciences (AREA)
• General Health & Medical Sciences (AREA)
• Medical Informatics (AREA)
• Arrangements For Transmission Of Measured Signals (AREA)
• Safety Devices In Control Systems (AREA)
• Traffic Control Systems (AREA)

Priority Applications (2)

Applications Claiming Priority (2)

Publications (1)

Family

ID=67841058

Family Applications (1)

Country Status (4)

Citations (5)

Family Cites Families (6)

• 2018
  • 2018-09-03 DE DE102018214921.6A patent/DE102018214921A1/de active Pending
• 2019
  • 2019-08-30 WO PCT/EP2019/073182 patent/WO2020048879A1/de not_active Ceased
  • 2019-08-30 JP JP2021509762A patent/JP7416765B2/ja active Active
  • 2019-08-30 EP EP19762355.6A patent/EP3847592B1/de active Active

Patent Citations (6)

Also Published As

Similar Documents

Legal Events