CN110867096A - Mountain road safety control system and method suitable for vehicles with multiple automatic driving grades - Google Patents
Mountain road safety control system and method suitable for vehicles with multiple automatic driving grades Download PDFInfo
- Publication number
- CN110867096A CN110867096A CN201910947842.0A CN201910947842A CN110867096A CN 110867096 A CN110867096 A CN 110867096A CN 201910947842 A CN201910947842 A CN 201910947842A CN 110867096 A CN110867096 A CN 110867096A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- base station
- vehicles
- mountain
- information
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/164—Centralised systems, e.g. external to vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a mountainous road safety control system and method suitable for vehicles of various automatic driving grades, and belongs to the field of automatic driving vehicle control management. The invention arranges an edge computing base station under the mountain legs, and uniformly delivers the unmanned vehicles running on the mountain road to the edge computing base station for management control, and the computing decision of the unmanned vehicles running is completely completed by the edge computing base station. Because the high-precision mountain area map is stored in the edge calculation base station, the position information of all vehicles in the mountain area can be obtained, and the edge calculation base station has strong calculation capacity, the driving of the unmanned vehicle under the control of the mountain area edge calculation base station is safer and more reliable compared with the independent control of the unmanned vehicle. The invention has the characteristics of less equipment quantity, simple control method, reliable control and easy realization, and can ensure the driving safety of vehicles in mountainous areas to a great extent.
Description
Technical Field
The invention relates to the field of automatic driving vehicle control, in particular to a mountain automatic driving vehicle control system and method based on an edge computing base station.
Background
In recent years, with the development of new-generation information technologies such as artificial intelligence, visual computing, internet of things, radar, high-precision maps, high-performance computing and the like, automatic driving has achieved breakthrough, and the current automatic driving level has reached the level of L3 and is moving towards the level of L4. It is expected that autonomous vehicles will be put into practical use in the near future. However, autonomous vehicles and non-autonomous vehicles may be present on the road simultaneously for a long time after autonomous driving has just been put into use, which may present a number of difficulties in the control and management of the vehicles.
The automatic driving vehicle mainly realizes the automatic driving of the vehicle by the cooperative cooperation of artificial intelligence, visual calculation, radar, a monitoring device and a global positioning system, and in a mountain area with more sharp turns and more visual fields and sensing blind areas, the automatic driving vehicle can not make a proper and accurate decision because the automatic driving vehicle can not sense the front vehicle in time, so that the serious accidents of collision, overturning and even flying down a cliff are caused.
Therefore, how to reasonably and effectively manage and control the autonomous vehicles in the mountainous area so that the vehicles can safely and orderly run even when the autonomous vehicles and the non-autonomous vehicles coexist becomes a problem which must be solved before the autonomous vehicles are put into actual use. At present, the research aiming at the problem at home and abroad is few, and no similar documents can be found.
Disclosure of Invention
The invention provides a management and control system and a management and control method for mountain automatic driving vehicles based on an edge computing base station, aiming at the problem of how to reasonably and effectively manage and control the automatic driving vehicles under the condition that the automatic driving vehicles and non-automatic driving vehicles coexist in the initial stage of the formal use of the automatic driving vehicles, so that the automatic driving vehicles can safely and orderly run under extreme road conditions such as a mountain area.
The specific technical scheme of the invention is as follows:
a mountain road safety control system suitable for vehicles of various automatic driving grades comprises an entrance monitoring station, an exit monitoring station, an edge computing base station, vehicles and a cloud end; the mountain road has a bidirectional lane; the entrance and exit monitoring station is arranged at the entrance and exit of the mountain road, and is internally provided with a camera, a radar, a wireless signal transceiver and a license plate recognition system based on an OCR technology; the edge computing base station is arranged under the mountains of the mountains, and is internally provided with a super computer and a wireless signal transceiver, the super computer is provided with a 5G network module, a storage module and a computing module, and the storage module is stored with a deep learning network and a high-precision mountainous area three-dimensional electronic map;
the cameras in the entrance and exit monitoring stations are mainly responsible for shooting pictures of vehicles entering and exiting a mountain and transmitting the pictures to a license plate recognition system based on an OCR technology, and the license plate recognition system based on the OCR technology is responsible for recognizing license plate number information of the vehicles entering and exiting the mountain according to the received pictures and transmitting the license plate number information to the wireless signal transceivers in the entrance and exit monitoring stations for transmission; the radar in the entrance and exit monitoring station is mainly responsible for detecting the entering and exiting vehicles and measuring the speed information of the entering vehicles, and transmitting the speed information to the wireless signal transceiver in the entrance and exit monitoring station for transmission; the wireless signal transceiver in the entrance and exit monitoring station and the wireless signal transceiver in the edge computing base station are mainly responsible for transceiving wireless signals and carrying out information interaction; the 5G network module in the supercomputer in the edge computing base station can connect the supercomputer with a cloud end, so that the computer can download information from the cloud end or upload the information to the cloud end, the storage module is mainly responsible for storing various information, and the computing module is mainly responsible for decision calculation of unmanned vehicles in mountainous areas to obtain a control scheme; the deep learning network stored in the storage module in the super computer in the edge computing base station is used for decision calculation of the unmanned vehicles in the mountainous area, and the high-precision three-dimensional electronic map in the mountainous area is used for accurately restoring the position and the environment of each vehicle on the mountains, so that the decision control of the edge computing base station on the unmanned vehicles is more reasonable and safer;
the edge calculation base station is connected with the access monitoring station through a wireless network to transmit information; the edge computing base station is connected with the vehicle through a wireless network for information transmission (except for vehicles incapable of receiving and transmitting wireless signals); the edge computing base station can be connected with a cloud end through a 5G network, so that information can be downloaded from the cloud end or uploaded to the cloud end;
the vehicle comprises six automatic driving grades of vehicles L0-L5 divided by the International automobile engineering Association; dividing the vehicle according to different driving types again, wherein the vehicle of L0 is a traditional vehicle, the vehicles of L1-L3 are intelligent driving vehicles, and the vehicles of L4 and L5 are unmanned driving vehicles;
the traditional vehicle is not provided with driving auxiliary equipment, cannot receive and transmit wireless signals, cannot perform information interaction with the outside and needs to be driven by a driver; the intelligent driving vehicle is provided with a vehicle-mounted camera, a vehicle-mounted millimeter wave radar, a vehicle-mounted network CAN transceiver and a GPS positioning system, so that auxiliary driving CAN be realized, and the intelligent driving vehicle still needs to be controlled by a driver; the unmanned vehicle is provided with a vehicle-mounted camera, a vehicle-mounted millimeter wave radar, a vehicle-mounted network CAN transceiver, a GPS positioning system and a decision control system, is highly intelligent and is not driven by a driver;
the vehicle-mounted camera is used for acquiring road conditions around the vehicle and vehicle information; the vehicle-mounted millimeter wave radar is used for acquiring relative position information and speed information of the vehicle and surrounding vehicles; the vehicle-mounted network CAN transceiver is used for being connected with other external equipment through a wireless network to realize information interaction; the GPS is used for accurately positioning the vehicles in the mountainous area; the decision control system is used for driving control of the unmanned vehicle;
when the traditional vehicle cannot be detected by other vehicles, the position of the traditional vehicle on the mountain road, which is stored in a storage module of the edge calculation base station, is an estimated position, and a road section with the length of 2d before and after the estimated position is taken as a center is marked as a dangerous road section, wherein d ═ k ═ v × t, k is a prediction uncertainty coefficient and is a constant value obtained by training a neural network model in the storage module, v is the normal driving speed of the mountain area corresponding to the type of the traditional vehicle, and t is the time that the vehicle passes from departure detection; the length of the dangerous road section is continuously increased along with the increase of the time for detecting the conventional vehicle to get away from, the front and the back of the dangerous road section are limited by the nearest equipment with the detection function, and the equipment with the detection function refers to an intelligent driving vehicle, an unmanned driving vehicle and an entrance and exit monitoring station; the estimated position and the dangerous road section continuously move towards the vehicle running direction at the normal running speed of the mountainous area corresponding to the traditional vehicle type; when the traditional vehicle is detected by other intelligent driving vehicles or unmanned vehicles again, the position information stored in the storage module of the edge computing base station is updated, and the length of the dangerous road section is reduced to zero;
a mountain road safety management method suitable for vehicles with multiple automatic driving grades comprises the following steps:
step1, when a vehicle drives into a mountain road from a mountain road entrance and exit, the entrance and exit monitoring station detects that the vehicle enters the mountain through a radar, a camera shoots a picture of the vehicle, a license plate recognition system recognizes the license plate number of the vehicle, and after recognition is finished, mountain entering information and license plate number information of the vehicle are transmitted to an edge computing base station through a wireless signal transceiver;
step2, the edge computing base station obtains model information, automatic driving level information and other vehicle data information of the vehicle through 5G network inquiry from the cloud by means of the received license plate number information, the automatic driving type of the vehicle is judged according to the automatic driving level of the vehicle, after the judgment, if the vehicle is a traditional vehicle, Step3.1 is executed, if the vehicle is an intelligent driving vehicle, Step3.2 is executed, and if the vehicle is an unmanned vehicle, Step3.3 is executed;
step3.1, estimating the position of the vehicle on a mountain road by the edge computing base station by means of the normal running speed of the vehicle of the type in the mountain area obtained by query and a high-precision mountain area three-dimensional electronic map stored in a super computer, and marking a dangerous road section according to the estimated position; in the driving process, when other unmanned vehicles or intelligent vehicles detect the vehicle, the vehicle which detects the vehicle sends the position information of the vehicle to the edge computing base station, and the edge computing base station updates the position information of the vehicle in the storage module; when the entrance and exit monitoring station detects that the vehicle goes out of a mountain through a radar and a camera, information is sent to inform the edge computing base station, the edge computing base station finishes the estimation and calculation of the position of the vehicle, and the driving data of the vehicle is substituted into a neural network model stored in a storage module for training, so that the k value of the prediction uncertainty coefficient is optimized;
step3.2, the edge computing base station and the vehicle are butted through an information transmission protocol, and the edge computing base station acquires the authority of inquiring the position information of the vehicle in real time; when the entrance and exit monitoring station detects that the vehicle goes out of a mountain through a radar and a camera, information is sent to inform the edge computing base station, the protocol between the edge computing base station and the workshop is removed, the butt joint is interrupted, the edge computing base station substitutes the driving data of the vehicle into a deep learning network model stored in a storage module for deep learning, and the reliability of decision control on the unmanned vehicle is enhanced;
step3.3, the edge computing base station and the vehicle are butted through an information transmission protocol and a control protocol, the edge computing base station acquires the authority for inquiring the vehicle information in real time and the authority for controlling the vehicle to run, the original vehicle self-control running mode is changed into a base station control running mode, and a decision computing center is transferred to a super computer in the edge computing base station through a decision control system of the vehicle; when the entrance and exit monitoring station detects that the vehicle goes out of a mountain through a radar and a camera, information is sent to inform the edge computing base station, the protocol between the edge computing base station and the workshop is removed, the butt joint is interrupted, the vehicle recovers the original driving state, the edge computing base station substitutes the driving data of the vehicle into a deep learning network model stored in a storage module for deep learning, and the reliability of decision control on the unmanned vehicle is enhanced;
the unmanned vehicle running under the control of the edge calculation base station may meet other vehicles near the intersection of the curve of the mountain road, and the specific control method in this case is as follows:
when the distance between the unmanned vehicle and the front mountain curve entrance is less than or equal to x1, the edge calculation base station counts vehicles on a road section with the distance between the other end of the curve entrance and the curve entrance being within x2 (x1 and x2 are both preset values, and x1 is less than x2), and adopts one of the following four schemes according to the counted vehicle types;
the first scheme is as follows: if no vehicle or only unmanned vehicle exists on the counted road section, the scheme is adopted; the edge calculation base station controls the vehicle to keep the vehicle to normally run in a lane and pass through a bend;
scheme II: if only intelligent driving vehicles exist on the counted road section, the scheme is adopted; the edge calculation base station firstly sends information to inform the intelligent driving vehicle of paying attention to the fact that a vehicle is arranged at the other end of the curve port, and predicts which vehicle firstly drives to the curve port according to the distance between the two vehicles and the curve port and the current driving speed of the two vehicles, if the unmanned vehicle firstly drives to the curve port, the edge calculation base station controls the unmanned vehicle to accelerate, after the unmanned vehicle passes through the curve port of the mountain road, the edge calculation base station controls the unmanned vehicle to recover the original driving state, and the intelligent driving vehicle and the edge calculation base station finish vehicle meeting at the side; if the intelligent driving vehicle firstly drives to the curve opening, the edge computing base station controls the unmanned vehicle to decelerate, after the intelligent driving vehicle passes through the curve opening, the edge computing base station controls the unmanned vehicle to recover the original driving state, and the intelligent driving vehicle finishes meeting at the side and then passes through the curve opening;
the third scheme is as follows: if only the traditional vehicles exist on the counted road section, the scheme is adopted; the edge calculation base station performs pre-estimation calculation and judgment, if the unmanned vehicle can pass through a mountain road junction before the front section of the dangerous section corresponding to the traditional vehicle reaches the mountain road junction, the edge calculation base station controls the unmanned vehicle to run at an accelerated speed, after the unmanned vehicle passes through the mountain road junction, the edge calculation base station controls the unmanned vehicle to recover the original running state and finish vehicle meeting with the traditional vehicle at the side, otherwise, the edge calculation base station controls the unmanned vehicle to run at a decelerated speed, after the traditional vehicle passes through the mountain road junction, the edge calculation base station controls the unmanned vehicle to recover the original running state, finish vehicle meeting with the traditional vehicle at the side and then pass through the mountain road junction;
and the scheme is as follows: if the various types of vehicles exist on the counted road section, the scheme is adopted; the edge calculation base station controls the unmanned vehicle to decelerate, controls the unmanned vehicle to restore the original driving state after all the counted vehicles pass through the mountain road junction, finishes meeting with the counted vehicles on the side, and then passes through the mountain road junction;
the invention has the beneficial effects that: according to the invention, the edge computing base station is set up, and the original vehicles which are isolated from each other are linked, so that unified management control on the automatic driving vehicles in the mountainous area is realized, the condition that the oncoming vehicles cannot be found due to the existence of a vision blind area or a monitoring blind area under the extreme working condition of the mountainous area and further the risks cannot be avoided by timely reacting is effectively avoided, the problem that how to reasonably and effectively manage and control the automatic driving vehicles under the condition that the automatic driving vehicles coexist with the non-automatic driving vehicles at the initial stage of formal use of the automatic driving vehicles is solved, the automatic driving vehicles can safely and orderly run under the extreme road condition of the mountainous area is solved, and the running of the automatic driving vehicles under the dangerous working condition of the mountainous area becomes safe and reliable; in addition, the automatic driving vehicle control method of the invention enables the automatic driving vehicle in the mountainous area to run more orderly, can effectively improve the vehicle passing and bending passing efficiency and reduces the occurrence of traffic jam conditions.
Drawings
FIG. 1 is a general diagram of a mountain area autonomous vehicle control system based on edge computing base stations;
FIG. 2 is a chart of an autopilot type division of the mountain vehicle; (ii) a
FIG. 3 is a schematic view of the dangerous segment;
FIG. 4 is a control flow chart of the mountain vehicle;
FIG. 5 is a flow chart of the control of the crossing of an unmanned vehicle at a mountain road junction;
FIG. 6 is a control schematic diagram of two unmanned vehicles meeting at the entrance of a mountain curve;
FIG. 7 is a control schematic diagram of the unmanned vehicle and the intelligent driving vehicle when meeting at the intersection of a mountain road curve;
FIG. 8 is a control schematic diagram of an unmanned vehicle and a conventional vehicle meeting at a mountain curve intersection;
the notations in the figures have the following meanings:
1-mountains, 2-mountains, 3-mountains, entrances and exits, 4-entrance monitoring stations, 41-cameras, 42-license plate recognition systems, 43-radars, 44-first wireless signal transceivers, 5-edge calculation base stations, 51-second wireless signal transceivers, 52-super computers, 521-5G network modules, 522-storage modules, 5221-deep learning networks, 5222-high-precision mountainous area three-dimensional electronic maps, 523-calculation modules, 6-vehicles, 61-traditional vehicles, 62-intelligent driving vehicles, 601-vehicle-mounted cameras, 602-vehicle-mounted millimeter wave radars, 603-vehicle-mounted network CAN transceivers, 604-GPS positioning systems, 605-decision control systems, 63-unmanned vehicles, 7-cloud end, 8-wireless network, 9-5G network and 10-dangerous road section.
Detailed Description
The invention will be further explained with reference to the drawings.
A mountain road safety management system suitable for vehicles with various automatic driving grades is shown in figure 1 and is characterized by comprising a mountain (1), a mountain road (2), a mountain road access (3), an access monitoring station (4), an edge computing base station (5), vehicles (6) and a cloud (7); the mountain road (2) has a bidirectional lane; the entrance and exit monitoring station (4) is arranged at the mountain road entrance and exit (3), and is internally provided with a camera (41), a radar (43), a first wireless signal transceiver (44) and a license plate recognition system (42) based on an OCR technology; the edge calculation base station (5) is arranged under the mountain corner of the mountain range (1), a super computer (52) and a second wireless signal transceiver (51) are arranged in the edge calculation base station, the super computer (52) is provided with a 5G network module (521), a storage module (522) and a calculation module (523), and a deep learning network (5221) and a high-precision mountain three-dimensional electronic map (5222) are stored in the storage module (522);
the camera (41) in the entrance and exit monitoring station (4) is mainly responsible for shooting pictures of vehicles entering and exiting a mountain and transmitting the pictures to the license plate recognition system (42) based on the OCR technology, and the license plate recognition system (42) based on the OCR technology is responsible for recognizing license plate number information of the vehicles entering and exiting the mountain according to the received pictures and transmitting the license plate number information to the first wireless signal transceiver (44) in the entrance and exit monitoring station (4) for transmission; the radar (43) in the entrance and exit monitoring station (4) is mainly responsible for detecting the entering and exiting vehicles and measuring the speed information of the entering vehicles, and transmitting the speed information to the first wireless signal transceiver (44) in the entrance and exit monitoring station (4) for transmission; a first wireless signal transceiver (44) in the entrance monitoring station (4) and a second wireless signal transceiver (51) in the edge computing base station (5) are mainly responsible for transceiving wireless signals and carrying out information interaction; a 5G network module (521) in a supercomputer (52) in the edge computing base station (5) can establish connection between the supercomputer (52) and a cloud end (7), so that the computer can download information from the cloud end (7) or upload the information to the cloud end (7), a storage module (522) is mainly responsible for storage of various information, and a calculation module (523) is mainly responsible for decision calculation of unmanned vehicles (63) in mountainous areas to obtain a control scheme; the deep learning network (5221) stored in the storage module (522) of the super computer (52) in the edge computing base station (5) is used for decision calculation of the unmanned vehicles (63) in the mountainous area, and the high-precision three-dimensional electronic map (5222) in the mountainous area is used for accurately restoring the position and environment of each vehicle on the mountains (1), so that the decision control of the edge computing base station (5) on the unmanned vehicles (63) is more reasonable and safer;
the edge calculation base station (5) is connected with the entrance and exit monitoring station (4) through a wireless network (8) for information transmission; the edge computing base station (5) is connected with the vehicle (6) through a wireless network (8) for information transmission (except for vehicles which cannot transmit and receive wireless signals); the edge computing base station (5) can be connected with the cloud end (7) through a 5G network (9), so that information can be downloaded from the cloud end (7) or uploaded to the cloud end (7);
the vehicle (6) comprises six automatic driving grades of vehicles L0-L5 which are divided by the International automobile engineering society; the vehicle is divided again according to different driving types, the vehicle of L0 is a traditional vehicle (61), the vehicles of L1-L3 are intelligent driving vehicles (62), and the vehicles of L4 and L5 are unmanned driving vehicles (63), as shown in the figure 2;
the traditional vehicle (61) is not provided with driving auxiliary equipment, cannot transmit and receive wireless signals, cannot perform information interaction with the outside and needs to be driven by a driver; the intelligent driving vehicle (62) is provided with a vehicle-mounted camera (601), a vehicle-mounted millimeter wave radar (602), a vehicle-mounted network CAN transceiver (603) and a GPS positioning system (604), so that driving assistance CAN be realized, but the intelligent driving vehicle still needs to be controlled by a driver; the unmanned vehicle (63) is provided with a vehicle-mounted camera (601), a vehicle-mounted millimeter wave radar (602), a vehicle-mounted network CAN transceiver (603), a GPS positioning system (604) and a decision control system (605), is highly intelligent and is not driven by a driver;
the vehicle-mounted camera (601) is used for acquiring road conditions and vehicle information around the vehicle (6); the vehicle-mounted millimeter wave radar (602) is used for acquiring relative position information and speed information of a vehicle and surrounding vehicles; the vehicle-mounted network CAN transceiver (603) is used for being connected with other external equipment through a wireless network (8) to realize information interaction; the GPS positioning system (604) is used for realizing accurate positioning on the vehicles (6) in the mountainous area; -the decision control system (605) is used for driving control of the unmanned vehicle (63);
when the conventional vehicle (61) cannot be detected by other vehicles, the position of the conventional vehicle (61) on the mountain road (2) stored in the storage module (522) of the edge computing base station (5) is an estimated position, and a road section with the length of 2d before and after the estimated position is taken as a center is marked as a dangerous road section (10), wherein d is k, v and t, k are prediction uncertainty coefficients and are constant values obtained by training a neural network model in the storage module, v is the normal driving speed of the mountain area corresponding to the vehicle type of the conventional vehicle (61), and t is the time elapsed from the departure detection of the vehicle; the length of the dangerous road section (10) is continuously increased along with the increase of the time for detecting the conventional vehicle (61) to get away from, the front and the back of the dangerous road section are limited by the nearest equipment with a detection function, and the equipment with the detection function refers to an intelligent driving vehicle (62), an unmanned vehicle (63) and a gateway monitoring station (4), as shown in the attached figure 3; the estimated position and the dangerous road section (10) continuously move towards the vehicle running direction at the normal running speed of the mountain area corresponding to the vehicle type of the traditional vehicle (61); when the traditional vehicle (61) is detected by other intelligent driving vehicles (62) or unmanned vehicles (63) again, the position information stored in the storage module (522) of the edge calculation base station (5) is updated, and the length of the dangerous road section (10) is reduced to zero;
a mountain road safety management method suitable for vehicles with various automatic driving grades is disclosed, the control flow of which is shown in figure 4, and the method specifically comprises the following steps:
step1, when a vehicle drives into a mountain road (2) from a mountain road entrance (3), the entrance monitoring station (4) detects the entrance of the vehicle into the mountain through a radar (43), takes a picture of the vehicle through a camera (41), passes the picture to a license plate recognition system (42) to recognize the license plate number of the vehicle, and transmits the entrance information and the license plate number information of the vehicle to an edge calculation base station (5) through a first wireless signal transceiver (44) after the recognition is finished;
step2, the edge computing base station (5) inquires and obtains model information, automatic driving level information and other vehicle data information of the vehicle from a cloud end (7) through a 5G network (9) by means of the received license plate number information, the automatic driving type of the vehicle is judged according to the automatic driving level of the vehicle, after judgment, if the vehicle is a traditional vehicle (61), Step3.1 is executed, if the vehicle is an intelligent driving vehicle (62), Step3.2 is executed, and if the vehicle is an unmanned vehicle (63), Step3.3 is executed;
step3.1, estimating the position of the vehicle on the mountain road (2) by the edge calculation base station (5) by means of the normal running speed of the vehicle of the type in the mountain area obtained by inquiry and a high-precision three-dimensional mountain area electronic map (5222) stored in a super computer (52), and marking a dangerous road section (10) according to the estimated position; in the driving process, when other unmanned vehicles (63) or intelligent vehicles detect the vehicle, the vehicle which detects the vehicle sends the position information of the vehicle to the edge computing base station (5), and the edge computing base station (5) updates the position information of the vehicle in the storage module (522); when the entrance and exit monitoring station (4) detects that the vehicle is going out of a mountain through a radar (43) and a camera (41), information is sent to inform the edge calculation base station (5), the edge calculation base station (5) finishes the estimation calculation of the position of the vehicle, and the driving data of the vehicle is substituted into a neural network model stored in a storage module (522) for training, so that the k value of the prediction uncertainty coefficient is optimized;
step3.2, the edge computing base station (5) and the vehicle are butted through a specific protocol, and the edge computing base station (5) acquires the authority of inquiring the position information of the vehicle in real time; when the entrance monitoring station (4) detects that the vehicle is going out of a mountain through a radar (43) and a camera (41), information is sent to inform the edge computing base station (5), the protocol between the edge computing base station (5) and the workshop is released, the butt joint is interrupted, and the edge computing base station (5) substitutes the driving data of the vehicle into a deep learning network model (5221) stored in a storage module (522) for deep learning, so that the reliability of decision control on the unmanned vehicle is enhanced;
step3.3, the edge computing base station (5) and the vehicle are butted through a specific protocol, the edge computing base station (5) acquires the authority for inquiring the vehicle information in real time and the authority for controlling the vehicle to run, the vehicle is converted from the original vehicle self-control running mode into a base station control running mode, and a decision computing center is transferred into a super computer (52) in the edge computing base station (5) through a decision control system (605) of the vehicle; when the entrance monitoring station (4) detects that the vehicle is going out of a mountain through a radar (43) and a camera (41), information is sent to inform the edge computing base station (5), the protocol between the edge computing base station (5) and the vehicle is released, the butt joint is interrupted, the vehicle restores the original driving state, and the edge computing base station (5) substitutes the driving data of the vehicle into a deep learning network model (5221) stored in a storage module (522) for deep learning, so that the reliability of decision control on the unmanned vehicle is enhanced;
the unmanned vehicle (63) running under the control of the edge computing base station (5) may meet other vehicles near the curve of the mountain road, and the control flow chart in the situation is shown in fig. 5, and the specific control method is as follows:
when the distance between the unmanned vehicle (63) and the front curve entrance is less than or equal to x1, the edge calculation base station (5) counts vehicles (x1 and x2 are preset values and x1 is less than x2) on a road section within the range that the distance between the other end of the curve entrance and the curve entrance is x2, and one of the following four schemes is adopted according to the counted vehicle types;
the first scheme is as follows: if no vehicle or only a driverless vehicle (63) exists on the counted road section, adopting the scheme; the edge calculation base station (5) controls the vehicle to keep the vehicle to normally run in a lane and pass through a curve opening; for example, as shown in fig. 6, there is one unmanned vehicle (63) at position 3, the unmanned vehicle (63) at position 1 is about to meet with it, and both unmanned vehicles (63) are kept under the control of the edge computing base station (5) and should be driven in the lane normally respectively, so that safe meeting can be carried out at the position 2 of the curve intersection without danger;
scheme II: if only intelligent driving vehicles (62) exist on the counted road section, the scheme is adopted; the edge calculation base station (5) firstly sends information to inform the intelligent driving vehicle (62) of paying attention to the fact that a vehicle is arranged at the other end of the curve port, and estimates which vehicle firstly drives to the curve port according to the distance between the two vehicles and the curve port and the current driving speed of the two vehicles, if the unmanned vehicle (63) firstly drives to the curve port, the edge calculation base station (5) controls the unmanned vehicle (63) to accelerate, after the unmanned vehicle passes through the curve port of the mountain road, the edge calculation base station (5) controls the unmanned vehicle (63) to recover the original driving state, and meeting with the intelligent driving vehicle (62) is completed at the side; if the intelligent driving vehicle (62) firstly drives to a curve opening, the edge calculation base station (5) controls the unmanned vehicle (63) to decelerate, after the intelligent driving vehicle (62) passes through the curve opening of the mountain road, the edge calculation base station (5) controls the unmanned vehicle (63) to restore the original driving state, and finishes meeting with the intelligent driving vehicle (62) at the side, and then passes through the curve opening; for example, as shown in fig. 7, there is an intelligent driving vehicle (62) at position 3, the unmanned vehicle (63) at position 1 is about to meet with the intelligent driving vehicle, the edge calculation base station (5) calculates the unmanned vehicle (63), and will arrive at the corner first, the unmanned vehicle (63) accelerates under the control of the edge calculation base station, and after it passes through the corner, the original driving state is recovered, and the intelligent driving vehicle (62) at position 2 finishes meeting;
the third scheme is as follows: if only the traditional vehicles (61) exist on the counted road section, the scheme is adopted; the edge calculation base station (5) performs estimation calculation and judgment, if the unmanned vehicle (63) can pass through a road junction before the front section of the dangerous section (10) corresponding to the traditional vehicle (61) reaches the road junction, the edge calculation base station (5) controls the unmanned vehicle (63) to run at an accelerated speed, after the unmanned vehicle passes through the road junction, the edge calculation base station (5) controls the unmanned vehicle (63) to recover the original running state and finish meeting with the traditional vehicle (61) at the side, otherwise, the edge calculation base station (5) controls the unmanned vehicle (63) to run at a decelerated speed, after the traditional vehicle (61) passes through the road junction, the edge calculation base station (5) controls the unmanned vehicle (63) to recover the original running state and finish meeting with the traditional vehicle (61) at the side, then passing through a bend; for example, as shown in fig. 8, there is a conventional vehicle (61) at position 3, the unmanned vehicle (63) at position 1 is about to meet with the conventional vehicle, the edge calculation base station (5) calculates the unmanned vehicle (63), and will arrive at the corner, the unmanned vehicle (63) accelerates under the control of the edge calculation base station, and after passing through the corner, the original driving state is restored, and the unmanned vehicle (63) and the intelligent vehicle (62) finish meeting at position 2;
and the scheme is as follows: if the various types of vehicles exist on the counted road section, the scheme is adopted; the edge calculation base station (5) controls the unmanned vehicle (63) to decelerate, after all the counted vehicles pass through the mountain road junction, the edge calculation base station (5) controls the unmanned vehicle (63) to restore the original driving state, and the vehicles meet the counted vehicles at the side, and then pass through the junction;
in summary, in the system and method for managing and controlling the automatically driven vehicles in the mountainous area based on the edge computing base station of the embodiment, the edge computing base station uniformly controls all the automatically driven vehicles in the mountainous area. The edge computing base station collects the position information of all vehicles in the mountainous area, and controls the automatic driving vehicle after comprehensively considering the information, so that the safety and the reliability of the automatic driving vehicle in the mountainous area are improved. In addition, when the unmanned vehicle runs in a mountain area, the calculation processing and decision center of the vehicle data is transferred from the vehicle to the edge calculation base station, so that the calculation operation efficiency is greatly improved, the decision time is shortened, and the vehicle can react faster to deal with emergency situations.
The present invention can be easily implemented by those skilled in the art from the above-described embodiments. It should be understood, however, that the intention is not to limit the invention to the particular embodiments described. On the basis of the disclosed embodiments, a person skilled in the art can combine different technical features at will, thereby implementing different technical solutions.
Claims (8)
1. A mountain road safety control system adapted for use with a plurality of automatic driving class vehicles, comprising: the system comprises an entrance monitoring station (4), an edge calculation base station (5) and a cloud end (7);
the entrance and exit monitoring station (4) is internally provided with a camera (41), a radar (43), a first wireless signal transceiver (44) and a license plate recognition system (42) based on an OCR technology;
the edge computing base station (5) is internally provided with a supercomputer (52) and a second wireless signal transceiver (51); the super computer (52) comprises a 5G network module (521), a storage module (522) and a calculation module (523); the storage module (522) is internally provided with a deep learning network (5221) and a high-precision mountain three-dimensional electronic map (5222);
the camera (41) in the entrance and exit monitoring station (4) is responsible for shooting pictures of the vehicles entering and exiting the mountain and transmitting the pictures to the license plate recognition system (42) based on the OCR technology, and the license plate recognition system (42) based on the OCR technology is responsible for recognizing license plate number information of the vehicles entering and exiting the mountain according to the received pictures and transmitting the license plate number information to the first wireless signal transceiver (44) in the entrance and exit monitoring station (4) for transmission; the radar (43) in the entrance and exit monitoring station (4) is responsible for detecting the entering and exiting vehicles and measuring the speed information of the entering vehicles, and transmits the speed information to the first wireless signal transceiver (44) in the entrance and exit monitoring station (4) for transmission; a first wireless signal transceiver (44) in the entrance monitoring station (4) and a second wireless signal transceiver (51) in the edge computing base station (5) are responsible for transceiving wireless signals and carrying out information interaction; a 5G network module (521) in a supercomputer (52) in the edge computing base station (5) can establish connection between the supercomputer (52) and a cloud end (7), so that the computer can download information from the cloud end (7) or upload the information to the cloud end (7), a storage module (522) is responsible for storage of various information, and a calculation module (523) is responsible for decision calculation of unmanned vehicles (63) in a mountain area to obtain a control scheme; the deep learning network (5221) stored in the storage module (522) of the super computer (52) in the edge computing base station (5) is used for decision-making computation of the unmanned vehicles (63) in the mountainous area, and the high-precision three-dimensional electronic map (5222) in the mountainous area is used for accurately restoring the position and the environment information of each vehicle on the mountains (1) so as to assist the edge computing base station (5) in decision-making control of the unmanned vehicles (63);
the edge calculation base station (5) is connected with the entrance and exit monitoring station (4) through a wireless network (8) for information transmission; the edge computing base station (5) is connected with the vehicle (6) through a wireless network (8) for information transmission; the edge computing base station (5) can be connected with the cloud end (7) through the 5G network (9), and information is downloaded from the cloud end (7) or uploaded to the cloud end (7).
2. The mountain road safety control system adapted to various automatic driving class vehicles according to claim 1, wherein the entrance monitoring station (4) is provided at a mountain entrance (3).
3. The mountain road safety control system adapted for use with multiple autonomous-driving-class vehicles according to claim 1, characterized in that the edge calculation base station (5) is disposed under the feet of the mountain (1).
4. The mountain road safety control system adapted to a plurality of automatic driving class vehicles according to claim 1, wherein the vehicle (6) comprises six automatic driving class vehicles classified by the international automotive engineering society of engineers from L0 to L5; the vehicle is divided again according to different driving types, the vehicle of L0 is a traditional vehicle (61), the vehicles of L1-L3 are intelligent driving vehicles (62), and the vehicles of L4 and L5 are unmanned driving vehicles (63);
the traditional vehicle (61) is not provided with driving auxiliary equipment, cannot transmit and receive wireless signals, cannot perform information interaction with the outside and needs to be driven by a driver; the intelligent driving vehicle (62) is provided with a vehicle-mounted camera (601), a vehicle-mounted millimeter wave radar (602), a vehicle-mounted network CAN transceiver (603) and a GPS positioning system (604), so that driving assistance CAN be realized, but the intelligent driving vehicle still needs to be controlled by a driver; the unmanned vehicle (63) is provided with a vehicle-mounted camera (601), a vehicle-mounted millimeter wave radar (602), a vehicle-mounted network CAN transceiver (603), a GPS positioning system (604) and a decision control system (605), is highly intelligent and is not driven by a driver;
the vehicle-mounted camera (601) is used for acquiring road conditions and vehicle information around the vehicle (6); the vehicle-mounted millimeter wave radar (602) is used for acquiring relative position information and speed information of a vehicle and surrounding vehicles; the vehicle-mounted network CAN transceiver (603) is used for being connected with other external equipment through a wireless network (8) to realize information interaction; the GPS positioning system (604) is used for realizing accurate positioning on the vehicles (6) in the mountainous area; the decision control system (605) is used for driving control of the unmanned vehicle (63).
5. The mountain road safety control system applicable to vehicles with multiple automatic driving grades as claimed in claim 4, characterized in that when the conventional vehicle (61) cannot be detected by other vehicles, the position of the conventional vehicle on the mountain road (2) stored in the storage module (522) of the edge computing base station (5) is an estimated position, and a road section with a length of 2d before and after the estimated position is marked as a dangerous road section (10), wherein d k v t is a prediction uncertainty coefficient and is a constant value obtained by training a neural network model in the storage module, v is a mountain normal driving vehicle speed corresponding to the vehicle type of the conventional vehicle (61), and t is a time elapsed from the vehicle being detected to be present; the length of the dangerous road section (10) is continuously increased along with the increase of the time for detecting the conventional vehicle (61) to get away from, the front and the back of the dangerous road section are limited by the nearest equipment with a detection function, and the equipment with the detection function comprises an intelligent driving vehicle (62), an unmanned driving vehicle (63) and an entrance and exit monitoring station (4); the estimated position and the dangerous road section (10) continuously move towards the vehicle running direction at the normal running speed of the mountain area corresponding to the vehicle type of the traditional vehicle (61); when the conventional vehicle (61) is detected by other intelligent driving vehicles (62) or unmanned vehicles (63) again, the position information stored in the storage module (522) of the edge calculation base station (5) is updated, and the length of the dangerous road section (10) is reduced to zero.
6. A mountain road safety control system adapted for use with multiple autodrive class vehicles as claimed in any one of claims 1 to 5, wherein the control system is adapted for use with mountain roads having bidirectional lanes.
7. A mountain road safety control method suitable for vehicles with multiple automatic driving grades is characterized by comprising the following steps:
step1, when a vehicle drives into a mountain road (2) from a mountain road entrance (3), the entrance monitoring station (4) detects the entrance of the vehicle into the mountain through a radar (43), takes a picture of the vehicle through a camera (41), passes the picture to a license plate recognition system (42) to recognize the license plate number of the vehicle, and transmits the entrance information and the license plate number information of the vehicle to an edge calculation base station (5) through a first wireless signal transceiver (44) after the recognition is finished;
step2, the edge computing base station (5) inquires and obtains model information, automatic driving level information and other vehicle data information of the vehicle from a cloud end (7) through a 5G network (9) by means of the received license plate number information, the automatic driving type of the vehicle is judged according to the automatic driving level of the vehicle, after judgment, if the vehicle is a traditional vehicle (61), Step3.1 is executed, if the vehicle is an intelligent driving vehicle (62), Step3.2 is executed, and if the vehicle is an unmanned vehicle (63), Step3.3 is executed;
step3.1, estimating the position of the vehicle on the mountain road (2) by the edge calculation base station (5) by means of the normal running speed of the vehicle of the type in the mountain area obtained by inquiry and a high-precision three-dimensional mountain area electronic map (5222) stored in a super computer (52), and marking a dangerous road section (10) according to the estimated position; in the driving process, when other unmanned vehicles (63) or intelligent vehicles detect the vehicle, the vehicle which detects the vehicle sends the position information of the vehicle to the edge computing base station (5), and the edge computing base station (5) updates the position information of the vehicle in the storage module (522); when the entrance and exit monitoring station (4) detects that the vehicle is going out of a mountain through a radar (43) and a camera (41), information is sent to inform the edge calculation base station (5), the edge calculation base station (5) finishes the estimation calculation of the position of the vehicle, and the driving data of the vehicle is substituted into a neural network model stored in a storage module (522) for training, so that the k value of the prediction uncertainty coefficient is optimized;
step3.2, the edge computing base station (5) and the vehicle are butted through an information transmission protocol, and the edge computing base station (5) acquires the authority of inquiring the position information of the vehicle in real time; when the entrance monitoring station (4) detects that the vehicle is going out of a mountain through a radar (43) and a camera (41), information is sent to inform the edge computing base station (5), the protocol between the edge computing base station (5) and the workshop is released, the butt joint is interrupted, and the edge computing base station (5) substitutes the driving data of the vehicle into a deep learning network model (5221) stored in a storage module (522) for deep learning, so that the reliability of decision control on the unmanned vehicle is enhanced;
step3.3, the edge computing base station (5) is in butt joint with the vehicle through an information transmission protocol and a control protocol, the edge computing base station (5) acquires the authority for inquiring the vehicle information in real time and the authority for controlling the vehicle to run, the vehicle is converted from the original vehicle self-control running mode into a base station control running mode, and a decision computing center is transferred into a super computer (52) in the edge computing base station (5) through a decision control system (605) of the vehicle; when the entrance monitoring station (4) detects that the vehicle is going out of a mountain through a radar (43) and a camera (41), information is sent to inform the edge computing base station (5), the protocol between the edge computing base station (5) and the vehicle is released, the butt joint is interrupted, the vehicle restores the original driving state, and the edge computing base station (5) substitutes the driving data of the vehicle into a deep learning network model (5221) stored in a storage module (522) for deep learning, so that the reliability of decision control on the unmanned vehicle is enhanced.
8. The mountain road safety control method suitable for vehicles of multiple automatic driving grades as claimed in claim 7, characterized in that when the unmanned vehicle (63) running under the control of the edge calculation base station (5) meets other vehicles near the entrance of the mountain curve, the specific control method is as follows:
when the distance between the unmanned vehicle (63) and the front curve entrance is less than or equal to x1, the edge calculation base station (5) counts vehicles (x1 and x2 are preset values and x1 is less than x2) on a road section within the range that the distance between the other end of the curve entrance and the curve entrance is x2, and one of the following four schemes is adopted according to the counted vehicle types;
the first scheme is as follows: if no vehicle or only a driverless vehicle (63) exists on the counted road section, adopting the scheme; the edge calculation base station (5) controls the vehicle to keep the vehicle to normally run in a lane and pass through a curve opening;
scheme II: if only intelligent driving vehicles (62) exist on the counted road section, the scheme is adopted; the edge calculation base station (5) firstly sends information to inform the intelligent driving vehicle (62) of paying attention to the fact that a vehicle is arranged at the other end of the curve port, and estimates which vehicle firstly drives to the curve port according to the distance between the two vehicles and the curve port and the current driving speed of the two vehicles, if the unmanned vehicle (63) firstly drives to the curve port, the edge calculation base station (5) controls the unmanned vehicle (63) to accelerate, after the unmanned vehicle passes through the curve port of the mountain road, the edge calculation base station (5) controls the unmanned vehicle (63) to recover the original driving state, and meeting with the intelligent driving vehicle (62) is completed at the side; if the intelligent driving vehicle (62) firstly drives to a curve opening, the edge calculation base station (5) controls the unmanned vehicle (63) to decelerate, after the intelligent driving vehicle (62) passes through the curve opening of the mountain road, the edge calculation base station (5) controls the unmanned vehicle (63) to restore the original driving state, and finishes meeting with the intelligent driving vehicle (62) at the side, and then passes through the curve opening;
the third scheme is as follows: if only the traditional vehicles (61) exist on the counted road section, the scheme is adopted; the edge calculation base station (5) performs estimation calculation and judgment, if the unmanned vehicle (63) can pass through a road junction before the front section of the dangerous section (10) corresponding to the traditional vehicle (61) reaches the road junction, the edge calculation base station (5) controls the unmanned vehicle (63) to run at an accelerated speed, after the unmanned vehicle passes through the road junction, the edge calculation base station (5) controls the unmanned vehicle (63) to recover the original running state and finish meeting with the traditional vehicle (61) at the side, otherwise, the edge calculation base station (5) controls the unmanned vehicle (63) to run at a decelerated speed, after the traditional vehicle (61) passes through the road junction, the edge calculation base station (5) controls the unmanned vehicle (63) to recover the original running state and finish meeting with the traditional vehicle (61) at the side, then passing through a bend;
and the scheme is as follows: if the various types of vehicles exist on the counted road section, the scheme is adopted; the edge calculation base station (5) controls the unmanned vehicle (63) to decelerate, after all the counted vehicles pass through the mountain road junction, the edge calculation base station (5) controls the unmanned vehicle (63) to restore the original driving state, and the vehicles meet the counted vehicles at the side, and then pass through the junction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910947842.0A CN110867096B (en) | 2019-10-08 | 2019-10-08 | Mountain road safety control system and method suitable for vehicles with multiple automatic driving grades |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910947842.0A CN110867096B (en) | 2019-10-08 | 2019-10-08 | Mountain road safety control system and method suitable for vehicles with multiple automatic driving grades |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110867096A true CN110867096A (en) | 2020-03-06 |
| CN110867096B CN110867096B (en) | 2021-07-20 |
Family
ID=69652274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910947842.0A Active CN110867096B (en) | 2019-10-08 | 2019-10-08 | Mountain road safety control system and method suitable for vehicles with multiple automatic driving grades |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110867096B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112052959A (en) * | 2020-09-04 | 2020-12-08 | 深圳前海微众银行股份有限公司 | Automatic driving training method, equipment and medium based on federal learning |
| CN113470350A (en) * | 2021-06-16 | 2021-10-01 | 中铁大桥局集团有限公司 | Traffic scheduling method for sidewalk |
| US11288520B2 (en) | 2020-06-25 | 2022-03-29 | Toyota Motor Engineering & Manufacturing N.A. Inc. | Systems and methods to aggregate and distribute dynamic information of crowdsourcing vehicles for edge-assisted live map service |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100882580B1 (en) * | 2008-04-07 | 2009-02-09 | 게이트마켓 주식회사 | Automatic vending machine on-line controlling system |
| US9889856B1 (en) * | 2016-08-09 | 2018-02-13 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for controlling unmanned vehicle |
| CN108492603A (en) * | 2018-04-25 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of edge calculations station and the automatic Pilot method based on edge calculations station |
| CN207966200U (en) * | 2017-12-27 | 2018-10-12 | 中国船舶重工集团公司第七一0研究所 | A kind of mountainous area highway early warning delivery system |
| CN108944930A (en) * | 2018-07-05 | 2018-12-07 | 合肥工业大学 | A kind of automatic follow the bus method and system of drive simulating person's characteristic based on LSTM |
| CN109377061A (en) * | 2018-10-30 | 2019-02-22 | 百度在线网络技术（北京）有限公司 | Stage division, device, equipment, storage medium and the vehicle of unmanned vehicle |
-
2019
- 2019-10-08 CN CN201910947842.0A patent/CN110867096B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100882580B1 (en) * | 2008-04-07 | 2009-02-09 | 게이트마켓 주식회사 | Automatic vending machine on-line controlling system |
| US9889856B1 (en) * | 2016-08-09 | 2018-02-13 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for controlling unmanned vehicle |
| CN207966200U (en) * | 2017-12-27 | 2018-10-12 | 中国船舶重工集团公司第七一0研究所 | A kind of mountainous area highway early warning delivery system |
| CN108492603A (en) * | 2018-04-25 | 2018-09-04 | 济南浪潮高新科技投资发展有限公司 | A kind of edge calculations station and the automatic Pilot method based on edge calculations station |
| CN108944930A (en) * | 2018-07-05 | 2018-12-07 | 合肥工业大学 | A kind of automatic follow the bus method and system of drive simulating person's characteristic based on LSTM |
| CN109377061A (en) * | 2018-10-30 | 2019-02-22 | 百度在线网络技术（北京）有限公司 | Stage division, device, equipment, storage medium and the vehicle of unmanned vehicle |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11288520B2 (en) | 2020-06-25 | 2022-03-29 | Toyota Motor Engineering & Manufacturing N.A. Inc. | Systems and methods to aggregate and distribute dynamic information of crowdsourcing vehicles for edge-assisted live map service |
| CN112052959A (en) * | 2020-09-04 | 2020-12-08 | 深圳前海微众银行股份有限公司 | Automatic driving training method, equipment and medium based on federal learning |
| CN112052959B (en) * | 2020-09-04 | 2023-08-25 | 深圳前海微众银行股份有限公司 | Automatic driving training method, equipment and medium based on federal learning |
| CN113470350A (en) * | 2021-06-16 | 2021-10-01 | 中铁大桥局集团有限公司 | Traffic scheduling method for sidewalk |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110867096B (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240094741A1 (en) | Control of automated following in vehicle convoys | |
| CN109164809B (en) | Autonomous following control system and method for vehicle formation | |
| JP6724059B2 (en) | Method, apparatus and system for controlling a vehicle passing through an intersection | |
| CN110867096B (en) | Mountain road safety control system and method suitable for vehicles with multiple automatic driving grades | |
| US20180056998A1 (en) | System and Method for Multi-Vehicle Path Planning Technical Field | |
| CN113460042B (en) | Vehicle driving behavior recognition method and recognition device | |
| CN111422196A (en) | Intelligent networking automatic driving system and method suitable for mini bus | |
| CN109413572A (en) | Vehicle collision prewarning and the optimization method and system of speed guidance | |
| KR20210050925A (en) | Vehicle collision avoidance apparatus and method | |
| JP2023508114A (en) | AUTOMATED DRIVING METHOD, RELATED DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM | |
| CN109460042B (en) | Automatic driving control method and system | |
| JP6755071B2 (en) | Vehicle travel control device | |
| CN110949376B (en) | Vehicle control device, vehicle control method, and storage medium | |
| CN112429016A (en) | Automatic driving control method and device | |
| CN111724614A (en) | Traffic control system for autonomous vehicles | |
| US20210109535A1 (en) | Systems And Methods For Controlling An Unmanned Self-Powered Follow Vehicle Following A Lead Vehicle With Independent Hazard Avoidance By The Follow Vehicle | |
| CN114792149A (en) | Track prediction method and device and map | |
| CN109656242A (en) | A kind of automatic Pilot planning driving path planning system | |
| JP2020154622A (en) | Traffic control system | |
| CN113167038B (en) | Method and device for vehicle to pass through barrier gate cross bar | |
| CN108154712A (en) | For running the method and apparatus of vehicle | |
| Mourllion et al. | Collaborative perception for collision avoidance | |
| CN115328137A (en) | Control method and control device of unmanned equipment | |
| Juberts et al. | Development and test results for a vision-based approach to avcs | |
| Sathiyan et al. | A comprehensive review on cruise control for intelligent vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |