CN115158360A - Automatic driving vehicle over-bending control system and method thereof - Google Patents
Automatic driving vehicle over-bending control system and method thereof Download PDFInfo
- Publication number
- CN115158360A CN115158360A CN202210954336.6A CN202210954336A CN115158360A CN 115158360 A CN115158360 A CN 115158360A CN 202210954336 A CN202210954336 A CN 202210954336A CN 115158360 A CN115158360 A CN 115158360A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- curve
- strategy
- automatic driving
- 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.)
- Pending
Links
- 238000005452 bending Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 238000011217 control strategy Methods 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 4
- 238000013499 data model Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 230000007306 turnover Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- 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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
-
- 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
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/403—Image sensing, e.g. optical camera
-
- 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
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
- B60W2420/408—Radar; Laser, e.g. lidar
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/40—High definition maps
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a control system and a method for automatically driving a vehicle to pass a curve, wherein the system comprises the following steps: the system comprises a cloud server, a central gateway, vehicle-mounted data transmission equipment, an automatic driving controller, a vehicle drive-by-wire actuator, a map and positioning module, a light and rain sensor, a camera group and a millimeter wave radar group. The method adopts the cloud-based curve database, when the automatic driving vehicle needs to curve, the optimal curve-passing strategy is searched and matched in the cloud database and issued to the vehicle, the automatic driving system of the vehicle smoothly completes curve-passing according to the issued optimal curve-passing strategy, and data of the vehicle line-control actuator when the vehicle passes the curve is uploaded to the cloud. Under the condition of meeting driving safety, aiming at a large-curvature curve and a continuous curve, the method can greatly improve the over-bending success rate, reduce the taking times of a driver, improve the driving experience and even realize 100 percent over-bending success rate.
Description
Technical Field
The invention relates to the technical field of automatic driving of automobiles, in particular to a system and a method for controlling the automatic driving of an automobile to pass a curve.
Background
With the increasing level of automotive intelligence, automated driving of vehicles is possible. At present, a plurality of vehicle types in the market can realize high-order intelligent driving, namely, under the condition that the attention of a driver is concentrated, the vehicle can autonomously drive on a limited structured road automatically, the two hands and the two feet of the driver are released, and the fatigue of the driver is relieved.
According to the SAEJ3016 classification standard, the automatic level of the vehicle is in the L2+/L3 stage at present, the automatic driving function must be used in a limited ODD scene, and the limitation of available scenes exists, for example, when a curve with large curvature or a continuous curve scene is passed, the automatic driving system can exit and require a driver to take over driving. This is also one of the main reasons that the popularity of the current high-order intelligent driving is not high.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: in order to solve the technical problems of low availability and frequent exit of an automatic driving system for curves with large curvature and curves with high difficulty and continuous curves in the prior art, the invention provides the automatic driving vehicle over-bending control system and the method thereof, which can greatly improve over-bending success rate, reduce the number of times of taking over by a driver and improve driving experience.
The technical scheme adopted by the invention for solving the technical problems is as follows: an autonomous vehicle cornering control system, comprising: a cloud server, and
the central gateway is connected with the cloud server through vehicle-mounted data transmission equipment;
an autopilot controller connected to the central gateway;
the vehicle drive-by-wire actuator is connected with the central gateway;
the map and positioning module is connected with the central gateway;
the light and rain sensor is connected with the central gateway;
the camera group is connected with the automatic driving controller;
and the millimeter wave radar group is connected with the automatic driving controller.
Further, the cloud server comprises a processor and a database, the processor is connected with the database, and the processor is connected with the central gateway through the vehicle-mounted data transmission equipment; and a plurality of historical success bending strategies are stored in the database.
The invention also provides a method for controlling the automatic driving vehicle to pass through the curve, which adopts an automatic driving vehicle curve passing control system and comprises the following steps:
the method comprises the following steps that S1, a vehicle is in an automatic driving mode, the camera group is used for detecting the surrounding environment information of the vehicle, the light and rain sensor is used for detecting weather information, the millimeter wave radar group is used for detecting the surrounding obstacle information of the vehicle, and the map and positioning module is used for acquiring the current road information and the vehicle position information;
s2, if the map and positioning module finds that the vehicle is about to drive into a curve, the central gateway sends the acquired surrounding environment information, weather information, surrounding obstacle information of the vehicle, road information and vehicle position information of the vehicle to a cloud server through vehicle-mounted data transmission equipment;
s3, the cloud server searches in a database according to the received various information, if an optimal historical turning strategy matched with the current vehicle condition is searched, the optimal historical turning strategy is sent to an automatic driving controller, the automatic driving controller generates a vehicle execution instruction and sends the vehicle execution instruction to a vehicle line control actuator, and the vehicle line control actuator controls the vehicle to automatically pass through a curve according to the vehicle execution instruction;
and S4, if the historical successful curve passing strategy matched with the current vehicle condition is not searched, prompting the driver to take over the vehicle and carry out curve passing.
Further, the method further comprises: the automatic driving controller calculates an optimal control strategy for the vehicle to pass a curve according to various information;
and comparing the retrieved optimal historical successful bending strategy with the calculated optimal control strategy, and selecting the better strategy from the two strategies as a vehicle bending execution strategy.
Further, the execution data of the successful bending after the driver takes over the vehicle is uploaded to a cloud server to serve as a new historical successful bending strategy.
Further, when the vehicle runs, the millimeter wave radar group calculates the safe distance between the vehicle and the obstacle;
when the over-bending strategy is executed, the automatic driving controller detects whether the distance between the current vehicle and the obstacle meets the safety distance, and if so, the over-bending strategy is normally executed until the over-bending is finished; and if not, prompting the driver to take over the vehicle to carry out the turning.
Further, the vehicle executes instructions that include at least: vehicle acceleration or deceleration, steering angle, and engine torque.
Furthermore, the camera group is connected with the automatic driving controller through CAN, CAN-FD, LVDS or Ethernet.
Further, the central gateway is connected with the vehicle-mounted data transmission device through an ethernet, and the vehicle-mounted data transmission device is wirelessly connected with the cloud server through a 4G or 5G network.
Further, the map and positioning module is used for providing a navigation data model, high-precision map information and high-precision vehicle positioning information, and determining the current lane, the geographic position and the upcoming curve information of the vehicle.
The beneficial effect of the invention is that,
1. the invention adopts a success strategy based on vehicle historical data, when the vehicle is about to bend, the success strategy is searched and issued in the database, and the automatic driving controller can also calculate an optimal control strategy, compares the two strategies and selects a more optimal strategy to execute, thus aiming at the curve with large curvature and the continuous curve under the condition of meeting the driving safety, the invention can greatly improve the automatic bending power, reduce the taking times of the driver and improve the driving experience. Even in the road test stage before mass production, through sufficient curve test, 100% of over-bending forming power can be realized after mass production of the vehicle type.
2. The hardware modules used in the method multiplex the existing intelligent automatic driving system, the cost is not increased, the vehicle data used in the method are all the existing data of the existing vehicle, no additional sensor is needed, only the combing and the classification are needed during the cloud data maintenance, an agile searching scheme is established, and the indexing time is reduced.
3. The invention can enable the automatic driving vehicle to be suitable for wider road scenes, and is beneficial to popularization of higher-order L4 or L5 automatic driving technology.
Drawings
The invention is further illustrated with reference to the following figures and examples.
Fig. 1 is a schematic configuration diagram of an autonomous vehicle cornering control system according to the present invention.
FIG. 2 is a flow chart of an autonomous vehicle cornering control method of the invention.
Fig. 3 is a detailed flowchart of the autonomous vehicle cornering control method of the invention.
In the figure: 1. a cloud server; 2. a central gateway; 3. a vehicle-mounted data transmission device; 4. an automatic driving controller; 5. a vehicle drive-by-wire actuator; 6. a map and positioning module; 7. a light and rain sensor; 8. a camera group; 9. a millimeter wave radar group; 11. a processor; 12. a database.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention. Furthermore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
As shown in fig. 1, the automatic driving vehicle cornering control system of the present invention includes: cloud server 1, central gateway 2, on-vehicle data transmission equipment 3, automatic driving controller 4, vehicle drive-by-wire executor 5, map and orientation module 6, light rainfall sensor 7, camera group 8 and millimeter wave radar group 9, central gateway 2 passes through on-vehicle data transmission equipment 3 with cloud server 1 and is connected, automatic driving controller 4 is connected with central gateway 2, vehicle drive-by-wire executor 5 is connected with central gateway 2, map and orientation module 6 are connected with central gateway 2, light rainfall sensor 7 is connected with central gateway 2, camera group 8 is connected with automatic driving controller 4, millimeter wave radar group 9 is connected with automatic driving controller 4.
In other words, the camera group 8 may collect environmental information around the vehicle and send it to the automatic driving controller 4; the millimeter wave radar group 9 can sense the obstacle information around the vehicle and send the obstacle information to the automatic driving controller 4; the map and positioning module 6 can provide navigation information, map information and vehicle positioning information and send the information to the central gateway 2 if the vehicle is going to pass a curve; the light and rain sensor 7 can sense weather, detect whether the rain falls and the magnitude of the rain, and send the rain to the central gateway 2; the automatic driving controller 4 can send environmental information around the vehicle and obstacle information around the vehicle to the central gateway 2, the central gateway 2 can transmit various received information to the cloud server 1, the cloud server 1 can search and find whether a matched historical successful bending strategy exists according to the received information, if yes, the searched historical successful bending strategy is issued to the central gateway 2, the central gateway 2 is transmitted to the automatic driving controller 4, the automatic driving controller 4 can generate a vehicle execution instruction according to the historical successful bending strategy and transmit the vehicle execution instruction to the vehicle drive-by-wire actuator 5, and therefore the vehicle can automatically bend according to the historical successful bending strategy.
Under the condition of meeting the driving safety, aiming at a large-curvature curve and a continuous curve, the automatic over-bending success rate can be greatly improved, the number of times of taking over by a driver is reduced, the driving experience is improved, and even 100 percent of over-bending success rate can be realized.
For example, the cloud server 1 includes a processor 11 and a database 12, the processor 11 is connected with the database 12, and the processor 11 is connected with the central gateway 2 through the vehicle-mounted data transmission device 3; the database 12 stores a plurality of historical work-over-bending strategies. The database 12 contains various historical successful turning strategies, the historical successful turning strategies are classified and sorted according to vehicle types, weather information and curve types, and the processor 11 can match the turning strategies suitable for specific vehicle types, specific weather and specific curves in the database 12 according to the received current various information of the vehicle. The historical successful turn-passing strategy in the database 12 is based on historical data of vehicle turn-passing, for example, automatic driving execution data and manual driving execution data of the same vehicle type in the same curve for successful turn-passing under different weather conditions; the automatic driving execution data and the manual driving execution data of different vehicle types in the same curve for completing and bending; the automatic driving execution data and the manual driving execution data of the same vehicle type in different curves for completing and bending; and so on. In other words, the historical power overbending strategy performs data generation based on a large number of historical overbending.
For example, the camera group 8 may be a group of front-view cameras, a group of panoramic cameras (i.e., the cameras are disposed around the vehicle), or a group of panoramic cameras, etc., and may comprehensively collect the environmental information around the vehicle. The millimeter wave radar is a detection radar working in a millimeter wave band, and the detection result is not easily influenced by weather and lighting conditions by utilizing radio direction finding and distance measuring. In this embodiment, the millimeter wave radar group 9 may be a group of forward millimeter wave radars, a group of rear corner millimeter wave radars, or a group of front corner millimeter wave radars, etc., and may monitor the distance between the vehicle and the obstacle and the direction of the obstacle in an all-around manner. The automatic driving controller 4 can generate a vehicle execution instruction according to a historical successful turning strategy issued by the cloud server 1, and can also calculate the vehicle execution instruction according to obstacle information, environmental information, vehicle positions and the like around the vehicle, and the vehicle drive-by-wire actuator 5 can make the vehicle smoothly turn according to the vehicle execution instruction. The automatic driving controller 4 may have only an automatic driving function or both the automatic driving and parking functions. The vehicle by-wire actuator 5 may be a combination of EPS/ESC/VCU/HCU/EMS. The central gateway 2 is mainly used for data interaction between modules.
As shown in fig. 2 to 3, the present invention further provides a method for controlling the turning of the autonomous vehicle, which uses a system for controlling the turning of the autonomous vehicle. The method comprises the following steps:
s1, the vehicle is in an automatic driving mode, the camera group 8 is used for detecting the surrounding environment information of the vehicle, the light and rain sensor 7 is used for detecting weather information, the millimeter wave radar group 9 is used for detecting the surrounding obstacle information of the vehicle, and the map and positioning module 6 is used for acquiring the current road information and the vehicle position information.
And S2, if the map and positioning module 6 finds that the vehicle is about to drive into a curve, the central gateway 2 sends the acquired surrounding environment information, weather information, surrounding obstacle information, road information and vehicle position information of the vehicle to the cloud server 1 through the vehicle-mounted data transmission equipment 3.
And S3, the cloud server 1 searches the database 12 according to the received various information, if an optimal historical turning strategy matched with the current vehicle condition is searched, the optimal historical turning strategy is sent to the automatic driving controller 4, the automatic driving controller 4 generates a vehicle execution instruction and sends the vehicle execution instruction to the vehicle drive-by-wire actuator 5, and the vehicle drive-by-wire actuator 5 controls the vehicle to automatically turn the curve according to the vehicle execution instruction.
And S4, if the historical successful curve passing strategy matched with the current vehicle condition is not searched, prompting the driver to take over the vehicle and carry out curve passing.
In other words, when a vehicle in automatic driving is about to drive into a curve, the central gateway 2 uploads the acquired various information to the cloud server 1 through the vehicle-mounted data transmission device 3, the processor 11 searches in the database 12, and if an optimal historical successful bending strategy matched with the current vehicle condition (such as vehicle type, weather, curve type and the like) is searched, the optimal historical successful bending strategy is sent to the automatic driving controller 4; if not, the driver temporarily takes over the vehicle until the curve is successfully traversed. Under the condition of meeting the driving safety, aiming at the large-curvature curve and the continuous curve, the automatic bending-over power can be greatly improved, the number of times of taking over by a driver is reduced, and the driving experience is improved.
Specifically, the method further comprises the following steps: the automatic driving controller 4 calculates an optimal control strategy for the vehicle to pass a curve according to various information; and comparing the retrieved optimal historical successful bending strategy with the calculated optimal control strategy, and selecting the better strategy from the two strategies as a vehicle bending execution strategy. In other words, the automatic driving controller 4 may also calculate an optimal control strategy suitable for the current situation according to various current information (environment information, obstacle information, weather information, positioning information, etc.), compare the calculated optimal control strategy with the retrieved optimal historical turning strategy, and select the better strategy of the two as the final turning execution strategy. Thus, the success rate of automatic over-bending can be further improved. For example, the automatic driving controller 4 may calculate the optimal control strategy using an ant colony algorithm or an a-star algorithm, and generate the execution command using a PID algorithm or an MPC algorithm.
For example, the method may also upload the execution data of the successful passing of the vehicle after the driver takes over the vehicle to the cloud server 1 as a new historical successful passing strategy, expand the historical data in the database 12, and improve the success rate of the subsequent automatic passing of the vehicle.
Specifically, the millimeter wave radar group 9 calculates a safe distance between the vehicle and the obstacle while the vehicle is running. When the over-bending strategy is executed, the automatic driving controller 4 detects whether the distance between the current vehicle and the obstacle meets the safety distance, and if so, the over-bending strategy is normally executed until the over-bending is finished; and if not, prompting the driver to take over the vehicle to carry out the turning. In other words, if the distance between the vehicle and the surrounding obstacles is greater than the safety distance, the vehicle can normally and automatically turn over, and if not, there is a risk of an accident, requiring the driver to take over the vehicle to turn over. The safe distance can be determined by the predicted collision time between the vehicle and the obstacle, and can be set according to actual conditions.
For example, the vehicle-executed instructions include at least: vehicle acceleration or deceleration, steering angle, and engine torque. The camera group 8 and the automatic driving controller 4 are connected by CAN, CAN-FD, LVDS or Ethernet. When LVDS or ethernet connection is used, the data transmitted by the camera group 8 is image data taken by each camera. When the CAN or CAN-FD connection is adopted, the data transmitted by the camera group 8 are the environmental detection result of the camera and the vehicle state information, including the curve position, the distance between the vehicle and the curve, the vehicle speed, the curve type, the number of lane lines, the lane line type, the lane width, the confidence coefficient, etc. The millimeter wave radar group 9 is connected with the automatic driving controller 4 by CAN, CAN-FD or Ethernet, and the transmitted data is the obstacle information detected by the millimeter wave radar and the state information of the vehicle, including the distance between the vehicle and the obstacle, the transverse and longitudinal position, the transverse and longitudinal speed, the signal quality, the transverse and longitudinal position variance, the transverse and longitudinal speed variance and the like of the vehicle. The automatic driving controller 4 and the central gateway 2 are connected by CAN, CAN-FD or Ethernet, and the transmitted data are transverse and longitudinal control instructions of the whole vehicle and strategy data for optimizing the passing of a curve, including steering angle, transverse and longitudinal acceleration, vehicle speed, course angle, transverse and longitudinal control request and handshake signals, actuator state and response, vehicle type information, weather state, map information and the like. The map and positioning module 6 and the central gateway 2 are connected by CAN, CAN-FD or Ethernet, and the transmitted data are map position information, navigation routes and vehicle self-positioning information. The vehicle line control actuator 5 and the central gateway 2 are connected by CAN or CAN-FD, and the transmitted data are the transverse and longitudinal control signals of the whole vehicle and the feedback of the execution state of the controller. The light and rain sensor 7 and the central gateway 2 are connected by CAN, CAN-FD or LIN, and the transmitted data are the magnitude of rain and the illumination intensity. The central gateway 2 and the vehicle-mounted data transmission equipment 3 are connected by adopting a gigabit or hundred-megabyte vehicle-mounted Ethernet, and transmitted data comprise vehicle types, vehicle positioning information, curve information, vehicle states, weather states, optimized curve passing strategy data and the like. The vehicle-mounted data transmission equipment 3 is connected with the cloud server 1 through a 4G or 5G wireless network, and transmitted data comprise vehicle types, vehicle positioning information, curve information, vehicle states, weather states, optimized curve passing strategy data and the like.
In summary, compared with the prior art, the invention has at least the following advantages:
1. the invention adopts a success strategy based on vehicle historical data, when the vehicle is about to bend, the success strategy is searched and issued in the database 12, and the automatic driving controller 4 can also calculate an optimal control strategy, compare the two strategies and select a better strategy to execute, thus aiming at the curve with large curvature and the continuous curve under the condition of meeting the driving safety, the invention can greatly improve the automatic bending forming power, reduce the taking times of the driver and improve the driving experience. Even in the road test stage before mass production, through sufficient curve test, 100% of over-bending forming power can be realized after mass production of the vehicle type.
2. The hardware modules used by the method multiplex the existing intelligent automatic driving system, the cost is not increased, the vehicle data used by the method are all the existing data of the existing vehicle, a sensor is not additionally arranged, only the combing and the classifying are needed during the maintenance of cloud data, an agile searching scheme is established, and the indexing time is reduced.
3. The invention solves the problem that the automatic driving vehicle frequently exits under difficult large-curvature curves and continuous curves, can realize full-course automatic driving in the real sense, enables the automatic driving vehicle to be suitable for wider road scenes, and is beneficial to the technical popularization of higher-order L4 or L5 automatic driving.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the contents of the specification, and must be determined by the scope of the claims.
Claims (10)
1. An autonomous vehicle cornering control system, comprising:
cloud server (1), and
the central gateway (2) is connected with the cloud server (1) through vehicle-mounted data transmission equipment (3);
an autonomous driving controller (4), the autonomous driving controller (4) being connected to the central gateway (2);
the vehicle drive-by-wire actuator (5), the vehicle drive-by-wire actuator (5) is connected with the central gateway (2);
a map and location module (6), the map and location module (6) being connected to the central gateway (2);
a light and rain sensor (7), wherein the light and rain sensor (7) is connected with the central gateway (2);
a camera group (8), the camera group (8) being connected to the automatic driving controller (4);
and the millimeter wave radar group (9), wherein the millimeter wave radar group (9) is connected with the automatic driving controller (4).
2. The autonomous vehicle cornering control system according to claim 1, wherein said cloud server (1) comprises a processor (11) and a database (12), said processor (11) being connected to said central gateway (2) through said onboard data transmission device (3); the database (12) stores various historical work-making bending strategies.
3. An autonomous vehicle cornering control method using the autonomous vehicle cornering control system according to claims 1-2, said method comprising the steps of:
the method comprises the following steps that S1, a vehicle is in an automatic driving mode, the camera group (8) is used for detecting the surrounding environment information of the vehicle, the light and rain sensor (7) is used for detecting weather information, the millimeter wave radar group (9) is used for detecting the surrounding obstacle information of the vehicle, and the map and positioning module (6) is used for acquiring the current road information and the vehicle position information;
s2, if the map and positioning module (6) finds that the vehicle is about to drive into a curve, the central gateway (2) sends the acquired ambient environment information, weather information, obstacle information around the vehicle, road information and vehicle position information of the vehicle to the cloud server (1) through the vehicle-mounted data transmission equipment (3);
s3, the cloud server (1) searches in a database (12) according to the received various information, if an optimal historical turning strategy matched with the current vehicle condition is searched, the optimal historical turning strategy is sent to an automatic driving controller (4), the automatic driving controller (4) generates a vehicle execution instruction and sends the vehicle execution instruction to a vehicle drive-by-wire actuator (5), and the vehicle drive-by-wire actuator (5) controls the vehicle to automatically pass through a curve according to the vehicle execution instruction;
and S4, if the historical successful curve passing strategy matched with the current vehicle condition is not searched, prompting the driver to take over the vehicle and carry out curve passing.
4. The autonomous-vehicle cornering control method of claim 3, further comprising:
the automatic driving controller (4) calculates an optimal control strategy for vehicle turning according to various information;
and comparing the retrieved optimal historical successful bending strategy with the calculated optimal control strategy, and selecting the better strategy from the two strategies as a vehicle bending execution strategy.
5. The autonomous vehicle cornering control method of claim 3,
and uploading the execution data of the successful bending after the driver takes over the vehicle to a cloud server (1) as a new historical successful bending strategy.
6. The autonomous vehicle cornering control method of claim 4,
when the vehicle runs, the millimeter wave radar group (9) calculates the safe distance between the vehicle and the obstacle;
when the over-bending strategy is executed, if the over-bending strategy is met, the automatic driving controller (4) normally executes the over-bending strategy until the over-bending is finished; and if not, prompting the driver to take over the vehicle to carry out the turning.
7. The autonomous-vehicle cornering control method according to claim 3, wherein the vehicle execution instructions at least include: vehicle acceleration or deceleration, steering angle, and engine torque.
8. The autonomous-vehicle cornering control method according to claim 3, wherein the connection between the camera group (8) and the autonomous-vehicle controller (4) is through CAN, CAN-FD, LVDS or Ethernet.
9. The autonomous vehicle turning control method according to claim 3, characterized in that the central gateway (2) is connected to the vehicle-mounted data transmission device (3) through an Ethernet, and the vehicle-mounted data transmission device (3) is wirelessly connected to the cloud server (1) through a 4G or 5G network.
10. The autonomous-vehicle cornering control method according to claim 3, wherein the map and location module (6) is adapted to provide a navigation data model, high-precision map information and high-precision vehicle location information, determine a current lane of the vehicle, a geographical position and upcoming curve information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210954336.6A CN115158360A (en) | 2022-08-10 | 2022-08-10 | Automatic driving vehicle over-bending control system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210954336.6A CN115158360A (en) | 2022-08-10 | 2022-08-10 | Automatic driving vehicle over-bending control system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115158360A true CN115158360A (en) | 2022-10-11 |
Family
ID=83478971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210954336.6A Pending CN115158360A (en) | 2022-08-10 | 2022-08-10 | Automatic driving vehicle over-bending control system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115158360A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114056350A (en) * | 2021-11-08 | 2022-02-18 | 国汽智控(北京)科技有限公司 | Control method, device, equipment and medium for automatic driving |
-
2022
- 2022-08-10 CN CN202210954336.6A patent/CN115158360A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114056350A (en) * | 2021-11-08 | 2022-02-18 | 国汽智控(北京)科技有限公司 | Control method, device, equipment and medium for automatic driving |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107933560B (en) | Vehicle control device | |
| CN111434554B (en) | Controlling an autonomous vehicle based on passenger and context aware driving style profiles | |
| US10525973B2 (en) | Vehicle traveling control device | |
| US10503165B2 (en) | Input from a plurality of teleoperators for decision making regarding a predetermined driving situation | |
| EP3644294B1 (en) | Vehicle information storage method, vehicle travel control method, and vehicle information storage device | |
| US10274961B2 (en) | Path planning for autonomous driving | |
| CN102463991B (en) | Method and device for determining a plausible lane for guiding a vehicle and motor vehicle | |
| CN110857093A (en) | Vehicle travel control system | |
| US11584248B2 (en) | Method of parking an autonomous driving vehicle for autonomous charging | |
| CN110576849A (en) | Vehicle travel control device | |
| US11603098B2 (en) | Systems and methods for eye-tracking data collection and sharing | |
| CN111267855A (en) | System and method for controlling an autonomous vehicle | |
| CN112526960A (en) | Automatic driving monitoring system | |
| JP7137332B2 (en) | Vehicle travel control device | |
| RU2721436C1 (en) | Driving assistance method and driving assistance device | |
| CN115158360A (en) | Automatic driving vehicle over-bending control system and method thereof | |
| JP7324020B2 (en) | Traffic control system | |
| US11364921B2 (en) | Object recognition apparatus, object recognition method, and vehicle | |
| CN114763157A (en) | Method for multidimensional lane matching for autonomous vehicle positioning | |
| CN113428173B (en) | Static curvature error compensation control logic for an autonomous vehicle | |
| US11577758B2 (en) | Autonomous vehicle park-and-go scenario design | |
| CN113619597A (en) | Planning system for automatic vehicle speed limit change | |
| EP4147936B1 (en) | Drive with caution under uncertainty for an autonomous driving vehicle | |
| CN113044058A (en) | Three-point turn for automatic driving vehicle | |
| US20240001963A1 (en) | Vehicle systems and related methods with autonomous courtesy avoidance |
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 |