CN113173178B - Automatic driving control method and system for vehicle - Google Patents
Automatic driving control method and system for vehicle Download PDFInfo
- Publication number
- CN113173178B CN113173178B CN202110635659.4A CN202110635659A CN113173178B CN 113173178 B CN113173178 B CN 113173178B CN 202110635659 A CN202110635659 A CN 202110635659A CN 113173178 B CN113173178 B CN 113173178B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- track
- vehicle
- controller
- master controller
- 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.)
- Active
Links
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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/029—Adapting to failures or work around with other constraints, e.g. circumvention by avoiding use of failed parts
-
- 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
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/007—Emergency override
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/029—Adapting to failures or work around with other constraints, e.g. circumvention by avoiding use of failed parts
- B60W2050/0292—Fail-safe or redundant systems, e.g. limp-home or backup systems
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/53—Road markings, e.g. lane marker or crosswalk
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention provides an automatic driving control method and system for a vehicle, and relates to the technical field of vehicles. The method comprises the following steps: the master controller acquires first environmental information and map information around the vehicle in real time and sends the first environmental information and the map information to the slave controller; the slave controller acquires second environment information around the vehicle in real time; the slave controller judges whether the master controller fails or not; if so, the slave controller plans a parking path according to the first environment information, the map information and the second environment information which are sent by the master controller for the last time, and controls the vehicle to automatically park according to the parking path. The automatic driving control method provided by the invention has high parking safety and good comfort.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to an automatic driving control method and system for a vehicle.
Background
With the development of science and technology, the safety of the automatic driving technology is more and more concerned. According to the classification of the automatic driving system, the automatic driving system of the L4 level is defined as a system which does not need to be taken over by people and can be stopped safely. In order to reach the L4 level, the industry mainly adopts a redundancy design in the prior art, that is, a margin is added to an original system to ensure that safety measures can be still made when the system is in an unexpected situation (such as downtime) so as to improve the safety and reliability of the system. In addition, various redundancy schemes have been derived for different operating scenarios and system cost requirements, but are essentially hybrid modes of sensor redundancy, actuator redundancy, and computing platform redundancy.
In order to meet the requirements of processing sensor data such as multipath vision, laser radar, millimeter wave radar and the like, the automatic driving computing platform generally adopts a computing platform with rich interfaces and high computing power. However, the software and hardware of the platform are complex, the requirements of vehicle specifications are difficult to achieve, the reliability is difficult to guarantee, and the cost is high. In order to improve the reliability of the platform, the same hardware backup is adopted in some technical schemes, but the cost of the whole system is higher, and the occurrence of similar faults cannot be avoided. In other technical schemes, a Micro Control Unit (MCU) without sensing capability is used as a backup controller, but because the front obstacle cannot be detected and predicted, only emergency braking can be performed, and the parking comfort is poor.
Disclosure of Invention
An object of the first aspect of the present invention is to provide an automatic driving control method with high parking safety and good comfort.
It is a further object of the first aspect of the present invention to provide an automatic driving control method with high driving safety.
A second aspect of the present invention is to provide an automatic driving control system having high parking safety and good comfort.
According to the first aspect described above, the present invention provides an automatic driving control method for a vehicle, for controlling an automatic driving control system of the vehicle, the automatic driving control system including a master controller and a slave controller that are communicatively connected, the automatic driving control method including:
the master controller acquires first environmental information and map information around the vehicle in real time and sends the first environmental information and the map information to the slave controller;
the slave controller acquires second environment information around the vehicle in real time;
the slave controller judges whether the master controller fails or not;
if yes, the slave controller plans a parking path according to the first environment information, the map information and the second environment information which are sent by the master controller last time, and controls the vehicle to automatically park according to the parking path.
Optionally, the step of obtaining, by the controller in real time, second environmental information around the vehicle further includes:
the slave controller sends the second environment information to the master controller;
and the main controller generates a driving path for controlling the automatic driving of the vehicle according to the second environment information, the first environment information and the map information.
Optionally, the first environmental information is acquired by a first set of sensors disposed on the vehicle;
the second environmental information is acquired by a second set of sensors disposed on the vehicle.
Optionally, the step of determining, by the slave controller, whether the master controller fails includes:
and when the slave controller does not receive the heartbeat packet of the master controller within the preset interval time, judging that the master controller fails, generating and sending the heartbeat packet to the slave controller by the master controller, and stopping sending the heartbeat packet when the first group of sensors are abnormal and/or the communication between the master controller and the chassis of the vehicle is abnormal.
Optionally, the planning, by the slave controller, an initial parking path according to the first environment information and the map information that are sent by the master controller last time includes:
the slave controller obtains the first environmental information, the second environmental information and the map information according to a first preset formula to obtain a one-dimensional longitudinal track and a one-dimensional transverse track;
performing Kalman filtering on the one-dimensional longitudinal track and the one-dimensional transverse track to obtain a filtered one-dimensional longitudinal track and a filtered one-dimensional transverse track;
removing the filtered one-dimensional longitudinal track which does not meet a first preset condition, and generating a one-dimensional transverse longitudinal track pair by the filtered one-dimensional transverse track and the filtered one-dimensional longitudinal track left after removal;
performing cost evaluation on all the one-dimensional transverse and longitudinal track pairs according to a track evaluation function, and taking out the one-dimensional transverse and longitudinal track pairs corresponding to the cost evaluation values from small to large according to the cost evaluation values to combine to generate a two-dimensional track;
judging whether the two-dimensional track meets a second preset condition or not;
and if so, generating the parking path according to the two-dimensional track.
Optionally, after determining whether the two-dimensional trajectory meets a second preset condition, the method further includes:
if the two-dimensional track does not meet the second preset condition;
the slave controller obtains the one-dimensional transverse track and the one-dimensional longitudinal track from the first environment information, the second environment information and the map information according to a second preset formula;
sorting the one-dimensional transverse tracks and the one-dimensional longitudinal tracks according to a preset rule and then combining to obtain transverse and longitudinal track pairs;
judging whether the transverse and longitudinal track pair meets the hard collision requirement of the vehicle;
and if so, generating the parking path according to the transverse and longitudinal track pair.
Optionally, the first preset formula is:
where t is time, s is longitudinal distance, d is transverse distance, a 0 -a 5 And b 0 -b 5 Are all constants.
Optionally, the first preset condition is that the following conditions are simultaneously satisfied:
the last time point of the one-dimensional longitudinal track is zero;
the distance between the tail end of the one-dimensional longitudinal track and the stop line is smaller than a preset value;
the speed, the acceleration and the jerk of each time point on the one-dimensional longitudinal track are all within respective first preset ranges.
Optionally, the second preset condition is that the following conditions are simultaneously satisfied:
the speed, the acceleration and the jerk of each time point on the two-dimensional track are all in respective second preset ranges;
the two-dimensional trajectory satisfies a hard crash requirement of the vehicle.
According to the second aspect, the invention further provides an automatic driving control system for a vehicle, which comprises a master controller and a slave controller, wherein the master controller is used for acquiring first environmental information and map information around the vehicle in real time and sending the first environmental information and the map information to the slave controller; the slave controller is used for acquiring second environment information around the vehicle in real time, sending the second environment information to the master controller, judging whether the master controller breaks down or not, if so, planning a parking path according to the first environment information, the map information and the second environment information which are sent by the master controller for the last time, and controlling the vehicle to automatically park according to the parking path.
The automatic driving control method provided by the invention has the advantages that the slave controller runs at the background, can recognize the abnormity of the master controller, and reasonably executes braking to control safe parking when detecting the fault of the master controller. Specifically, first environmental information and map information around the vehicle are acquired by the master controller in real time, and second environmental information around the vehicle is acquired by the slave controller in real time, and the master controller transmits the acquired first environmental information and map information to the slave controller. And when the slave controller judges that the master controller is abnormal, planning a parking path of the vehicle according to the first environment information and the map information sent by the master controller and the second environment information acquired by the slave controller, and controlling the vehicle to automatically park according to the parking path. According to the automatic driving control method provided by the invention, the main controller controls the vehicle when the main controller is normal, when the main controller is abnormal, the sub controller takes over the vehicle, plans the parking path according to the related information, and finally controls the vehicle to park according to the parking path, and a buffer driving distance is arranged before the vehicle completely stops, so that unnecessary emergency braking can be avoided as far as possible, and the curve braking operation can be realized, and thus the safety and the comfort during parking can be improved. Therefore, compared with the scheme of directly stopping the vehicle when the controller is abnormal in the prior art, the automatic driving control method provided by the invention has high safety and comfort when the vehicle stops when the main controller is abnormal.
Further, when the master controller is normal, the second environment information sent by the slave controller is received, and a driving path for controlling the automatic driving of the vehicle is generated after the second environment information, the first environment information and the map information are fused. Compared with the prior art, the driving path planned by the main controller has more considered factors, so that the safety of the automatic driving can be further improved.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the invention will be described in detail hereinafter by way of example and not by way of limitation with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:
FIG. 1 is a block flow diagram of an automated driving control method for a vehicle according to one embodiment of the invention;
FIG. 2 is a block diagram of an autopilot control system for a vehicle according to one embodiment of the invention;
FIG. 3 is a block flow diagram of an automated driving control method for a vehicle according to another embodiment of the invention;
fig. 4 is a vehicle coordinate system diagram at the time of performing parking according to an automatic driving control method for a vehicle according to an embodiment of the present invention;
fig. 5 is a deceleration curve at the time of parking in the automatic driving control method for the vehicle according to one embodiment of the present invention;
fig. 6 is a deceleration curve at the time of parking according to another embodiment of the automatic driving control method for a vehicle of the present invention;
fig. 7 is a deceleration curve at the time of parking according to still another embodiment of the automatic driving control method for a vehicle of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
Fig. 1 is a block flow diagram of an automatic driving control method for a vehicle according to one embodiment of the present invention. Fig. 2 is a block diagram of the automatic driving control system for a vehicle according to one embodiment of the present invention. As shown in fig. 1, the present invention provides an autopilot control method for a vehicle, for controlling an autopilot control system of the vehicle, the vehicle including a chassis 50, the autopilot control system including a master controller 10 and a slave controller 20 communicatively coupled, the master controller 10 and the slave controller 20 each being coupled to the chassis 50, the autopilot control method including:
s10: the master controller 10 acquires first environment information and map information around the vehicle in real time and sends the first environment information and the map information to the slave controller 20;
s20: acquiring second environmental information around the vehicle in real time from the controller 20;
s30: the slave controller 20 judges whether the master controller 10 has a failure;
s40: if so, the slave controller 20 plans a parking path according to the first environment information and the map information and the second environment information which are sent by the master controller 10 for the last time, and controls the vehicle to automatically park according to the parking path.
The first environment information comprises obstacle information, the map information comprises lane line information, and the second environment information comprises obstacle information, lane line information, road edge information and the like.
In the automatic driving control method provided in this embodiment, the slave controller 20 operates in the background, and the slave controller 20 can recognize an abnormality of the master controller 10, and when it detects that the master controller 10 has a failure, it reasonably executes braking to control a safe stop. Specifically, first environmental information and map information around the vehicle are acquired by the master controller 10 in real time, and second environmental information around the vehicle is acquired by the slave controller 20 in real time, and the master controller 10 transmits the acquired first environmental information and map information to the slave controller 20. When the slave controller 20 determines that the master controller 10 is abnormal, a parking path of the vehicle is planned based on the first environment information and the map information transmitted by the master controller 10 and the second environment information acquired by itself, and the vehicle is controlled to be automatically parked based on the parking path. According to the automatic driving control method provided by the invention, when the main controller 10 is normal, the main controller 10 controls the vehicle, when the main controller 10 is abnormal, the sub controller 20 takes over the vehicle, plans the parking path according to the related information, and finally controls the vehicle to park according to the parking path, and a buffer driving distance is provided before the vehicle completely stops, so that unnecessary emergency braking can be avoided as far as possible, and the curve braking operation is realized, and thus, the safety and the comfort during parking can be improved. Therefore, compared with the prior art that the vehicle is directly stopped when the controller is abnormal, the automatic driving control method provided by the invention has high safety and comfort when the main controller 10 is abnormal and the vehicle is stopped.
In a preferred embodiment, the slave controller 20 has basic sensing capability, receives the last frame of sensing data sent by the master controller 10, and executes a safety take-over strategy according to the working conditions, so that unnecessary emergency braking can be avoided as much as possible, and a curve braking operation can be realized, thereby improving driving safety compared with direct braking.
Fig. 3 is a block flow diagram of an automatic driving control method for a vehicle according to another embodiment of the present invention. As shown in fig. 3, in a specific embodiment, step S20 is followed by:
s50: the slave controller 20 sends the second environment information to the master controller 10;
s60: the main controller 10 generates a travel path for controlling the automatic driving of the vehicle based on the second environment information, the first environment information, and the map information.
In the present embodiment, when the master controller 10 is normal, the second environment information transmitted from the controller 20 is received, and the travel route for controlling the automatic driving of the vehicle is generated by fusing the second environment information, the first environment information, and the map information. Compared with the prior art, the driving path planned by the main controller 10 has more considered factors, so that the safety of the automatic driving can be further improved.
In one particular embodiment, the first environmental information is acquired by a first set of sensors 30 disposed on the vehicle and the second environmental information is acquired by a second set of sensors 40 disposed on the vehicle. Preferably, the first set of sensors 30 is a multi-vision, lidar, millimeter-wave radar, and more preferably, the first set of sensors 30 is a forward-facing camera, a panoramic camera, a millimeter-wave radar, a lidar, and a combination positioning device, and the second set of sensors 40 is a forward-facing mid-focus camera (different from the forward-facing camera of the first set of sensors 30) and a forward-facing millimeter-wave radar. The main controller 10 is a large computational platform with rich interfaces, generally a domain controller with high computational power, and can be accessed to multiple paths of vision, laser radar and millimeter wave radar. Considering the system cost, an embedded software and hardware system with low computational power and high reliability is selected from the controller 20, generally a typical ADAS controller, has basic sensing capability, and can be accessed to a forward middle-focus camera and a forward millimeter wave radar. During normal operation, on one hand, the slave controller 20 transmits the original data of the forward vision and forward millimeter wave radar to the master controller 10 through the ethernet, the master controller 10 performs the fusion of the omnidirectional sensors, performs the automatic driving decision planning and the issuing of the driving control command, and each actuator of the chassis CAN network responds to the command issued by the master controller 10 in a normal state. On the other hand, the slave controller 20 also receives the target information fused by the master controller 10 and the planned driving road path information, and takes over when the master controller 10 is judged to be abnormal, and at the moment, each controller on the chassis CAN network preferentially responds to the command of the slave controller 20. Of course, the slave controller 20 may also receive the raw data collected by the master controller 10, and then plan a parking path after fusing the raw data collected by the slave controller and the raw data sent by the master controller 10, and each controller on the chassis CAN network preferentially responds to the command from the slave controller 20.
In one embodiment, the step of determining whether the master controller 10 has failed from the slave controller 20 includes:
when the slave controller 20 does not receive the heartbeat packet of the master controller 10 within the preset interval time, it is determined that the master controller 10 fails, the heartbeat packet is generated by the master controller 10 and sent to the slave controller 20, and the sending of the heartbeat packet is stopped when the first group of sensors 30 is abnormal and/or the communication between the master controller 10 and the chassis of the vehicle is abnormal.
In order to ensure that the slave controller 20 monitors the state of the master controller 10 safely and reliably and meets the communication bandwidth requirement, two information interaction channels are arranged between the master controller 10 and the slave controller 20. Specifically, the master controller 10 and the slave controller 20 are both connected to a chassis of the vehicle, preferably in a CAN communication connection, for acquiring chassis information and controlling the chassis. The master controller 10 is communicatively connected to the slave controller 20, preferably by an ethernet connection. The main controller 10 is provided with a CAN communication module and a TCP server, the CAN communication module is used for realizing the connection between the main controller 10 and the chassis, and the TCP server is used for realizing the connection between the main controller 10 and the slave controller 20. After the master controller 10 is started, the CAN communication module is started to be in communication connection with the chassis, and the master controller receives chassis information and sends a control message to the chassis. Meanwhile, the master controller 10 starts the TCP server, waits for the ethernet connection to be established with the slave controller 20, and after the connection is successfully established, the master controller 10 will send the heartbeat packet and the perception-related data (the first environment information and the map information) to the slave controller 20 at regular time. In both cases, the slave controller 20 will take over the vehicle, respectively: if the first group of sensors 30 is abnormal, the master controller 10 system stops the CAN communication module and stops sending the heartbeat packet to the slave controller 20, and the slave controller 20 takes over the vehicle; if the first group of sensors 30 is normal but the CAN communication module is abnormal, the master controller 10 will stop sending heartbeat packets to the slave controller 20, and the slave controller 20 will take over the vehicle. The chassis is provided with a driving controller, a braking controller, a gear controller, a steering controller, a vehicle body controller and the like. Under the condition that the main controller 10 is normal, each controller in the chassis executes the instruction issued by the main controller 10 to perform automatic driving, and under the condition that the main controller 10 is abnormal, each controller in the chassis executes the instruction issued by the controller 20 to perform automatic parking.
Specifically, the slave controller 20 is provided with a Canbus module, and the Canbus module is in a monitoring state after the slave controller 20 is started, and waits for the network connection to be established with the master controller 10. After the network connection is established, the heartbeat packet and the control packet sent by the main controller 10 are periodically detected. If the master controller 10 fails to stop sending the heartbeat packet or detects that the control message is lost, the slave controller 20 records a frame of heartbeat packet, the first environment information and the map information which are sent by the master computer last.
In a specific embodiment, the planning of the initial parking path by the slave controller 20 according to the first environment information and the map information last transmitted by the master controller 10 includes:
obtaining a one-dimensional longitudinal track and a one-dimensional transverse track from the controller 20 according to a first preset formula by using the first environment information, the second environment information and the map information;
performing Kalman filtering on the one-dimensional longitudinal track and the one-dimensional transverse track to obtain a filtered one-dimensional longitudinal track and a filtered one-dimensional transverse track;
removing the filtered one-dimensional longitudinal track which does not meet the first preset condition, and generating a one-dimensional transverse longitudinal track pair by the filtered one-dimensional transverse track and the filtered one-dimensional longitudinal track left after removal;
performing cost evaluation on all the one-dimensional transverse and longitudinal track pairs according to the track evaluation function, and taking out the one-dimensional transverse and longitudinal track pairs corresponding to the cost evaluation values from small to large according to the cost evaluation values to combine to generate a two-dimensional track;
judging whether the two-dimensional track meets a second preset condition or not;
and if so, generating a parking path according to the two-dimensional track.
The parking path generated by the embodiment is a normal path.
The present embodiment is a parking path planning process performed after the controller 20 takes over the vehicle. The second environment information sensed in real time is fused with the first environment information and the map information transmitted from the master controller 10 by the slave controller 20. Fig. 4 is a vehicle coordinate system diagram at the time of performing parking according to an automatic driving control method for a vehicle according to an embodiment of the present invention. As shown in fig. 4, when a vehicle travels on a large-curvature road, for example, a quarter turn, a problem of vehicle travel in the case of an unexpected take-over occurs, and a vehicle can be prevented from rushing out of the road, and can be safely stopped on the road, and a reasonable deceleration can be selected based on a judgment of collision with an obstacle.
In a specific embodiment, after determining whether the two-dimensional trajectory satisfies the second preset condition, the method further includes:
if the two-dimensional track does not meet a second preset condition;
obtaining a one-dimensional transverse track and a one-dimensional longitudinal track from the controller 20 according to a second preset formula by using the first environment information, the second environment information and the map information;
sorting the one-dimensional transverse tracks and the one-dimensional longitudinal tracks according to a preset rule and then combining to obtain transverse and longitudinal track pairs;
judging whether the transverse and longitudinal track pair meets the hard collision requirement of the vehicle;
if yes, a parking path is generated according to the transverse and longitudinal track pairs.
The scheme provided by the embodiment aims at the situation that the two-dimensional track does not meet the second preset condition, and the generated parking path is the alternative track. And when all the tracks do not meet the second preset condition, indicating that the common track cannot be planned, and entering an alternative track generation module. The generation and selection of the alternative tracks are relatively simple, a series of complex cost evaluations are not required like the common tracks, and only hard collision detection is required.
In a specific embodiment, the first predetermined formula is:
where t is time, s is longitudinal distance, d is transverse distance, a 0 -a 5 And b 0 -b 5 Are all constants. The formula is suitable for generation of common tracks.
When the alternative track is generated, the formula for generating the one-dimensional transverse track in the second preset formula is the same as the transverse track in the first preset formula, and when the one-dimensional longitudinal track is generated, the acceleration is set to be constant, and the acceleration is the second derivative of the distance s to the time t, then: a0= s0, a1= v0, a2=1/2a, a3= a4= a5=0, wherein a is 0 -a 5 Are all constants, a is acceleration, v0 is velocity, resulting in acceleration of [ -0.1, -1.0, -2.0, -3.0, -4.0 [ -1.0 [ -2.0 [ ]]. In the above embodiment, the generation process of the alternative trajectory includes: firstly, arranging the planned one-dimensional longitudinal tracks (t, s) from small to large according to deceleration and arranging the planned one-dimensional transverse tracks (t, d) according to transverse distance; secondly, the one-dimensional longitudinal track and the one-dimensional transverse track are combined to generate a transverse-longitudinal track pair [ (t, s), (t, d)](ii) a Finally, the generated transverse and longitudinal track pairs are sequentially subjected to hard collision detection, and if the hard collision requirements are met, the hard collision detection is outputAnd selecting the track, and controlling the vehicle to automatically stop according to the alternative track by the controller 20. The sequence of the horizontal and vertical track pairs generated by combination is horizontal =0,0.5,0.5,1, -1 …, and vertical a = -0.1,1,2,3,4 …. The alternative trajectory is mainly used in an emergency situation and thus the constraint on the deceleration derivative value is relaxed compared to the trajectory evaluation function, and fig. 5 is a deceleration curve at the time of stop of the automatic driving control method for a vehicle according to one embodiment of the present invention, in which the solid line represents the speed of the normal trajectory and the dotted line represents the speed of the alternative trajectory, although the end deceleration of the normal trajectory is the same as the deceleration of the alternative trajectory, and is 4m/s 2 However, since the normal trajectory must be considered for comfort, the deceleration is gradually increased to 4m/s 2 The time and distance to decelerate to zero are therefore much larger than for the alternative trajectory.
Fig. 6 is a deceleration curve at the time of parking in an automatic driving control method for a vehicle according to another embodiment of the present invention. Fig. 7 is a deceleration curve at the time of parking according to still another embodiment of the automatic driving control method for a vehicle of the present invention. In some embodiments, the alternative trajectory and the normal trajectory intersect, which indicates that the braking distance is the same (as shown in fig. 6) or that it takes the same time to decelerate from the same speed to zero (as shown in fig. 7), with the solid line representing the speed of the normal trajectory and the dashed line representing the speed of the alternative trajectory in fig. 6 and 7. As can be seen from fig. 6 and 7, the deceleration at the end of the normal trajectory is much greater than the deceleration at the alternative trajectory to produce the same braking distance or the same braking time. When the evaluation function of the normal trajectory is determined, i.e. the boundary value of the deceleration is known, the lower deceleration boundary of the alternative trajectory can be estimated approximately, so that the braking distance or braking time of the alternative trajectory is smaller than the behavior of the normal trajectory.
In a specific embodiment, the first preset condition is that the following conditions are simultaneously satisfied:
the last time point of the one-dimensional longitudinal track is zero;
the distance between the tail end of the one-dimensional longitudinal track and the stop line is smaller than a preset value;
the speed, the acceleration and the jerk of each time point on the one-dimensional longitudinal track are within respective first preset ranges.
The first preset range is selected according to the vehicle type, for example: the speed is not more than 30km/h at most, and the acceleration is not more than +/-3 m/s 2 The acceleration does not exceed +/-4 m/s 2 。
In a specific embodiment, the second preset condition is that the following conditions are simultaneously satisfied:
the speed, the acceleration and the jerk of each time point on the two-dimensional track are all in respective second preset ranges;
the two-dimensional trajectory satisfies the hard crash requirements of the vehicle.
Wherein, the second preset range is selected according to the vehicle type, for example: the speed is not more than 30km/h at most, and the acceleration is not more than +/-3 m/s 2 Acceleration not exceeding +/-4 m/s 2 。
The present invention also provides an automatic driving control system for a vehicle, which generally includes a master controller and a slave controller 20, the master controller 10 being configured to acquire first environmental information and map information around the vehicle in real time and transmit the first environmental information and the map information to the slave controller 20; the slave controller 20 is configured to obtain second environment information around the vehicle in real time and send the second environment information to the master controller 10, and determine whether the master controller 10 has a fault, if so, the slave controller 20 plans a parking path according to the first environment information and the map information that are sent by the master controller 10 for the last time and the second environment information, and controls the vehicle to automatically park according to the parking path.
The present embodiment provides an automatic driving control system including a master controller 10 and a slave controller 20. The slave controller 20 operates in the background, and can recognize the abnormality of the master controller 10, and when it detects that the master controller 10 has a failure, braking is executed reasonably to control safe parking. Specifically, first environmental information and map information around the vehicle are acquired by the master controller 10 in real time, and second environmental information around the vehicle is acquired by the slave controller 20 in real time, and the master controller 10 transmits the acquired first environmental information and map information to the slave controller 20. When the slave controller 20 determines that the master controller 10 is abnormal, a parking path of the vehicle is planned based on the first environment information and the map information transmitted by the master controller 10 and the second environment information acquired by itself, and the vehicle is controlled to be automatically parked based on the parking path. According to the automatic driving control method provided by the invention, when the main controller 10 is normal, the main controller 10 controls the vehicle, when the main controller 10 is abnormal, the sub controller 20 takes over the vehicle, plans the parking path according to the related information, and finally controls the vehicle to park according to the parking path, and a buffer driving distance is provided before the vehicle completely stops, so that unnecessary emergency braking can be avoided as far as possible, and the curve braking operation is realized, and thus, the safety and the comfort during parking can be improved. Therefore, compared with the prior art that the vehicle is directly stopped when the controller is abnormal, the automatic driving control method provided by the invention has high safety and comfort when the main controller 10 is abnormal and the vehicle is stopped.
In one embodiment, the autopilot control system further includes a first set of sensors 30 and a second set of sensors 40, the first set of sensors 30 coupled to the master controller 10 for obtaining first environmental information and map information, and the second set of sensors 40 coupled to the slave controller 20 for obtaining second environmental information. Preferably, the first set of sensors 30 is a multi-vision, lidar, millimeter-wave radar, preferably a forward-facing camera, a panoramic camera, a millimeter-wave radar, lidar, and a combination positioning device, and the second set of sensors 40 is a forward-facing mid-focus camera (different from the forward-facing camera in the first set of sensors 30) and a forward-facing millimeter-wave radar.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.
Claims (8)
1. An autopilot control method for a vehicle, characterized by an autopilot control system for controlling the vehicle, the autopilot control system including a master controller and a slave controller communicatively coupled, the autopilot control method comprising:
the master controller acquires first environmental information and map information around the vehicle in real time and sends the first environmental information and the map information to the slave controller;
the slave controller acquires second environmental information around the vehicle in real time;
the slave controller judges whether the master controller fails or not;
if so, the slave controller plans a parking path according to the first environment information, the map information and the second environment information which are sent by the master controller for the last time, and the slave controller obtains a one-dimensional longitudinal track and a one-dimensional transverse track according to a first preset formula by the first environment information, the second environment information and the map information; performing Kalman filtering on the one-dimensional longitudinal track and the one-dimensional transverse track to obtain a filtered one-dimensional longitudinal track and a filtered one-dimensional transverse track; removing the filtered one-dimensional longitudinal track which does not meet a first preset condition, and generating a one-dimensional transverse longitudinal track pair by the filtered one-dimensional transverse track and the filtered one-dimensional longitudinal track left after removal; performing cost evaluation on all the one-dimensional transverse and longitudinal track pairs according to a track evaluation function, and taking out the one-dimensional transverse and longitudinal track pairs corresponding to the cost evaluation values from small to large according to the cost evaluation values to combine to generate a two-dimensional track; judging whether the two-dimensional track meets a second preset condition, if not, obtaining the one-dimensional transverse track and the one-dimensional longitudinal track from the first environment information, the second environment and the map information by the slave controller according to a second preset formula, sequencing the one-dimensional transverse track and the one-dimensional longitudinal track according to a preset rule, and then combining to obtain a transverse track pair and a longitudinal track pair; the speed, the acceleration and the jerk of each time point on the two-dimensional track are all within respective second preset ranges, and the two-dimensional track meets the hard collision requirement of the vehicle;
and controlling the vehicle to automatically stop according to the parking path.
2. The automatic driving control method according to claim 1, wherein the step of acquiring, from the controller, the second environmental information around the vehicle in real time further includes, after the step of:
the slave controller sends the second environment information to the master controller;
and the main controller generates a driving path for controlling the automatic driving of the vehicle according to the second environment information, the first environment information and the map information.
3. The automatic driving control method according to claim 2, characterized in that the first environmental information is acquired by a first group of sensors provided on the vehicle;
the second environmental information is acquired by a second set of sensors disposed on the vehicle.
4. The automatic driving control method according to claim 3, wherein the step of the slave controller determining whether the master controller is malfunctioning includes:
when the slave controller does not receive the heartbeat packet of the master controller within the preset interval time, the master controller is judged to be in fault, the heartbeat packet is generated by the master controller and is sent to the slave controller, and the sending of the heartbeat packet is stopped when the communication between the master controller and the first group of sensors and/or the communication between the master controller and the chassis of the vehicle is abnormal.
5. The autopilot control method of claim 1 wherein the slave controller deriving a one-dimensional longitudinal trajectory and a one-dimensional lateral trajectory from the first environmental information, the second environmental information, and the map information according to a first predetermined formula further comprises:
performing cost evaluation on all the one-dimensional transverse and longitudinal track pairs according to a track evaluation function, taking out the one-dimensional transverse and longitudinal track pairs corresponding to the cost evaluation values from small to large according to the cost evaluation values to combine to generate a two-dimensional track, and then judging whether the two-dimensional track meets a second preset condition; and if so, generating the parking path according to the two-dimensional track.
6. The automatic driving control method according to claim 5, characterized in that the first preset formula is:
where t is time, s is longitudinal distance, d is transverse distance, a 0 -a 5 And b 0 -b 5 Are all constants.
7. The automatic driving control method according to claim 5, characterized in that the first preset condition is that the following conditions are simultaneously satisfied:
the last time point of the one-dimensional longitudinal track is zero;
the distance between the tail end of the one-dimensional longitudinal track and the stop line is smaller than a preset value;
the speed, the acceleration and the jerk of each time point on the one-dimensional longitudinal track are all within respective first preset ranges.
8. The automatic driving control system for the vehicle is characterized by comprising a master controller and a slave controller, wherein the master controller is used for acquiring first environment information and map information around the vehicle in real time and sending the first environment information and the map information to the slave controller; the slave controller is used for acquiring second environment information around the vehicle in real time, sending the second environment information to the master controller and judging whether the master controller fails or not, if so, the slave controller plans a parking path according to the first environment information, the map information and the second environment information which are sent by the master controller for the last time, and the slave controller obtains a one-dimensional longitudinal track and a one-dimensional transverse track according to a first preset formula from the first environment information, the second environment information and the map information; performing Kalman filtering on the one-dimensional longitudinal track and the one-dimensional transverse track to obtain a filtered one-dimensional longitudinal track and a filtered one-dimensional transverse track; removing the filtered one-dimensional longitudinal track which does not meet a first preset condition, and generating a one-dimensional transverse longitudinal track pair by the filtered one-dimensional transverse track and the filtered one-dimensional longitudinal track left after removal; performing cost evaluation on all the one-dimensional transverse and longitudinal track pairs according to a track evaluation function, and taking out the one-dimensional transverse and longitudinal track pairs corresponding to the cost evaluation values from small to large according to the cost evaluation values to combine to generate a two-dimensional track; judging whether the two-dimensional track meets a second preset condition, if not, obtaining the one-dimensional transverse track and the one-dimensional longitudinal track from the first environment information, the second environment and the map information by the slave controller according to a second preset formula, sequencing the one-dimensional transverse track and the one-dimensional longitudinal track according to a preset rule, and then combining to obtain a transverse track pair and a longitudinal track pair; the speed, the acceleration and the jerk of each time point on the two-dimensional track are all in respective second preset ranges; the two-dimensional trajectory meets a hard crash requirement of the vehicle; and controlling the vehicle to automatically stop according to the parking path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110635659.4A CN113173178B (en) | 2021-06-08 | 2021-06-08 | Automatic driving control method and system for vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110635659.4A CN113173178B (en) | 2021-06-08 | 2021-06-08 | Automatic driving control method and system for vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113173178A CN113173178A (en) | 2021-07-27 |
| CN113173178B true CN113173178B (en) | 2022-10-18 |
Family
ID=76927627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110635659.4A Active CN113173178B (en) | 2021-06-08 | 2021-06-08 | Automatic driving control method and system for vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113173178B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113442924A (en) * | 2021-08-03 | 2021-09-28 | 浙江吉利控股集团有限公司 | Vehicle track planning method and system |
| CN114237104A (en) * | 2021-12-02 | 2022-03-25 | 东软睿驰汽车技术（沈阳）有限公司 | Automatic driving area controller and vehicle |
| CN114435394A (en) * | 2021-12-22 | 2022-05-06 | 安徽建德基文化传媒有限公司 | Control system of unmanned automobile |
| CN114291115A (en) * | 2022-01-06 | 2022-04-08 | 云控智行科技有限公司 | Automatic driving vehicle safe parking track planning method |
| CN115923686B (en) * | 2022-12-17 | 2024-06-18 | 中国重汽集团济南动力有限公司 | Dual-engine hot standby whole vehicle control system, method and new energy vehicle |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108196547A (en) * | 2018-01-08 | 2018-06-22 | 北京图森未来科技有限公司 | A kind of automated driving system |
| CN109032132A (en) * | 2018-07-06 | 2018-12-18 | 联合汽车电子有限公司 | Vehicle driving system and method |
| CN109343529A (en) * | 2018-10-30 | 2019-02-15 | 奇瑞汽车股份有限公司 | Control method for vehicle and device |
| CN110386148A (en) * | 2019-06-26 | 2019-10-29 | 北京汽车集团有限公司 | Control method, device and the vehicle of automatic driving vehicle |
| CN110745144A (en) * | 2019-12-23 | 2020-02-04 | 吉利汽车研究院（宁波）有限公司 | Automatic driving control system, control method and equipment |
| CN111661062A (en) * | 2019-03-05 | 2020-09-15 | 阿里巴巴集团控股有限公司 | Automatic driving control method, device and system |
| CN112849055A (en) * | 2021-02-24 | 2021-05-28 | 清华大学 | Intelligent automobile information flow redundancy safety control system based on chassis domain controller |
-
2021
- 2021-06-08 CN CN202110635659.4A patent/CN113173178B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108196547A (en) * | 2018-01-08 | 2018-06-22 | 北京图森未来科技有限公司 | A kind of automated driving system |
| CN109032132A (en) * | 2018-07-06 | 2018-12-18 | 联合汽车电子有限公司 | Vehicle driving system and method |
| CN109343529A (en) * | 2018-10-30 | 2019-02-15 | 奇瑞汽车股份有限公司 | Control method for vehicle and device |
| CN111661062A (en) * | 2019-03-05 | 2020-09-15 | 阿里巴巴集团控股有限公司 | Automatic driving control method, device and system |
| CN110386148A (en) * | 2019-06-26 | 2019-10-29 | 北京汽车集团有限公司 | Control method, device and the vehicle of automatic driving vehicle |
| CN110745144A (en) * | 2019-12-23 | 2020-02-04 | 吉利汽车研究院（宁波）有限公司 | Automatic driving control system, control method and equipment |
| CN112849055A (en) * | 2021-02-24 | 2021-05-28 | 清华大学 | Intelligent automobile information flow redundancy safety control system based on chassis domain controller |
Non-Patent Citations (2)
| Title |
|---|
| 基于轨迹匹配的模仿学习在类人机器人运动行为中的研究;门玉森;《中国优秀硕士学文论文全文数据库》;20170331;全文 * |
| 校园智能公交车避障控制策略研究;魏国亮;《万方学时期刊数据库》;20201231;第8，30-40页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113173178A (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113173178B (en) | Automatic driving control method and system for vehicle | |
| CN111935201B (en) | In-vehicle communication system, in-vehicle communication method and device | |
| US11398944B2 (en) | Vehicle fault handling method, apparatus, device and storage medium | |
| CN110077420B (en) | Automatic driving control system and method | |
| US11472428B2 (en) | Vehicle control system and control method | |
| JP7193289B2 (en) | In-vehicle electronic control system | |
| US11203350B2 (en) | Vehicle control system | |
| EP3223195B1 (en) | Device and method for detecting object | |
| US9606538B2 (en) | Device and method for the autonomous control of motor vehicles | |
| CN110481565A (en) | The control method of automatic driving vehicle and the control device of automatic driving vehicle | |
| US20190171205A1 (en) | Controlling the operation of a vehicle | |
| CN110155047A (en) | A kind of anti-collision control method, device, system and vehicle | |
| CN112041213B (en) | Method for operating an autonomously operable device and autonomously operable device | |
| US20210229685A1 (en) | Vehicle control apparatus, vehicle, vehicle control method, and non-transitory computer-readable storage medium | |
| CN114212102B (en) | Auxiliary driving method, system and device for avoiding lateral collision | |
| CN110949402A (en) | Alarm area determination method and device, storage medium and vehicle | |
| KR20210031128A (en) | Driver assistance apparatus and method thereof | |
| DE102019201689A1 (en) | Method and control unit for operating an autonomous vehicle | |
| CN116668992A (en) | Vehicle accident handling method, computer readable storage medium and vehicle | |
| US20240199072A1 (en) | Method for operating an assistance system, and assistance system | |
| CN113442924A (en) | Vehicle track planning method and system | |
| CN110341723B (en) | Vehicle control method, device and system | |
| CN112810608A (en) | Vehicle travel control device and vehicle control system | |
| JP7521639B2 (en) | Driving Control System | |
| JP7573993B2 (en) | A driving control method for autonomous vehicles by forming cluster groups |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 310051 No. 1760, Jiangling Road, Hangzhou, Zhejiang, Binjiang District Patentee after: ZHEJIANG GEELY HOLDING GROUP Co.,Ltd. Patentee after: Zhejiang Geely Remote New Energy Commercial Vehicle Group Co.,Ltd. Patentee after: Zhejiang Geely new energy Commercial Vehicle Development Co.,Ltd. Address before: 310051 No. 1760, Jiangling Road, Hangzhou, Zhejiang, Binjiang District Patentee before: ZHEJIANG GEELY HOLDING GROUP Co.,Ltd. Patentee before: ZHEJIANG GEELY NEW ENERGY COMMERCIAL VEHICLE GROUP Co.,Ltd. Patentee before: Zhejiang Geely new energy Commercial Vehicle Development Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230721 Address after: 310051 No. 1760, Jiangling Road, Hangzhou, Zhejiang, Binjiang District Patentee after: ZHEJIANG GEELY HOLDING GROUP Co.,Ltd. Patentee after: Zhejiang Geely Remote New Energy Commercial Vehicle Group Co.,Ltd. Address before: 310051 No. 1760, Jiangling Road, Hangzhou, Zhejiang, Binjiang District Patentee before: ZHEJIANG GEELY HOLDING GROUP Co.,Ltd. Patentee before: Zhejiang Geely Remote New Energy Commercial Vehicle Group Co.,Ltd. Patentee before: Zhejiang Geely new energy Commercial Vehicle Development Co.,Ltd. |