Collision risk control method, device and medium for intelligent vehicle operating system

Abstract

The present application provides a collision risk control method, device and medium for an intelligent automobile operating system. The method includes: obtaining a road segmentation area and a target object under each of the road segmentation areas, and confirming whether there is a ghost-peek risk in the segmentation blind area in the road segmentation area according to different target object types, wherein the target object is an entity with a collision risk; if there is the ghost-peek risk in the segmentation blind area, then obtaining the vehicle's collision avoidance operation restriction conditions according to the different target object types, and outputting the operation restriction conditions to a vehicle control module, wherein the vehicle control module includes a program for calculating and outputting vehicle control parameters; confirming whether the vehicle control parameters output by the vehicle control module meet the safety output threshold, and outputting the confirmation result of whether the vehicle control parameters meet the safety output threshold. The method of the present application can improve the safety performance of the assisted driving system.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a collision risk control method, device and medium for an intelligent automobile operating system. Background Art

[0002] The intelligent car operating system includes systems that can realize different functions, such as the car computer and the assisted driving system. The car computer refers to the on-board information system installed in the intelligent car operating system; the assisted driving system is an auxiliary system that assists the vehicle driver in driving. When the assisted driving system can no longer continue to assist driving, it will issue an alarm to the driver, allowing the driver to take over the driving work in time.

[0003] Now the application of assisted driving systems has been expanded and gradually developed into urban navigation assistance. Intelligent driving vehicles will rely on assisted driving systems to independently complete driving tasks in various road conditions and vehicle usage scenarios in the city. However, the urban road environment is complex and prone to ghost risks, that is, other road participants may suddenly jump out of the blind spot, and the vehicle itself may be unable to safely avoid obstacles, resulting in collision risks.

[0004] Therefore, ensuring that the assisted driving system can perform safe assisted driving is an urgent problem to be solved. Summary of the invention

[0005] The present application provides a collision risk control method, device and medium for an intelligent automobile operating system, which are used to solve the problem that the safety performance of the auxiliary driving system in the prior art is not high enough.

[0006] In a first aspect, the present application provides a collision risk control method for an intelligent automobile operating system, comprising:

[0007] Acquire a road segmentation area and a target object under each of the road segmentation areas, and confirm whether there is a risk of ghosting in a segmentation blind area in the road segmentation area according to different target object types, wherein the target object is an entity with a collision risk;

[0008] If the segmented blind spot has the risk of ghosting, then obtaining the operation restriction conditions for the vehicle to avoid collision according to the different types of the target objects, and outputting the operation restriction conditions to the vehicle control module, wherein the vehicle control module includes a program for calculating and outputting vehicle control parameters;

[0009] Confirm whether the vehicle control parameter output by the vehicle control module meets the safety output threshold, and output a confirmation result of whether the vehicle control parameter meets the safety output threshold.

[0010] In a possible implementation, acquiring the road segmentation area and the target objects under each of the road segmentation areas, and confirming whether there is a ghosting risk in the segmentation blind area in the road segmentation area according to different target object types, includes:

[0011] Acquire the perception space of the vehicle, divide the perception space into a plurality of the road segmentation areas, and acquire the target object under each of the road segmentation areas, wherein the road segmentation areas include a drivable area and a non-drivable area, and the segmentation blind area includes a drivable blind area of ​​the drivable area and a non-drivable blind area of ​​the non-drivable area;

[0012] According to different target types in each of the road segmentation areas, confirm the geometric size and kinematic constraints of the target;

[0013] According to the geometric size and kinematic constraints of the target object, it is confirmed whether there is a risk of ghosting in the segmentation blind area in the road segmentation area.

[0014] In a possible implementation, obtaining the operation restriction conditions for avoiding collision of the vehicle according to different target object types includes:

[0015] According to the target object type of the target object, obtaining the reaction conditions of the vehicle when different target object types collide with the vehicle, wherein the target object types include pedestrians, two-wheeled vehicles and cars, and the reaction conditions include driving distance and driving direction;

[0016] According to the reaction condition of the vehicle, the operation restriction condition of the vehicle is obtained, wherein the operation restriction condition includes the maximum speed of the vehicle, the steering angle range and the speed limit values ​​at different steering angles.

[0017] In a possible implementation, the confirming whether the vehicle control parameter output by the vehicle control module meets the safety output threshold includes:

[0018] Obtaining output information of the vehicle control module and confirming the activated assisted driving function, wherein the output information includes the vehicle control parameters;

[0019] Obtain the safety output threshold corresponding to the vehicle control parameter under the activated assisted driving function, and confirm whether the vehicle control parameter meets the safety output threshold.

[0020] In a possible implementation, the method further includes:

[0021] If the current driving path of the vehicle is the main driving path, confirming whether there is a collision risk on the main driving path according to a radar target, wherein the radar target is a target obtained by radar perception;

[0022] If it is confirmed that there is no collision risk on the main driving path according to the radar target, then confirming whether there is a collision risk on the main driving path according to the fused target, wherein the fused target is a target object sensed by a non-radar object sensing device;

[0023] If it is confirmed according to the fusion target object that there is no collision risk on the main driving path, the vehicle continues to be controlled to travel according to the main driving path.

[0024] In a possible implementation, if it is confirmed according to the radar target that there is a collision risk on the main driving path, the method further includes:

[0025] Determining whether there is a collision risk in the redundant driving path according to the fusion target object;

[0026] If it is confirmed according to the fusion target that the redundant driving path does not have a collision risk, confirming according to the radar target whether the redundant driving path has a collision risk;

[0027] If it is determined according to the radar target that there is no collision risk in the redundant driving path, the current driving path of the vehicle is switched to the redundant driving path.

[0028] In a possible implementation, the method further includes:

[0029] If any one of the multiple devices under test has an abnormality, the vehicle is controlled to stop safely, wherein the device under test includes an output monitoring module, a vehicle actuator and a vehicle sensor, the output monitoring module is used to monitor the output information of the vehicle control module, the output information includes the vehicle control parameters, and the vehicle actuator is a control device that controls the operation of the vehicle.

[0030] In a second aspect, the present application provides a collision risk control device for an intelligent automobile operating system, comprising:

[0031] An acquisition module, used to acquire a road segmentation area and a target object under each of the road segmentation areas, and to confirm whether there is a ghost head-on risk in a segmentation blind area in the road segmentation area according to different target object types, wherein the target object is an entity with a collision risk;

[0032] A first processing module is used for obtaining operation restriction conditions for avoiding collision of the vehicle according to different types of the target objects if the segmented blind area has the risk of ghosting, and outputting the operation restriction conditions to a vehicle control module, wherein the vehicle control module includes a program for calculating and outputting vehicle control parameters;

[0033] The second processing module is used to confirm whether the vehicle control parameter output by the vehicle control module meets the safety output threshold, and output a confirmation result of whether the vehicle control parameter meets the safety output threshold.

[0034] In a third aspect, the present application provides a collision risk control device for an intelligent automobile operating system, comprising: at least one processor and a memory;

[0035] The memory stores computer-executable instructions;

[0036] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the collision risk control method of the intelligent automobile operating system as described above.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the collision risk control method of the intelligent automobile operating system as described above.

[0038] The present application provides a collision risk control method, device and medium for an intelligent automobile operating system, which obtains a road segmentation area and a target object under each of the road segmentation areas, and confirms whether there is a ghost peeking risk in the segmentation blind area in the road segmentation area according to different target object types, wherein the target object is an entity with a collision risk; if there is the ghost peeking risk in the segmentation blind area, the operating restriction conditions for the vehicle to avoid collision are obtained according to the different target object types, and the operating restriction conditions are output to a vehicle control module, wherein the vehicle control module includes a program for calculating and outputting vehicle control parameters; confirms whether the vehicle control parameters output by the vehicle control module meet a safety output threshold, and outputs a confirmation result of whether the vehicle control parameters meet the safety output threshold.

[0039] In the above method, the operation restriction conditions are obtained through the road conditions, and the operation restriction conditions are output to the vehicle control module, so that the module for calculating the vehicle control parameters calculates the corresponding vehicle control parameters according to the operation restriction conditions to avoid driving risks; when confirming the operation restriction conditions, the road segmentation area and the targets under each road segmentation area are used to determine whether there is a ghost peeking risk to the vehicle in the segmentation blind area. The ghost peeking risk calculation process is different for targets of different target types, and needs to be calculated separately according to different target types; when it is confirmed that there is a risk that a target may suddenly jump out and cause a collision with the vehicle, that is, the ghost peeking risk, the operation restriction conditions for the vehicle to avoid collision with different targets are obtained according to the target type; the operation restriction conditions are output to the vehicle control module, so that the vehicle control module can plan the vehicle control parameters according to the operation restriction conditions; the vehicle control parameters planned by the vehicle control module also need to meet the safety output threshold to ensure safe driving of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0041] Figure 1 A schematic diagram of the structure of a vehicle control and monitoring system provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a collision risk control method for an intelligent vehicle operating system provided in an embodiment of the present application Figure 1 ;

[0043] Figure 3 A schematic diagram of a collision risk control method for an intelligent vehicle operating system provided in an embodiment of the present application Figure 2 ;

[0044] Figure 4 A schematic diagram of the logical structure of a restriction condition modification module provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of a collision risk control method for an intelligent vehicle operating system provided in an embodiment of the present application Figure 3 ;

[0046] Figure 6 A schematic diagram of the logical structure of an output monitoring module provided in an embodiment of the present application;

[0047] Figure 7A schematic diagram of a collision risk control method for an intelligent vehicle operating system provided in an embodiment of the present application Figure 4 ;

[0048] Figure 8 A schematic diagram of the logical structure of a path selection module provided in an embodiment of the present application;

[0049] Fig. 9 A diagram of a collision risk control device for an intelligent automobile operating system provided by an embodiment of the present invention;

[0050] Fig.10 A hardware schematic diagram of a collision risk control device for an intelligent automobile operating system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] The assisted driving system is an auxiliary system that assists the vehicle driver in driving. When the assisted driving system can no longer continue to assist in driving, it will issue an alarm to the driver, allowing the driver to take over the driving work in time.

[0053] Now the application of assisted driving systems has been expanded and gradually developed into urban navigation assistance. Intelligent driving vehicles will rely on assisted driving systems to independently complete driving tasks in various road conditions and vehicle usage scenarios in the city. In this situation, a large number of safety-related long-tail issues will arise. One of the most prominent problems is the risk of ghost peeking, that is, other road participants suddenly jump out of the blind spot of vision, and the vehicle itself cannot safely avoid obstacles, resulting in the risk of safety collision.

[0054] After determining that there is a collision risk, the existing vehicle collision avoidance module takes emergency braking action; the collision risk is only controlled within the range of visible targets, and only emergency braking can be provided as a safety action, resulting in reduced availability of the assisted driving system once a risk occurs.

[0055] In order to ensure that the assisted driving system can perform safe assisted driving and to ensure the availability of the assisted driving system, the present application proposes a collision risk control method for an intelligent automobile operating system.

[0056] The following describes the implementation process of a collision risk control method for an intelligent automobile operating system proposed in the present application in conjunction with the accompanying drawings and specific embodiments.

[0057] Figure 1 This is a schematic diagram of the structure of a vehicle control and monitoring system provided in an embodiment of the present application. Figure 1 As shown, the vehicle control monitoring system includes: an output monitoring module, a restriction condition correction module, a path selection module, and a fault monitoring module;

[0058] The vehicle control monitoring system is a functional system arranged in the auxiliary driving system. The functions of the vehicle control monitoring system are realized by various modules, and each module is arranged with a corresponding program; for example, the restriction condition correction module includes a program for calculating the operation restriction condition;

[0059] The restriction condition correction module can calculate the road segmentation area and the target objects under each road segmentation area through the data obtained by the monitoring equipment on the vehicle; the monitoring equipment can be used to detect lane lines, calculate the drivable area, locate and perceive the target object, and the fusion module for sensing the target object is composed of a non-radar object sensing device, the positioning module in the monitoring equipment performs positioning, the lane line detection module in the monitoring equipment is used to detect the lane line, and the drivable area calculation module is used to calculate the drivable area;

[0060] The constraint correction module can confirm whether there is a ghost peeking risk in the segmentation blind area in the road segmentation area according to different target object types. If there is a ghost peeking risk, the constraint correction module can calculate the operation constraint conditions for the vehicle to avoid collision according to different target object types, and output the operation constraint conditions to the vehicle control module; the vehicle control module is used to control the automatic driving of the vehicle in the auxiliary driving system, including a program for calculating and outputting vehicle control parameters, and the vehicle operates according to the vehicle control parameters;

[0061] The output monitoring module is used to monitor the output of the vehicle control module, including monitoring whether the vehicle control parameters meet the safety output threshold and outputting the corresponding monitoring results. If the safety output threshold is not met, the abnormality can be reported to the vehicle's domain control safety island, so that the domain control safety island can notify the driver to take over the vehicle;

[0062] The path selection module can recommend a suitable driving route to the vehicle control module through the radar perception module, the fusion module and the path planning module (including the main path planning module and the redundant path planning module);

[0063] The fault monitoring module can monitor whether the vehicle actuator, monitoring equipment, radar perception module, path planning module, and output monitoring module have any faults, and report the faults to the vehicle's domain control safety island in a timely manner;

[0064] Among them, the vehicle actuator is the control device that controls the operation of the vehicle, including the Electronic Control Unit (ECU), steering gear, and acceleration slip regulation (ESP), etc.

[0065] Figure 1 The solid arrow in the middle is the function information transmission path, and the function information is such as the operation constraint of the constraint correction module; the dotted arrow is the fault information transmission path, and the fault information is such as the fault detected by the fault monitoring module.

[0066] Figure 2 A schematic diagram of a collision risk control method for an intelligent vehicle operating system provided in an embodiment of the present application Figure 1 .like Figure 2 As shown, the method includes:

[0067] S201, obtaining a road segmentation area and a target object under each of the road segmentation areas, and confirming whether there is a risk of ghosting in a segmentation blind spot in the road segmentation area according to different target object types, wherein the target object is an entity with a collision risk.

[0068] Taking the vehicle as a reference point, the segmentation range is confirmed within a certain distance range. Within the segmentation range, multiple road segmentation areas are segmented. Through the corresponding detection equipment, the target object under each road segmentation area can be obtained and fed back to the constraint correction module;

[0069] Targets of different target types have different kinematic restrictions, so targets corresponding to different target types need to be confirmed separately whether there is a risk of ghosting, that is, whether the target will suddenly appear from the segmentation blind spot in the road segmentation area in the possible driving direction of the vehicle, causing a collision risk to the vehicle; the target is an entity with a collision risk, and the entity with a collision risk can be all entities in the segmentation blind spot, including static entities and dynamic entities, or only dynamic entities; the segmentation blind spot is a road segmentation area with a visual blind spot relative to the vehicle.

[0070] S202. If the risk of ghosting exists in the segmented blind spot, the operating restriction conditions for the vehicle to avoid collision are obtained according to the different types of the target objects, and the operating restriction conditions are output to a vehicle control module, wherein the vehicle control module includes a program for calculating and outputting vehicle control parameters.

[0071] When there is a segmentation blind spot around the vehicle, if the constraint condition correction module obtains that the segmentation blind spot may cause a risk of ghosting, then the constraint condition correction module calculates the vehicle's operating constraints under the condition that the vehicle will not collide with targets of different target types based on the targets corresponding to different target types; the operating constraints obtained by the constraint condition correction module will be output to the vehicle control module, and the vehicle control module can adjust the vehicle control parameters according to the operating constraints calculated by the constraint condition correction module.

[0072] S203: confirm whether the vehicle control parameter output by the vehicle control module meets the safety output threshold, and output a confirmation result of whether the vehicle control parameter meets the safety output threshold.

[0073] Various driving parameters of the vehicle during driving have corresponding safety output thresholds, and the driving parameters may have different safety output thresholds when the vehicle is in different functional modes. For example, the acceleration limit of the vehicle is different in different functional modes;

[0074] The output monitoring module is used to monitor the output of the vehicle control module. It can monitor whether the vehicle control parameters output by the vehicle control module meet the safety output threshold. When it is confirmed that the vehicle control parameters do not meet the safety output threshold, the confirmation result will be fed back to the domain control safety island, and the driver will be prompted to take over the vehicle through the domain control safety island.

[0075] In an embodiment of the present application, operating restrictions are obtained through road conditions and output to a vehicle control module, so that a module for calculating vehicle control parameters can calculate corresponding vehicle control parameters according to the operating restrictions to avoid driving risks. When confirming the operating restrictions, the road segmentation area and the targets under each road segmentation area are used to determine whether there is a ghosting risk to the vehicle in the segmentation blind spots. The ghosting risk calculation process for targets of different target types is different, and needs to be calculated separately according to different target types. When it is confirmed that there is a risk that a target may suddenly jump out and cause a collision with the vehicle, that is, a ghosting risk, the operating restrictions for the vehicle to avoid collisions with different targets are obtained according to the target type. The operating restrictions are output to the vehicle control module so that the vehicle control module can plan the vehicle control parameters according to the operating restrictions. The vehicle control parameters planned by the vehicle control module also need to meet the safety output threshold to ensure safe driving of the vehicle.

[0076] Figure 3 A schematic diagram of a collision risk control method for an intelligent vehicle operating system provided in an embodiment of the present application Figure 2 . Figure 4 A logical structure diagram of a restriction condition modification module provided in an embodiment of the present application. Figure 3As shown, the method includes:

[0077] S301. Acquire the perception space of the vehicle, divide the perception space into a plurality of road segmentation areas, and acquire the target object under each of the road segmentation areas, wherein the road segmentation areas include a drivable area and a non-drivable area, and the segmented blind spots include a drivable blind spot of the drivable area and a non-drivable blind spot of the non-drivable area.

[0078] like Figure 4 As shown, the restriction condition correction module can obtain lane information, drivable area, and sensed target objects through the lane detection module, drivable area calculation module, and fusion module on the vehicle, respectively. Among them, the lane detection module includes camera detection, which can confirm a segmentation range (sensing space) for the vehicle, and the drivable area in the segmentation range is confirmed by the drivable area calculation module;

[0079] The restriction condition correction module determines a plurality of road segmentation areas according to the segmentation range in the lane line information, wherein the road segmentation area includes a drivable area and a non-drivable area, the drivable area includes a drivable visible area and a drivable blind area, the non-drivable area includes a non-drivable visible area and a non-drivable blind area, and the segmented blind area includes a drivable blind area and a non-drivable blind area;

[0080] The fusion module can obtain the name, position, speed, direction of travel, etc. of the perceived target object. The constraint correction module can confirm the target object in each road segmentation area based on the information about the target object obtained by the fusion module, and thus obtain the target object in the segmentation blind spot.

[0081] S302: confirming the geometric size and kinematic constraints of the target object according to different target object types in each of the road segmentation areas.

[0082] Targets in the segmentation blind spot may pose a risk of ghosting to the vehicle. Different target types in the segmentation blind spot in each road segmentation area are obtained. Different target types include pedestrians, two-wheeled vehicles and cars. The geometric dimensions and kinematic limitations of different targets are obtained according to different target types. The kinematic limitations include the maximum driving speed of the target, etc.

[0083] S303: Determine whether there is a risk of ghosting in a segmentation blind area in the road segmentation area according to the geometric size and kinematic constraints of the target object.

[0084] For vehicles, targets are entities that may suddenly appear, and their geometric dimensions and kinematic limitations are different, resulting in different ghosting risks. Based on the geometric dimensions and kinematic limitations of targets of different types, it can be confirmed whether targets of different types have ghosting risks. For example, weights are set for geometric dimensions and kinematic limitations, and ghosting risk values ​​are calculated. When the ghosting risk value exceeds the preset risk threshold, it is confirmed that there is a ghosting risk, and targets with larger geometric dimensions and faster movement speeds are more likely to have ghosting risks.

[0085] After the restriction correction module confirms that there is a risk of ghosting, it calculates the operating restriction conditions for the vehicle to avoid the risk:

[0086] For example, according to the target type of the target object, the reaction conditions of the vehicle when different target types collide with the vehicle are obtained, wherein the target types include pedestrians, two-wheeled vehicles and cars, and the reaction conditions include driving distance and driving direction;

[0087] According to the reaction condition of the vehicle, the operation restriction condition of the vehicle is obtained, wherein the operation restriction condition includes the maximum speed of the vehicle, the steering angle range and the speed limit values ​​at different steering angles.

[0088] In a road segmentation area, when a target object may have a risk of peeking out, a motion hypothesis can be made for the target object based on the target object type, and the reaction conditions of the vehicle when a collision occurs can be obtained based on the motion hypothesis; the motion hypothesis includes assuming the speed and direction at which the target object is most likely to collide with the vehicle in the current motion state; based on the reaction conditions of the vehicle when a collision occurs under the motion hypothesis and the motion state of the vehicle, the operating restrictions for avoiding the collision can be calculated; the operating restrictions can also be calculated based on the type of obstruction and the static or dynamic condition of the obstruction.

[0089] In the embodiment of the present application, based on the road segmentation area and different target object types, the ghost peeking risks corresponding to the different target object types and the operating restrictions of the vehicle under the ghost peeking risks are respectively confirmed, so as to specifically avoid the collision risks that the targets of different target object types may cause to the vehicle.

[0090] Figure 5 A schematic diagram of a collision risk control method for an intelligent vehicle operating system provided in an embodiment of the present application Figure 3 . Figure 6 A schematic diagram of the logical structure of an output monitoring module provided in an embodiment of the present application. Figure 5 As shown, the method includes:

[0091] S501. Obtain output information of the vehicle control module and confirm an activated assisted driving function, wherein the output information includes the vehicle control parameters.

[0092] like Figure 6 As shown, the output monitoring module is used to read the output information of the vehicle control module, and to obtain the activated assisted driving function of the vehicle actuator (current function activation status) and the current vehicle speed; wherein, the output information includes vehicle control parameters, and the vehicle control parameters include acceleration, deceleration, and steering wheel angle, and different assisted driving functions correspond to different safety output thresholds.

[0093] S502: Obtain the safety output threshold corresponding to the vehicle control parameter under the activated assisted driving function, and confirm whether the vehicle control parameter meets the safety output threshold.

[0094] Obtain the currently activated assisted driving function, and correspondingly obtain the safety output threshold corresponding to the current vehicle control parameter; wherein the safety output threshold includes maximum speed, maximum acceleration, maximum acceleration gradient value, maximum deceleration, maximum braking force, maximum steering wheel angle, maximum steering wheel angular velocity, maximum steering wheel angular velocity gradient value, maximum deceleration gradient value, and maximum braking force gradient value;

[0095] Output diagnosis can be performed based on the output of the vehicle control module and the safety output threshold. Based on the currently confirmed safety output threshold, confirm whether the vehicle control parameters are within the safety output threshold limit range. If they are within the safety output threshold limit range, confirm that the vehicle can operate according to the output of the vehicle control module. If they exceed the safety output threshold limit range, confirm that the abnormality is fed back to the fault monitoring module, and the output monitoring module feeds back the abnormality to the domain safety island, promptly reminding the driver to take over the vehicle driving work.

[0096] In an embodiment of the present application, when the vehicle control module outputs vehicle control parameters according to operating constraints, the output of the vehicle control module is monitored by the output monitoring module to ensure that the output of the vehicle control module meets the safety output thresholds under different assisted driving functions of the vehicle, thereby ensuring safe driving.

[0097] Figure 7 A schematic diagram of a collision risk control method for an intelligent vehicle operating system provided in an embodiment of the present application Figure 4 . Figure 8 A schematic diagram of the logical structure of a path selection module provided in an embodiment of the present application. Figure 7 As shown, the method includes:

[0098] S701. If the current driving path of the vehicle is the main driving path, confirm whether there is a collision risk on the main driving path according to a radar target, wherein the radar target is a target obtained through radar perception.

[0099] like Figure 8 As shown, the main driving path can be planned through the main path planning module and the radar perception module; the redundant driving path can be planned according to the redundant path planning module and the fusion module; the main driving path and the redundant driving path can be selected through the path selection module, and the selected path can be output to the vehicle control module; the main driving path is the route or trajectory mainly used by the vehicle during driving, which can be obtained through the analysis of the best route selection, path planning, traffic flow, etc.

[0100] The radar sensing module selected in this embodiment uses a laser radar to sense targets and obtains radar targets under radar perception; the vehicle has a current driving path, and the current driving path is obtained based on the last path planning. If the current driving path is the main driving path, then the radar target can be used to confirm whether there is a collision risk in the main driving path.

[0101] S702: If it is confirmed that there is no collision risk on the main driving path according to the radar target, then it is confirmed whether there is a collision risk on the main driving path according to the fused target, wherein the fused target is a target sensed by a non-radar object sensing device.

[0102] The main driving path is actually the path obtained by the radar target perceived by the radar sensing module. After confirming that there is no collision risk on the main driving path through the radar target, it is also possible to confirm whether there is a collision risk on the main driving path through the fusion target, and further confirm the safety of the main driving path; wherein, the fusion target is the target perceived by the fusion module. When the radar sensing module uses radar as the object sensing device, the fusion module uses a non-radar object sensing device. When the radar sensing module uses a lidar, the fusion module uses an object sensing device other than the lidar.

[0103] S703: If it is confirmed according to the fusion target object that there is no collision risk on the main driving path, continue to control the vehicle to travel according to the main driving path.

[0104] If the main driving path is confirmed to have no collision risk based on both the radar target and the fusion target, the vehicle can continue to drive along the main driving path. If there is a risk based on either the radar target or the fusion target, the vehicle can try to switch to the redundant driving path.

[0105] The way to switch to the redundant driving path is as follows:

[0106] For example, if it is confirmed according to the radar target that there is a collision risk on the main driving path, the method further includes:

[0107] Determining whether there is a collision risk in the redundant driving path according to the fusion target object;

[0108] If it is confirmed according to the fusion target that the redundant driving path does not have a collision risk, confirming according to the radar target whether the redundant driving path has a collision risk;

[0109] If it is determined according to the radar target that there is no collision risk in the redundant driving path, the current driving path of the vehicle is switched to the redundant driving path.

[0110] The redundant driving path is a path obtained through the fusion target perceived by the fusion module. After confirming that there is no collision risk on the redundant driving path through the fusion target, the radar target is used to confirm whether there is a collision risk on the redundant driving path. If both the fusion target and the radar target confirm that there is no collision risk on the main driving path, the current driving path of the vehicle can be switched to the redundant driving path if there is a risk on the main driving path. The main driving path is the preferred path.

[0111] In an embodiment of the present application, the main path planning module and the radar perception module plan a main driving path, the redundant path planning module and the fusion module plan a redundant driving path, and the collision risk of the main driving path is confirmed through the fusion target of the fusion module, and the collision risk of the redundant driving path is confirmed through the radar perception module, and the path risk is cross-verified to ensure safe driving.

[0112] The vehicle control module can calculate the vehicle control parameters based on the operation restriction conditions and the path selected by the path selection module, and feed the vehicle control parameters back to the output monitoring module.

[0113] Some devices in the vehicle need to be monitored for faults. These devices under fault monitoring are called devices under test. The monitoring process of the fault monitoring module includes:

[0114] If any one of the multiple devices under test has an abnormality, the vehicle is controlled to stop safely, wherein the device under test includes an output monitoring module, a vehicle actuator and a vehicle sensor, the output monitoring module is used to monitor the output information of the vehicle control module, the output information includes the vehicle control parameters, and the vehicle actuator is a control device that controls the operation of the vehicle.

[0115] The fault monitoring module monitors the working status of multiple devices under test in the vehicle, confirms whether the device under test has a fault, obtains the fault information of the device under test for analysis, and screens the fault type that affects the effective execution of the control command. If there is a fault type that affects the effective execution of the control command, the vehicle control module is notified to switch to the branch of the vehicle control module and enter a safe parking state;

[0116] For example, the fault monitoring module confirms the vehicle actuator fault information based on the vehicle actuator, parses the vehicle actuator fault information, queries the safety status corresponding to the fault, reports the abnormality to the domain control safety island, and requests the vehicle control module to switch to the branch;

[0117] The fault monitoring module confirms the fault information of the vehicle sensors and algorithm nodes according to the algorithms of each module in the vehicle sensors, main path planning module, redundant path planning module, radar / lidar perception module and monitoring equipment, and analyzes it, queries the safety status corresponding to the fault, reports the exception to the domain control safety island, and requests the vehicle control module to switch to the branch; the fault monitoring module can also receive exception reports from the output monitoring module.

[0118] In the embodiment of the present application, by monitoring the modules / devices that need to be monitored for faults, timely response to fault information is ensured to ensure the safety of autonomous driving.

[0119] Fig. 9 A collision risk control device diagram of an intelligent automobile operating system provided by an embodiment of the present invention is shown in FIG. Fig. 9 As shown, the device includes: an acquisition module 901, a first processing module 902 and a second processing module 903;

[0120] The acquisition module 901 is used to acquire the road segmentation area and the target objects under each of the road segmentation areas, and confirm whether there is a ghost-peek risk in the segmentation blind area in the road segmentation area according to different target object types, wherein the target object is an entity with a collision risk.

[0121] The acquisition module 901 is further used to acquire the perception space of the vehicle, divide the perception space into a plurality of road segmentation areas, and acquire the target object under each of the road segmentation areas, wherein the road segmentation area includes a drivable area and a non-drivable area, and the segmentation blind area includes a drivable blind area of ​​the drivable area and a non-drivable blind area of ​​the non-drivable area;

[0122] According to different target types in each of the road segmentation areas, confirm the geometric size and kinematic constraints of the target;

[0123] According to the geometric size and kinematic constraints of the target object, it is confirmed whether there is a risk of ghosting in the segmentation blind area in the road segmentation area.

[0124] The first processing module 902 is used to obtain the operating restriction conditions for the vehicle to avoid collision according to different types of the target objects if there is the risk of ghosting in the segmented blind spot, and output the operating restriction conditions to the vehicle control module, wherein the vehicle control module includes a program for calculating and outputting vehicle control parameters.

[0125] The first processing module 902 is further used to obtain, according to the target type of the target object, the reaction conditions of the vehicle when different target types collide with the vehicle, wherein the target types include pedestrians, two-wheeled vehicles and cars, and the reaction conditions include driving distance and driving direction;

[0126] According to the reaction condition of the vehicle, the operation restriction condition of the vehicle is obtained, wherein the operation restriction condition includes the maximum speed of the vehicle, the steering angle range and the speed limit values ​​at different steering angles.

[0127] The second processing module 903 is used to confirm whether the vehicle control parameter output by the vehicle control module meets the safety output threshold, and output a confirmation result of whether the vehicle control parameter meets the safety output threshold.

[0128] The second processing module 903 is further used to obtain output information of the vehicle control module and confirm the activated auxiliary driving function, wherein the output information includes the vehicle control parameters;

[0129] Obtain the safety output threshold corresponding to the vehicle control parameter under the activated assisted driving function, and confirm whether the vehicle control parameter meets the safety output threshold.

[0130] The present application also provides a collision risk control device for an intelligent automobile operating system, comprising: at least one processor and a memory;

[0131] The memory stores computer-executable instructions;

[0132] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the collision risk control method of the intelligent automobile operating system.

[0133] Fig.10 The hardware schematic diagram of the collision risk control device of the intelligent automobile operating system provided by the embodiment of the present invention. Fig.10As shown, the collision risk control device 100 of the intelligent automobile operating system provided in this embodiment includes: at least one processor 1001 and a memory 1002. The device 100 also includes a communication component 1003. The processor 1001, the memory 1002 and the communication component 1003 are connected via a bus 1004.

[0134] In the specific implementation process, at least one processor 1001 executes the computer execution instructions stored in the memory 1002, so that at least one processor 1001 executes the collision risk control method of the intelligent automobile operating system as described above.

[0135] The specific implementation process of the processor 1001 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0136] In the above Fig.10 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0137] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0138] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0139] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the collision risk control method of the intelligent automobile operating system as described above is implemented.

[0140] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0141] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0142] The division of the units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0145] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variation, use or adaptation of the present invention, which follows the general principles of the present invention and includes common knowledge or conventional techniques in the art not disclosed by the present invention, is not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof.

Claims

1. A collision risk control method for an intelligent vehicle operating system, characterized in that: include: Acquire a road segmentation area and a target object under each of the road segmentation areas, and confirm whether there is a risk of ghosting in a segmentation blind area in the road segmentation area according to different target object types, wherein the target object is an entity with a collision risk; If the segmented blind spot has the risk of ghosting, then obtaining the operation restriction conditions for the vehicle to avoid collision according to the different types of the target objects, and outputting the operation restriction conditions to the vehicle control module, wherein the vehicle control module includes a program for calculating and outputting vehicle control parameters; Confirm whether the vehicle control parameter output by the vehicle control module meets the safety output threshold, and output a confirmation result of whether the vehicle control parameter meets the safety output threshold.

2. The method according to claim 1, characterized in that: The acquiring of the road segmentation area and the target objects under each of the road segmentation areas, and confirming whether there is a ghosting risk in the segmentation blind area in the road segmentation area according to different target object types, includes: Acquire the perception space of the vehicle, divide the perception space into a plurality of the road segmentation areas, and acquire the target object under each of the road segmentation areas, wherein the road segmentation areas include a drivable area and a non-drivable area, and the segmentation blind area includes a drivable blind area of ​​the drivable area and a non-drivable blind area of ​​the non-drivable area; According to different target types in each of the road segmentation areas, confirm the geometric size and kinematic constraints of the target; According to the geometric size and kinematic constraints of the target object, it is confirmed whether there is a risk of ghosting in the segmentation blind area in the road segmentation area.

3. The method according to claim 2, characterized in that The obtaining of the vehicle's operating restriction conditions for avoiding collision according to different target object types includes: According to the target object type of the target object, obtaining the reaction conditions of the vehicle when different target object types collide with the vehicle, wherein the target object types include pedestrians, two-wheeled vehicles and cars, and the reaction conditions include driving distance and driving direction; According to the reaction condition of the vehicle, the operation restriction condition of the vehicle is obtained, wherein the operation restriction condition includes the maximum speed of the vehicle, the steering angle range and the speed limit values ​​at different steering angles.

4. The method according to claim 1, characterized in that The confirming whether the vehicle control parameter output by the vehicle control module meets the safety output threshold comprises: Obtaining output information of the vehicle control module and confirming the activated assisted driving function, wherein the output information includes the vehicle control parameters; Obtain the safety output threshold corresponding to the vehicle control parameter under the activated assisted driving function, and confirm whether the vehicle control parameter meets the safety output threshold.

5. The method according to claim 1, characterized in that The method further comprises: If the current driving path of the vehicle is the main driving path, confirming whether there is a collision risk on the main driving path according to a radar target, wherein the radar target is a target obtained by radar perception; If it is confirmed that there is no collision risk on the main driving path according to the radar target, then confirming whether there is a collision risk on the main driving path according to the fused target, wherein the fused target is a target object sensed by a non-radar object sensing device; If it is confirmed according to the fusion target object that there is no collision risk on the main driving path, the vehicle continues to be controlled to travel according to the main driving path.

6. The method according to claim 5, characterized in that If it is confirmed according to the radar target that there is a collision risk on the main driving path, the method further includes: Determining whether there is a collision risk in the redundant driving path according to the fusion target object; If it is confirmed according to the fusion target that the redundant driving path does not have a collision risk, confirming according to the radar target whether the redundant driving path has a collision risk; If it is determined according to the radar target that there is no collision risk in the redundant driving path, the current driving path of the vehicle is switched to the redundant driving path.

7. The method according to claim 1, characterized in that The method further comprises: If any one of the multiple devices under test has an abnormality, the vehicle is controlled to stop safely, wherein the device under test includes an output monitoring module, a vehicle actuator and a vehicle sensor, the output monitoring module is used to monitor the output information of the vehicle control module, the output information includes the vehicle control parameters, and the vehicle actuator is a control device that controls the operation of the vehicle.

8. A collision risk control device for an intelligent automobile operating system, characterized in that: include: An acquisition module, used to acquire a road segmentation area and a target object under each of the road segmentation areas, and to confirm whether there is a ghost head-on risk in a segmentation blind area in the road segmentation area according to different target object types, wherein the target object is an entity with a collision risk; A first processing module is used for obtaining operation restriction conditions for avoiding collision of the vehicle according to different types of the target objects if the segmented blind area has the risk of ghosting, and outputting the operation restriction conditions to a vehicle control module, wherein the vehicle control module includes a program for calculating and outputting vehicle control parameters; The second processing module is used to confirm whether the vehicle control parameter output by the vehicle control module meets the safety output threshold, and output a confirmation result of whether the vehicle control parameter meets the safety output threshold.

9. A collision risk control device for an intelligent automobile operating system, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the collision risk control method of the intelligent automobile operating system as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the collision risk control method of the intelligent automobile operating system as described in any one of claims 1 to 7 are implemented.

Images