Driving authority allocation method, apparatus and device under human-machine co-driving, and vehicle, medium and program product

Abstract

Provided in the present disclosure are a driving authority allocation method, apparatus and device under human-machine co-driving, and a vehicle, a medium and a program product. The method comprises: on the basis of a risk source type in a traveling environment, ego-vehicle operating condition information, risk source operating condition information, and a distance between an ego-vehicle and a risk source, calculating a total field intensity corresponding to traveling risk partitions; on the basis of line-of-sight information of a driver, determining risk region position information sensed by the driver; calculating a risk sensing consistency index on the basis of the total field intensity corresponding to the traveling risk partitions and the risk region position information; and determining a driving authority handover weight on the basis of the risk sensing consistency index and a preset risk sensing consistency index threshold value.

Description

Method, device, equipment, vehicle, medium and program product for allocating driving rights under human-machine co-driving

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202311623315.7 filed on November 30, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the field of intelligent driving technology, and in particular to a method, device, equipment, vehicle, medium, and program product for allocating driving rights in a human-machine co-driving environment. Background Art

[0004] With the increasing power of smart car hardware and the maturity of driving theory systems, the level of vehicle automation is increasing. However, before the purely technical challenge of fully autonomous driving is widely realized, human-machine co-driving will exist for some time to come. Human-machine co-driving refers to the situation where the task of driving the vehicle is shared by the natural driver and the intelligent driving system in scenarios where fully autonomous driving cannot be guaranteed. The human-machine co-driving interaction system is considered a key factor in the safe operation of intelligent driving vehicles at this stage. It provides an interactive method for exchanging driving information and operations between humans and machines, and its design makes autonomous driving behavior clearer and more intuitive.

[0005] However, high-level intelligent driving systems cannot yet fully cope with complex traffic environments, and drivers are more capable of handling complex environments than intelligent driving systems. Therefore, integrating manual and intelligent driving to achieve a reasonable allocation of driving rights is key to leveraging the advantages of human-machine co-driving and ensuring driving safety, and it is also a pressing issue that needs to be addressed.

[0006] Summary of the Invention

[0007] The embodiments of the present disclosure provide a method, device, equipment, vehicle, medium and program product for allocating driving rights in a human-machine co-pilot environment, which can improve the technical problem in the prior art of being unable to achieve reasonable allocation of driving rights in a human-machine co-pilot environment.

[0008] In a first aspect of the present disclosure, a method for allocating driving rights in human-machine co-driving is provided, including: calculating the total field strength corresponding to each driving risk zone according to the risk source type, the vehicle operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source in the driving environment; determining the risk area location information perceived by the driver according to the driver's line of sight information; calculating the risk perception consistency index based on the total field strength and risk area location information corresponding to each driving risk zone; and determining the driving right switching weight based on the risk perception consistency index and a preset risk perception consistency index threshold, so as to perform driving right switching allocation according to the driving right switching weight.

[0009] In a second aspect of the present disclosure, a device for allocating driving rights in human-machine co-driving is provided, including: a first calculation module, which is used to calculate the total field strength corresponding to each driving risk zone according to the risk source type, the vehicle operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source in the driving environment; a determination module, which is used to determine the risk area location information perceived by the driver according to the driver's line of sight information; a second calculation module, which is used to calculate the risk perception consistency index based on the total field strength and risk area location information corresponding to each driving risk zone; and an allocation module, which is used to determine the driving right switching weight based on the risk perception consistency index and a preset risk perception consistency index threshold, so as to perform driving right switching allocation through the driving right switching weight.

[0010] In a third aspect of the present disclosure, a device for allocating driving rights in a human-machine co-pilot environment is provided, comprising a processor, a memory, and a program for allocating driving rights in a human-machine co-pilot environment stored in the memory and executable by the processor, wherein when the program for allocating driving rights in a human-machine co-pilot environment is executed by the processor, the steps of the method for allocating driving rights in a human-machine co-pilot environment provided in the first aspect are implemented.

[0011] In a fourth aspect of the present disclosure, a vehicle is provided, comprising the driving right allocation device under human-machine co-driving provided in the third aspect above.

[0012] In a fifth aspect of the present disclosure, a computer-readable storage medium is provided, comprising a program for allocating driving rights in a human-machine co-pilot environment stored thereon, wherein when the program for allocating driving rights in a human-machine co-pilot environment is executed by a processor, the steps of the method for allocating driving rights in a human-machine co-pilot environment provided in the first aspect are implemented.

[0013] In a sixth aspect of the present disclosure, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the steps of the method for allocating driving rights in human-machine co-driving provided in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] FIG1 is a flow chart of a method for allocating driving rights in a human-machine co-piloting system according to some embodiments of the present disclosure;

[0015] FIG2 is a schematic diagram of driving risk zoning within the cockpit visual range according to some embodiments of the present disclosure;

[0016] FIG3 is a schematic diagram of risk area matching according to some embodiments of the present disclosure;

[0017] FIG4 is a schematic diagram of risk area matching according to other embodiments of the present disclosure;

[0018] FIG5 is a schematic diagram of functional modules of a device for allocating driving rights in a human-machine co-driving situation according to some embodiments of the present disclosure; and

[0019] FIG6 is a schematic diagram of the hardware structure of a driving right allocation device in a human-machine co-driving situation according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0021] To make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be described in further detail below with reference to the accompanying drawings.

[0022] In a first aspect, some embodiments of the present disclosure provide a method for allocating driving rights in a human-machine co-pilot scenario. Referring to FIG. 1 , FIG. 1 is a flow chart illustrating an embodiment of a method for allocating driving rights in a human-machine co-pilot scenario according to some embodiments of the present disclosure. As shown in FIG. 1 , the method includes steps S10 through S40.

[0023] In step S10 , the total field strength corresponding to each driving risk zone is calculated according to the risk source type, the vehicle operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source in the driving environment.

[0024] In some embodiments, the driving risk zones around the vehicle can be partitioned according to the visible range of the vehicle cockpit to obtain multiple driving risk zones. Figure 2 is a schematic diagram of the driving risk zone division according to the visible range of the cockpit of some embodiments of the present disclosure. Referring to Figure 2, some embodiments of the present disclosure will partition the driving risk zones around the vehicle according to the visible range of the vehicle cockpit to obtain 8 driving risk zones. Among them, zones 2, 3, 4, 5, 6 and 7 are the driving risk zones in the direction of the front windshield respectively; zones 1 and 8 are the driving risk zones on the left and right sides and in the direction of the rearview mirror (rear). It should be noted that the above zones are only exemplary presentations, and other zone settings can be made according to actual needs to obtain driving risk zones of different numbers and sizes, which are not limited here.

[0025] For each driving risk zone, at each sampling moment within a preset sampling period, the total field strength corresponding to each driving risk zone will be calculated based on the risk source type in the driving environment of the vehicle, the vehicle's operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source. The total field strength corresponding to the driving risk zone is used to characterize the degree of risk posed by the risk source in the driving risk zone to the vehicle. The distribution of driving risk areas perceived by the intelligent driving system can be characterized by the magnitude of the total field strength of different driving risk zones. Among them, the operating condition information may include speed and quality; the risk source may include a dynamic risk source and a static risk source. The risk source type corresponding to different risk sources can be set according to actual needs and is not limited here. In some embodiments, dynamic risk sources may include dynamic objects around the vehicle, such as a moving vehicle, and static risk sources may include static objects around the vehicle, such as a stationary vehicle.

[0026] In step S20 : ​​the location information of the risk area perceived by the driver is determined based on the driver's line of sight information.

[0027] It is understandable that, because a driver's attention changes in real time while driving, the risk area perceived by the driver may fall within the aforementioned driving risk zones or may lie outside of them. Therefore, in some embodiments, the driver's line of sight may be captured at each sampling moment within a preset sampling period to detect changes in the driver's attention to the risk zones surrounding the vehicle. This allows the driver's attention to be located in the driving risk zone, thereby obtaining risk zone location information corresponding to the driver's perceived risk zone.

[0028] In some embodiments, eye tracking technology can be used to capture the driver's line of sight information to locate the risk area perceived by the driver. The method and principle of how eye tracking technology determines the area of ​​attention by detecting the movement trajectory of the driver's eyes during driving, the reaction time and reaction frequency to the road environment, etc. can be found in related technologies and will not be repeated here.

[0029] In step S30 , a risk perception consistency index is calculated based on the total field strength and risk area location information corresponding to each driving risk partition.

[0030] It can be understood that the greater the total field strength, the greater the likelihood that the intelligent driving system believes that the driving risk zone is risky. In other words, the driving risk zone with a greater total field strength is more likely to become a risk area perceived by the intelligent driving system. Therefore, the degree of risk in each driving risk zone can be learned through the total field strength corresponding to each driving risk zone, and then the risk zone perceived by the intelligent driving system can be determined; the risk zone perceived by the intelligent driving system is then matched with the risk zone perceived by the driver, which can be determined through the risk zone location information. That is, it is determined whether the risk areas perceived by the intelligent driving system and the driver are consistent, and the risk perception consistency index can be determined. The risk perception consistency index is used to characterize the degree of match between the risk area perceived by the intelligent driving system and the risk area perceived by the driver. The higher the risk perception consistency index, the higher the degree of match between the risk area perceived by the intelligent driving system and the driver.

[0031] In step S40 : a driving right switching weight is determined based on the risk perception consistency index and a preset risk perception consistency index threshold, so as to allocate the driving right switching according to the driving right switching weight.

[0032] It is understandable that the risk perception consistency index threshold refers to the index value corresponding to when the risk area perceived by the intelligent driving system and the driver are completely consistent. Its specific value can be determined according to actual needs or after testing, and is not limited here. In some embodiments, the risk assessment consistency will be calculated using the risk perception consistency index and the risk perception consistency index threshold. In some embodiments, a relative safety index can be designed based on the risk perception consistency index to describe the level of risk assessment consistency. For example, it can be based on the following formula: RM = M / M* (1)

[0033] The relative safety index used to describe the consistency level of risk assessment is obtained. In formula (1), RM represents the relative driving risk consistency index, M represents the risk perception consistency index, and M* represents the risk perception consistency index threshold.

[0034] In some implementations, the driving right switching weight may be assigned based on formula (2) and the relative driving risk consistency index:

[0035] In formula (2), W represents the driving right switching weight, which represents the speed of human-machine driving right switching. It should be noted that the specific value setting of the above driving right switching weight is only an exemplary presentation and can be adjusted according to actual needs. As long as the relative driving risk consistency index is lower, the corresponding driving right switching weight is larger, and the relative driving risk consistency index is higher, the corresponding driving right switching weight is smaller. It should be understood that the lower the relative driving risk consistency index, the faster the driving right switching, and when the relative driving risk consistency index is higher, the driving right is handed over to the intelligent driving system and the driving right is not switched.

[0036] The driving right switching weight can be used to characterize whether it is necessary to switch the human-machine driving right, and when it is necessary to switch the human-machine driving right, the length of the switching transition time adopted. In some embodiments, when the relative driving risk consistency index is less than 0.3, it means that the relative driving risk consistency index is low, and at this time, it is necessary to quickly switch the driving right, that is, the switching transition time can be relatively short; when the relative driving risk consistency index is in the range of [0.3, 0.6), it means that the relative driving risk consistency index is at an intermediate level, and the driving right needs to be switched, but the switching speed does not need to be very fast, that is, the switching transition time can be relatively long; and when the relative driving risk consistency index is greater than or equal to 0.6, it means that the relative driving risk consistency index is high, and there is no need to switch the driving right at this time. For example, if the vehicle is currently controlled by the intelligent driving system, it can still be controlled by the intelligent driving system. It should be noted that the above relative driving risk consistency index range is only a presentation of an embodiment, and can also be adjusted according to actual needs.

[0037] Some embodiments of the present disclosure provide a method for allocating driving rights under human-machine co-driving. By calculating the driving risk field intensity, the risk area perceived by the intelligent driving system can be obtained, and the risk area perceived by the driver can be obtained based on the risk area location information determined by the driver's line of sight information; then, based on the degree of matching between the two, the consistency of human-machine risk perception can be determined, and then based on the consistency of human-machine risk perception and the risk perception consistency index threshold, the driving right switching weight can be objectively calculated, and the driving right switching can be allocated based on the driving right switching weight, thereby realizing a reasonable allocation of driving rights under human-machine co-driving. It can be seen that this embodiment uses the human-machine risk assessment results to determine the ownership of the driving rights of the vehicle, so as to make up for the experience disadvantage of the high-order intelligent driving system in a complex environment, and thus give full play to the advantages of human-machine co-driving.

[0038] In some embodiments, the process of calculating the total field strength corresponding to each driving risk zone based on the risk source type, the vehicle operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source in the driving environment may include: calculating the potential field strength corresponding to each driving risk zone based on the static risk source type, the vehicle operating condition information, and the distance between the vehicle and the static risk source in the driving environment, wherein the vehicle operating condition information includes the vehicle mass and the vehicle speed; calculating the kinetic field strength corresponding to each driving risk zone based on the dynamic risk source type, the dynamic risk source operating condition information, the vehicle operating condition information, and the distance between the vehicle and the dynamic risk source in the driving environment, wherein the dynamic risk source operating condition information includes the dynamic risk source mass and the dynamic risk source speed; and calculating the total field strength corresponding to each driving risk zone based on the potential field strength and the kinetic field strength. It can be understood that the potential energy field strength corresponding to the driving risk zone refers to the field strength of the potential energy field generated by the static risk source in the driving risk zone on the vehicle itself, and the kinetic energy field strength corresponding to the driving risk zone refers to the field strength of the kinetic energy field generated by the dynamic risk source in the driving risk zone on the vehicle itself.

[0039] In some implementations, the potential energy field strength corresponding to each driving risk zone may be calculated using the following formula:

[0040] In formula (3), E R represents the potential energy field strength, k R represents the potential energy field coefficient, m1 represents the mass of the vehicle, v1 represents the speed of the vehicle, D1 represents the distance between the vehicle and the static risk source, T R Indicates the type coefficient corresponding to the static risk source type.

[0041] In some embodiments, the kinetic energy field strength corresponding to each driving risk zone may be calculated using the following formula:

[0042] In formula (4), E V represents the kinetic energy field strength, k V represents the kinetic energy field coefficient, m1 represents the mass of the vehicle, v1 represents the speed of the vehicle, D2 represents the distance between the vehicle and the dynamic risk source, m2 represents the mass of the dynamic risk source, v2 represents the speed of the dynamic risk source, T V Indicates the type coefficient corresponding to the dynamic risk source type.

[0043] In some embodiments, the driving risk field is divided into potential energy field and kinetic energy field, and the risk source is divided into static risk source and dynamic risk source. Among them, for the potential energy field, the static risk source types include but are not limited to roadblocks, stationary vehicles, stationary pedestrians, traffic lights and other stationary objects. Different static risk source types have different type coefficients T R , T RThe specific value of can be determined according to actual needs and is not limited here. For example, the T corresponding to the roadblock is R Set to 0.3, the T corresponding to the stationary vehicle R Set to 0.5, the T corresponding to the traffic light R Set to 0.8, the T corresponding to the stationary pedestrian R Set to 1.0.

[0044] For the kinetic energy field, the types of dynamic risk sources include but are not limited to moving objects such as moving vehicles and moving pedestrians. Different types of dynamic risk sources also have different type coefficients T. V , T V The specific value setting of can be determined according to actual needs and is not limited here. For example, the T corresponding to a moving vehicle is V Set to 0.5 for the moving pedestrian V It should be noted that the moving vehicles can also be subdivided and the corresponding T V Values, such as motor vehicles and non-motor vehicles.

[0045] In addition, it should be noted that the potential field coefficient k R and the kinetic energy field coefficient k V The specific value setting can be determined according to actual needs, as long as the potential field coefficient k R Greater than the kinetic energy field coefficient k V That's it.

[0046] When calculating the field strength in the potential energy field, the field strength of the vehicle in the potential energy field generated by different risk sources can be determined based on the positions of stationary objects such as roadblocks, stationary vehicles, and traffic lights in the driving environment and the vehicle's speed:

[0047] In formula (5), E R represents the potential energy field strength, m1 represents the mass of the vehicle, v1 represents the speed of the vehicle, and D1 represents the distance between the vehicle and the static risk source.

[0048] When calculating the field strength in the kinetic energy field, the field strength of the vehicle in the kinetic energy field generated by different risk sources can be determined based on the position and speed of moving objects such as moving vehicles and pedestrians in the driving environment that may collide with the vehicle:

[0049] In formula (6), E VRepresents the kinetic energy field strength, m1 represents the mass of the vehicle, v1 represents the speed of the vehicle, D2 represents the distance between the vehicle and the dynamic risk source, m2 represents the mass of the dynamic risk source, and v2 represents the speed of the dynamic risk source. It should be noted that for the mass of a moving vehicle, when the moving vehicle is identified as a motor vehicle, the mass of the motor vehicle can be obtained through data interaction through the Internet of Things. Of course, a mass mean value can also be set for the motor vehicle based on empirical values; when the moving vehicle is identified as a non-motor vehicle, a mass mean value can be set for the non-motor vehicle based on empirical values. For moving pedestrians, three-dimensional scanning can be performed through image recognition technology to calculate the corresponding mass. Of course, a mass mean value can also be set for the non-motor vehicle based on empirical values. It should be understood that the specific method for determining the mass of a moving object can be selected according to actual needs and is not limited here.

[0050] For each driving risk zone, the distribution of driving risk areas perceived by the intelligent driving system can be derived based on the location of the risk source and the potential energy field and kinetic energy field it generates. That is, the sum of the driving risk field strength of each driving risk zone can be determined based on the location of the risk source: E i =E R,i +E V,i (7)

[0051] In formula (7): E i represents the total field strength in the driving risk zone i, i∈[1,2,3,4,5,6,7,8], E R,i represents the potential energy field strength within the driving risk zone i, E V,i represents the kinetic energy field strength within the driving risk zone i. After calculating the total field strength of each driving risk zone, the driving risk distribution of each driving risk zone can be obtained.

[0052] In some embodiments, the process of calculating the risk perception consistency index based on the total field strength and risk area location information corresponding to each driving risk zone may include: determining the driving risk zone with a total field strength greater than a field strength threshold as a target risk zone, and determining the target risk zone with the largest total field strength as a system-perceived risk zone; and when it is determined based on the risk area location information that a driver perception zone exists in the driving risk zone, matching the risk zones based on the driver perception zone, the target risk zone, and the system-perceived risk zone to obtain a target matching degree, and using the target matching degree as the risk perception consistency index. The driver perception zone refers to the area where the driver's attention is focused.

[0053] In some embodiments, the field strength threshold may represent the minimum field strength corresponding to a risk in a particular area. Specifically, as long as the field strength value of a driving risk zone exceeds the field strength threshold, the driving risk zone is considered risky and becomes a target risk zone. If the field strength value of a driving risk zone is less than or equal to the field strength threshold, the driving risk zone is considered riskless or has very low risk, and thus will not become a target risk zone. It should be noted that the specific value of the field strength threshold can be determined based on actual needs and is not limited here. For example, the field strength threshold can be set to 0.

[0054] For the target risk partitions, in some embodiments, the partition with the highest risk identified by the intelligent driving system can be determined from the target risk partitions based on the size relationship of the total field strength between each target risk partition, and this partition can be used as the system-perceived risk area, that is, the intelligent driving system assesses that the risk in the system-perceived risk area is the highest.

[0055] In some embodiments, the human-machine risk perception orientation consistency calculation will also be performed, that is, whether the area where the driver's attention is located is determined in the driving risk zone based on the risk area location information; if so, it means that there is a driver perception area. In other words, the orientation of human-machine risk perception is consistent, and the driver perception area, target risk zone and system perception risk area are further matched for risk perception consistency to obtain the target matching degree, and the target matching degree is used as the risk perception consistency index.

[0056] In some embodiments, the above-mentioned process of matching risk areas based on the driver perception area, the target risk partition and the system perception risk area to obtain the target matching degree may include: determining whether the driver perception area and the system perception risk area are the same; if they are the same, using the first matching value as the target matching degree; if they are not the same, determining the second matching value corresponding to each target risk partition according to the driver's line of sight information, and using the largest second matching value as the target matching degree, wherein the first matching value is greater than the second matching value.

[0057] In some embodiments, the matching of human-machine perception risk areas can be performed according to preset matching rules. For example, first determine whether the driver's perception area is the same as the system's perception risk area. If they are the same, assign a first matching value f1 to the target matching degree. If they are different, further matching of the driver's perception area and each target risk partition is performed based on factors such as field strength, human eye attention range, pupil position, line of sight angle, and driving habits (i.e., when a risk in the field of view attracts the driver's attention, the driver will use peripheral vision to perceive the nearby area). The same or different second matching values ​​f2 are assigned to each target risk partition, and the largest second matching value f2 is used as the target matching degree. It should be noted that the specific settings of the first matching value f1 and the second matching value f2 can be determined according to actual needs and are not limited here. For example, the first matching value f1 can be 1, and the second matching value f2 can be 0.8, 0.6, or 0.5, etc.

[0058] FIG3 is a schematic diagram of risk area matching according to some embodiments of the present disclosure, and FIG4 is a schematic diagram of risk area matching according to other embodiments of the present disclosure. Referring to FIG3 , assuming that the driver's perception area (the circled area in FIG3 ) and the system's perceived risk area (the diamond-shaped area in FIG3 ) are both driving risk area 1, the first matching value f1 = 1 is used as the target matching value, i.e., the risk perception consistency index c = 1. Referring to FIG4 , assuming that the driver's perception area (the circled area in FIG4 ) is driving risk area 8, the system's perceived risk area (the diamond-shaped area in FIG4 ) is driving risk area 7, and the target risk areas are driving risk areas 4, 6, 7, and 8. The total field strength values ​​of driving risk areas 4, 6, 7, and 8 are X1 to X4, respectively, and the order from largest to smallest is X3 > X1 > X2 > X4. In this case, since the driver's perception area and the system's perceived risk area are different, matching is performed based on factors such as field strength, human eye attention range, pupil position, line of sight angle, and driving habits.

[0059] For example, if the human eye's attention range is on driving risk zones 4, 7, and 8, and driving risk zones 4, 7, and 8 are within the driver's pupil gaze position and line of sight angle, 0.8 is used as the second matching value f2 of driving risk zone 7, 0.6 is used as the second matching value f2 of driving risk zone 4, 0.6 is used as the second matching value f2 of driving risk zone 8, and 0.5 is used as the second matching value f2 of driving risk zone 6. Since 0.8 is the largest, f2=0.8 is used as the target matching value at this time, that is, the risk perception consistency index c=0.8.

[0060] It should be understood that at the initial moment of vehicle startup, the driving right of the vehicle belongs to the intelligent driving system. However, since the driver has a reaction time to the risk perception in the driving environment and the driver may be tired and distracted, this embodiment can use the risk perception consistency assessment results at the current moment (i.e., the current sampling moment) and in the past period of time (i.e., the preset sampling period) as a basis for allocating driving rights.

[0061] Therefore, in some embodiments, the risk perception consistency index M may be calculated based on the average value of the risk perception consistency index within a preset sampling period:

[0062] In formula (8), c j represents the risk perception consistency index corresponding to the j-th sampling moment, and M represents the average value of the risk perception consistency index within n sampling periods.

[0063] In some embodiments, after the step of determining the risk area location information perceived by the driver based on the driver's line of sight information, it also includes: when it is determined based on the risk area location information that there is no driver perception area in the driving risk zone, controlling the driving right to be switched to the driver and issuing a danger warning.

[0064] In some embodiments, if it is determined based on the risk area location information that the area where the driver's attention is located is not in the driving risk zone, then it means that the driver's attention is not in the driving risk area, that is, there is no driver perception area. In other words, the directions of human-machine risk perception are inconsistent; at this time, the driving right is returned to the driver, and a danger warning is issued to remind the driver to increase his attention and take over the driving right.

[0065] In some embodiments, when calculating the consistency of human-machine risk perception orientation, the consistency of human-machine risk perception orientation can be determined based on the number of times a driving risk area is marked as a driver perception area within a preset sampling period. Specifically, if a driving risk area is observed by the driver once, it is marked as a driver perception area once. Therefore, if the driver observes it N times within the preset sampling period, the driving risk area will be marked as a driver perception area N times.

[0066] In some implementations, the human-machine risk perception orientation consistency calculation is performed based on the total number of times all driving risk zones are marked within a preset sampling period:

[0067] In formulas (9) to (11), A irepresents the number of times the i-th driving risk partition is marked as the driver’s perception area within n sampling moments, a j,i Indicates whether the i-th driving risk partition is marked as the driver perception area at the j-th sampling moment, a j,i =1 means it is marked as the driver perception area, a j,i = 0 indicates that the area is not marked as a driver perception area, and A represents the total number of times the eight driving risk zones were marked as driver perception areas within n sampling moments. When A is greater than 0, it indicates that at least one of the eight driving risk zones has been observed by the driver at least once. In other words, the area where the driver's attention is focused is within the driving risk zone. This indicates that a driver perception area exists, indicating that the direction of human and machine risk perception is consistent. In this case, the risk perception consistency index needs to be further calculated to determine the relative driving risk consistency index, and then the driving right switching weight is calculated based on this relative driving risk consistency index.

[0068] If A is equal to 0, it means that the area where the driver's attention is located is not in the driving risk zone, and it is determined that there is no driver perception area, that is, the direction of human-machine risk perception is inconsistent; at this time, the driving right is returned to the driver, and a danger warning is issued to remind the driver to increase his attention and take over the driving right.

[0069] In summary, the embodiments of the present disclosure explain the human-machine co-driving strategy in a high-level intelligent driving system from four aspects: driving risk area division, driving risk field strength calculation, human-machine driving risk consistency judgment, and driving rights allocation. The human-machine risk assessment results are used to determine the ownership of the vehicle's driving rights, effectively realizing the reasonable allocation of driving rights under human-machine co-driving, so as to make up for the experience disadvantage of high-level intelligent driving systems in complex environments, and thus give full play to the advantages of human-machine co-driving.

[0070] In the second aspect, some embodiments of the present disclosure further provide a device for allocating driving rights under human-machine co-driving. FIG5 is a functional module diagram of the device for allocating driving rights under human-machine co-driving according to some embodiments of the present disclosure. Referring to FIG5 , the device for allocating driving rights under human-machine co-driving may include: a first calculation module 501, which is used to calculate the total field strength corresponding to each driving risk zone according to the risk source type, the vehicle operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source in the driving environment; a determination module 502, which is used to determine the risk area location information perceived by the driver according to the driver's line of sight information; a second calculation module 503, which is used to calculate the risk perception consistency index based on the total field strength corresponding to each driving risk zone and the risk area location information; an allocation module 504, which is used to determine the driving right switching weight based on the risk perception consistency index and a preset risk perception consistency index threshold, so as to perform driving right switching allocation according to the driving right switching weight.

[0071] In some embodiments, the first calculation module 501 is specifically used to: calculate the potential energy field strength corresponding to each driving risk zone based on the static risk source type in the driving environment, the vehicle operating condition information, and the distance between the vehicle and the static risk source, wherein the vehicle operating condition information includes the vehicle mass and the vehicle speed; calculate the kinetic energy field strength corresponding to each driving risk zone based on the dynamic risk source type in the driving environment, the dynamic risk source operating condition information, the vehicle operating condition information, and the distance between the vehicle and the dynamic risk source, wherein the dynamic risk source operating condition information includes the dynamic risk source mass and the dynamic risk source speed; and calculate the total field strength corresponding to each driving risk zone based on the potential energy field strength and the kinetic energy field strength.

[0072] In some embodiments, the potential energy field strength is calculated using the following formula:

[0073] In formula (12), E R represents the potential energy field strength, k R represents the potential energy field coefficient, m1 represents the mass of the vehicle, v1 represents the speed of the vehicle, D1 represents the distance between the vehicle and the static risk source, T R Indicates the type coefficient corresponding to the static risk source type.

[0074] In some embodiments, the kinetic energy field strength is calculated using the following formula:

[0075] In formula (13), E V represents the kinetic energy field strength, k V represents the kinetic energy field coefficient, m1 represents the mass of the vehicle, v1 represents the speed of the vehicle, D2 represents the distance between the vehicle and the dynamic risk source, m2 represents the mass of the dynamic risk source, v2 represents the speed of the dynamic risk source, T V Indicates the type coefficient corresponding to the dynamic risk source type.

[0076] In some embodiments, the second calculation module 503 is specifically used to: take the driving risk partition with a total field strength greater than the field strength threshold as the target risk partition, and take the target risk partition with the largest total field strength as the system perception risk area; and when it is determined based on the risk area location information that there is a driver perception area in the driving risk partition, perform risk area matching based on the driver perception area, the target risk partition and the system perception risk area to obtain a target matching degree, and use the target matching degree as the risk perception consistency index.

[0077] In some embodiments, the second calculation module 503 is further specifically used to: determine whether the driver perception area is the same as the system perception risk area; if they are the same, use the first matching value as the target matching degree; and if they are not the same, determine the second matching value corresponding to each target risk partition based on the driver's line of sight information, and use the largest second matching value as the target matching degree, wherein the first matching value is greater than the second matching value.

[0078] In some embodiments, the allocation module 504 is further configured to: when it is determined based on the risk area location information that there is no driver perception area in the driving risk zone, control the driving right to be switched to the driver and issue a danger warning.

[0079] It should be noted that the functional implementation of each module in the above-mentioned driving rights allocation device under human-machine co-pilot corresponds to the various steps in the above-mentioned driving rights allocation method embodiment under human-machine co-pilot, and its functions and implementation processes will not be repeated here one by one.

[0080] In a third aspect, some embodiments of the present disclosure provide a device for allocating driving rights in a shared human-machine environment, comprising a processor, a memory, and a program for allocating driving rights in a shared human-machine environment stored in the memory and executable by the processor. When executed by the processor, the program implements the steps of any of the aforementioned methods for allocating driving rights in a shared human-machine environment. For example, the device for allocating driving rights in a shared human-machine environment may be an in-vehicle terminal, or alternatively, the device may be a personal computer (PC), laptop computer, server, or other device with data processing capabilities.

[0081] FIG6 is a schematic diagram of the hardware structure of a device for allocating driving rights in a human-machine co-pilot system according to some embodiments of the present disclosure. Referring to FIG6 , in some embodiments of the present disclosure, the device for allocating driving rights in a human-machine co-pilot system may include a processor 601 , a memory 602 , a communication interface 603 , and a communication bus 604 .

[0082] The communication bus 604 may be of any type and is used to interconnect the processor 601 , the memory 602 , and the communication interface 603 .

[0083] Communication interface 603 includes input / output (I / O) interfaces, physical interfaces, and logical interfaces, used to interconnect components within the device for allocating driving rights under shared human-machine driving, as well as interfaces used to interconnect the device with other devices (e.g., other computing devices or user devices). Physical interfaces can include Ethernet, fiber, or ATM interfaces; user devices can include displays, keyboards, and the like.

[0084] The memory 602 may be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0085] Processor 601 may be a general-purpose processor that can call a program for allocating driving rights in a human-machine co-pilot environment stored in a memory and execute the method for allocating driving rights in a human-machine co-pilot environment provided by an embodiment of the present disclosure. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the program for allocating driving rights in a human-machine co-pilot environment is called may refer to the various embodiments of the method for allocating driving rights in a human-machine co-pilot environment provided by the present disclosure and will not be further described here.

[0086] Those skilled in the art will understand that the hardware structure shown in FIG6 does not constitute a limitation to the present disclosure, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0087] Fourthly, some embodiments of the present disclosure further provide a computer-readable storage medium. This computer-readable storage medium stores a program for allocating driving rights in a shared human-machine environment. When executed by a processor, this program implements the steps of the method for allocating driving rights in a shared human-machine environment, as described in the aforementioned method embodiments of the present disclosure. It should be noted that the methods implemented when this program is executed can be referenced to the various embodiments of the method for allocating driving rights in a shared human-machine environment provided in the present disclosure and will not be further elaborated upon here.

[0088] In a fifth aspect, some embodiments of the present disclosure provide a vehicle, including the driving rights allocation device under human-machine co-driving provided in the third aspect above.

[0089] In a sixth aspect, some embodiments of the present disclosure provide a computer program product comprising computer instructions, which, when executed by a processor, implement the steps of the method for allocating driving rights under human-machine co-driving provided in the aforementioned method embodiment.

[0090] It should be noted that the serial numbers of the embodiments disclosed above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0091] The terms "including" and "having" and any variations thereof in the specification and claims of the present disclosure and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to be different types.

[0092] In the description of the embodiments of the present disclosure, the words "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of the present disclosure should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0093] In the description of the embodiments of the present disclosure, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present disclosure, “multiple” refers to two or more than two.

[0094] In some processes described in the embodiments of the present disclosure, multiple operations or steps are included that appear in a specific order. However, it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present disclosure or may be executed in parallel. The sequence numbers of the operations are only used to distinguish different operations and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0095] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course, by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in each embodiment of the present disclosure.

[0096] The above are merely exemplary embodiments of the present disclosure and are not intended to limit the patent scope of the present disclosure. Any equivalent structure or equivalent process transformation made using the contents of the present disclosure and the drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present disclosure.

Claims

1. A method for allocating driving rights in human-machine co-driving, comprising: The total field strength corresponding to each driving risk zone is calculated according to the risk source type, the vehicle operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source in the driving environment; Determine the location information of the risk area perceived by the driver according to the driver's sight information; The risk perception consistency index is calculated based on the total field strength and risk area location information corresponding to each driving risk zone; as well as A driving right switching weight is determined based on the risk perception consistency index and a preset risk perception consistency index threshold, so that the driving right switching allocation is performed through the driving right switching weight.

2. The method for allocating driving rights in human-machine co-driving as claimed in claim 1, wherein: The total field strength corresponding to each driving risk zone is calculated according to the risk source type in the driving environment, the vehicle operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source, including: Calculate the potential energy field strength corresponding to each driving risk partition based on the type of static risk source in the driving environment, the vehicle operating condition information, and the distance between the vehicle and the static risk source, wherein the vehicle operating condition information includes the vehicle mass and the vehicle speed; Calculate the kinetic energy field strength corresponding to each driving risk zone based on the type of dynamic risk source in the driving environment, the working condition information of the dynamic risk source, the working condition information of the own vehicle, and the distance between the own vehicle and the dynamic risk source. The working condition information of the dynamic risk source includes the mass of the dynamic risk source and the speed of the dynamic risk source; and The total field strength corresponding to each driving risk zone is calculated based on the potential energy field strength and the kinetic energy field strength.

3. The method for allocating driving rights in a human-machine co-driving environment as claimed in claim 2, wherein: The potential energy field strength is calculated using the following formula: In the formula, E R represents the potential energy field strength, k R represents the potential field coefficient, m1 represents the mass of the vehicle, v1 represents the speed of the vehicle, D1 represents the distance between the vehicle and the static risk source, T R Indicates the type coefficient corresponding to the static risk source type.

4. The method for allocating driving rights in a human-machine co-driving environment as claimed in claim 2, wherein: The kinetic energy field strength is calculated using the following formula: In the formula, E V represents the kinetic energy field strength, k V represents the kinetic energy field coefficient, m1 represents the mass of the vehicle, v1 represents the speed of the vehicle, D2 represents the distance between the vehicle and the dynamic risk source, m2 represents the mass of the dynamic risk source, v2 represents the speed of the dynamic risk source, T V Indicates the type coefficient corresponding to the dynamic risk source type.

5. The method for allocating driving rights in a human-machine co-driving environment as claimed in claim 1, wherein: The risk perception consistency index is calculated based on the total field strength corresponding to each driving risk zone and the risk area location information, including: The driving risk zone with a total field strength greater than the field strength threshold is used as the target risk zone, and the target risk zone with the largest total field strength is used as the system perception risk area; and When it is determined that there is a driver perception area in the driving risk partition based on the risk area location information, risk area matching is performed based on the driver perception area, the target risk partition and the system perception risk area to obtain a target matching degree, and the target matching degree is used as a risk perception consistency index.

6. The method for allocating driving rights in a human-machine co-driving situation as claimed in claim 5, wherein: The performing risk area matching based on the driver perception area, the target risk partition and the system perception risk area to obtain a target matching degree includes: Determining whether the driver perception area is the same as the system perception risk area; If they are the same, the first matching value is used as the target matching degree; and If they are not the same, the second matching values ​​corresponding to the target risk partitions are determined according to the driver's line of sight information, and the largest second matching value is used as the target matching degree, wherein the first matching value is greater than the second matching value.

7. The method for allocating driving rights in human-machine co-driving as claimed in claim 1, further comprising, after the step of determining the location information of the risk area perceived by the driver according to the driver's line of sight information: When it is determined that there is no driver perception area in the driving risk zone based on the risk area location information, the driving right is switched to the driver and a danger warning is issued.

8. A device for allocating driving rights in a human-machine co-driving environment, comprising: The first calculation module is used to calculate the total field strength corresponding to each driving risk zone according to the risk source type in the driving environment, the vehicle operating condition information, the risk source operating condition information, and the distance between the vehicle and the risk source; A determination module, which is used to determine the location information of the risk area perceived by the driver based on the driver's line of sight information; The second calculation module is used to calculate the risk perception consistency index based on the total field strength and risk area location information corresponding to each driving risk zone; as well as An allocation module is used to determine a driving right switching weight based on a risk perception consistency index and a preset risk perception consistency index threshold, so as to perform driving right switching allocation through the driving right switching weight.

9. A device for allocating driving rights in a human-machine co-driving situation, comprising a processor, a memory, and a program for allocating driving rights in a human-machine co-driving situation stored in the memory and executable by the processor, wherein when the program for allocating driving rights in a human-machine co-driving situation is executed by the processor, the steps of the method for allocating driving rights in a human-machine co-driving situation as described in any one of claims 1 to 7 are implemented.

10. A vehicle, comprising the driving right allocation device under human-machine co-driving as claimed in claim 9.

11. A computer-readable storage medium, comprising a program for allocating driving rights in a human-machine co-driving situation stored thereon, wherein when the program for allocating driving rights in a human-machine co-driving situation is executed by a processor, the steps of the method for allocating driving rights in a human-machine co-driving situation as described in any one of claims 1 to 7 are implemented.

12. A computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the method for allocating driving rights in human-machine co-driving according to any one of claims 1 to 7.

Images