Decision method, device and electronic equipment of autonomous vehicle

Abstract

The disclosure provides a decision-making method and device of an autonomous vehicle and an electronic device, and relates to the technical field of artificial intelligence, in particular to the technical field of autonomous driving. The specific implementation scheme is: obtaining historical operation data of a first vehicle on a target road; identifying a current scene of the target road based on the historical operation data; and deciding an autonomous driving behavior of the first vehicle based on the current scene to obtain the autonomous driving behavior of the first vehicle. Thus, the historical operation data of the first vehicle on the target road can be considered to identify the current scene of the target road to make the autonomous driving behavior decision. Compared with the related art, which mostly relies on real-time perception data to make the autonomous driving behavior decision, the inaccuracy of the autonomous driving behavior decision caused by the perception blind area is avoided, and the accuracy and efficiency of the autonomous driving behavior decision are improved without the need for real-time collection of perception data.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of automatic driving, and in particular to a decision-making method and device for an automatic driving vehicle, an electronic device, a storage medium, and a computer program product. BACKGROUND

[0002] At present, with the continuous development of artificial intelligence technology, automatic driving has been widely applied in the field of vehicles, and has the advantages of high automation and high intelligence. In the related technology, the automatic driving behavior of the vehicle is mostly decided by relying on real-time perception data. However, the perception blind area will lead to low accuracy of automatic driving behavior decision-making, and the collection and processing process of perception data is time-consuming, which leads to low efficiency of automatic driving behavior decision-making. SUMMARY

[0003] The present disclosure provides a decision-making method and device for an automatic driving vehicle, an electronic device, a storage medium, and a computer program product.

[0004] According to an aspect of the present disclosure, a decision-making method for an automatic driving vehicle is provided, comprising: obtaining historical operation data of a first vehicle on a target road; identifying a current scene of the target road based on the historical operation data; and deciding an automatic driving behavior of the first vehicle based on the current scene, to obtain the automatic driving behavior of the first vehicle.

[0005] According to another aspect of the present disclosure, a decision-making device for an automatic driving vehicle is provided, comprising: an obtaining module configured to obtain historical operation data of a first vehicle on a target road; an identifying module configured to identify a current scene of the target road based on the historical operation data; and a decision-making module configured to decide an automatic driving behavior of the first vehicle based on the current scene, to obtain the automatic driving behavior of the first vehicle.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a decision-making method for an automatic driving vehicle.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, and the computer instructions are used to enable the computer to execute a decision-making method for an automatic driving vehicle.

[0008] According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the steps of the decision-making method of an autonomous vehicle.

[0009] It should be understood that the details described in this section are not intended to identify key or critical features of the embodiments of the present disclosure, nor are they used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0011] Figure 1 is a flowchart of a decision-making method of an autonomous vehicle according to a first embodiment of the present disclosure;

[0012] Figure 2 is a flowchart of a decision-making method of an autonomous vehicle according to a second embodiment of the present disclosure;

[0013] Figure 3 is a flowchart of a decision-making method of an autonomous vehicle according to a third embodiment of the present disclosure;

[0014] Figure 4 is a flowchart of a decision-making method of an autonomous vehicle according to a fourth embodiment of the present disclosure;

[0015] Figure 5 is a flowchart of a decision-making method of an autonomous vehicle according to a fifth embodiment of the present disclosure;

[0016] Figure 6 is a block diagram of a decision-making device of an autonomous vehicle according to a first embodiment of the present disclosure;

[0017] Figure 7 is a block diagram of an electronic device for implementing a decision-making method of an autonomous vehicle according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, descriptions of well-known functions and structures are omitted in the following description.

[0019] AI(Artificial Intelligence, artificial intelligence) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. At present, AI technology has the advantages of high automation, high accuracy and low cost, and has been widely applied.

[0020] Automatic driving is a comprehensive system of sensors, computers, artificial intelligence, communication, navigation and positioning, pattern recognition, machine vision, intelligent control and other frontier disciplines. In the 21st century, with the substantial increase in physical computing power, the rapid development of dynamic vision technology and the rapid development of artificial intelligence technology, key technologies such as route navigation, obstacle avoidance and emergency decision-making have been solved, and automatic driving technology has made breakthrough progress.

[0021] Figure 1 is a flowchart of the decision-making method of the automatic driving vehicle according to the first embodiment of the present disclosure.

[0022] As shown in Figure 1 , the decision-making method of the automatic driving vehicle of the first embodiment of the present disclosure comprises:

[0023] S101, obtaining historical operation data of the first vehicle on a target road.

[0024] It should be noted that the execution subject of the decision-making method of the automatic driving vehicle of the present embodiment can be a hardware device with data information processing capability and / or the necessary software required to drive the hardware device to work. Optionally, the execution subject can include workstations, servers, computers, user terminals and other intelligent devices. Among them, the user terminal includes but is not limited to mobile phones, computers, smart voice interaction devices, smart home appliances, vehicle terminals, etc.

[0025] It should be noted that the first vehicle is an automatic driving vehicle, and the target road is not limited, for example, the target road can include expressways, expressways, main roads, secondary roads, branch roads, etc. Taking the first vehicle as a bus as an example, the target road can include the road on the bus line.

[0026] It should be noted that the historical operation data is not limited, for example, the historical operation data includes the identification of the target road, the time data, the historical scene of the target road, the position of the first vehicle, the speed of the first vehicle, the data collected by the perception module on the first vehicle, etc.

[0027] Among them, the identification of the target road can include the number and name of the target road.

[0028] The time data can include a historical time when the first vehicle enters the target road, a historical time when the first vehicle leaves the target road, a time period when the first vehicle travels on the target road, a date, a weekday or a holiday, and the like.

[0029] The historical scene of the target road can include a queuing scene, a parking scene, a construction scene, and the like.

[0030] The queuing scene can include a scenario in which the speed of the first vehicle changes from a non-zero value to zero (i.e., the first vehicle changes from moving to stationary) under the condition of road congestion, a traffic signal indicating that the vehicle stops traveling, a traffic signal being blocked, and the like, and a scenario in which the first vehicle travels slowly.

[0031] The parking scene can include a scenario in which a second vehicle temporarily parks, illegally parks, and the like, such as a scenario in which the second vehicle temporarily parks on the roadside. The second vehicle is not the same vehicle as the first vehicle.

[0032] The perception module is not limited too much, and can include a camera, a laser radar, a sensor, and the like. The data collected by the perception module can include an image, a video, point cloud data, and the like.

[0033] In an embodiment, the historical operation data of the first vehicle on the target road is obtained by obtaining a historical operation database of the first vehicle, and obtaining the historical operation data of the target road from the historical operation database based on the identification of the target road. It can be understood that the historical operation database includes historical operation data of a plurality of candidate roads.

[0034] In an embodiment, the operation data of the first vehicle can be collected during the travel of the first vehicle, and the operation data is stored in a set storage space for subsequent acquisition.

[0035] In some examples, the historical duration of the first vehicle traveling on the target road can be obtained. If the historical duration is greater than a set threshold, it indicates that the first vehicle has a long duration of traveling on the target road, and the historical scene of the target road can be determined as a queuing scene.

[0036] In some examples, the operation data of the first vehicle can be collected by the perception module on the first vehicle during the travel of the first vehicle, and / or the operation data of the first vehicle can be obtained based on the data collected by the perception module of the first vehicle.

[0037] For example, obstacle recognition can be performed on the image collected by the perception module of the first vehicle. If the obstacle is the second vehicle and the second vehicle is in the same lane as the first vehicle, the historical scene of the target road can be determined to be a queuing scene. Or, if the obstacle is the second vehicle and the second vehicle is in the rightmost lane of the target road, the historical scene of the target road can be determined to be a parking scene. Or, if the obstacle is construction equipment, the historical scene of the target road can be determined to be a construction scene.

[0038] In some examples, users can annotate the operational data of the first vehicle while it is in motion, thus obtaining the operational data of the first vehicle. Taking a bus as an example, users could include safety officers, drivers, etc.

[0039] For example, users can annotate historical scenarios on a target road. If the target road is congested and the first vehicle is moving slowly, the user can annotate the historical scenario of the target road as a queuing scenario. If there are temporarily parked vehicles on the side of the target road, the user can annotate the historical scenario of the target road as a parking scenario. If there is a construction section on the target road, the user can annotate the historical scenario of the target road as a construction scenario.

[0040] S102 identifies the current scene of the target road based on historical operational data.

[0041] In one implementation, historical operation data includes the historical duration of the first vehicle traveling on the target road. Based on the historical operation data, the current scenario of the target road is identified, including obtaining the current duration of the first vehicle traveling on the target road. If the difference between the current duration and the historical duration is greater than a set threshold, it indicates that the current duration exceeds the historical duration by a large margin, and the current scenario of the target road can be determined to be a queuing scenario.

[0042] In one implementation, historical operational data includes historical scenes of the target road. Based on this historical operational data, the current scene of the target road is identified, including determining the historical scene as the current scene. For example, if the historical scene of the target road is a construction scene, then the construction scene can be determined as the current scene.

[0043] In one implementation, historical operational data includes historical scenes of the target road. Based on the historical operational data, the current scene of the target road is identified, including filtering the current scene from multiple historical scenes.

[0044] In some cases, the current scenario is selected from multiple historical scenarios, including obtaining the frequency of historical scenarios and identifying the historical scenario with the highest frequency as the current scenario.

[0045] In some examples, the current scene is filtered out from the plurality of historical scenes, including identifying a time period in which the current time is located, and determining a historical scene corresponding to the time period as the current scene. Thus, the time period in which the current time is located and the historical scene can be comprehensively considered in the method to determine the current scene.

[0046] It can be understood that the target road can correspond to different historical scenes in different time periods. For example, the historical scene corresponding to the target road in the time period from 8:00 to 9:00 can be a queuing scene, and the historical scene corresponding to the target road in the time period from 11:00 to 13:00 can be a parking scene.

[0047] If the current time is 7:30, the time period in which the current time is located can be identified as the time period from 8:00 to 9:00, and the queuing scene can be determined as the current scene. Alternatively, if the current time is 11:30, the time period in which the current time is located can be identified as the time period from 11:00 to 13:00, and the parking scene can be determined as the current scene.

[0048] In S103, the automatic driving behavior of the first vehicle is determined based on the current scene, and the automatic driving behavior of the first vehicle is obtained.

[0049] In an implementation, the automatic driving behavior of the first vehicle is determined based on the current scene, and the automatic driving behavior of the first vehicle is obtained, including planning an automatic driving route of the first vehicle based on the current scene, obtaining the automatic driving route of the first vehicle, and determining the automatic driving behavior of the first vehicle based on the automatic driving route, and obtaining the automatic driving behavior of the first vehicle. Thus, the automatic driving route can be planned based on the current scene in the method to determine the automatic driving behavior.

[0050] In an implementation, the automatic driving behavior of the first vehicle is determined based on the current scene, and the automatic driving behavior of the first vehicle is obtained, including determining that the automatic driving strategy of the first vehicle is to continue driving in the original lane in response to the current scene being a queuing scene, determining the automatic driving behavior of the first vehicle based on the automatic driving strategy, and obtaining the automatic driving behavior of the first vehicle. It can be understood that the automatic driving behavior of the first vehicle in this embodiment can include straight driving, braking, parking, etc.

[0051] In an implementation, the automatic driving behavior of the first vehicle is determined based on the current scene, and the automatic driving behavior of the first vehicle is obtained, including determining that the automatic driving strategy of the first vehicle is to change lanes in response to the current scene being a parking scene, determining the automatic driving behavior of the first vehicle based on the automatic driving strategy, and obtaining the automatic driving behavior of the first vehicle. It can be understood that the automatic driving behavior of the first vehicle in this embodiment can include changing lanes and overtaking.

[0052] In an implementation, the automatic driving behavior of the first vehicle is determined based on the current scene, and the automatic driving behavior of the first vehicle is determined based on the automatic driving strategy. It can be understood that the automatic driving behavior of the first vehicle in the embodiment can include changing lanes and the like.

[0053] In summary, according to the automatic driving vehicle decision method of the embodiment of the present disclosure, the historical operation data of the first vehicle on the target road is obtained, the current scene of the target road is identified based on the historical operation data, the automatic driving behavior of the first vehicle is determined based on the current scene, and the automatic driving behavior of the first vehicle is obtained. Therefore, the historical operation data of the first vehicle on the target road can be considered to identify the current scene of the target road to determine the automatic driving behavior, compared with the related art which mainly relies on real-time perception data to determine the automatic driving behavior, the inaccuracy of the automatic driving behavior determination caused by the perception blind area is avoided, and the accuracy and efficiency of the automatic driving behavior determination are improved.

[0054] Figure 2 is a flowchart of an automatic driving vehicle decision method according to a second embodiment of the present disclosure.

[0055] As shown in Figure 2 , the automatic driving vehicle decision method of the second embodiment of the present disclosure includes:

[0056] S201, obtaining historical operation data of a first vehicle on a target road.

[0057] The related content of step S201 can be referred to the above-mentioned embodiments, which will not be repeated here.

[0058] S202, obtaining obstacle data of the first vehicle.

[0059] It should be noted that the obstacle is not limited too much, for example, the obstacle can include a second vehicle, a pedestrian, a construction device, etc. The construction device can include a conical barrel, a water horse, a road roller, etc.

[0060] It should be noted that the obstacle data is not limited too much, for example, it can include the category, position, speed, size, etc. of the obstacle.

[0061] In an implementation, the obstacle data of the first vehicle is obtained based on the data collected by the perception module on the first vehicle.

[0062] In some examples, the image collected by the perception module of the first vehicle can be subjected to obstacle recognition to obtain the category, position, size, etc. of the obstacle.

[0063] In some examples, the speed of the obstacle can be extracted from the data collected by the speed sensor of the first vehicle.

[0064] S203, based on the historical operation data and the obstacle data, identify the current scene.

[0065] In an implementation, identifying the current scene based on the historical operation data and the obstacle data can include the following possible implementations:

[0066] Method 1, obtain the current duration of the first vehicle driving on the target road, in response to the difference between the current duration and the historical duration being greater than a set threshold, and the obstacle being a second vehicle, determine that the current scene is a queuing scene.

[0067] Method 2, in response to the historical scene including a queuing scene, and the obstacle being a second vehicle, and the second vehicle being in the same lane as the first vehicle, determine that the current scene is a queuing scene.

[0068] Method 3, in response to the historical scene including a queuing scene, and the obstacle being a second vehicle, and the speed of the second vehicle being less than or equal to a first set threshold, determine that the current scene is a queuing scene.

[0069] Method 4, in response to the historical scene including a queuing scene, and the obstacle being a second vehicle, and the traffic signal on the target road being blocked, or the traffic signal indicating that the vehicle stop driving, determine that the current scene is a queuing scene.

[0070] Method 5, in response to the historical scene including a queuing scene, and the obstacle being a second vehicle, and the interval between two adjacent second vehicles being in a first set interval, determine that the current scene is a queuing scene.

[0071] It should be noted that the first set interval is not limited too much, for example, it can be 0.3 to 3 meters.

[0072] Method 6, in response to the historical scene including a queuing scene, and the obstacle being a second vehicle, obtain the distance between the first vehicle and the intersection connected to the target road, based on the number of second vehicles and the distance, determine that the current scene is a queuing scene.

[0073] In some examples, based on the number of second vehicles and the distance, determining that the current scene is a queuing scene includes obtaining the ratio of the distance and the number of second vehicles, in response to the ratio being in a second set interval, determining that the current scene is a queuing scene.

[0074] It should be noted that the second set interval is not limited too much, for example, it can be 2 to 5 meters.

[0075] Method 7, in response to the historical scene including a parking scene, and the obstacle being a second vehicle, and the second vehicle being in the rightmost lane on the target road, determining that the current scene is a parking scene.

[0076] Method 8, in response to the historical scene including a parking scene, and the obstacle being a second vehicle, and the second vehicle being stationary, determining that the current scene is a parking scene.

[0077] Method 9, in response to the historical scene including a parking scene, and the obstacle being a second vehicle, and the surrounding area of the second vehicle existing pedestrians, determining that the current scene is a parking scene.

[0078] Method 10, in response to the historical scene including a construction scene, and the obstacle being a construction equipment, determining that the current scene is a construction scene.

[0079] Method 11, in response to the historical scene including a construction scene, and the obstacle being a construction equipment, based on the size and position of the construction equipment, obtaining a passable space of the original lane of the first vehicle, and in response to the passable space being less than a set threshold, determining that the current scene is a construction scene.

[0080] S204, based on the current scene, making a decision on the automatic driving behavior of the first vehicle, to obtain the automatic driving behavior of the first vehicle.

[0081] The related content of step S204 can be referred to the above-mentioned embodiments, which will not be repeated here.

[0082] In summary, according to the decision method of the automatic driving vehicle of the embodiments of the present disclosure, the obstacle data of the first vehicle is obtained, and the current scene is identified based on the historical operation data and the obstacle data. Thus, the historical operation data and the obstacle data of the first vehicle can be considered comprehensively to identify the current scene of the target road, so as to make a decision on the automatic driving behavior, thereby improving the accuracy and efficiency of the decision on the automatic driving behavior.

[0083] Figure 3 is a flowchart of the decision method of the automatic driving vehicle according to the third embodiment of the present disclosure.

[0084] As Figure 3 shown, the decision method of the automatic driving vehicle of the third embodiment of the present disclosure comprises:

[0085] S301, obtaining the historical operation data of the first vehicle on the target road.

[0086] S302, obtaining the obstacle data of the first vehicle.

[0087] The details of steps S301-S302 can be found in the above embodiments and will not be repeated here.

[0088] S303, based on obstacle data, determines candidate scenarios for the target road.

[0089] It should be noted that the number of candidate scenarios can be at least one.

[0090] In one implementation, candidate scenarios for the target road are determined based on obstacle data, including the following possible implementation methods:

[0091] Method 1: In response to the obstacle being a second vehicle, candidate scenarios are determined to include parking scenarios and queuing scenarios.

[0092] Method 2: In response to the obstacle being a second vehicle and the speed of the second vehicle being less than or equal to a second set threshold, the candidate scenarios are determined to include parking scenarios and queuing scenarios.

[0093] It should be noted that the second threshold is not subject to many restrictions; for example, it may include 5 km / h.

[0094] Method 3: In response to the obstacle being construction equipment, determine the candidate scenarios, including construction scenarios.

[0095] Method 4: In response to the obstacle being construction equipment, based on the size and location of the construction equipment, obtain the passable space of the original lane of the first vehicle; in response to the passable space being less than a set threshold, determine that the candidate scenario includes the construction scenario.

[0096] S304, in response to historical scenarios including candidate scenarios, determine the current scenario as a candidate scenario.

[0097] For example, based on obstacle data, candidate scenarios for the target road can be determined, including parking scenarios and queuing scenarios. If the historical scenarios of the target road include parking scenarios, the current scenario can be determined to be a parking scenario. Alternatively, if the historical scenarios of the target road include queuing scenarios, the current scenario can be determined to be a queuing scenario.

[0098] For example, based on obstacle data, it can be determined that candidate scenarios for the target road include construction scenarios. If the historical scenarios of the target road include construction scenarios, then the current scenario can be determined to be a construction scenario.

[0099] In one implementation, determining the current scene as a candidate scene in response to the inclusion of candidate scenes in historical scenes includes identifying the time period in which the current moment is located, and determining the current scene as a candidate scene in response to the inclusion of candidate scenes in historical scenes corresponding to the time period. Thus, this method can determine the current scene as a candidate scene when the historical scenes corresponding to the current time period include candidate scenes.

[0100] For example, the historical scene corresponding to the time period of 8:00-9:00 of the target road includes a queuing scene, and the historical scene corresponding to the time period of 11:00-13:00 of the target road includes a parking scene. The candidate scene includes the queuing scene and the parking scene.

[0101] If the current time is 7:30, it can be identified that the current time is in the time period of 8:00-9:00, and the historical scene corresponding to the time period of 8:00-9:00 includes the queuing scene. Therefore, it can be determined that the current scene is the queuing scene.

[0102] If the current time is 11:30, it can be identified that the current time is in the time period of 11:00-13:00, and the historical scene corresponding to the time period of 11:00-13:00 includes the parking scene. Therefore, it can be determined that the current scene is the parking scene.

[0103] In an embodiment, in a case where the obstacle is a second vehicle and the candidate scene is a parking scene, before determining that the current scene is the candidate scene, the method further includes identifying that the second vehicle is stationary, and / or identifying that the second vehicle is in a rightmost lane on the target road, and / or identifying that a surrounding area of the second vehicle has a pedestrian. Thus, in the method, the current scene can be determined to be the parking scene when the second vehicle is stationary, and / or the second vehicle is in the rightmost lane on the target road, and / or the surrounding area of the second vehicle has the pedestrian, and the historical scene includes the parking scene.

[0104] In an embodiment, in a case where the obstacle is a second vehicle and the candidate scene is a queuing scene, before determining that the current scene is the candidate scene, the method further includes identifying that a speed of the second vehicle is less than or equal to a second set threshold, and / or identifying that the second vehicle is in the same lane as the first vehicle, and / or identifying that a traffic signal on the target road is blocked, or the traffic signal indicates that vehicles stop driving. Thus, in the method, the current scene can be determined to be the queuing scene when the speed of the second vehicle is slow, and / or the second vehicle is in the same lane as the first vehicle, and / or the traffic signal is blocked, or the traffic signal indicates that vehicles stop driving, and the historical scene includes the queuing scene.

[0105] S305, based on the current scene, making a decision on an automatic driving behavior of the first vehicle, to obtain the automatic driving behavior of the first vehicle.

[0106] The related content of step S305 can be referred to the above embodiments, which will not be described here.

[0107] In summary, according to the decision-making method of the automatic driving vehicle, the candidate scene of the target road can be determined based on the obstacle data, and the current scene can be determined to be the candidate scene when the historical scene includes the candidate scene.

[0108] Figure 4 is a flowchart of a decision-making method of an autonomous vehicle according to the fourth embodiment of the present disclosure.

[0109] As shown in Figure 4 , the decision-making method of the autonomous vehicle according to the fourth embodiment of the present disclosure comprises:

[0110] S401, obtaining historical operation data of a first vehicle on a target road.

[0111] S402, obtaining obstacle data of the first vehicle.

[0112] S403, determining a candidate scene of the target road based on the obstacle data.

[0113] The related content of steps S401-S403 can be referred to the above embodiments, which will not be described here.

[0114] S404, in response to the historical scene including the candidate scene, obtaining a probability that the current scene is the candidate scene based on a number of historical operation data corresponding to the candidate scene.

[0115] S405, determining that the current scene is the candidate scene when the probability is greater than or equal to a first set threshold.

[0116] In an implementation, the number of historical operation data corresponding to the candidate scene is positively correlated with the probability that the current scene is the candidate scene.

[0117] In an implementation, obtaining the probability that the current scene is the candidate scene based on the number of historical operation data corresponding to the candidate scene comprises: obtaining a total number of historical operation data corresponding to the historical scene, and obtaining the probability that the current scene is the candidate scene based on the number of historical operation data corresponding to the candidate scene and the total number of historical operation data.

[0118] In some examples, obtaining the probability that the current scene is the candidate scene based on the number of historical operation data corresponding to the candidate scene and the total number of historical operation data comprises: determining the ratio of the number of historical operation data corresponding to the candidate scene to the total number of historical operation data as the probability that the current scene is the candidate scene.

[0119] For example, if the candidate scene includes a queuing scene and a parking scene, if the number of historical operation data corresponding to the queuing scene of the historical scene of the target road is 20, the number of historical operation data corresponding to the parking scene of the historical scene of the target road is 5, and the total number of historical operation data corresponding to the historical scene of the target road is 30.

[0120] The ratio of the number of the historical operation data corresponding to the queuing scene to the total number is 66.7%, and 66.7% is determined as the probability that the current scene is the queuing scene. The ratio of the number of the historical operation data corresponding to the parking scene to the total number is 16.7%, and 16.7% is determined as the probability that the current scene is the parking scene.

[0121] If the first set threshold is 60%, the probability that the current scene is the queuing scene is greater than the first set threshold, and it is determined that the current scene is the queuing scene.

[0122] S406, based on the current scene, making a decision on the automatic driving behavior of the first vehicle to obtain the automatic driving behavior of the first vehicle.

[0123] The related content of step S406 can be referred to the above-mentioned embodiments, which will not be repeated here.

[0124] In summary, according to the decision-making method of the automatic driving vehicle of the embodiments of the present disclosure, the number of the historical operation data corresponding to the candidate scene can be considered to obtain the probability that the current scene is the candidate scene, and when the probability is greater, it is determined that the current scene is the candidate scene.

[0125] Figure 5 is a flowchart of the decision-making method of the automatic driving vehicle according to the fifth embodiment of the present disclosure.

[0126] As shown in Figure 5 , the decision-making method of the automatic driving vehicle of the fifth embodiment of the present disclosure comprises:

[0127] S501, obtaining the historical operation data of the first vehicle on the target road.

[0128] S502, based on the historical operation data, identifying the current scene of the target road.

[0129] S503, based on the current scene, making a decision on the automatic driving behavior of the first vehicle to obtain the automatic driving behavior of the first vehicle.

[0130] The related content of steps S501-S503 can be referred to the above-mentioned embodiments, which will not be repeated here.

[0131] S504, controlling the first vehicle to perform the automatic driving behavior.

[0132] S505, in the process of controlling the first vehicle to perform the automatic driving behavior, identifying that the set switching condition is met, and switching the current scene from the first scene to the second scene.

[0133] In the embodiments of the present disclosure, after the current scene is switched from the first scene to the second scene, step S503 and the subsequent steps can be returned to be executed.

[0134] It should be noted that the setting switching condition is not limited too much.

[0135] In an implementation, the switching of the current scene from the first scene to the second scene in response to the identification of the satisfaction of the setting switching condition includes, in the case that the first scene is the parking scene, in response to the speed of the third vehicle in the original lane of the first vehicle changing from a non-zero to zero (i.e., the third vehicle changing from moving to stationary), and / or the speed of the third vehicle being greater than or equal to a second setting threshold, indicating that the third vehicle is a queuing vehicle, identifying the satisfaction of the first switching condition, and switching the current scene from the parking scene to the queuing scene. Thus, in the method, the third vehicle can be identified as a queuing vehicle based on the speed of the third vehicle in the original lane, and then the satisfaction of the first switching condition is identified, and the switching from the parking scene to the queuing scene is realized.

[0136] It should be noted that the second setting threshold is not limited too much, for example, it can be 3 km / h.

[0137] For example, if the first scene is the parking scene, the automatic driving behavior includes lane changing, overtaking, etc., and in the process of controlling the first vehicle to perform lane changing and overtaking, in response to the speed of the third vehicle in the original lane of the first vehicle changing from 5 km / h to zero, and / or the speed of the third vehicle being greater than or equal to 3 km / h, the satisfaction of the first switching condition is identified, and the current scene is switched from the parking scene to the queuing scene.

[0138] The automatic driving behavior of the first vehicle can be decided based on the queuing scene, and the automatic driving behavior of the first vehicle includes stopping lane changing behavior, stopping overtaking behavior, returning to the original lane, straight driving, braking, stopping, etc., and the first vehicle is controlled to perform the above automatic driving behavior.

[0139] In an implementation, the switching of the current scene from the first scene to the second scene in response to the identification of the satisfaction of the setting switching condition includes, in the case that the first scene is the queuing scene, in response to the waiting time of the first vehicle being greater than or equal to a third setting threshold, indicating that the waiting time of the first vehicle is relatively long, identifying the satisfaction of the second switching condition, and switching the current scene from the queuing scene to the parking scene. Thus, in the method, the satisfaction of the second switching condition can be identified when the waiting time of the first vehicle is relatively long, and the switching from the queuing scene to the parking scene is realized.

[0140] It should be noted that the waiting time of the first vehicle can include a time period during which the speed of the first vehicle is less than or equal to a second setting threshold, or a time period during which the first vehicle is stationary.

[0141] It should be noted that the third setting threshold is not limited too much, for example, it can include the opening time of a traffic signal, for example, it can be 2 minutes.

[0142] For example, if the first scene is a queuing scene, the automatic driving behavior includes straight driving, braking, stopping, etc. During the process of controlling the first vehicle to perform straight driving, braking, and stopping, if the third set threshold is 2 minutes, the second switching condition is met in response to the waiting time of the first vehicle reaching 2 minutes, and the current scene is switched from the queuing scene to the parking scene.

[0143] Based on the parking scene, the automatic driving behavior of the first vehicle can be decided, and the automatic driving behavior of the first vehicle includes lane changing, overtaking, etc. The first vehicle is controlled to perform the above automatic driving behavior.

[0144] In summary, according to the decision method of the automatic driving vehicle of the embodiment of the present disclosure, after obtaining the automatic driving behavior of the first vehicle, the automatic driving behavior of the first vehicle can be controlled to perform the automatic driving behavior. During the process of controlling the first vehicle to perform the automatic driving behavior, the set switching condition is met, the current scene is switched from the first scene to the second scene, and the subsequent steps of deciding the automatic driving behavior of the first vehicle based on the current scene are returned. Therefore, the current scene can be switched when the set switching condition is met, and the current scene can be updated in time, especially suitable for the case where the current scene is misjudged, which improves the accuracy of the current scene and further improves the accuracy of the automatic driving behavior decision.

[0145] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution comply with relevant laws and regulations and do not violate public order and good customs.

[0146] According to the embodiments of the present disclosure, the present disclosure also provides a decision device of an automatic driving vehicle for implementing the above-mentioned decision method of an automatic driving vehicle.

[0147] Figure 6 is a block diagram of the decision device of the automatic driving vehicle according to the first embodiment of the present disclosure.

[0148] As Figure 6 shown, the decision device 600 of the automatic driving vehicle of the embodiment of the present disclosure includes an acquisition module 601, an identification module 602, and a decision module 603.

[0149] The acquisition module 601 is configured to acquire historical operation data of a first vehicle on a target road.

[0150] The identification module 602 is configured to identify a current scene of the target road based on the historical operation data.

[0151] The decision module 603 is configured to decide an automatic driving behavior of the first vehicle based on the current scene, and obtain the automatic driving behavior of the first vehicle.

[0152] In an embodiment of the present disclosure, the identification module 602 is further configured to: obtain obstacle data of the first vehicle; and identify the current scene based on the historical operation data and the obstacle data.

[0153] In an embodiment of the present disclosure, the historical operation data comprises historical scenes of the target road, and the identification module 602 is further configured to: determine a candidate scene of the target road based on the obstacle data; and determine the current scene as the candidate scene in response to the historical scenes comprising the candidate scene.

[0154] In an embodiment of the present disclosure, the identification module 602 is further configured to: determine that the candidate scene comprises a parking scene or a queuing scene in response to the obstacle being a second vehicle; or determine that the candidate scene comprises a construction scene in response to the obstacle being a construction device.

[0155] In an embodiment of the present disclosure, the identification module 602 is further configured to: identify a time period at the current time; and determine the current scene as the candidate scene in response to a historical scene corresponding to the time period comprising the candidate scene.

[0156] In an embodiment of the present disclosure, the identification module 602 is further configured to: obtain a probability that the current scene is the candidate scene based on a quantity of historical operation data corresponding to the candidate scene in response to the historical scenes comprising the candidate scene; and determine the current scene as the candidate scene in response to the probability being greater than or equal to a first preset threshold.

[0157] In an embodiment of the present disclosure, in a case where the obstacle is the second vehicle and the candidate scene is a parking scene, the identification module 602 is further configured to: identify that the second vehicle is stationary; and / or identify that the second vehicle is in a rightmost lane on the target road; and / or identify that a surrounding area of the second vehicle has a pedestrian before determining the current scene as the candidate scene.

[0158] In an embodiment of the present disclosure, in a case where the obstacle is the second vehicle and the candidate scene is a queuing scene, the identification module 602 is further configured to: identify that a speed of the second vehicle is less than or equal to a second preset threshold; and / or identify that the second vehicle and the first vehicle are in a same lane; and / or identify that a traffic signal on the target road is blocked or the traffic signal indicates that the vehicle stop driving before determining the current scene as the candidate scene.

[0159] In an embodiment of the present disclosure, the switching module is further configured to: control the first vehicle to perform the automatic driving behavior; during the process of controlling the first vehicle to perform the automatic driving behavior, identify that a preset switching condition is met, switch the current scenario from the first scenario to a second scenario, and return to perform the steps of deciding the automatic driving behavior of the first vehicle based on the current scenario and the subsequent steps.

[0160] In an embodiment of the present disclosure, the switching module is further configured to: in a case where the first scenario is a parking scenario, in response to a speed of a third vehicle in an original lane of the first vehicle changing from a non-zero value to zero and / or the speed of the third vehicle being greater than or equal to a second preset threshold, identify that a first switching condition is met, and switch the current scenario from the parking scenario to a queuing scenario.

[0161] In an embodiment of the present disclosure, the switching module is further configured to: in a case where the first scenario is a queuing scenario, in response to a waiting time of the first vehicle being greater than or equal to a third preset threshold, identify that a second switching condition is met, and switch the current scenario from the queuing scenario to the parking scenario.

[0162] In summary, the decision device of the automatic driving vehicle in the embodiment of the present disclosure acquires historical operation data of the first vehicle on the target road, identifies the current scenario of the target road based on the historical operation data, decides the automatic driving behavior of the first vehicle based on the current scenario, and obtains the automatic driving behavior of the first vehicle. Thus, the historical operation data of the first vehicle on the target road can be considered to identify the current scenario of the target road to decide the automatic driving behavior, compared with the related art which mostly relies on real-time perception data to decide the automatic driving behavior, and the inaccuracy of the automatic driving behavior decision caused by the perception blind area, the present solution does not need to collect perception data in real time, and the accuracy and efficiency of the automatic driving behavior decision are improved.

[0163] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0164] Figure 7A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0165] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. The RAM 703 may also store various programs and data required for the operation of the electronic device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0166] Multiple components in electronic device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of displays, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows electronic device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0167] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as... Figures 1 to 5The decision-making method of the autonomous vehicle described above. For example, in some embodiments, the decision-making method of the autonomous vehicle can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, portions or all of the computer program can be loaded onto and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the decision-making method of the autonomous vehicle described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the decision-making method of the autonomous vehicle by any other suitable means, such as by means of firmware.

[0168] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0169] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0170] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0171] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0172] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0173] The computer system can include clients and servers. This relationship can be. The servers are generally remote from the users and can be accessed via the Internet using a communication network. The relationship can be a client-server relationship over a communications network, and as such, the aforementioned devices can be referred to as a client and a server, respectively. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, and solves the defects of large management difficulty and weak business scalability in traditional physical hosts and VPS services (Virtual Private Server, or VPS for short). The server can also be a server of a distributed system, or a server combined with a blockchain.

[0174] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the steps of the decision-making method of the autonomous vehicle according to the above-mentioned embodiments of the present disclosure.

[0175] It should be understood that the steps shown in the above forms can be reordered, added or deleted. For example, the steps described in the present disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

[0176] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A decision-making method of an autonomous vehicle, comprising: obtaining historical operation data of a first vehicle on a target road; identifying a current scene of the target road based on the historical operation data; making a decision on an autonomous driving behavior of the first vehicle based on the current scene, to obtain the autonomous driving behavior of the first vehicle; wherein the identifying the current scene of the target road based on the historical operation data comprises: obtaining obstacle data of the first vehicle; identifying the current scene based on the historical operation data and the obstacle data; the historical operation data comprises a historical scene of the target road; and the identifying the current scene based on the historical operation data and the obstacle data comprises: determining a candidate scene of the target road based on the obstacle data; in response to the historical scene comprising the candidate scene, determining the current scene as the candidate scene.

2. The method of claim 1, wherein, the determining the candidate scene of the target road based on the obstacle data comprises: in response to the obstacle being a second vehicle, determining that the candidate scene comprises a parking scene or a queuing scene; or in response to the obstacle being a construction device, determining that the candidate scene comprises a construction scene.

3. The method of claim 1, wherein, the determining the current scene as the candidate scene in response to the historical scene comprising the candidate scene comprises: identifying a time period at a current time; in response to a historical scene corresponding to the time period comprising the candidate scene, determining the current scene as the candidate scene.

4. The method of claim 1, wherein, the determining the current scene as the candidate scene in response to the historical scene comprising the candidate scene comprises: in response to the historical scene comprising the candidate scene, obtaining a probability that the current scene is the candidate scene based on a quantity of historical operation data corresponding to the candidate scene; identifying that the probability is greater than or equal to a first set threshold, to determine that the current scene is the candidate scene.

5. The method of claim 2, wherein, in a case where the obstacle is the second vehicle and the candidate scene is the parking scene, before the determining the current scene as the candidate scene, the method further comprises: identifying that the second vehicle is stationary; and / or identifying that the second vehicle is in a rightmost lane on the target road; and / or identifying that a surrounding area of the second vehicle has a pedestrian.

6. The method of claim 2, wherein, in a case where the obstacle is the second vehicle and the candidate scene is the queuing scene, before the determining the current scene as the candidate scene, the method further comprises: identifying that a speed of the second vehicle is less than or equal to a second set threshold; and / or identifying that the second vehicle and the first vehicle are in a same lane; and / or identifying that a traffic signal on the target road is blocked or indicates that the vehicle stop driving.

7. The method of any one of claims 1-6, wherein, after the obtaining the autonomous driving behavior of the first vehicle, the method further comprises: controlling the first vehicle to perform the autonomous driving behavior. In a process of controlling the first vehicle to perform the automatic driving behavior, it is identified that a set switching condition is met, the current scene is switched from the first scene to a second scene, and the subsequent steps of performing the decision on the automatic driving behavior of the first vehicle based on the current scene are returned.

8. The method of claim 7, wherein, The identification that the set switching condition is met and the current scene is switched from the first scene to the second scene comprises: In a case where the first scene is a parking scene, in response to a speed of a third vehicle in an original lane of the first vehicle changing from a non-zero value to zero, and / or the speed of the third vehicle being greater than or equal to a second set threshold, a first switching condition is identified to be met, and the current scene is switched from the parking scene to a queuing scene.

9. The method of claim 7, wherein, The identification that the set switching condition is met and the current scene is switched from the first scene to the second scene comprises: In a case where the first scene is a queuing scene, in response to a waiting duration of the first vehicle being greater than or equal to a third set threshold, a second switching condition is identified to be met, and the current scene is switched from the queuing scene to the parking scene.

10. A decision device of an automatic driving vehicle, comprising: an acquisition module configured to acquire historical operation data of a first vehicle on a target road; an identification module configured to identify a current scene of the target road based on the historical operation data; a decision module configured to make a decision on an automatic driving behavior of the first vehicle based on the current scene, to obtain the automatic driving behavior of the first vehicle; wherein the identification module is further configured to: acquire obstacle data of the first vehicle; identify the current scene based on the historical operation data and the obstacle data; the historical operation data comprises historical scenes of the target road, and the identification module is further configured to: determine a candidate scene of the target road based on the obstacle data; in response to the historical scene comprising the candidate scene, determine that the current scene is the candidate scene.

11. The apparatus of claim 10, wherein, the identification module is further configured to: in response to the obstacle being a second vehicle, determine that the candidate scene comprises a parking scene and a queuing scene; or in response to the obstacle being construction equipment, determine that the candidate scene comprises a construction scene.

12. The apparatus of claim 10, wherein, the identification module is further configured to: identify a time period at a current time; in response to a historical scene corresponding to the time period comprising the candidate scene, determine that the current scene is the candidate scene.

13. The apparatus of claim 10, wherein, the identification module is further configured to: in response to the historical scene comprising the candidate scene, obtain a probability that the current scene is the candidate scene based on a quantity of historical operation data corresponding to the candidate scene; identify that the probability is greater than or equal to a first set threshold, to determine that the current scene is the candidate scene.

14. The apparatus of claim 11, wherein, in a case where the obstacle is the second vehicle and the candidate scene is a parking scene, before the determination that the current scene is the candidate scene, the identification module is further configured to: identify that the second vehicle is stationary; and / or identify that the second vehicle is in a rightmost lane on the target road; and / or identify that a surrounding area of the second vehicle has a pedestrian.

15. The apparatus of claim 11, wherein, In a case where the obstacle is the second vehicle and the candidate scenario is a queuing scenario, before the determining that the current scenario is the candidate scenario, the identifying module is further configured to: identify that a speed of the second vehicle is less than or equal to a second preset threshold; and / or, identify that the second vehicle is in a same lane as the first vehicle; and / or, identify that a traffic signal on the target road is blocked, or the traffic signal indicates the vehicle to stop driving.

16. The apparatus of any one of claims 10-15, wherein, Further comprising: a switching module, configured to: control the first vehicle to perform the automatic driving behavior; in a process of controlling the first vehicle to perform the automatic driving behavior, identify that a preset switching condition is met, switch the current scenario from a first scenario to a second scenario, and return to perform the subsequent steps of determining, based on the current scenario, an automatic driving behavior of the first vehicle and making a decision thereon.

17. The apparatus of claim 16, wherein, The switching module is further configured to: in a case where the first scenario is a parking scenario, in response to a speed of a third vehicle in an original lane of the first vehicle changing from a non-zero value to zero, and / or the speed of the third vehicle being greater than or equal to a second preset threshold, identify that a first switching condition is met, and switch the current scenario from the parking scenario to a queuing scenario.

18. The apparatus of claim 16, wherein, The switching module is further configured to: in a case where the first scenario is a queuing scenario, in response to a waiting time of the first vehicle being greater than or equal to a third preset threshold, identify that a second switching condition is met, and switch the current scenario from the queuing scenario to the parking scenario.

19. An electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the decision-making method of the autonomous vehicle according to any one of claims 1-9.

20. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the decision-making method of the autonomous vehicle according to any one of claims 1-9.

21. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the decision-making method of the autonomous vehicle according to any one of claims 1-9.

Images