Automatic driving vehicle control method and device, vehicle control equipment and storage medium

Abstract

The application discloses an automatic driving vehicle control method and device, a vehicle control device and a storage medium. In the embodiment of the application, when the width of the drivable area of the host vehicle is less than a preset width, the length of the drivable area is greater than a preset length, and there is an oncoming vehicle on the road during driving of the host vehicle, a first back-off cost of the host vehicle and a second back-off cost of the oncoming vehicle are calculated according to road data and vehicle data, and the host vehicle is controlled according to the first back-off cost and the second back-off cost. The back-off cost represents the difficulty of the vehicle backing off for the oncoming vehicle, so that the vehicle with a smaller back-off cost can be used as the back-off vehicle, the problem that the automatic driving vehicle cannot decide whether to back off for the oncoming vehicle, resulting in emergency braking and being stuck, is solved, whether to back off for the oncoming vehicle is decided after the back-off cost is calculated according to the road data and the vehicle data, and the automatic driving vehicle and the social vehicle are ensured to meet on a narrow road.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving vehicle technology, and in particular to an autonomous driving vehicle control method, apparatus, vehicle control device and storage medium. Background Art

[0002] As more and more self-driving vehicles are driving on the road, they will inevitably meet other vehicles.

[0003] like Figure 1 As shown in a and b, the main vehicle 1 (autonomous driving vehicle) is on a "single-plank bridge" road when driving on a narrow road. Figure 1 As shown in a, only one car can pass through the single-lane road, or as Figure 1 As shown in b, the road has multiple lanes, but due to the presence of a large number of illegal parking or other obstacles on both sides or one side of the road, the width w of the drivable area can only meet the needs of one car. Figure 1 In the scenario shown, when the main vehicle 1 and the oncoming vehicle 2 both enter the road, the main vehicle 1 finds it difficult to decide whether to back up and give way to the oncoming vehicle 2, causing the main vehicle 1 to brake suddenly and get stuck on the road. Backstage personnel are required to remotely control the main vehicle 1 or go to the scene to solve the problem of the main vehicle 1 being stuck. Summary of the Invention

[0004] The present invention provides an autonomous driving vehicle control method, device, vehicle control equipment and storage medium to solve the problem in the prior art that when an oncoming autonomous driving vehicle is passing on a narrow road, it is unable to decide whether to back up and give way, causing the autonomous driving vehicle to brake suddenly and get stuck.

[0005] In a first aspect, the present invention provides a method for controlling an autonomous driving vehicle, comprising:

[0006] During the driving process of the main vehicle, determining whether the road condition of the road currently located by the main vehicle is a preset road condition, in which the width of the drivable area of ​​the main vehicle is less than a preset width and the length of the drivable area is greater than a preset length;

[0007] If yes, when there is an oncoming vehicle on the road, obtaining road data of the road and vehicle data of the vehicle on the road;

[0008] Calculating a first retreat yielding cost for the host vehicle and a second retreat yielding cost for the oncoming vehicle based on the road data and the vehicle data;

[0009] The host vehicle is controlled according to the first backing-up yielding cost and the second backing-up yielding cost.

[0010] In a second aspect, the present invention provides an autonomous driving vehicle control device, comprising:

[0011] a road condition determination module, configured to determine, during the driving process of the host vehicle, whether the road condition of the road currently on which the host vehicle is located is a preset road condition, wherein the width of the drivable area of ​​the host vehicle in the preset road condition is less than a preset width and the length of the drivable area is greater than a preset length;

[0012] an environmental data acquisition module, configured to acquire road data of the road and vehicle data of vehicles on the road when there is an oncoming vehicle on the road;

[0013] a back-up yielding cost calculation module, configured to calculate a first back-up yielding cost for the host vehicle and a second back-up yielding cost for the oncoming vehicle based on the road data and the vehicle data;

[0014] A vehicle control module is used to control the host vehicle according to the first back-up yielding cost and the second back-up yielding cost.

[0015] In a third aspect, the present invention provides a vehicle control device, the vehicle control device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the autonomous driving vehicle control method described in the first aspect of the present invention.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, which are used to enable a processor to implement the autonomous driving vehicle control method described in the first aspect of the present invention when executed.

[0020] In an embodiment of the present invention, when it is determined that the width of the main vehicle's drivable area is less than a preset width and the length of the drivable area is greater than a preset length during the main vehicle's driving, and when there is an oncoming vehicle on the road, a first back-up yielding cost for the main vehicle and a second back-up yielding cost for the oncoming vehicle are calculated based on road data and vehicle data, and the main vehicle is controlled based on the first back-up yielding cost and the second back-up yielding cost. The first back-up yielding cost indicates the degree of difficulty for the main vehicle to back up and yield to the oncoming vehicle, and the second back-up yielding cost indicates the degree of difficulty for the oncoming vehicle to back up and yield to the main vehicle. Therefore, when the first back-up yielding cost is less than or equal to the second back-up yielding cost, the main vehicle is controlled to back up and yield to the oncoming vehicle. When the first back-up yielding cost is greater than the second back-up yielding cost, the oncoming vehicle is prompted to back up and yield to the main vehicle. This solves the problem of an autonomous driving vehicle being unable to decide whether to give way to an oncoming vehicle, resulting in sudden braking and being stuck, and realizes the decision of whether to give way to the oncoming vehicle after calculating the yielding cost based on road data and vehicle data. This ensures that the autonomous driving vehicle and social vehicles can meet on narrow and long roads, thereby improving the performance of the autonomous driving vehicle.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a schematic diagram of a scenario in which an autonomous driving vehicle meets another vehicle according to an embodiment of the present invention;

[0024] Figure 2 This is a flowchart of an autonomous driving vehicle control method provided in Example 1 of the present invention;

[0025] Figure 3 This is a flow chart of a method for controlling an autonomous driving vehicle provided in the second embodiment of the present invention;

[0026] Figure 4 This is a schematic structural diagram of an autonomous driving vehicle control device provided in Example 3 of the present invention;

[0027] Figure 5 It is a structural diagram of a vehicle control device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] Example 1

[0030] Figure 2 This is a flow chart of a method for controlling an autonomous vehicle provided in the first embodiment of the present invention. This embodiment is applicable to situations where an autonomous vehicle meets an oncoming vehicle on a long and narrow road. The method can be executed by an autonomous vehicle control device, which can be implemented in the form of hardware and / or software. The autonomous vehicle control device can be configured in a vehicle control device, such as an onboard computer of an autonomous vehicle, a background server that communicates with the autonomous vehicle, or other vehicle control devices. Figure 2 As shown, the automatic driving vehicle control method includes:

[0031] S201. During the driving of the host vehicle, determine whether the road condition of the road currently located by the host vehicle is a preset road condition.

[0032] Among them, the main vehicle is an autonomous driving vehicle. The width of the main vehicle's drivable area in the preset road condition is less than the preset width, and the length of the drivable area is greater than the preset length. The preset width is the width that can only allow one vehicle to pass through, and the preset length is N times the length of the main vehicle, where N can be greater than or equal to 3, that is, the preset road condition is a road condition similar to a "single-plank bridge".

[0033] like Figure 1 As shown, the road with the preset road condition may be a single-lane road, and the width of the single-lane road only allows one vehicle to pass through, such as Figure 1 The middle figure a shows a single lane road. Figure 1 In Figure a, the width W of the drivable area of ​​the main vehicle 1 is less than the preset width, and the length L of the drivable area is greater than the preset length, wherein the preset width is less than or equal to the sum of the widths of the main vehicle 1 and the oncoming vehicle 2, that is, the drivable area of ​​the main vehicle in the preset road condition is a narrow and long area.

[0034] The road with the preset road condition may also be a multi-lane road, but due to obstacles on the road, the road can only pass one vehicle, such as Figure 1 As shown in Figure b, the road is a two-lane road, but due to the presence of multiple continuous obstacles 3 on both sides of the road, the width W of the drivable area on the road is smaller than the preset width, and the length L is greater than the preset length.

[0035] It should be noted that Figure 1 The straight road in the figure is only used as an example. In actual scenarios, the road with preset road conditions may also be a curved road, which is not limited in this embodiment.

[0036] In an optional embodiment, semantic information of the road on which the main vehicle is located can be obtained from a preset semantic map based on the current position of the main vehicle. The semantic information includes the road type of the road. When the road type is a single lane and the length of the road is greater than a preset length, it is determined that the road condition of the road currently located by the main vehicle is the preset road condition, and S202 is executed.

[0037] In another optional embodiment, the road environment can also be sensed by sensors on the main vehicle to identify obstacles and then obtain a drivable area. When the length of the drivable area is greater than a preset length and the width is less than a preset width, it is determined that the road condition of the main vehicle is currently located as the preset road condition, and S202 is executed.

[0038] S202: When there is an oncoming vehicle on the road, obtain road data of the road and vehicle data of the vehicle on the road.

[0039] In this embodiment, the oncoming vehicle is a vehicle traveling in the opposite direction of the main vehicle. The oncoming vehicle can be a private vehicle or an autonomous driving vehicle. The main vehicle can perceive the driving environment through lidar, millimeter-wave radar, and camera to identify vehicles on the road and thus detect oncoming vehicles on the road.

[0040] Road data can include data such as the road curb position, lane line position, road shape and curvature, etc. The above road data can be obtained from the semantic map. Of course, road data can also be obtained through real-time perception by sensors on the main vehicle.

[0041] Vehicle data can be the status data of vehicles that can be perceived by the main vehicle on the road. For example, it can include data such as the position, speed, acceleration, vehicle type, and distance between vehicles of the main vehicle, the vehicle behind the main vehicle, the oncoming vehicle, and the vehicle behind the oncoming vehicle. The main vehicle can perceive the environment through sensors to identify vehicles and obtain vehicle data of each vehicle.

[0042] S203 : Calculate a first backing-off cost for the host vehicle and a second backing-off cost for the oncoming vehicle based on the road data and the vehicle data.

[0043] In this embodiment, the first back-up cost represents the degree of difficulty for the main vehicle to back up and give way to the oncoming vehicle, and the second back-up cost represents the degree of difficulty for the oncoming vehicle to back up and give way to the main vehicle. In the preset road conditions of this embodiment, the degree of difficulty for the main vehicle or the oncoming vehicle to back up and give way is related to factors such as the number of vehicles in the backing direction, the type of vehicle, and the shape of the road. The first back-up cost can be calculated by factors such as the number of vehicles behind the main vehicle, the type of vehicle, and the shape of the road, and the second back-up cost can be calculated by factors such as the number of vehicles behind the oncoming vehicle, the type of vehicle, and the shape of the road. In one example, weights can be set for various factors, and the weighted sum of various factors can be used to obtain the back-up cost. In another example, after setting the weights, the weighted average can be calculated as the back-up cost. This embodiment does not limit the method of calculating the back-up cost.

[0044] S204: Control the host vehicle according to the first backing-up yielding cost and the second backing-up yielding cost.

[0045] The smaller the vehicle's reversing yield cost, the less difficult it is for the vehicle to reversing and yield, and the more reasonable it is for the vehicle to reversing and yield. Therefore, the first reversing yield cost and the second reversing yield cost can be compared. If the first reversing yield cost of the main vehicle is smaller, the main vehicle is controlled to reverse and yield to the oncoming vehicle.

[0046] If the second backing-up cost of the oncoming vehicle is small, the main vehicle is controlled to send a backing-up signal to the oncoming vehicle to prompt the oncoming vehicle to back up and give way to the main vehicle. For example, the main vehicle can signal, honk, broadcast voice, display text messages, etc. to the rear vehicle. When the oncoming vehicle is detected to back up and give way, the main vehicle is controlled to continue driving forward.

[0047] In an embodiment of the present invention, when it is determined that the width of the main vehicle's drivable area is less than a preset width and the length of the drivable area is greater than a preset length during the main vehicle's driving, and when there is an oncoming vehicle on the road, a first back-up yielding cost for the main vehicle and a second back-up yielding cost for the oncoming vehicle are calculated based on road data and vehicle data, and the main vehicle is controlled based on the first back-up yielding cost and the second back-up yielding cost. The first back-up yielding cost indicates the degree of difficulty for the main vehicle to back up and yield to the oncoming vehicle, and the second back-up yielding cost indicates the degree of difficulty for the oncoming vehicle to back up and yield to the main vehicle. Therefore, when the first back-up yielding cost is less than or equal to the second back-up yielding cost, the main vehicle is controlled to back up and yield to the oncoming vehicle. When the first back-up yielding cost is greater than the second back-up yielding cost, the oncoming vehicle is prompted to back up and yield to the main vehicle. This solves the problem of an autonomous driving vehicle being unable to decide whether to give way to an oncoming vehicle, resulting in sudden braking and being stuck, and realizes the decision of whether to give way to the oncoming vehicle after calculating the yielding cost based on road data and vehicle data. This ensures that the autonomous driving vehicle and social vehicles can meet on narrow and long roads, thereby improving the performance of the autonomous driving vehicle.

[0048] Example 2

[0049] Figure 3 This is a flow chart of a method for controlling an autonomous vehicle provided in the second embodiment of the present invention. This embodiment of the present invention is optimized based on the above-mentioned first embodiment. Figure 3 As shown, the automatic driving vehicle control method includes:

[0050] S301 . While the host vehicle is traveling, obtain obstacle data on the road where the host vehicle is currently located through sensors.

[0051] Obstacles are objects on the road that hinder vehicle travel, such as parked vehicles, fallen trees, or fences built for road maintenance. Obstacle data can be the location, size, etc. of the obstacle, such as the length and width of the obstacle.

[0052] The sensor can be at least one of a high-frequency radar (millimeter wave), a lidar, a camera, or an ultrasonic radar. The sensor can be installed around the vehicle or on the roof. The sensor can acquire environmental data about the vehicle's current road and identify obstacles based on this environmental data, obtaining data such as the obstacle's location, size, and type.

[0053] S302: Determine a drivable area of ​​the host vehicle on the road based on obstacle data.

[0054] In this embodiment, the width of the drivable area of ​​the main vehicle in the preset road condition is smaller than the preset width, and the length of the drivable area is greater than the preset length. After determining the position, external dimensions and other data of the obstacle, the drivable area of ​​the main vehicle can be determined from the road in combination with the external dimensions of the main vehicle, the position of the obstacle, and the external dimensions of the obstacle.

[0055] like Figure 1 As shown in Figure b, multiple continuous obstacles 3 are detected on both sides of the road. The space between two obstacles 3 on the same side is not large enough to form an avoidance space for the main vehicle 1. The area between the multiple continuous obstacles 3 on both sides is the drivable area of ​​the main vehicle. The width of the drivable area is w and the length is L.

[0056] S303: When the width of the drivable area is smaller than the preset width and the length of the drivable area is larger than the preset length, determine that the road condition is the preset road condition.

[0057] In this embodiment, the preset width can be the width of a road that can only accommodate one vehicle. For example, the preset width can be 2.5 m. The preset length can be set according to the body length of the main vehicle. For example, the preset length can be greater than or equal to 3 times the body length of the main vehicle.

[0058] After determining the drivable area and obtaining the length and width of the drivable area, if the width of the drivable area is less than the preset width and the length is greater than the preset length, the drivable area is a narrow area that can only accommodate one vehicle, and the road condition of the road is determined to be the preset road condition. This embodiment determines the drivable area by detecting obstacle data, and determines that the road condition of the host vehicle's current road is the preset road condition when the width of the drivable area is less than the preset width and the length is greater than the preset length. This can identify the presence of narrow drivable areas formed by obstacles such as illegally parked vehicles on multi-lane roads, thereby determining whether the road condition of the host vehicle on the multi-lane road is the preset road condition.

[0059] In another optional embodiment, during the driving process of the main vehicle, semantic information of the road on which the main vehicle is currently located can be obtained from a pre-established semantic map. The semantic information includes the road type of the road, and it is determined whether the road type of the road is a single lane. The length of the road is also obtained. If the road type of the road is a single lane and the length is greater than a preset length, the road condition of the road is determined to be the preset road condition. For example, Figure 1 As shown in a, the main vehicle 1 can map its current position to the semantic map, and read the semantic information of the road where the mapped position of the main vehicle 1 is located in the semantic map. The voice information can indicate that the lane type of the road where the mapped position of the main vehicle 1 is located is a single lane. If the length of the road is greater than the preset length, it is determined that the main vehicle 1 is traveling on a narrow road that can only accommodate one vehicle, and the road condition of the road is determined to be the preset road condition.

[0060] The semantic information of the current road is obtained based on the semantic map, without the need to obtain environmental information to determine the road conditions, which is more efficient.

[0061] S304. When there is an oncoming vehicle on the road, first vehicle data of the vehicle behind the main vehicle, first road data of the road behind the main vehicle, second vehicle data of the vehicle behind the oncoming vehicle, and second road data of the road behind the oncoming vehicle are obtained through sensors.

[0062] In this embodiment, the first road data of the road behind the main vehicle may include data such as the length of the road behind the main vehicle, the shape of the road, etc., and the first vehicle data behind the main vehicle may include the number of vehicles behind the main vehicle, the type of vehicle, the estimated number of vehicles located in the blind spot when a blind spot exists, whether there are vehicles of a specified type, etc. Similarly, the second road data of the road behind the oncoming vehicle may include data such as the length of the road behind the oncoming vehicle, the shape of the road, etc., and the second vehicle data behind the oncoming vehicle may include the number of vehicles behind the oncoming vehicle, the type of vehicle, the estimated number of vehicles located in the blind spot when a blind spot exists, whether there are vehicles of a specified type, etc.

[0063] This embodiment can use sensors on the host vehicle to sense the environment and obtain environmental data. The environmental data can then be used to identify the number and type of vehicles, estimate the number of vehicles in the blind spot, and so on. For example, the acquired environmental data can be point cloud data, image data, or other data. The point cloud or image data can be input into the target detection model to obtain data on the number and type of vehicles. The host vehicle can also obtain road data such as the length and shape (e.g., curvature) of the road behind the host vehicle or behind oncoming vehicles from the semantic map. Of course, the host vehicle can also obtain road data such as the length and shape (e.g., curvature) of the road behind the host vehicle or behind oncoming vehicles through sensors.

[0064] S305 : Calculate a first retreating yielding cost for the host vehicle using the first vehicle data and the first road data.

[0065] After obtaining the first vehicle data and the first road data, a first backing-off cost of the host vehicle may be calculated based on the first vehicle data and the first road data. For example, a preset formula may be used to calculate the first backing-off cost.

[0066] In one example, the first retreat yield cost of the host vehicle can be calculated using the following formula:

[0067] DB=w1×len+w2×curv+w3×Sum(car_type_i)+w4×Est_bz+w5×Est_urgent

[0068] Wherein, len is the distance the main vehicle needs to back up when giving way in the first road data, curv is the road difficulty coefficient of the road behind the main vehicle in the first road data, Sum(car_type_i) is the coefficient sum of the vehicle types in the first vehicle data, Est_urgent is the total number of vehicles of the preset type in the first vehicle data, Est_bz is the number of vehicles in the blind spot of the estimated road in the first vehicle data, and w1, w2, w3, w4, and w5 are weights.

[0069] Among them, the reversing distance required by the main vehicle when reversing to give way is the distance from the current position to the road exit behind the main vehicle. The longer the required reversing distance is, the more difficult it is for the main vehicle to reversing to give way to the oncoming vehicle, and the greater the cost of the main vehicle's first reversing to give way.

[0070] The road difficulty coefficient is the difficulty factor when backing up to yield. Generally speaking, the more winding the road, the greater the difficulty of backing up. For example, the road can be discretized into 1-meter intervals, and the number of discretized points is F_len (rounded down). The road curvature corresponding to each discretized point is kappa_i. If kappa_i squared is kappa2_i, then: curv = Sum(kappa2_i), where i = 0, 1, 2, ..., F_len, and Sum is the summation formula.

[0071] Different types of vehicles behind the main vehicle mean different levels of difficulty for the rear vehicle to back up and give way. For example, when the vehicle is a large truck, since the large truck has a slower backing speed and requires a larger space for reversing and side parking, it is inconvenient to back up and give way, so the coefficient of the corresponding vehicle is larger; when the vehicle is a small car, since the small car has a faster backing speed and is more convenient to back up and give way, the coefficient of the corresponding vehicle is smaller. Calculating the sum of the coefficients of the vehicle types in the first vehicle data can be used as a concentrated representation of the types of vehicles behind the main vehicle.

[0072] The preset type of vehicle may be an emergency vehicle, that is, a vehicle that needs to pass quickly, such as an ambulance, a fire truck, a police car, etc. Then the weight w5 of Est_urgent may be set higher than the weights of other factors.

[0073] When detecting vehicles behind, the vehicle may have blind spots. This means the vehicle can also estimate the number of vehicles in the blind spot and use this estimate as a reference factor. Due to the uncertainty involved in estimating the number of vehicles in the blind spot, the weight w4 for Est_bz can be lower than that for other factors.

[0074] In one example of this embodiment, when a preset type of vehicle is present among the oncoming vehicles or behind the oncoming vehicle, such as a fire truck or ambulance, the host vehicle is controlled to reverse and yield. Similarly, when a preset type of vehicle is behind the host vehicle, the oncoming vehicle can be identified as the yielding vehicle, giving priority to the preset type of vehicle to quickly pass.

[0075] This embodiment calculates the first reversing yield cost of the main vehicle based on the weights and the first vehicle data and the first road data, taking into account multiple factors such as the reversing distance, the difficulty coefficient of the road, the coefficient of the vehicle type, the number of vehicles in the blind spot, and the preset type of vehicles. The importance of each factor is adjusted through weights, so that the first reversing yield cost of the main vehicle can be calculated more objectively and reasonably.

[0076] S306: Calculate a second yielding cost for the oncoming vehicle using the second vehicle data and the second road data.

[0077] The calculation method of the second retreat concession price is similar to that of the first retreat concession price, and reference may be made to S305 , which is not described here.

[0078] S307: Control the host vehicle according to the first backing-up yielding cost and the second backing-up yielding cost.

[0079] Optionally, it can be determined whether the first backing-up cost is greater than the second backing-up cost; if so, a prompt message is generated to prompt the oncoming vehicle to back up, and when the oncoming vehicle is detected to back up, the main vehicle is controlled to drive according to the planned driving trajectory; if not, the main vehicle is controlled to reverse and yield.

[0080] The smaller the retreat cost, the more reasonable it is for the vehicle to retreat. Therefore, the first retreat cost of the main vehicle and the second retreat cost of the oncoming vehicle can be compared, and the party with the smaller retreat cost can be selected as the one giving way, making the vehicle avoidance decision more reasonable.

[0081] When the second backing-up cost of the oncoming vehicle is small, the host vehicle is controlled to generate prompt information to prompt the oncoming vehicle to back up, such as flashing lights and honking the horn, and when the oncoming vehicle is detected to back up, the host vehicle can be controlled to continue driving according to the planned driving trajectory.

[0082] In an optional embodiment of the present invention, after the prompt information is generated, if the oncoming vehicle is not detected to back up and give way within a preset time period, the main vehicle is controlled to back up and give way to avoid the main vehicle and the oncoming vehicle being stuck on the road and causing traffic jams.

[0083] In an optional embodiment of the present invention, before controlling the main vehicle according to the first back-up yielding cost and the second back-up yielding cost, a prompt message is sent to the remote monitoring server to prompt the back-end personnel to remotely monitor the main vehicle. By having the back-end personnel monitor the main vehicle, on the one hand, the correctness of the main vehicle's execution of the yielding strategy can be monitored. On the other hand, if the main vehicle is executing the yielding strategy and the owners of other vehicles do not cooperate, for example, when the main vehicle wants to back up and yield, the owners of the vehicles behind the main vehicle are unwilling to back up and yield, at this time the back-end personnel can remotely communicate with the owners of other vehicles, or go to the scene to handle it.

[0084] In an embodiment of the present invention, when it is determined that the width of the main vehicle's drivable area is less than a preset width and the length of the drivable area is greater than a preset length during the main vehicle's driving, and when there is an oncoming vehicle on the road, a first back-up yielding cost for the main vehicle and a second back-up yielding cost for the oncoming vehicle are calculated based on road data and vehicle data, and the main vehicle is controlled based on the first back-up yielding cost and the second back-up yielding cost. The first back-up yielding cost indicates the degree of difficulty for the main vehicle to back up and yield to the oncoming vehicle, and the second back-up yielding cost indicates the degree of difficulty for the oncoming vehicle to back up and yield to the main vehicle. Therefore, when the first back-up yielding cost is less than or equal to the second back-up yielding cost, the main vehicle is controlled to back up and yield to the oncoming vehicle. When the first back-up yielding cost is greater than the second back-up yielding cost, the oncoming vehicle is prompted to back up and yield to the main vehicle. This solves the problem of an autonomous driving vehicle being unable to decide whether to give way to an oncoming vehicle, resulting in sudden braking and being stuck, and realizes the decision of whether to give way to the oncoming vehicle after calculating the yielding cost based on road data and vehicle data. This ensures that the autonomous driving vehicle and social vehicles can meet on narrow and long roads, thereby improving the performance of the autonomous driving vehicle. On the other hand, this embodiment calculates the cost of a vehicle's reversing and yielding based on weights, vehicle data, and road data, taking into account multiple factors such as the reversing distance, the difficulty coefficient of the road, the coefficient of the vehicle type, the number of vehicles in the blind spot, and the preset type of vehicles. The importance of each factor is adjusted through weights, so that the cost of a vehicle's reversing and yielding can be calculated more objectively and reasonably.

[0085] Example 3

[0086] Figure 4 This is a schematic diagram of the structure of an automatic driving vehicle control device provided by the fourth embodiment of the present invention. Figure 4 As shown, the automatic driving vehicle control device includes:

[0087] The road condition determination module 401 is configured to determine whether the road condition of the main vehicle is a preset road condition during the main vehicle's driving process, wherein the preset road condition is that the width of the main vehicle's drivable area is less than a preset width and the length of the drivable area is greater than a preset length;

[0088] An environmental data acquisition module 402 is configured to acquire road data of the road and vehicle data of vehicles on the road when there is an oncoming vehicle on the road;

[0089] A back-up yielding cost calculation module 403 is configured to calculate a first back-up yielding cost for the host vehicle and a second back-up yielding cost for the oncoming vehicle based on the road data and the vehicle data;

[0090] The vehicle control module 404 is configured to control the host vehicle according to the first backing-up yielding cost and the second backing-up yielding cost.

[0091] Optionally, the road condition judgment module 401 includes:

[0092] A semantic information acquisition submodule is used to acquire semantic information of the road on which the main vehicle is currently located from a pre-established semantic map during the main vehicle's driving process, wherein the semantic information includes the road type of the road;

[0093] a judgment submodule, configured to judge whether the road type of the road is a single lane, and obtain the length of the road;

[0094] The first road condition determination submodule is configured to determine that the road condition of the road is a preset road condition when the road type of the road is a single lane and the length of the road is greater than a preset length.

[0095] Optionally, the road condition judgment module 401 further includes:

[0096] The obstacle data acquisition submodule is used to acquire obstacle data on the road where the main vehicle is currently located through sensors during the main vehicle's driving process;

[0097] a drivable area determination submodule, configured to determine a drivable area of ​​the host vehicle on the road based on the obstacle data;

[0098] The second road condition determination submodule determines that the road condition is a preset road condition when the width of the drivable area is smaller than the preset width and the length of the drivable area is larger than the preset length.

[0099] Optionally, the environmental data acquisition module 402 includes:

[0100] The environmental data acquisition submodule is used to acquire first vehicle data of the vehicle behind the main vehicle, first road data of the road behind the main vehicle, second vehicle data of the vehicle behind the oncoming vehicle, and second road data of the road behind the oncoming vehicle through sensors.

[0101] Optionally, the back-off cost calculation module 403 includes:

[0102] a first backing-off cost calculation submodule, configured to calculate a first backing-off cost for the host vehicle using the first vehicle data and the first road data;

[0103] The second backing-off cost calculation submodule is configured to calculate a second backing-off cost for the oncoming vehicle using the second vehicle data and the second road data.

[0104] Optionally, the first fallback cost calculation submodule includes:

[0105] The first back-off cost calculation unit is used to calculate the first back-off cost using the following formula: DB = w1×len+w2×curv+w3×Sum(car_type_i)+w4×Est_bz+w5×Est_urgent

[0106] Among them, len is the distance that the main vehicle needs to retreat when giving way in the first road data, curv is the road difficulty coefficient of the road behind the main vehicle in the first road data, Sum(car_type_i) is the coefficient sum of the vehicle types in the first vehicle data, Est_urgent is the total number of vehicles of the preset type in the first vehicle data, Est_bz is the number of vehicles estimated in the blind spot of the road in the first vehicle data, and w1, w2, w3, w4, and w5 are weights.

[0107] Optionally, the vehicle control module 404 further includes:

[0108] a retreat concession cost comparison submodule, configured to determine whether the first retreat concession cost is greater than the second retreat concession cost;

[0109] an oncoming vehicle yield prompting submodule, configured to generate a prompt message to prompt the oncoming vehicle to back up when the first backing-up yielding cost is greater than the second backing-up yielding cost, and to control the host vehicle to travel according to the planned driving trajectory when the oncoming vehicle backs up and yields;

[0110] The host vehicle yielding control submodule is configured to control the host vehicle to reverse and yield when the first yielding cost is less than the second yielding cost.

[0111] Optionally, the vehicle control module 404 further includes:

[0112] The host vehicle yielding control submodule is used to control the host vehicle to reverse and yield when the oncoming vehicle is not detected to reverse and yield within a preset time period.

[0113] Optionally, the autonomous driving vehicle control device further includes:

[0114] The prompt information sending module is used to send prompt information to the remote monitoring server to prompt the backstage personnel to remotely monitor the main vehicle.

[0115] The autonomous driving vehicle control device provided in the embodiment of the present invention can execute the autonomous driving vehicle control method provided in the first and second embodiments of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0116] Example 4

[0117] Figure 5A schematic diagram of a vehicle control device 50 that can be used to implement an embodiment of the present invention is shown. Vehicle control device 50 is intended to represent devices including various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.

[0118] like Figure 5 As shown, the vehicle control device includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52, a random access memory (RAM) 53, etc., which is communicatively connected to the at least one processor 51. The memory stores a computer program that can be executed by the at least one processor, and the processor 51 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 52 or the computer program loaded from the storage unit 58 to the random access memory (RAM) 53. Various programs and data required for the operation of the vehicle control device 50 can also be stored in the RAM 53. The processor 51, ROM 52, and RAM 53 are connected to each other via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0119] Multiple components in the vehicle control device 50 are connected to the I / O interface 55, including an input unit 56, such as a keyboard, a mouse, a camera for acquiring depth images, etc.; an output unit 57, such as various types of displays, speakers, etc.; a storage unit 58, such as a magnetic disk, an optical disk, etc.; and a communication unit 59, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 59 allows the vehicle control device 50 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0120] The processor 51 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 51 executes the various methods and processes described above, such as the autonomous vehicle control method.

[0121] In some embodiments, the autonomous vehicle control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as a storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or installed on the vehicle control device 50 via the ROM 52 and / or the communication unit 59. When the computer program is loaded into the RAM 53 and executed by the processor 51, one or more steps of the autonomous vehicle control method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the autonomous vehicle control method in any other appropriate manner (e.g., by means of firmware).

[0122] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0124] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on a vehicle control device 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the vehicle control device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0126] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, 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), a blockchain network, and the Internet.

[0127] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0128] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0129] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for controlling an autonomous vehicle, characterized in that: include: During the driving process of the main vehicle, determining whether the road condition of the road currently located by the main vehicle is a preset road condition, in which the width of the drivable area of ​​the main vehicle is less than a preset width and the length of the drivable area is greater than a preset length; If there is an oncoming vehicle on the road, first vehicle data of the vehicle behind the host vehicle, first road data of the road behind the host vehicle, second vehicle data of the vehicle behind the oncoming vehicle, and second road data of the road behind the oncoming vehicle are acquired through sensors; Calculating a first retreat yield cost for the host vehicle using the first vehicle data and the first road data; Calculating a second yielding cost for the oncoming vehicle using the second vehicle data and the second road data; controlling the host vehicle according to the first backing-up yielding cost and the second backing-up yielding cost; The first retreat concession cost is calculated using the following formula: DB=w1×len+w2×curv+w3×Sum(car_type_i)+w4×Est_bz+w5×Est_urgent; Among them, len is the distance that the main vehicle needs to retreat when giving way in the first road data, curv is the road difficulty coefficient of the road behind the main vehicle in the first road data, Sum(car_type_i) is the coefficient sum of the vehicle types in the first vehicle data, Est_urgent is the total number of vehicles of the preset type in the first vehicle data, Est_bz is the estimated number of vehicles in the blind spot of the road in the first vehicle data, and w1, w2, w3, w4, and w5 are weights.

2. The method according to claim 1, wherein During the driving process of the host vehicle, determining whether the road condition of the road currently located by the host vehicle is a preset road condition includes: During the driving process of the host vehicle, semantic information of the road on which the host vehicle is currently located is obtained from a pre-established semantic map, wherein the semantic information includes the road type of the road; Determining whether the road type of the road is a single lane, and obtaining the length of the road; When the road type of the road is a single lane and the length is greater than a preset length, it is determined that the road condition of the road is a preset road condition.

3. The method according to claim 1, wherein During the driving process of the host vehicle, determining whether the road condition of the road currently located by the host vehicle is a preset road condition includes: While the main vehicle is traveling, data of obstacles on the road currently located by the main vehicle is acquired through sensors; determining a drivable area of ​​the host vehicle on the road according to the obstacle data; When the width of the drivable area is smaller than the preset width and the length of the drivable area is larger than the preset length, it is determined that the road condition of the road is the preset road condition.

4. The method according to any one of claims 1 to 3, wherein The controlling the host vehicle according to the first backing-off cost and the second backing-off cost includes: determining whether the first retreat concession price is greater than the second retreat concession price; If yes, a prompt message is generated to prompt the oncoming vehicle to back up, and when the oncoming vehicle is detected to back up and yield, the host vehicle is controlled to drive according to the planned driving trajectory; If not, control the host vehicle to reverse and give way.

5. The method according to claim 4, wherein After generating the prompt information, it also includes: When the oncoming vehicle is not detected to back up and yield within a preset time period, the host vehicle is controlled to back up and yield.

6. The method according to any one of claims 1 to 3, wherein: The vehicle data includes the type of the vehicle behind the oncoming vehicle, and after obtaining the road data of the road and the vehicle data of the vehicles on the road, further includes: When the vehicles behind the oncoming vehicle include vehicles of a preset type, the host vehicle is controlled to reverse and give way.

7. The method according to any one of claims 1 to 3, wherein: Before controlling the host vehicle according to the first retreat yielding cost and the second retreat yielding cost, the method further includes: Send a prompt message to the remote monitoring server to prompt the backend personnel to remotely monitor the host vehicle.

8. An automatic driving vehicle control device, characterized in that: include: a road condition determination module, configured to determine, during the driving process of the host vehicle, whether the road condition of the road currently on which the host vehicle is located is a preset road condition, wherein the width of the drivable area of ​​the host vehicle in the preset road condition is less than a preset width and the length of the drivable area is greater than a preset length; an environmental data acquisition module, configured to acquire road data of the road and vehicle data of vehicles on the road when there is an oncoming vehicle on the road; a back-up yielding cost calculation module, configured to calculate a first back-up yielding cost for the host vehicle and a second back-up yielding cost for the oncoming vehicle based on the road data and the vehicle data; a vehicle control module, configured to control the host vehicle according to the first backing-up yielding cost and the second backing-up yielding cost; The environmental data acquisition module includes: an environmental data acquisition submodule, configured to acquire, through sensors, first vehicle data of a vehicle behind the main vehicle, first road data of a road behind the main vehicle, second vehicle data of a vehicle behind the oncoming vehicle, and second road data of the road behind the oncoming vehicle; The back-off cost calculation module includes: a first backing-off cost calculation submodule, configured to calculate a first backing-off cost for the host vehicle using the first vehicle data and the first road data; a second retreat yield cost calculation submodule, configured to calculate a second retreat yield cost for the oncoming vehicle using the second vehicle data and the second road data; The first back-off cost calculation submodule includes: The first retreat concession cost calculation unit is used to calculate the first retreat concession cost using the following formula: DB=w1×len+w2×curv+w3×Sum(car_type_i)+w4×Est_bz+w5×Est_urgent; Among them, len is the distance that the main vehicle needs to retreat when giving way in the first road data, curv is the road difficulty coefficient of the road behind the main vehicle in the first road data, Sum(car_type_i) is the coefficient sum of the vehicle types in the first vehicle data, Est_urgent is the total number of vehicles of the preset type in the first vehicle data, Est_bz is the estimated number of vehicles in the blind spot of the road in the first vehicle data, and w1, w2, w3, w4, and w5 are weights.

9. A vehicle control device, characterized in that: The vehicle control device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the autonomous driving vehicle control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the automatic driving vehicle control method according to any one of claims 1 to 7 when executed.

Images