Security pass method, apparatus, electronic device, and storage medium

Abstract

The method comprises the following steps: acquiring a target obstacle within a preset distance range according to a vehicle-mounted sensor; acquiring a blind area polygon of a perception blind area based on the target obstacle; obtaining a relationship lane associated with a current lane of a vehicle according to a high-definition map; acquiring a collision intersection between the relationship lane and the blind area polygon, and determining a target intersection as the collision intersection closest to the current lane of the vehicle; and determining an expected speed of the vehicle according to the target intersection, so as to reduce a collision risk between the vehicle and an obstacle in the perception blind area. The method improves the driving safety of an autonomous vehicle in a driving environment with a blind area, and reduces the production cost.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of automatic driving, in particular to a safe passing method and device, electronic equipment and storage medium. BACKGROUND

[0002] In automatic driving, the vehicle obtains environmental information completely depending on vehicle-mounted sensors, such as laser radar, millimeter wave radar, camera, etc. Through these sensors, after a series of perception algorithms, the information is transmitted to the vehicle-mounted core controller, so that the automatic driving vehicle can run a series of decision planning algorithms according to the information, and can control the vehicle to move autonomously in a complex environment. These sensors are generally installed on the top of the vehicle, which is farther than the distance seen by humans, but if there is a vehicle or a wall on the side, it will block a part of the sensor's view angle (blind area), causing the sensor to be unable to observe the intersection in front of the left or right, which brings a certain safety risk to the automatic driving vehicle. If a fast obstacle suddenly appears in the blind area at this time, the automatic driving vehicle may not be able to avoid in time, thereby causing a dangerous accident. The same is true for human drivers driving, there will also be a certain perception blind area, but the human driver will make some flexible actions according to the environment, so that driving can be safer and more reliable. But for the automatic driving vehicle, if it is not perceived, it is considered safe at this time, and it cannot understand the environment like a human.

[0003] At present, the solution to the perception blind area in the automatic driving vehicle is that Baidu automatic driving adopts a vehicle-road cooperation technology, that is, a vehicle-road system device is installed at each traffic intersection, which has a camera and can perceive the environment in the intersection in real time, and send the information to the automatic driving vehicle about to enter the intersection. This method has two shortcomings, first, it increases the vehicle-road cooperation device at each intersection, which consumes a lot of manpower and material resources, and increases the cost, second, the blind area is not completely generated in the intersection, and there may be a vehicle parked by the road, and a road extends in front of the vehicle, which will also cause a blind area and a collision risk, at this time the vehicle-road cooperation technology cannot solve this problem. SUMMARY

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a safe passing method, device, electronic equipment and storage medium, which improves the driving safety of the automatic driving vehicle in the driving environment with a blind area, and reduces the production cost.

[0005] In a first aspect, embodiments of this disclosure provide a safe passage method, the method comprising: acquiring target obstacles within a preset distance range using vehicle-mounted sensors; acquiring blind zone polygons of a perception blind zone based on the target obstacles; obtaining a relational lane associated with the current lane of the vehicle using a high-precision map; acquiring collision intersection points between the relational lanes and the blind zone polygons, and determining the collision intersection point closest to the current lane of the vehicle as a target intersection point; and determining the desired speed of the vehicle based on the target intersection point to reduce the collision risk between the vehicle and obstacles located in the perception blind zone.

[0006] Secondly, embodiments of this disclosure also provide a safe passage device, which includes: a first acquisition module, configured to acquire target obstacles within a preset distance range based on vehicle-mounted sensors; a second acquisition module, configured to acquire a blind zone polygon based on the target obstacles; a first determination module, configured to obtain a relational lane associated with the current lane of the vehicle based on a high-precision map; a second determination module, configured to acquire the collision intersection point between the relational lane and the blind zone polygon, and determine the collision intersection point closest to the current lane of the vehicle as the target intersection point; and a third determination module, configured to determine the desired speed of the vehicle based on the target intersection point, so as to reduce the collision risk between the vehicle and obstacles in the perception blind zone.

[0007] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the secure passage method as described above.

[0008] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the secure passage method described above.

[0009] This disclosure provides a safe passage method that obtains a perception blind zone polygon based on onboard sensors and target obstacles, and determines the target intersection point based on the collision intersection point between the lane and the blind zone polygon. The method then determines the desired speed of the vehicle based on the target intersection point, thus solving the problem of blind zones caused by excessively large target obstacles within the perception range of onboard sensors, which prevents autonomous vehicles from perceiving other obstacles behind the blind zone. This reduces the cost of vehicle-road cooperation and improves the safety of vehicle passage. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0011] Figure 1 This is a flowchart of a safe passage method according to an embodiment of the present disclosure;

[0012] Figure 2 This is a schematic diagram of a blind zone polygon of a target obstacle in an embodiment of this disclosure;

[0013] Figure 3 This is a schematic diagram of a lane relationship in an embodiment of this disclosure;

[0014] Figure 4 This is a schematic diagram of the collision intersection point between a lane and a blind spot polygon in one embodiment of this disclosure;

[0015] Figure 5 This is a schematic diagram of a road surface scenario under limited conditions according to an embodiment of this disclosure;

[0016] Figure 6 This is a schematic diagram of the structure of a safe passage device according to an embodiment of this disclosure;

[0017] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. Detailed Implementation

[0018] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0020] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0021] Currently, Baidu's autonomous driving solution for blind spots in autonomous vehicles employs vehicle-to-infrastructure (V2I) technology. This involves installing a V2I system at each intersection, equipped with cameras, to perceive the intersection environment in real time and send information to autonomous vehicles approaching the intersection. This approach has two drawbacks: First, adding V2I devices to every intersection is extremely resource-intensive and increases costs. Second, blind spots are not limited to intersections; they can also occur if a vehicle is parked on the side of the road or if a road extends out in front of the vehicle, creating a blind spot and posing a collision risk. In such cases, V2I technology cannot address the problem.

[0022] To address the aforementioned issues, this disclosure provides a safe passage method that solves the problem of blind spots caused by excessively large target obstacles within the perception range of vehicle-mounted sensors, preventing autonomous vehicles from perceiving other obstacles behind the blind spots. This reduces the cost of vehicle-road cooperation and improves the safety of vehicle passage. Figure 1 This is a flowchart illustrating a secure passage method according to an embodiment of this disclosure. The method can be executed by a secure passage device, which can be implemented in software and / or hardware and can be configured in an electronic device, such as a server.

[0023] like Figure 1 As shown, the method may specifically include the following steps:

[0024] Step 110: Based on the vehicle-mounted sensors, acquire target obstacles within a preset distance range.

[0025] In one embodiment, acquiring target obstacles within a preset distance range using vehicle-mounted sensors includes: acquiring all obstacles within the preset distance range using the vehicle-mounted sensors; filtering all obstacles by type to acquire a first set of filtered obstacles; and identifying the first obstacle whose height is greater than the height of the vehicle as a target obstacle. Specifically, firstly, the vehicle-mounted sensors detect all obstacles within a range of 100 to 200 meters, filtering out obstacles such as pedestrians and bicycles that cannot obstruct the sensor's blind spot, and then calculating obstacles of the car, truck, and cargo types; comparing the height of the vehicle with the height of the car, truck, and cargo types of obstacles, identifying obstacles taller than the vehicle, and identifying these obstacles as target obstacles. It is determined that these target obstacles may have detection blind spots for the vehicle-mounted sensors.

[0026] Step 120: Based on the target obstacle, obtain the blind zone polygon of the perception blind zone.

[0027] In one embodiment, based on the positional relationship between the target obstacle and the vehicle-mounted sensor, the tangent point of the target obstacle and the tangent line starting from the vehicle-mounted sensor and passing through the tangent point are obtained based on a first preset algorithm; the tangent line is extended by a preset length in a direction away from the vehicle to obtain a vertex; and the blind zone polygon of the perception blind zone is determined based on the tangent point and the vertex. Figure 2 This is a schematic diagram of the blind zone polygon of a target obstacle according to an embodiment of this disclosure; as shown. Figure 2 As shown, based on the installation location of the vehicle-mounted sensor, such as the installation location of the vehicle's ego LiDAR, the tangent point of the target obstacle obj and the tangent line of the maximum angle enveloping the obstacle are obtained based on a first preset algorithm. The first preset algorithm includes brute-force search, binary search, etc. This invention uses the brute-force search method to obtain two tangent points, point_1 and point_2, between the target obstacle obj and the vehicle's ego. Extending the tangent line backwards away from the LiDAR by blind_area_length yields two vertices, denoted as point_3 and point_4. Connecting point_1, point_2, point_3, and point_4 sequentially forms a blind zone polygon. Here, blind_area_length is the distance extended backwards along the tangent line from the tangent point, obj is the obstacle and its shape perceived by the LiDAR, and lidar_pose is the installation location of the LiDAR.

[0028] Step 130: Based on the high-precision map, obtain the lanes associated with the current lane of this vehicle.

[0029] Figure 3 This is a schematic diagram of a relational lane in one embodiment of this disclosure. Based on a high-precision map, relational lanes associated with the current lane of the vehicle are obtained. Specifically, based on the pre-obtained high-precision map, we find lanes that intersect with the lane where the vehicle is located, such as merging lanes and crossing lanes. We define merging lanes and crossing lanes as relational lanes. For public roads, we assume that blind spots, such as vehicles, can only occur in relational lanes; therefore, the concept of blind spots only exists when relational lanes exist. See details in the reference section. Figure 3 As shown, the lanes associated with the lane ego_lane301 where this vehicle is located include merging lanes merge_lane_1401 and merge_lane_2402 that merge into this vehicle's lane, and crossing lanes cross_lane_1501 and cross_lane_2302 that cross this vehicle's lane.

[0030] Step 140: Obtain the collision intersection point of the relationship lane and the blind spot polygon, and determine the collision intersection point that is closest to the current lane of the vehicle as the target intersection point.

[0031] In one embodiment, obtaining the collision intersection point between the relational lane and the blind spot polygon includes...

[0032] Obtain sampling points corresponding to the lane in the high-precision map; traverse all sampling points based on a second preset algorithm to obtain at least one set of adjacent first and second sampling points, wherein the first sampling point is located outside the blind zone polygon, and the second sampling point is located inside the blind zone polygon; obtain sampling point rays based on the first and second sampling points; determine the intersection point between the sampling point rays and the blind zone polygon based on a collision detection algorithm, and determine the intersection point as the collision point between the lane and the blind zone polygon. Specifically, as follows... Figures 3-4 As shown, since the relationship lanes are often curved, there is currently no mathematical method to calculate the intersection point of the curve and the blind zone polygon. Therefore, this invention combines sampling and collision detection algorithms to obtain the collision intersection point of the blind zone polygon and the curve of the relationship lane. First, when we make high-precision maps, we have already sampled the relationship lanes and set a node point at a certain distance in the relationship lanes. The starting point of a relationship lane is node(1), and the ending point is node(n). Starting from node(1), we sequentially traverse to node(n) based on preset algorithms, such as area discrimination, angle discrimination, ray discrimination, etc. This invention uses the ray discrimination method to find the first sampling point and the second sampling point, such as Figure 4As shown, the current lane of this vehicle is ego_lane301, and the related lane is merge_lane_1401. The first set of adjacent sampling points is found: a first sampling point node(i-1) located outside the polygon and a second sampling point node(i) located inside the polygon. The second set of adjacent sampling points is found: a first sampling point node(k) located outside the polygon and a second sampling point node(k-1) located inside the polygon. A ray line_1 is drawn connecting the first sampling point node(i-1) and the second sampling point node(i). The collision intersection point between ray line_1 and the blind zone polygon is obtained using the collision detection algorithm and is denoted as point_1. A ray line_2 is drawn connecting the first sampling point node(k) and the second sampling point node(k-1). The intersection point between ray line_2 and the blind zone polygon is obtained using the collision detection algorithm and is identified as the collision intersection point, denoted as point_2. Therefore, the collision intersection points point_1 and point_2 between the blind zone polygon and the related lane merge_lane_1 are obtained. Collision detection algorithms include physical ray casting and GJK algorithms; this invention uses the Racast algorithm. Figure 3 As shown, the blind spot polygon can intersect with multiple related lanes, and each related lane adopts the above-mentioned... Figure 4 The collision point is obtained in this way.

[0033] In one embodiment, after obtaining the collision intersection point, the collision intersection point closest to the vehicle's current lane (ego_lane) is determined as the target intersection point. Specifically, after obtaining the collision intersection point, the distance from the collision intersection point to the vehicle's current lane is compared, with reference to... Figure 3 The system retrieves the collision points of related lanes 302 and 401, compares these points, and identifies the collision point closest to the vehicle's current lane 301 among all collision points in both lanes as the target intersection. (See detailed reference.) Figure 4 The distances from the collision intersection point_1 and the collision intersection point_2 to the current lane ego_lane of the vehicle are compared. It is determined that the distance from the collision intersection point_1 to the current lane ego_lane of the vehicle is less than the distance from the collision intersection point_2 to the current lane ego_lane of the vehicle. Therefore, the collision intersection point_1 is determined as the target intersection point.

[0034] Step 150: Determine the desired speed of the vehicle based on the target intersection point.

[0035] In one embodiment, the collision position at the intersection of the vehicle's current lane and the related lane is obtained; the maximum deceleration of the vehicle, the first distance from the vehicle's first current position to the collision position, and the second distance from the target intersection to the collision position are obtained; based on the relationship of relevant quantities under limited conditions, the desired speed of the vehicle is determined, wherein the relevant quantities include the speed of the assumed obstacle, the length of the assumed obstacle, the maximum deceleration of the vehicle, the first distance, and the second distance.

[0036] In one embodiment, the limiting condition is that when the vehicle decelerates uniformly from the first current position to the collision position at the maximum deceleration, the assumed obstacle moves uniformly from the target intersection position to the first position (B) at the speed of the assumed obstacle, and the distance the vehicle travels uniformly from the first current position to the collision position at the maximum deceleration is the first distance; the distance the assumed obstacle travels uniformly from the target intersection position to the first position (B) is the sum of the second distance and the length of the assumed obstacle. Specifically, refer to... Figure 5 As shown, the collision intersection point point_1 is determined as the target intersection point. Assuming there is a hypothetical obstacle obj at the target intersection point, based on the road network, the velocity obj_vel of the hypothetical obstacle obj and the second distance obj_dist_to_intersect from the target intersection point point_1 to the collision position O (assuming the obstacle is at position C) are determined. The distance traveled by the vehicle from its first current position M to the collision position O (assuming the vehicle is at position A) with maximum deceleration ego_max_dec is the first distance ego_dist_to_intersect. The collision position O is the position where the hypothetical obstacle collides with the vehicle when the vehicle is at position A and the obstacle is at position C. Wherein, under the condition that the vehicle decelerates uniformly from the first current position M to the collision position O at the maximum deceleration ego_max_dec, it is assumed that the speed of the obstacle obj is uniform from the target intersection point point_1 to the first position B, and the distance of the speed of the obstacle obj is uniform from the target intersection point point_1 to the first position B is the sum of the second distance and the assumed length of the obstacle.

[0037] In one embodiment, the relationship between the relevant quantities under the defined conditions is as follows:

[0038]

[0039]

[0040] ego_dist_to_intersect=ego_expect_vel*min(obj_t,ego_max_dec_t)+0.5*ego_max_dec*min(obj_t,ego_max_dec_t)*min(obj_t,ego_max_dec_t)(3)

[0041] Wherein, ego_dist_to_intersect represents the first distance, obj_dist_to_intersect represents the second distance, obj_length represents the length of the assumed obstacle, ego_expect_vel represents the expected speed of the vehicle, obj_vel represents the speed of the assumed obstacle, ego_max_dec represents the maximum deceleration of the vehicle, ego_max_dec_t represents the time taken for the vehicle to travel the first distance from the first current position, and obj_t represents the time taken for the assumed obstacle to reach the first position (B) at a constant speed from the target intersection position at the assumed obstacle speed.

[0042] In one embodiment, a first maximum speed limit for the vehicle to reach the collision location is obtained based on the time taken for the assumed obstacle to travel at a constant speed from the target intersection position to the first position (B); a second maximum speed limit for the vehicle to reach the collision location is obtained based on the first distance and the time taken for the vehicle to travel the first distance from the first current position; the speed limit values ​​of the first maximum speed limit and the second maximum speed limit are compared, and the maximum speed limit with the smallest speed limit value is determined as the desired speed.

[0043] Formula (3) can be written in the form of formulas (4) and (5), where the expected speed ego_expect_vel includes the first maximum speed limit ego_expect_vel-1 and the second maximum speed limit ego_expect_vel-2.

[0044] ego_dist_to_intersect=ego_expect_vel-1*obj_t+0.5*ego_max_dec*obj_t*obj_t (4)

[0045] ego_dist_to_intersect=ego_expect_vel-2*ego_max_dec_t+0.5*ego_max_dec*ego_max_dec_t*ego_max_dec_t (5)

[0046] Specifically, based on the obj_t obtained by formula (1) above, the obj_t is substituted into formula (4) to obtain the first maximum speed limit ego_expect_vel-1. Then, based on the formulas (2) and (5) above, the second maximum speed limit ego_expect_vel-2 is obtained. The speed limit values ​​of the first maximum speed limit ego_expect_vel-1 and the second maximum speed limit ego_expect_vel-2 are compared, and the maximum speed limit with the smallest speed limit value is determined as the desired speed.

[0047] This embodiment provides a safe passage method that obtains a perception blind zone polygon based on onboard sensors and target obstacles, and determines the target intersection point based on the collision intersection point between the lane and the blind zone polygon. The method then determines the desired speed of the vehicle based on the target intersection point, thus solving the problem of blind zones caused by excessively large target obstacles within the perception range of onboard sensors, which prevents autonomous vehicles from perceiving other obstacles behind the blind zone. This reduces the cost of vehicle-road cooperation and improves the safety of vehicle passage.

[0048] Figure 6 This is a schematic diagram of the structure of a safe passage device according to an embodiment of this disclosure. Figure 6 As shown, the device includes: a first acquisition module 210, a second acquisition module 220, a first determination module 230, a second determination module 240, and a third determination module 250. The first acquisition module 210 is used to acquire target obstacles within a preset distance range based on vehicle-mounted sensors. The second acquisition module 220 acquires a blind zone polygon based on the target obstacles. The first determination module 230 obtains a relational lane associated with the vehicle's current lane based on a high-precision map. The second determination module 240 acquires the collision intersection points between the relational lanes and the blind zone polygon, and determines the collision intersection point closest to the vehicle's current lane as the target intersection point. The third determination module 250 determines the vehicle's desired speed based on the target intersection point to reduce the collision risk between the vehicle and obstacles in the perception blind zone.

[0049] Optionally, the first acquisition module 210 includes a first acquisition unit, which is used to acquire all obstacles within a preset distance range through the vehicle-mounted sensor, filter all obstacles by type, acquire the first obstacle after filtering, and determine the first obstacle among the first obstacles whose height is greater than the height of the vehicle as the target obstacle.

[0050] Optionally, the second acquisition module 220 includes a second acquisition unit, which is used to: acquire the tangent point of the target obstacle and the tangent line starting from the vehicle sensor and passing through the tangent point based on the positional relationship between the target obstacle and the vehicle sensor, according to a first preset algorithm; extend the tangent line along a preset length away from the vehicle to obtain a vertex; and determine the blind zone polygon of the perception blind zone based on the tangent point and the vertex.

[0051] Optionally, the second determining module 240 includes a third acquisition unit, which is used to: acquire sampling points in the high-precision map corresponding to the lane in question; traverse all the sampling points based on a second preset algorithm to acquire at least one set of adjacent first sampling points and second sampling points, wherein the first sampling point is located outside the blind zone polygon and the second sampling point is located inside the blind zone polygon; acquire sample point rays based on the first sampling points and the second sampling points; determine the intersection point of the sample point rays and the blind zone polygon based on a collision detection algorithm, and determine the intersection point as the collision point between the lane in question and the blind zone polygon.

[0052] Optionally, the third determining module 250 includes a first determining unit, which is used to: obtain the collision position at the intersection of the current lane of the vehicle and the related lane; obtain the maximum deceleration of the vehicle, the first distance from the first current position of the vehicle to the collision position, and the second distance from the target intersection to the collision position; and determine the expected speed of the vehicle based on the relationship of relevant quantities under limited conditions, wherein the relevant quantities include the speed of the assumed obstacle, the length of the assumed obstacle, the maximum deceleration of the vehicle, the first distance, and the second distance.

[0053] The limiting conditions are as follows: when the vehicle decelerates uniformly from the first current position to the collision position at the maximum deceleration, the assumed obstacle moves uniformly from the target intersection position to the first position (B) at the speed of the assumed obstacle; the distance the vehicle travels uniformly from the first current position to the collision position at the maximum deceleration is the first distance; the distance the assumed obstacle travels uniformly from the target intersection position to the first position (B) is the sum of the second distance and the length of the assumed obstacle.

[0054] The relationship between the relevant quantities under the given conditions is as follows:

[0055] obj_t=(obj_dist_to_inersect+obj_length) / (obj_vel)

[0056] ego_max_dec_t=|(ego_expect_vel) / (ego_max_dec)|

[0057] ego_dist_to_intersect=ego_expect_vel*min(obj_t,ego_max_dec_t)+0.5*ego_max_dec*min(obj_t,ego_max_dec_t)*min(obj_t,ego_max_dec_t)

[0058] Wherein, ego_dist_to_intersect represents the first distance, obj_dist_to_intersect represents the second distance, obj_length represents the length of the assumed obstacle, ego_expect_vel represents the expected speed of the vehicle, obj_vel represents the speed of the assumed obstacle, ego_max_dec represents the maximum deceleration of the vehicle, ego_max_dec_t represents the time taken for the vehicle to travel the first distance from the first current position, and obj_t represents the time taken for the assumed obstacle to reach the first position (B) at a constant speed from the target intersection position at the assumed obstacle speed.

[0059] Optionally, the third determining module 250 includes a second determining unit, which is used to: obtain a first maximum speed limit for the vehicle to reach the collision position based on the time taken for the vehicle to travel at a constant speed from the target intersection position to the first position (B) based on the speed of the assumed obstacle; obtain a second maximum speed limit for the vehicle to reach the collision position based on the first distance and the time taken for the vehicle to travel the first distance from the first current position; compare the speed limit values ​​of the first maximum speed limit and the second maximum speed limit, and determine the maximum speed limit with the smallest speed limit value as the desired speed.

[0060] The safe passage device provided in this embodiment can execute the steps in the safe passage method provided in this embodiment, and has the execution steps and beneficial effects, which will not be described in detail here.

[0061] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. See below for details. Figure 7 It shows a schematic diagram of a structure suitable for implementing the electronic device 500 in the embodiments of this disclosure. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0062] like Figure 7As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 501, which can perform various appropriate actions and processes to implement the methods of the embodiments described herein, based on a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing device 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0063] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts, thereby implementing the secure passage method as described above. In such embodiments, the computer program can be downloaded and installed from a network via communication device 509, or installed from storage device 508, or installed from ROM 502. When the computer program is executed by processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0064] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0065] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire target obstacles within a preset distance range based on onboard sensors; acquire blind zone polygons of the perception blind spot based on the target obstacles; obtain relational lanes associated with the current lane of the vehicle based on a high-precision map; acquire collision intersection points between the relational lanes and the blind zone polygons, and determine the collision intersection point closest to the current lane of the vehicle as the target intersection point; and determine the desired speed of the vehicle based on the target intersection point to reduce the risk of collision between the vehicle and obstacles in the perception blind spot.

[0066] Optionally, when one or more of the above-described procedures are executed by the electronic device, the electronic device may also perform other steps described in the above embodiments.

[0067] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0068] Option 1: A safe passage method, the method comprising:

[0069] Based on the vehicle's onboard sensors, target obstacles within a preset distance range are identified;

[0070] Based on the target obstacle, obtain the blind zone polygon of the perception blind zone;

[0071] Based on the high-precision map, obtain the lane relationships associated with the current lane of this vehicle;

[0072] Obtain the collision intersection point between the relationship lane and the blind spot polygon, and determine the collision intersection point that is closest to the current lane of the vehicle as the target intersection point;

[0073] Based on the target intersection point, the desired speed of the vehicle is determined to reduce the risk of collision between the vehicle and obstacles in the perception blind spot.

[0074] Option 2, according to the method described in Option 1, the step of acquiring target obstacles within a preset distance range based on vehicle-mounted sensors includes:

[0075] The vehicle-mounted sensor acquires all obstacles within a preset distance range, filters all obstacles by type, and acquires the first filtered obstacle.

[0076] The first obstacle whose height is greater than that of the vehicle is identified as the target obstacle.

[0077] Option 3: According to the method described in Option 1 or 2, the step of obtaining the blind zone polygon based on the target obstacle includes:

[0078] Based on the positional relationship between the target obstacle and the vehicle-mounted sensor, the tangent point of the target obstacle and the tangent line starting from the vehicle-mounted sensor and passing through the tangent point are obtained based on a first preset algorithm.

[0079] Extend the tangent line by a predetermined length in a direction away from the vehicle to obtain the vertex;

[0080] The blind zone polygon of the perception blind zone is determined based on the tangent point and the vertex.

[0081] Option 4: According to the method described in Option 1 or 2, obtaining the collision intersection point between the relational lane and the blind spot polygon includes:

[0082] Obtain the sampling points corresponding to the lanes in the high-precision map;

[0083] Based on the second preset algorithm, all the sampling points are traversed to obtain at least one set of adjacent first sampling points and second sampling points, wherein the first sampling point is located outside the blind zone polygon and the second sampling point is located inside the blind zone polygon;

[0084] Based on the first sampling point and the second sampling point, obtain the sample point ray;

[0085] The intersection point of the sample point ray and the blind zone polygon is determined based on the collision detection algorithm, and the intersection point is determined as the collision intersection point between the related lane and the blind zone polygon.

[0086] Option 5: According to the method described in Option 1, determining the desired speed of the vehicle based on the target intersection point includes:

[0087] Obtain the collision location at the intersection of the vehicle's current lane and related lanes;

[0088] Get the vehicle’s maximum deceleration, the first distance from the vehicle’s first current position to the collision position, and the second distance from the target intersection point to the collision position;

[0089] Based on the relationship between relevant quantities under defined conditions, the desired speed of the vehicle is determined, wherein the relevant quantities include the speed of the assumed obstacle, the length of the assumed obstacle, the maximum deceleration of the vehicle, the first distance, and the second distance.

[0090] Option 6: According to the method described in Option 5, the limiting condition is:

[0091] When the vehicle decelerates uniformly from the first current position to the collision position at the maximum deceleration, the assumed obstacle moves uniformly from the target intersection position to the first position at the assumed obstacle's speed.

[0092] The distance from which the vehicle decelerates uniformly from the first current position to the collision position at the maximum deceleration is the first distance;

[0093] The distance by which the assumed obstacle travels at a constant speed from the target intersection point to the first position is the sum of the second distance and the length of the assumed obstacle.

[0094] Option 7: According to the method described in Option 6, the relationship between the relevant quantities under the specified conditions is as follows:

[0095]

[0096]

[0097] ego_dist_to_intersect=ego_expect_vel*min(obj_t,ego_max_dec_t)+0.5*ego_max_dec*min(obj_t,ego_max_dec_t)*min(obj_t,ego_max_dec_t)

[0098] Wherein, ego_dist_to_intersect represents the first distance, obj_dist_to_intersect represents the second distance, obj_length represents the length of the assumed obstacle, ego_expect_vel represents the expected speed of the vehicle, obj_vel represents the speed of the assumed obstacle, ego_max_dec represents the maximum deceleration of the vehicle, ego_max_dec_t represents the time taken for the vehicle to travel the first distance from the first current position, and obj_t represents the time taken for the assumed obstacle to reach the first position at a constant speed from the target intersection position at the assumed obstacle speed.

[0099] Option 8: The method described in any one of Options 5-7, wherein determining the desired speed of the vehicle based on the relationship between relevant quantities under limited conditions includes:

[0100] Based on the time it takes for the assumed obstacle to travel at a constant speed from the target intersection point to the first position, the first maximum speed limit for the vehicle to reach the collision position is obtained.

[0101] Based on the first distance and the time it takes for the vehicle to travel the first distance from the first current position, a second maximum speed limit for the vehicle to reach the collision position is obtained;

[0102] The speed limits of the first maximum speed limit and the second maximum speed limit are compared, and the maximum speed limit with the smallest speed limit value is determined as the desired speed.

[0103] Option 9: A safe passage device, comprising:

[0104] The first acquisition module is used to acquire target obstacles within a preset distance range based on the vehicle-mounted sensors;

[0105] The second acquisition module acquires the blind zone polygon of the perception blind zone based on the target obstacle;

[0106] The first determining module is used to obtain the lanes associated with the current lane of the vehicle based on the high-precision map;

[0107] The second determining module is used to obtain the collision intersection point between the relational lane and the blind spot polygon, and determine the collision intersection point closest to the current lane of the vehicle as the target intersection point;

[0108] The third determining module is used to determine the desired speed of the vehicle based on the target intersection point, so as to reduce the risk of collision between the vehicle and obstacles in the perception blind spot.

[0109] Option 10: An electronic device, the electronic device comprising:

[0110] One or more processors;

[0111] Storage device for storing one or more programs;

[0112] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of schemes 1-8.

[0113] Option 11: A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of Options 1-8.

[0114] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

Claims

1. A method for safe passage, characterized in that, The method includes: Based on the vehicle's onboard sensors, target obstacles within a preset distance range are identified; Based on the target obstacle, obtain the blind zone polygon of the perception blind zone; Based on the high-precision map, obtain the lane relationships associated with the current lane of this vehicle; Obtain the collision intersection point between the relationship lane and the blind spot polygon, and determine the collision intersection point that is closest to the current lane of the vehicle as the target intersection point; Based on the target intersection point, the desired speed of the vehicle is determined to reduce the risk of collision between the vehicle and obstacles in the perception blind spot; The step of obtaining the collision intersection point between the relational lane and the blind spot polygon includes: Obtain the sampling points corresponding to the lanes in the high-precision map; Based on the second preset algorithm, all the sampling points are traversed to obtain at least one set of adjacent first sampling points and second sampling points, wherein the first sampling point is located outside the blind zone polygon and the second sampling point is located inside the blind zone polygon; Based on the first sampling point and the second sampling point, obtain the sample point ray; The intersection point of the sample point ray and the blind zone polygon is determined based on the collision detection algorithm, and the intersection point is determined as the collision intersection point between the related lane and the blind zone polygon.

2. The method according to claim 1, characterized in that, The step of acquiring target obstacles within a preset distance range based on vehicle-mounted sensors includes: The vehicle-mounted sensor acquires all obstacles within a preset distance range, filters all obstacles by type, and acquires the first filtered obstacle. The first obstacle whose height is greater than that of the vehicle is identified as the target obstacle.

3. The method according to claim 1 or 2, characterized in that, The step of obtaining the blind zone polygon based on the target obstacle includes: Based on the positional relationship between the target obstacle and the vehicle-mounted sensor, the tangent point of the target obstacle and the tangent line starting from the vehicle-mounted sensor and passing through the tangent point are obtained based on a first preset algorithm. Extend the tangent line by a predetermined length in a direction away from the vehicle to obtain the vertex; The blind zone polygon of the perception blind zone is determined based on the tangent point and the vertex.

4. The method according to claim 1, characterized in that, Determining the desired speed of the vehicle based on the target intersection point includes: Obtain the collision location at the intersection of the vehicle's current lane and related lanes; Get the vehicle’s maximum deceleration, the first distance from the vehicle’s first current position to the collision position, and the second distance from the target intersection point to the collision position; Based on the relationship between relevant quantities under defined conditions, the desired speed of the vehicle is determined, wherein the relevant quantities include the speed of the assumed obstacle, the length of the assumed obstacle, the maximum deceleration of the vehicle, the first distance, and the second distance.

5. The method according to claim 4, characterized in that, The limiting conditions are as follows: When the vehicle decelerates uniformly from the first current position to the collision position at the maximum deceleration, the assumed obstacle moves uniformly from the target intersection position to the first position at the assumed obstacle's speed. The distance from which the vehicle decelerates uniformly from the first current position to the collision position at the maximum deceleration is the first distance; The distance by which the assumed obstacle travels at a constant speed from the target intersection point to the first position is the sum of the second distance and the length of the assumed obstacle.

6. The method according to claim 5, characterized in that, The relationship between the relevant quantities under the given conditions is as follows: obj_t = ego_max_dec_t = ego_dist_to_intersect = ego_expect_vel * min(obj_t, ego_max_dec_t) +0.5*ego_max_dec*min(obj_t,ego_max_dec_t)*min(obj_t,ego_max_dec_t) Wherein, ego_dist_to_intersect represents the first distance, obj_dist_to_intersect represents the second distance, obj_length represents the length of the assumed obstacle, ego_expect_vel represents the expected speed of the vehicle, obj_vel represents the speed of the assumed obstacle, ego_max_dec represents the maximum deceleration of the vehicle, ego_max_dec_t represents the time taken for the vehicle to travel the first distance from the first current position, and obj_t represents the time taken for the assumed obstacle to reach the first position at a constant speed from the target intersection position at the assumed obstacle speed.

7. The method according to any one of claims 4-6, characterized in that, Determining the desired speed of the vehicle based on the relationship between relevant quantities under defined conditions includes: Based on the time it takes for the assumed obstacle to travel at a constant speed from the target intersection point to the first position, the first maximum speed limit for the vehicle to reach the collision position is obtained. Based on the first distance and the time it takes for the vehicle to travel the first distance from the first current position, a second maximum speed limit for the vehicle to reach the collision position is obtained; The speed limits of the first maximum speed limit and the second maximum speed limit are compared, and the maximum speed limit with the smallest speed limit value is determined as the desired speed.

8. A safe passage device, characterized in that, include: The first acquisition module is used to acquire target obstacles within a preset distance range based on the vehicle-mounted sensors; The second acquisition module acquires the blind zone polygon of the perception blind zone based on the target obstacle; The first determining module is used to obtain the lanes associated with the current lane of the vehicle based on the high-precision map; The second determining module is used to obtain the collision intersection point between the relational lane and the blind spot polygon, and determine the collision intersection point closest to the current lane of the vehicle as the target intersection point; The third determining module is used to determine the desired speed of the vehicle based on the target intersection point, so as to reduce the risk of collision between the vehicle and obstacles in the perception blind spot; The second determining module includes a third obtaining unit, which is used for: Obtain the sampling points corresponding to the lanes in the high-precision map; Based on the second preset algorithm, all the sampling points are traversed to obtain at least one set of adjacent first sampling points and second sampling points, wherein the first sampling point is located outside the blind zone polygon and the second sampling point is located inside the blind zone polygon; Based on the first sampling point and the second sampling point, obtain the sample point ray; The intersection point of the sample point ray and the blind zone polygon is determined based on the collision detection algorithm, and the intersection point is determined as the collision intersection point between the related lane and the blind zone polygon.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images