Unmanned vehicle blind area obstacle avoidance control method and system and electronic equipment

Abstract

The invention discloses an unmanned vehicle blind area obstacle avoidance control method and system and electronic equipment. The method comprises the following steps: controlling a first unmanned vehicle to send a target area cooperation request when detecting a sensor blind area in a driving direction, wherein the target area cooperation request comprises sensor blind area position information; judging whether the second unmanned vehicle meets the condition of providing cooperation for the first unmanned vehicle or not; if yes, the second unmanned vehicle is controlled to scan the target area, and a target area scanning result is sent to the first unmanned vehicle. And according to the received target area scanning result, determining driving parameters of the first unmanned vehicle in the driving direction. The technical scheme of the invention is suitable for the scene of cooperative work of a plurality of unmanned vehicles such as warehouse logistics, production and manufacturing, effectively solves the problem of sensor blind areas in a traditional unmanned vehicle system, and improves the safety and reliability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent logistics equipment, and in particular to a blind spot obstacle avoidance control method, system and electronic equipment for an unmanned vehicle. Background Art

[0002] With the development of intelligent logistics, unmanned vehicles are increasingly being used in warehousing, production, and other scenarios. Unmanned vehicles typically rely on various sensors mounted on the vehicle, such as lidar and cameras, to perceive their surroundings for autonomous navigation and obstacle avoidance. However, due to limitations in sensor placement, sensing angle, and range, unmanned vehicles often have blind spots during operation. This is particularly true when turning, carrying large cargo, or operating in complex environments. These blind spots increase the risk of collision and compromise the vehicle's safe operation.

[0003] Currently, blind spots are primarily reduced by increasing the number of sensors or optimizing their layout. However, this approach is costly and cannot completely eliminate blind spots. Therefore, effectively solving the blind spot obstacle avoidance problem for autonomous vehicles and improving their safety and operational efficiency is a pressing issue for autonomous vehicles. Summary of the Invention

[0004] The present invention provides a blind spot obstacle avoidance control method, system and electronic equipment for unmanned vehicles. By having multiple unmanned vehicles collaboratively scan sensor blind spots, the resource allocation of multiple vehicle systems is optimized, and perception information is shared. This effectively solves the problem of missed obstacle detection caused by insufficient sensor coverage of a single vehicle, thereby improving the safe operation capability of unmanned vehicles.

[0005] According to one aspect of the present invention, a method for controlling blind spot obstacle avoidance for an unmanned vehicle is provided, the method comprising:

[0006] Controlling the first unmanned vehicle to issue a target area cooperation request when detecting a sensor blind spot in the driving direction, wherein the target area cooperation request includes the sensor blind spot location information;

[0007] Determine whether the second unmanned vehicle meets the conditions for providing cooperation to the first unmanned vehicle; if so, control the second unmanned vehicle to scan the target area and send the target area scanning results to the first unmanned vehicle.

[0008] Based on the received target area scanning result, the driving parameters of the first unmanned vehicle in the driving direction are determined.

[0009] According to another aspect of the present invention, a blind spot obstacle avoidance control system for an unmanned vehicle is provided, comprising at least two unmanned vehicles, the system comprising:

[0010] a collaboration request module configured to control the first unmanned vehicle to generate a target area collaboration request when detecting a sensor blind spot in the driving direction, the request including location information of the sensor blind spot; a collaboration management module, configured to determine whether the second unmanned vehicle meets the conditions for providing collaboration to the first unmanned vehicle; a scanning execution module, configured to control the second unmanned vehicle to scan the target area and send the scanning result to the first unmanned vehicle when the second unmanned vehicle meets the cooperation condition; A driving decision module is configured to determine driving parameters of the first unmanned vehicle in a driving direction according to the scanning results.

[0011] According to another aspect of the present invention, an electronic device is provided, comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] 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 control method for blind spot obstacle avoidance of an unmanned vehicle as described in any embodiment of the present invention.

[0015] The unmanned vehicle blind spot avoidance control method disclosed in the present invention, when a first unmanned vehicle detects a sensor blind spot in the direction of travel, sends a collaboration request containing the blind spot location to a second nearby unmanned vehicle; selects the optimal collaborator by evaluating the second unmanned vehicle's real-time location, sensor performance, and mission status, and has it scan the blind spot and transmit data back; generates obstacle information based on the fusion of multi-source scanning results, and dynamically adjusts the first unmanned vehicle's driving speed and path offset or triggers an emergency obstacle avoidance strategy. This technical solution utilizes the collaborative relationship between multiple unmanned vehicles through multi-vehicle collaborative scanning of sensor blind spots, optimizes multi-vehicle system resource allocation, and solves the problem of missed obstacle detection caused by insufficient sensor coverage of a single vehicle through information sharing, thereby improving driving safety.

[0016] 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

[0017] 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.

[0018] Figure 1This is a flow chart of a blind spot obstacle avoidance control method for an unmanned vehicle provided according to the first embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of an unmanned vehicle equipped with multiple sensors applicable to an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of an application scenario of the blind spot obstacle avoidance method for an unmanned vehicle provided in the second embodiment of the present invention;

[0021] Figure 4 2 is a flow chart of a method for controlling blind spot obstacle avoidance for an unmanned vehicle according to a third embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of a specific application scenario applicable to the fourth embodiment of the present invention;

[0023] Figure 6 This is a schematic structural diagram of a blind spot obstacle avoidance control system for an unmanned vehicle according to a fifth embodiment of the present invention;

[0024] Figure 7 The figure is a schematic diagram of the structure of an electronic device for implementing the blind spot obstacle avoidance control method for an unmanned vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Example 1

[0028] This embodiment discloses a method for controlling blind spot obstacle avoidance of an unmanned vehicle. Figure 1 As shown, the following steps are included:

[0029] Step S101: Determine the detection range of the first unmanned vehicle sensor.

[0030] In this embodiment, the unmanned vehicle is usually equipped with a variety of sensors to sense the surrounding environment, such as Figure 2 As shown, these sensors may include, but are not limited to, laser radars 1, 3, and 4 installed on the top, side horns, and rear of the vehicle, as well as a camera 2 in the middle of the vehicle. Each sensor has its own specific perception detection range and limitations. For example, the laser radar 1 on the top can generally provide obstacle detection over a wide range, but may have difficulty detecting low objects or highly reflective objects; the camera can provide rich visual information, but its performance will degrade in low-light conditions. In actual operation, the perception system calculates the current overall perception range of the unmanned vehicle by reading the real-time data from each sensor and combining it with the sensor's installation location and parameters. Specifically, the perception areas of each sensor can be fused in the vehicle coordinate system to obtain a complete perception coverage area.

[0031] Step S102: Determine whether there is a sensor blind spot based on the detection range and safe operating range of the first unmanned vehicle sensor.

[0032] In the embodiments of this disclosure, the safe operating range refers to the environmental perception range required for safe operation of the unmanned vehicle in its current state. Constraints include, but are not limited to, the vehicle's speed, vehicle dimensions, the dimensions of the cargo being transported, and the curvature of the travel path. The faster the vehicle's speed, the longer the required forward sensing distance; the larger the vehicle's dimensions, the larger the required surrounding sensing range. When an unmanned vehicle is transporting large cargo, cargo that extends beyond the pallet may partially obstruct the sensor's field of view, increasing blind spots. The smaller the turning radius of the travel path, the higher the requirements for the unmanned vehicle's lateral perception. In the embodiments of this disclosure, when planning the safe operating range, the safe operating range for straight sections is at least the width of the unmanned vehicle plus a certain safety distance (e.g., 0.5-1 meter). When setting the safe operating range for turning areas, it can be specifically planned based on the vehicle's minimum turning radius, and a certain safety distance must be left to prevent collisions with surrounding objects. The size of the safety distance can be customized as needed.

[0033] The unmanned vehicle system calculates the required safe operating range based on the current operating state and compares it with the actual sensing range determined in step S101. If there is an area within the safe operating range that is not covered by the sensor, it is considered a sensor blind spot.

[0034] Specifically, if Figure 2For example, when transporting large, loose items, the unmanned vehicle often wraps them to prevent them from falling. This wrapping film can easily obstruct the detection sensor 4 on the vehicle's fork arm, creating a blind spot. Sensor blind spots can also occur when the vehicle's route planning requires turns. These blind spots can prevent the vehicle from detecting obstacles within the area, increasing the risk of collision.

[0035] S103: Control the first unmanned vehicle to issue a target area cooperation request when detecting a sensor blind spot in the driving direction, wherein the target area cooperation request includes the sensor blind spot location information.

[0036] When the system determines that there is a sensor blind spot in the direction of travel of the unmanned vehicle, the first unmanned vehicle will issue a target area cooperation request. This request can be sent to other unmanned vehicles in the vicinity via a wireless communication network (such as WiFi or 5G).

[0037] Specifically, the target area collaboration request of the first unmanned vehicle disclosed in this embodiment includes the following information: the ID number of the first unmanned vehicle initiating the request, the coordinate position of the target area, and information such as the priority and request deadline. The ID number of the first unmanned vehicle is used to identify the request initiator; the coordinates of the target area are used to indicate the position and range of the blind spot that requires collaborative perception, usually expressed in a global coordinate system or a relative coordinate system; the priority is used to indicate the urgency of the request, and the priority information can be determined based on factors such as the size of the blind spot, driving speed, and the potential risk of collision with obstacles; the request deadline indicates by when the collaboration result needs to be obtained, which is usually related to the estimated time when the first unmanned vehicle arrives at the blind spot.

[0038] Step S104: Determine whether the second unmanned vehicle meets the conditions for providing cooperation to the first unmanned vehicle.

[0039] After receiving a collaboration request from the first, surrounding unmanned vehicles, such as the second unmanned vehicle, will determine whether they can provide collaboration based on their own status. The second unmanned vehicle can determine whether the collaboration conditions are met based on its own location information, such as whether it is in a position where it can observe the target area, sensor conditions, task priority, and resource status. Sensor conditions refer to whether the second unmanned vehicle's sensors can cover the target area; task priority refers to the comparison between the second unmanned vehicle's current task priority and the priority of the collaboration request; and resource status refers to whether the second unmanned vehicle's computing and communication resources are sufficient to support collaboration.

[0040] If the second unmanned vehicle meets the cooperation conditions, the process proceeds to step S105; otherwise, the unmanned vehicle will delay its response based on its own status.

[0041] Step S105: Control the second unmanned vehicle to scan the target area and send the target area scanning result to the first unmanned vehicle.

[0042] After confirming its availability for collaboration, the second unmanned vehicle will use its sensors to collect environmental information about the target area. Specifically, the second unmanned vehicle will scan the target area. The collected environmental information may include point cloud data, image data, and obstacle information. Point cloud data represents the three-dimensional position of objects in the environment; image data provides visual information about the target area, helping to identify obstacle types; and obstacle information refers to the location, size, and type of identified obstacles.

[0043] The second unmanned vehicle sends this information to the first unmanned vehicle via a wireless communication network. To reduce the communication burden, the system can compress or filter the data during implementation to transmit only the key information.

[0044] Step S106: Determine the driving parameters of the first unmanned vehicle in the driving direction based on the received target area scanning result.

[0045] After receiving the collaborative data, the first autonomous vehicle integrates it with its own sensory data to form a complete understanding of the environment. Based on this integrated environmental information, the system reassesses the safety of the driving path and adjusts driving speed based on the presence of obstacles in the blind spot. Alternatively, it optimizes steering strategies based on information about the traversable area. If an obstacle is detected on the originally planned path, the autonomous vehicle will replan the route. If a dangerous obstacle is detected in the blind spot, emergency braking will be applied.

[0046] In this way, the first unmanned vehicle can make safer and smarter driving decisions based on more comprehensive environmental information.

[0047] Example 2

[0048] Based on the first embodiment, Figure 3 As shown, this embodiment further describes a specific application scenario:

[0049] Scenario description: Inside a warehouse, a first unmanned vehicle 5 is carrying a large load 6, which partially blocks the sensor's field of view, creating a large blind spot 7. Furthermore, the first unmanned vehicle 5 needs to turn through a narrow passage, further increasing safety risks.

[0050] The first unmanned vehicle 5 detects a blind spot 7 formed by obstruction of the cargo 6, and the blind spot is located in the direction of the upcoming turn; the first unmanned vehicle 5 issues a target area cooperation request, which includes the location information of the blind spot 7, a priority identifier, and a deadline for requesting assistance.

[0051] A nearby second unmanned vehicle 8 is perfectly positioned to observe blind spot 7, and since it has no urgent missions, it confirms its availability for collaboration and scans blind spot 7. The scan reveals a low obstacle 9 within blind spot 7. The second unmanned vehicle 8 transmits this obstacle information to the first unmanned vehicle 5. Upon receiving this information, the first unmanned vehicle 5 adjusts its planned turning path, avoids obstacle 9, and safely passes through the passage. This collaborative approach effectively avoids potential collisions between the first unmanned vehicle 5 and obstacle 9, improving system safety and efficiency.

[0052] The unmanned vehicle blind spot obstacle avoidance control method provided by the embodiment of the present invention effectively solves the blind spot problem of a single vehicle sensor through collaborative perception between multiple unmanned vehicles, and significantly reduces the risk of collision accidents. Compared with traditional conservative strategies such as parking and observing or slowing down, this method can maintain high operating efficiency while ensuring safety. The accuracy and reliability of obstacle detection are improved through multi-source information fusion. It can flexibly respond to blind spot environments of different complexities, including intersections, shelf corners, narrow passages and other scenarios. This technical solution does not require the addition of additional hardware equipment, and can achieve the improvement of blind spot perception capabilities only through the optimization of software algorithms and communication protocols. This method can be easily expanded to a collaborative network of multiple unmanned vehicles. As the number of collaborative vehicles increases, the overall perception capability and safety performance of the system will be further improved.

[0053] It should be noted that in the blind spot obstacle avoidance method for unmanned vehicles disclosed in this embodiment, if multiple unmanned vehicles simultaneously issue collaboration requests, or if a single unmanned vehicle receives multiple collaboration requests, the system can prioritize them according to pre-set rules. Specifically, the system prioritizes safety and collision avoidance, prioritizing requests with high collision risk and urgent deadlines. For efficiency-focused applications such as express logistics, collaboration methods that can simultaneously accommodate multiple requests can be prioritized. In specific implementations, to reduce resource load, edge computing servers can be deployed within the warehouse, allowing unmanned vehicles to offload some computationally intensive tasks (such as point cloud processing and image recognition) to the edge servers. This reduces the computational burden on the unmanned vehicles and accelerates collaborative response times. Furthermore, the edge servers maintain global status information for all unmanned vehicles within the warehouse, including their locations, tasks, and resource status, helping to more efficiently match collaboration needs with capabilities and achieve globally optimal collaborative scheduling.

[0054] Example 3

[0055] This embodiment optimizes the collaborative feasibility assessment and judgment mechanism based on the above embodiment. Figure 4 As shown, the blind spot obstacle avoidance control method for unmanned vehicles provided by the embodiment of the present invention mainly describes the determination of whether the second unmanned vehicle meets the conditions for providing cooperation to the first unmanned vehicle. The specific determination method steps are as follows:

[0056] Step S301: The second unmanned vehicle that receives the cooperation request determines whether it meets the conditions for providing cooperation to the first unmanned vehicle based on its own status and its relationship with the target area. The judgment process specifically includes:

[0057] Collecting state parameters of the second unmanned vehicle, including relative position and angle parameters with respect to the target area;

[0058] Second, the unmanned vehicle sensor detection performance parameters, such as sensor type, accuracy, working status, etc.;

[0059] The second unmanned vehicle executes mission status parameters, such as current mission priority, workload, battery status, etc.

[0060] S302: Calculate the collaboration feasibility evaluation score S based on the collected status parameters.

[0061] When implementing the technical solution disclosed in this embodiment, the feasibility assessment reference score S = w1·S1 + w2·S2 + w3·S3 can be calculated using the following method. The constraints for determining whether the second unmanned vehicle can provide assistance in the technical solution disclosed in this embodiment primarily include the observation feasibility score, sensor performance, and the mission compatibility score, where S1 is a preset observation feasibility score calculated based on relative position and angle parameters with respect to the target area.

[0062] S2 is the sensor detection performance score, which can be a preset sensor detection performance determined based on the distance from the target area and environmental conditions; wherein the environmental conditions at least include light intensity.

[0063] S3 is the task compatibility score, calculated based on the current task priority and workload. w1, w2, and w3 are weight coefficients that can be adjusted according to the actual application scenario during implementation.

[0064] The method for determining whether the second unmanned vehicle meets the collaboration conditions is specifically described as follows: the calculation of the collaboration feasibility evaluation score S includes three main parts: observation feasibility score S1, sensor detection performance score S2, and task compatibility score S3.

[0065] The observation feasibility score S1 is based on the position and angle of the second unmanned vehicle relative to the target area. It can be calculated using the following formula: S1 = f(θ, d) = cos(θ) (1-d / dmax). θ is the angle between the second unmanned vehicle and the line connecting the target area, and can range from [0, π / 2]. When θ = 0, the second unmanned vehicle is facing the target area, resulting in optimal observation conditions. d is the distance from the second unmanned vehicle to the target area. dmax is the maximum distance the sensor can effectively detect.

[0066] When θ is close to 0 and d is small, the S1 value is close to 1, indicating that the observation conditions are excellent; when θ is close to π / 2 or d is close to dmax, the S1 value is close to 0, indicating that the observation conditions are poor.

[0067] Sensor detection performance score S 2， When making judgments, consider the impact of sensor characteristics and environmental factors on detection results. The following calculation formula, S2, can be used: g(d,e) = Qbase (1-d / dmax) e. Qbase is the sensor's base quality factor, which is related to sensor type, resolution, accuracy, and other characteristics. Its value is generally set in the range of [0.6, 1]. The meanings of d and dmax are as described above. e is the environmental impact factor, which considers the effects of factors such as lighting, weather, and occlusion on sensor performance. Its value is generally set in the range of [0.5, 1]. In adverse environmental conditions (such as rain, fog, and low light), the e value is low, resulting in an overall decrease in S2. In ideal environmental conditions, the e value is close to 1, and S2 is primarily affected by the sensor's base quality and distance.

[0068] The task compatibility score S3 is used to evaluate the compatibility between the second unmanned vehicle's current task and the provided collaboration. The calculation formula is:

[0069] S3=(1-P task / P max )·(1 – L task / L max ); where P task is the priority of the current task, P max The highest task priority; L task is the current workload, L max is the maximum workload capacity.

[0070] When the second unmanned vehicle has a lower task priority and a lighter workload, the S3 value is higher, indicating that there is more spare capacity to provide collaboration; conversely, when the task priority is higher or the workload is heavier, the S3 value is lower, indicating that it may be difficult to provide effective collaboration.

[0071] The final collaborative feasibility evaluation score S is obtained by weighted summation:

[0072] S= w1·S1 + w2·S2+ w3·S3

[0073] The weight coefficients w1, w2, and w3 should be adjusted based on the actual application scenario. If you prioritize the impact of observation conditions and sensor performance on collaboration, you might set w1 to 0.4, w2 to 0.4, and w3 to 0.2. Parameter values ​​can be adjusted as needed during implementation.

[0074] When the S value is greater than a preset threshold α (such as 0.7), it can be considered that the second unmanned vehicle meets the conditions for providing cooperation; otherwise, it is considered that the cooperation conditions are not met.

[0075] S303: Calculate the feasibility evaluation score of the second unmanned vehicle based on the collected parameters, and determine whether the cooperation conditions are met based on the evaluation result.

[0076] If the evaluation score S is higher than the preset evaluation threshold α (such as 0.7), it is determined that the second unmanned vehicle meets the conditions for providing cooperation; if the evaluation score S is not higher than the preset evaluation threshold α, it is determined that the second unmanned vehicle does not meet the conditions for providing cooperation.

[0077] Step S304: If the second unmanned vehicle meets the cooperation conditions, it is controlled to scan the target area.

[0078] During the scanning process, the second unmanned vehicle may need to temporarily interrupt its current mission or adjust the sensor or vehicle's direction of travel to ensure that the sensor scanning area covers the target area without affecting the current mission. The sensor used for scanning can be a lidar, high-definition camera, or other suitable perception device.

[0079] Step S305: The second unmanned vehicle sends the target area scanning result to the first unmanned vehicle.

[0080] Specifically, the second unmanned vehicle scanning results mainly include whether there are obstacles in the target area and the timestamp when the obstacle information is detected; if there are obstacles, the location, size, movement status and other information of the obstacle detection are provided.

[0081] Step S306: After receiving the target area scanning results, the first unmanned vehicle determines the current collision risk level based on its own perception information.

[0082] Specifically, the first unmanned vehicle's reference obstacle information primarily includes obstacle information detected by the vehicle itself and obstacle information received from other cooperating unmanned vehicles, such as the obstacle's location and shape. Location information includes the obstacle's center coordinates and boundary coordinates. Obstacle shape information includes the obstacle's size, geometry, and type recognition results.

[0083] The first unmanned vehicle perception system integrates the received target area obstacle information scan results from other assisting vehicles and / or the first unmanned vehicle's own perceived environmental information to determine an integrated target area scan result. Furthermore, based on the integrated target area obstacle information, the first unmanned vehicle's reference obstacle information is determined. The first unmanned vehicle reference obstacle information includes the location and shape information of obstacles within a preset range around the first unmanned vehicle.

[0084] The first unmanned vehicle updates the local obstacle map based on the obstacle information and determines the collision risk level. Based on the updated local obstacle map, the system determines the current collision risk level in combination with the first unmanned vehicle's current state (such as position, speed, direction, etc.) and the planned path. Collision risk levels are generally categorized into the following three categories:

[0085] If the distance between the obstacle and the unmanned vehicle is far, or the obstacle is not on the unmanned vehicle's planned path, the collision risk level is low risk; if the obstacle is on the unmanned vehicle's planned path, but the distance is sufficient for smooth avoidance, it should be medium risk; if the obstacle is on the unmanned vehicle's planned path and the distance is close, and there is an urgent need for obstacle avoidance, it is high risk.

[0086] Step S307: Based on the collision risk level, a corresponding obstacle avoidance strategy is adopted to determine the driving parameters of the first unmanned vehicle in the driving direction.

[0087] If the collision risk level is low, the system determines the maximum safe speed based on the distance between the target obstacle and the first unmanned vehicle. Generally speaking, the closer the distance, the lower the maximum safe speed.

[0088] If the collision risk level is medium, the system determines the lateral offset distance to avoid the obstacle based on the target obstacle's position relative to the first unmanned vehicle and the path curvature. The specific lateral offset distance calculation in this solution is primarily constrained by factors such as the size and shape of the obstacle, the unmanned vehicle's steering capability and dynamic characteristics, environmental constraints (such as aisle width), and safety distance requirements.

[0089] If the collision risk level is high, the system determines whether the current situation allows for safe avoidance. If not, the system controls the first autonomous vehicle to stop and wait. If the current path is impassable, the system requests rerouting and seeks an alternative route.

[0090] The specific implementation can also refer to the operating status of obstacles. For example, if there is a stationary obstacle in the target area, the first unmanned vehicle can adjust its driving path or speed based on the obstacle's position to ensure safe obstacle avoidance. If the second unmanned vehicle's scan of the target area shows the presence of a dynamic obstacle, the first unmanned vehicle can predict its future location based on the obstacle's trajectory and speed and dynamically adjust its driving parameters accordingly.

[0091] Throughout the blind spot obstacle detection collaboration process, the first and second unmanned vehicles maintain real-time communication to ensure timely updates of scanning results. Once the first unmanned vehicle safely passes through the blind spot, the collaboration ends and the two vehicles resume their original tasks.

[0092] The blind spot obstacle avoidance control method for unmanned vehicles provided by the present invention is suitable for scenarios where multiple unmanned vehicles work together, such as warehousing and logistics, manufacturing, etc. It adopts a collaborative feasibility assessment mechanism to ensure the efficiency and reliability of the collaborative process, avoid unnecessary collaborative requests and responses, and significantly reduce the risk of collisions caused by sensor blind spots. It effectively solves the problem of sensor blind spots in traditional unmanned vehicle systems and improves the safety and reliability of the system. This method does not require additional hardware equipment and achieves information sharing and collaborative perception through software algorithms, which is highly cost-effective and practical. Through collaborative perception in unmanned workshops, the problem of sensor blind spots is effectively solved, and the safety of unmanned vehicle operation is improved.

[0093] Example 4

[0094] The embodiments of this application document improve upon the aforementioned embodiments, primarily by determining reference obstacles within the sensor's blind spot based on the confidence level of the scanning results transmitted by the cooperating vehicles. Because the first unmanned vehicle may receive scanning results from multiple cooperating vehicles, these results may contain discrepancies or redundancies. Therefore, data fusion and integration are required to generate unified reference obstacle information.

[0095] Based on the first unmanned vehicle's reference obstacle information and confidence weight, the first unmanned vehicle's target obstacle information is determined. When implementing this technical solution, the confidence weight can be determined based on factors such as the distance between the cooperative unmanned vehicle and the target area, the accuracy level of the cooperative unmanned vehicle's sensors, and the suitability of the cooperative unmanned vehicle's viewing angle of the target area. Generally speaking, the closer the cooperative unmanned vehicle is to the target area, the higher the sensor accuracy, the more suitable the cooperative vehicle's viewing angle, and the higher the confidence level of the scanning result.

[0096] For the reference obstacle information provided by multiple collaborative vehicles, the system performs weighted fusion according to the credibility weight, and finally forms more accurate target obstacle information.

[0097] The following describes the process of determining the target obstacle information of the first unmanned vehicle based on the reference obstacle information and confidence weight of the first unmanned vehicle in conjunction with a specific scenario:

[0098] like Figure 5 As shown in the figure, in the intelligent warehousing system, since the observation angle of the first unmanned vehicle is limited due to the obstruction of its own sensor by the loaded goods, it sends a blind spot detection collaboration request to the three nearby unmanned transport vehicles (A, B, C). The three nearby collaborative unmanned transport vehicles (A, B, C) perform obstacle detection in the target area and feed back the detection results to the first unmanned vehicle for collaborative perception verification.

[0099] After the first unmanned vehicle receives the obstacle data fed back by each cooperative vehicle, it will perform weighted fusion of the obstacles based on the confidence of each cooperative vehicle's detection, and finally form more accurate target obstacle information. The confidence of the cooperative vehicle in detecting obstacles is affected by distance, sensor detection accuracy, and detection angle suitability. Specifically, the confidence of the detection result is inversely proportional to the Euclidean distance of the target area, and the distance weight Wd=1+k1·d1 (the attenuation coefficient k1 can be selected as 0.2 when implementing this technical solution, and d1 is the distance between the cooperative vehicle and the obstacle in the target area); the sensor accuracy weight (Ws) is set according to the type of sensor carried by the unmanned vehicle, such as 1.0 for lidar and 0.8 for camera. The angle suitability weight (Wa) is calculated based on the angle θ between the observation axis and the normal vector of the obstacle surface, Wa=cos(θ) (valid when θ≤60°)

[0100] The parameters of the cooperative vehicle are as follows: vehicle Distance d(m) Sensor Type Observation angle Detect obstacle coordinates (x, y) A 2.5 LiDAR 15° （2.1，3.0） B 3.0 LiDAR 60° （1.8，3.3） C 2.7 camera 60° （2.3，2.9） Table 1 Cooperative vehicle parameter information

[0101] Calculate the obstacle scanning results provided by unmanned transport vehicles A, B, and C according to the confidence weights:

[0102] 1. Unmanned transport vehicle A: Wd = 1 / (1 + 0.2 × 2.5) = 0.67; Ws = 1.0; Wa = cos(15°) ≈ 0.97; Total weight: WA = 0.67 × 1.0 × 0.97 ≈ 0.65

[0103] 2. Automated transport vehicle B: Wd = 1 / (1 + 0.2 × 3.0) = 0.63; Ws = 1.0; Wa = cos(60°) = 0.5; Total weight: WB = 0.63 × 1.0 × 0.5 = 0.32

[0104] 3. Unmanned transport vehicle C: Wd = 1 / (1 + 0.2 × 2.7) ≈ 0.65; Ws = 0.8; Wa = cos(60°) = 0.5; Total weight: WC = 0.65 × 0.8 × 0.5 = 0.26

[0105] Normalizing the calculated weights and performing weighted fusion yields the fused obstacle detection coordinates. This implementation effectively leverages the close-range, high-precision sensor of cooperative vehicle B and the optimal observation angle of cooperative vehicle A through dynamic weight allocation, while minimizing the impact of the long-range, low-precision sensor of forklift C. This effectively improves the reliability of the final output obstacle position coordinates.

[0106] The unmanned vehicle blind spot obstacle avoidance control method provided by the present invention effectively solves the blind spot problem of a single forklift sensor through collaborative perception between multiple unmanned vehicles, and significantly reduces the risk of collision accidents. Compared with traditional conservative strategies such as parking and observing or slowing down, this method can maintain high operating efficiency while ensuring safety. The accuracy and reliability of obstacle detection are improved through multi-source information fusion and credibility weight evaluation. It can flexibly respond to blind spot environments of different complexities, including intersections, shelf corners, narrow passages and other scenarios. Without adding additional hardware equipment, the blind spot perception capability can be improved only through the optimization of software algorithms and communication protocols, which has a good cost-effectiveness ratio. This method can be easily expanded to a collaborative network of multiple unmanned vehicles. As the number of collaborative forklifts increases, the overall perception capability and safety performance of the system will be further improved.

[0107] This invention is applicable to various scenarios where unmanned vehicles are used, such as logistics and warehousing centers, manufacturing workshops, and port terminals. It can significantly improve the safety and operational efficiency of unmanned vehicles in complex environments and has broad industrial application prospects. In high-density operating environments, where the coordinated operation of multiple unmanned vehicles is more common, the collaborative perception mechanism of this invention can fully leverage the advantages of swarm intelligence and bring about a qualitative improvement to the entire unmanned vehicle system.

[0108] Example 5

[0109] The embodiment of the present invention provides a blind spot obstacle avoidance control system for an unmanned vehicle, comprising at least two unmanned vehicles, such as Figure 6 It includes: a collaboration request module 510, a collaboration management module 520, a scan execution module 530 and a driving decision module 540:

[0110] The collaboration management module 520 is configured to include:

[0111] a state parameter acquisition unit configured to obtain a relative position of the second unmanned vehicle and the target area, sensor performance, and task priority;

[0112] An evaluation calculation unit is configured to calculate a collaboration feasibility score based on the state parameters, and the evaluation score formula is S = w1·S1 + w2·S2 + w3·S3;

[0113] S1 is the observation feasibility score preset based on the relative position and angle parameters with respect to the target area;

[0114] S2 is a sensor detection performance score preset based on the distance to the target area and environmental conditions; wherein the environmental conditions include at least light intensity conditions;

[0115] S3 is the task compatibility score calculated based on the priority and workload of the task currently being executed by the second unmanned vehicle;

[0116] w1, w2, and w3 are preset values ​​configured according to the task type;

[0117] The collaborative decision-making unit is configured to determine that the second unmanned vehicle meets the collaborative conditions when the evaluation score is higher than a preset threshold; and to determine that the second unmanned vehicle does not meet the collaborative conditions when the evaluation score is not higher than the preset threshold.

[0118] The unmanned vehicle blind spot control system provided in the embodiment of the present invention can execute the driving control method provided in any embodiment of the present invention mentioned above, and has the corresponding functions and beneficial effects of executing the driving control method. For detailed process, please refer to the relevant operations of the blind spot obstacle avoidance control method in the aforementioned embodiment.

[0119] Example 6

[0120] Figure 7 The following is a schematic diagram of an electronic device that can be used to implement the blind spot obstacle avoidance control method for an unmanned vehicle according to an embodiment of the present invention. The term "electronic device" is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The term "electronic device" may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided for illustrative purposes only and are not intended to limit the implementation of the present inventions described and / or claimed herein.

[0121] like Figure 7 As shown, electronic device 10 includes at least one processor 11 and memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by the at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer programs stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. An input / output (I / O) interface 15 is also connected to bus 14.

[0122] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0123] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 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 running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as the driving control method.

[0124] In some embodiments, the driving control method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the driving control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the driving control method in any other suitable manner (e.g., via firmware).

[0125] Various embodiments of the systems and techniques described above 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.

[0126] 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.

[0127] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: 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 electronic 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 input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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 blind spot obstacle avoidance control method for an unmanned vehicle, characterized in that: include: Controlling the first unmanned vehicle to issue a target area cooperation request when detecting a sensor blind spot in a driving direction, wherein the target area cooperation request includes the sensor blind spot location information; Determining whether the second unmanned vehicle meets the conditions for providing cooperation to the first unmanned vehicle; if so, controlling the second unmanned vehicle to scan the target area and sending the target area scanning result to the first unmanned vehicle; Determine the driving parameters of the first unmanned vehicle in the driving direction based on the received target area scanning result.

2. The method according to claim 1, characterized in that When the first unmanned vehicle detects a sensor blind spot in the driving direction, the first unmanned vehicle is controlled to issue a target area cooperation request. Before the target area cooperation request includes the sensor blind spot position information, the method further includes: Determine a detection range of the first unmanned vehicle sensor; and determine whether there is a blind spot of the sensor based on the detection range of the first unmanned vehicle sensor and a safe operating range; The constraints of the safe operating range include at least one of the following: driving speed, vehicle body size parameters, outer dimensions of the transported goods, and curvature of the driving path.

3. The method according to claim 1, characterized in that Determining whether the second unmanned vehicle meets the conditions for providing cooperation to the first unmanned vehicle includes: Collecting state parameters of the second unmanned vehicle to calculate a collaboration feasibility assessment score, wherein the state parameters include at least one of the following: relative position and angle parameters with respect to the target area, sensor detection performance parameters, and / or task execution state parameters; If the evaluation score is higher than a preset evaluation threshold, determining that the second unmanned vehicle meets the conditions for providing cooperation; If the evaluation score is not higher than the preset evaluation threshold, it is determined that the second unmanned vehicle does not meet the conditions for providing cooperation.

4. The method according to claim 3, characterized in that The formula for calculating the collaboration feasibility evaluation score is as follows: S = w1·S1 + w2·S2 + w3·S3 where: S1 is a preset observation feasibility score calculated based on the relative position and angle parameters with respect to the target area; S2 is a preset sensor performance score calculated based on the distance from the target area and environmental conditions; wherein the environmental conditions include at least light intensity; S3 is a task compatibility score calculated based on the priority and workload of the task currently being executed by the second unmanned vehicle; w1, w2, and w3 are preset values ​​configured according to the task type.

5. The method according to claim 1, wherein Determining the driving parameters of the first unmanned vehicle in the driving direction based on the received target area scanning result includes: Determining reference obstacle information of the first unmanned vehicle based on the received target area scanning result and / or environmental information perceived by the first unmanned vehicle itself, the reference obstacle information including position information and shape information of the obstacle; Based on the first unmanned vehicle reference obstacle information, a driving parameter of the first unmanned vehicle in a driving direction is determined.

6. The method according to claim 5, characterized in that Determining the driving parameters of the first unmanned vehicle in the driving direction further includes: updating a local obstacle map based on the first unmanned vehicle's reference obstacle information to determine a collision risk level; If the collision risk level is low risk, determining the maximum safe speed of the first unmanned vehicle based on the distance from the obstacle to the first unmanned vehicle; If the collision risk level is medium, determining a lateral offset distance for the first unmanned vehicle to avoid the obstacle based on the location information of the obstacle in the target area and the curvature of the path; If the collision risk level is high, the first unmanned vehicle is controlled to stop and wait or request to replan the route.

7. The method according to claim 1, characterized in that Control the first unmanned vehicle to issue a target area cooperation request when detecting a sensor blind spot in the driving direction. The target area cooperation request includes: The ID of the first unmanned vehicle that initiates the target area collaboration request, the coordinates of the target area, the priority, and the request deadline.

8. An unmanned vehicle blind spot obstacle avoidance control system, comprising at least two unmanned vehicles, characterized in that: include: a collaboration request module configured to control the first unmanned vehicle to generate a target area collaboration request when detecting a sensor blind spot in the driving direction, the request including location information of the sensor blind spot; a collaboration management module configured to determine whether the second unmanned vehicle meets the conditions for providing collaboration to the first unmanned vehicle; a scanning execution module configured to control the second unmanned vehicle to scan the target area when the collaboration conditions are met, and to send the scan results to the first unmanned vehicle; A driving decision module is configured to determine driving parameters of the first unmanned vehicle in a driving direction according to the scanning results.

9. The system according to claim 8, characterized in that The collaboration management module includes: a state parameter acquisition unit configured to obtain a relative position of the second unmanned vehicle and the target area, sensor performance, and task priority; An evaluation calculation unit is configured to calculate a collaboration feasibility evaluation score S = w1·S1 + w2·S2 + w3·S3 according to the state parameters, where: S1 is an observation feasibility score preset based on the relative position and angle parameters with respect to the target area; S2 is a sensor detection performance score preset based on the distance from the target area and environmental conditions; wherein the environmental conditions include at least light intensity conditions; S3 is a task compatibility score calculated based on the priority and workload of the task currently being executed by the second unmanned vehicle; w1, w2, and w3 are preset values ​​configured according to the task type; The collaborative decision-making unit is configured to determine that the second unmanned vehicle meets the collaborative condition when the evaluation score is higher than a preset threshold; and to determine that the second unmanned vehicle does not meet the collaborative condition when the evaluation score is not higher than the preset threshold.

10. An electronic device, characterized in that: The electronic 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 so that the at least one processor can execute the control method for blind spot obstacle avoidance of an unmanned vehicle according to any one of claims 1 to 7.

Images