Vehicle obstacle avoidance method, device and equipment based on structured narrow road

Abstract

The invention provides a vehicle obstacle avoidance method, device and equipment based on a structured narrow road, and is applied to the technical field of intelligent driving, the method can be applied to a target vehicle, and the target vehicle runs on the structured narrow road. The method comprises the steps that when it is detected that an obstacle exists in front of a target vehicle, obstacle information of the obstacle and road information of a structured narrow road are obtained based on multiple sensors of the target vehicle; and identifying the obstacle type of the obstacle based on the obstacle information. And determining an obstacle avoidance strategy of the target vehicle according to obstacle avoidance information corresponding to the obstacle type in the obstacle information and the road information. And controlling the target vehicle to avoid the obstacle according to the obstacle avoidance strategy. The problems that a traditional intelligent driving vehicle is low in passing efficiency, rigid in decision making and prone to causing secondary congestion risks in a narrow road scene can be solved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a vehicle obstacle avoidance method, device and equipment based on structured narrow roads. Background Technology

[0002] With the continuous development of intelligent driving technology, intelligent driving vehicles are being used more and more widely in urban transportation. Intelligent driving vehicles achieve autonomous navigation and decision-making through onboard sensors, high-precision maps, and artificial intelligence algorithms, which can improve driving safety and comfort to a certain extent. While intelligent driving systems typically operate smoothly on regular roads, their performance remains significantly lacking in special scenarios such as narrow roads.

[0003] In related technologies, the passage of intelligent driving vehicles in narrow road scenarios mainly relies on pre-set path planning and obstacle avoidance algorithms. These algorithms typically make decisions based on fixed rules or limited scenario data, making it difficult to cope with complex and ever-changing real-world road conditions. For example, when encountering narrow sections of road with two-way traffic, intelligent driving vehicles often need to wait for other vehicles to pass completely before proceeding, resulting in low traffic efficiency. Furthermore, the decision-making logic of existing systems is relatively rigid and lacks flexibility, easily causing vehicles to wait for each other or even become stuck, thus triggering secondary congestion. Due to the lack of effective coordination mechanisms, intelligent driving vehicles often perform less flexibly and efficiently than human drivers in such scenarios, thereby limiting their widespread applicability in real-world traffic environments. Summary of the Invention

[0004] The purpose of this application is to provide a vehicle obstacle avoidance method, device and equipment based on structured narrow roads, to solve the problems of low traffic efficiency, rigid decision-making and risk of secondary congestion faced by traditional intelligent driving vehicles in narrow road scenarios.

[0005] In a first aspect, embodiments of this application provide a vehicle obstacle avoidance method based on structured narrow roads, applied to a target vehicle traveling on a structured narrow road. The method includes: when an obstacle is detected in front of the target vehicle, acquiring obstacle information of the obstacle and road information of the structured narrow road based on multiple sensors of the target vehicle; identifying the obstacle type based on the obstacle information; determining an obstacle avoidance strategy for the target vehicle based on obstacle avoidance information corresponding to the obstacle type in the obstacle information and road information; and controlling the target vehicle to avoid the obstacle according to the obstacle avoidance strategy.

[0006] The vehicle obstacle avoidance method based on structured narrow roads provided in this application embodiment can obtain comprehensive and accurate obstacle and road information in front of the target vehicle by using multiple sensors working together. This allows the type of obstacle to be determined, and by analyzing the obstacle information, obstacle type, and road information in real time, an accurate obstacle avoidance strategy can be made in a timely manner. This helps to improve traffic efficiency, avoid traffic congestion caused by unnecessary parking, and reduce the risk of collision.

[0007] One possible implementation involves, when the obstacle type is a dynamic obstacle, the obstacle avoidance information includes the motion state information of the dynamic obstacle and the real-time distance between the dynamic obstacle and the target vehicle. Based on the obstacle avoidance information corresponding to the obstacle type in the obstacle information and road information, the obstacle avoidance strategy for the target vehicle is determined, including: extracting the motion state information of the dynamic obstacle and the real-time distance between the dynamic obstacle and the target vehicle from the obstacle information. Based on the motion state information and road information, the target vehicle's target speed is dynamically adjusted according to a preset speed adjustment algorithm to ensure that the real-time distance between the target vehicle and the dynamic obstacle remains within a safe distance range. The preset safe distance range is determined based on the target vehicle's current speed, the target vehicle's braking performance, and road information.

[0008] One possible implementation involves determining the obstacle avoidance strategy for a static obstacle. This includes the road marking type on the bypass side and the lateral distance between the obstacle and the centerline of the structured narrow road. Based on the obstacle information and the obstacle avoidance information corresponding to the obstacle type in the road information, the target vehicle's obstacle avoidance strategy is determined. This includes: if the road information indicates the structured narrow road is not an intersection, extracting the road marking type on the bypass side and the lateral distance between the obstacle and the centerline of the structured narrow road from the road information. If the road marking type is a dashed line and the lateral distance is greater than or equal to the dodgeable distance, determining the target vehicle's bypass route and bypass control parameters based on the obstacle information and road information. The vehicle is then controlled to travel along the bypass route to perform the obstacle avoidance operation. And / or, if the road marking type is a solid line, the lateral distance is less than the dodgeable distance, or the road information indicates the structured narrow road is an intersection, the obstacle avoidance strategy is determined to be stopping and avoiding the static obstacle.

[0009] One possible implementation involves using obstacle information including the location and shape information of static obstacles on a structured narrow road. Based on the obstacle and road information, the obstacle avoidance route and obstacle avoidance control parameters for the target vehicle are determined. This includes determining the obstacle avoidance route and obstacle avoidance control parameters based on the location, shape, and path planning algorithms, so that the target vehicle, under the control of the obstacle avoidance control parameters, bypasses the static obstacle from the current lane via an obstacle avoidance lane.

[0010] One possible implementation, when other vehicles are present in the obstacle avoidance lane, further includes: acquiring the driving status information of other vehicles; acquiring the lateral distance between the target vehicle and the obstacle avoidance lane, as well as the obstacle avoidance acceleration of the obstacle avoidance control parameters; predicting the relative motion trend between the target vehicle and adjacent vehicles during the obstacle avoidance operation based on the driving status information, lateral distance, and obstacle avoidance acceleration of other vehicles; if the relative motion trend indicates that the target vehicle will not collide with adjacent vehicles, controlling the target vehicle to travel according to the obstacle avoidance route and obstacle avoidance control parameters to enable the target vehicle to perform the obstacle avoidance operation; and / or, if the relative motion trend indicates that the target vehicle will collide with adjacent vehicles, determining the obstacle avoidance strategy as stopping to avoid a static obstacle.

[0011] One possible implementation of the vehicle avoidance method based on structured narrow roads provided in this application embodiment further includes: when the obstacle avoidance time for the target vehicle to avoid a static obstacle reaches a preset obstacle avoidance time, acquiring the latest obstacle information and the latest road information of the structured narrow road based on multiple sensors of the target vehicle; updating the obstacle avoidance strategy of the target vehicle based on the latest obstacle information and the latest road information; and controlling the target vehicle to avoid obstacles according to the updated obstacle avoidance strategy.

[0012] One possible implementation involves identifying the obstacle type based on obstacle information, including: determining the obstacle type as a dynamic obstacle when the obstacle's movement speed is not zero in multiple consecutive instances; and / or determining the obstacle type as a static obstacle when the obstacle's movement speed is zero and the obstacle's position is relatively fixed.

[0013] Secondly, embodiments of this application provide a vehicle obstacle avoidance method based on structured narrow roads, applied to a target vehicle traveling on a structured narrow road. The device includes: an acquisition module, an identification module, a determination module, and a control module.

[0014] The acquisition module is used to acquire obstacle information and road information of structured narrow roads based on multiple sensors of the target vehicle when an obstacle is detected in front of the target vehicle.

[0015] The recognition module is used to identify the obstacle type based on obstacle information.

[0016] The determination module is used to determine the obstacle avoidance strategy of the target vehicle based on the obstacle avoidance information corresponding to the obstacle type in the obstacle information and road information.

[0017] The control module is used to control the target vehicle to avoid obstacles according to the obstacle avoidance strategy.

[0018] Thirdly, embodiments of this application provide a vehicle obstacle avoidance device based on structured narrow roads. This device has the function of implementing the vehicle obstacle avoidance method based on structured narrow roads in the first aspect or any possible implementation thereof. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a computer, enable the computer to perform the vehicle obstacle avoidance method based on structured narrow roads as described in the first aspect or any possible implementation thereof.

[0020] Fifthly, embodiments of this application provide a computer program product containing instructions that, when run on a computer, enable the computer to execute the vehicle obstacle avoidance method based on structured narrow roads as described in the first aspect or any possible implementation thereof.

[0021] The technical effects of any of the design methods in aspects two through five can be found in aspect one or in different possible implementations of aspect one, and will not be repeated here. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 A schematic diagram of a vehicle obstacle avoidance system provided in an embodiment of this application; Figure 2 A schematic flowchart illustrating a vehicle obstacle avoidance method based on a structured narrow road, provided in an embodiment of this application; Figure 3 A schematic diagram of a vehicle obstacle avoidance device based on a structured narrow road, provided for an embodiment of this application; Figure 4 This is a schematic diagram of a vehicle obstacle avoidance system based on a structured narrow road, provided as an embodiment of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0026] Currently, the passage of intelligent driving vehicles in narrow road scenarios mainly relies on preset path planning and obstacle avoidance algorithms. The path planning algorithm determines an initial path based on map and environmental data, and then adjusts and optimizes it in real time by incorporating road topology and obstacle locations to ensure the path meets driving requirements. However, this path planning algorithm has significant shortcomings in narrow road scenarios. On the one hand, inaccurate estimations of road width and obstacle size may result in a planned path that does not meet the actual passage conditions, preventing the vehicle from passing smoothly. On the other hand, it lacks flexibility and real-time performance when dealing with complex and changing road conditions, making it difficult to make rapid adjustments.

[0027] Obstacle avoidance algorithms focus on identifying and responding to obstacles in motion. They acquire obstacle information through sensors, process and analyze the data to determine the obstacle's type, location, speed, etc., and then decide on the vehicle's obstacle avoidance actions, such as slowing down, stopping, or detouring. However, these algorithms have several problems. For example, their accuracy in identifying obstacle types is poor, prone to misjudgment or omission, affecting the accuracy of decision-making. Their prediction and response to dynamic obstacles are also not precise enough, making it difficult to accurately predict their movement trends and take timely and appropriate obstacle avoidance measures.

[0028] Based on this, embodiments of this application provide a vehicle obstacle avoidance method, apparatus, and device based on structured narrow roads, applied to a target vehicle traveling on a structured narrow road. The method includes: when an obstacle is detected in front of the target vehicle, acquiring obstacle information of the obstacle and road information of the structured narrow road based on multiple sensors of the target vehicle; identifying the obstacle type based on the obstacle information; determining an obstacle avoidance strategy for the target vehicle based on obstacle avoidance information corresponding to the obstacle type in the obstacle information and road information; and controlling the target vehicle to avoid the obstacle according to the obstacle avoidance strategy.

[0029] The vehicle obstacle avoidance method based on structured narrow roads provided in this application embodiment can obtain comprehensive and accurate obstacle and road information in front of the target vehicle by using multiple sensors working together. This allows the type of obstacle to be determined, and by analyzing the obstacle information, obstacle type, and road information in real time, an accurate obstacle avoidance strategy can be made in a timely manner. This helps to improve traffic efficiency, avoid traffic congestion caused by unnecessary parking, and reduce the risk of collision.

[0030] The methods provided in the embodiments of this application will now be described in conjunction with the accompanying drawings.

[0031] On one hand, embodiments of this application provide a vehicle obstacle avoidance system 100. For example... Figure 1 As shown, the vehicle obstacle avoidance system 100 may include multiple sensor devices 101 and a processor 102.

[0032] The sensor device 101 is used to collect obstacle information and road information in front of the vehicle and send the obstacle information and road information to the processor 102. For example, the sensor device may include, but is not limited to, lidar, cameras, millimeter-wave radar and ultrasonic sensors.

[0033] LiDAR, in particular, can be used to measure the distance to surrounding objects by emitting laser pulses and receiving reflected light. By generating high-precision 3D point cloud maps, it accurately depicts the outline and position of obstacles, as well as their real-time distance to vehicles. It can achieve centimeter-level measurement accuracy even in complex environments.

[0034] Cameras can be installed in multiple locations on a vehicle, including the front and rear bumpers, side mirrors, etc., to achieve 360-degree panoramic visual coverage. Cameras can be used to capture road image information and identify road marking types (e.g., dashed lines, solid lines, double solid lines), traffic signs, traffic lights, and obstacle types (e.g., pedestrians, bicycles, cars, trucks, etc.) on structured, narrow roads.

[0035] Millimeter-wave radar can be used to monitor changes in the speed and distance of objects around a vehicle. For example, by emitting millimeter-wave signals and receiving reflected waves, it can measure the relative speed, acceleration, and real-time distance of obstacles to a target vehicle.

[0036] Ultrasonic sensors can be used for short-range obstacle detection. For example, they can detect obstacles within a short distance around a vehicle. Ultrasonic sensors measure the real-time distance to obstacles by emitting ultrasonic waves and receiving the echoes, thus assisting other sensors in making accurate distance judgments.

[0037] The processor 102 is configured to, upon receiving obstacle information and road information sent by the sensor device 101, determine the obstacle avoidance strategy of the target vehicle using the vehicle obstacle avoidance method based on structured narrow roads provided in this application embodiment, and then control the target vehicle according to the obstacle avoidance strategy so that the target vehicle avoids obstacles.

[0038] It should be noted that the above Figure 1 The illustrated vehicle obstacle avoidance system 100 is merely an example of the application scenario of this application solution and is not intended to limit the application scenario of this application solution.

[0039] On the one hand, embodiments of this application provide a vehicle obstacle avoidance method based on structured narrow roads, which can be deployed by... Figure 1 The vehicle obstacle avoidance system 100 shown is activated. For example... Figure 2 As shown, the method may include the following steps.

[0040] S201, when an obstacle is detected in front of the target vehicle, obstacle information and road information of the structured narrow road are obtained based on multiple sensors of the target vehicle.

[0041] Specifically, when the target vehicle is traveling on a structured narrow road, multiple onboard sensors monitor the road conditions ahead in real time. When an obstacle is detected in front of the target vehicle, the multiple sensors acquire obstacle information as well as road information of the structured narrow road ahead of the vehicle.

[0042] For example, when an obstacle is detected in front of a target vehicle, a lidar scanner scans the road environment ahead, generating a detailed 3D point cloud model containing the obstacle's shape, size, and spatial location. This 3D point cloud model can accurately depict the obstacle's outline and its positional distribution within a structured, narrow road. A camera, based on the principle of binocular parallax, measures the real-time distance between the obstacle and the target vehicle. Simultaneously, the camera can identify the type of obstacle (e.g., pedestrians, bicycles, cars, trucks) and its motion state (e.g., stationary, uniform motion, accelerating motion). A millimeter-wave radar continuously monitors the obstacle's real-time speed, acceleration, and changes in its direction of motion. An ultrasonic sensor measures the real-time distance to the obstacle by emitting ultrasonic waves and receiving the echoes.

[0043] Furthermore, after receiving data from multiple sensors, the target vehicle fuses the data collected by these sensors. For example, an improved Kalman filter algorithm can be used to process this data. By performing time alignment and coordinate transformation on the data from different sensors, they are unified into the same spatiotemporal coordinate system. Then, the Kalman filter algorithm is used to eliminate noise interference in the data and filter out abnormal data points caused by sensor errors or other external factors, thereby generating unified and accurate obstacle and road information.

[0044] The obstacle information can include the precise location, type, and motion status of the obstacle, while the road information can include road boundaries, lane line types, and other road information, which can provide a data foundation for determining subsequent obstacle avoidance strategies.

[0045] S202, based on obstacle information, identifies the obstacle type of the obstacle.

[0046] Specifically, the target vehicle continuously monitors and analyzes the moving speed of obstacles based on obstacle information. The obstacle type is identified based on the obstacle's moving speed.

[0047] One possible implementation is to determine the obstacle type as a dynamic obstacle if the obstacle's movement speed is not zero after multiple consecutive determinations of obstacle information.

[0048] For example, when a target vehicle is traveling on a structured narrow road, if other vehicles, pedestrians, or bicycles in front of the target vehicle consistently move at speeds greater than zero and their positions are constantly changing, the obstacle can be identified as a dynamic obstacle. This process can effectively detect dynamic obstacles such as other vehicles, pedestrians, or bicycles in front of the target vehicle.

[0049] Another possible implementation is to determine the obstacle type as a static obstacle when the obstacle's movement speed is determined to be zero and the obstacle's position is relatively fixed.

[0050] For example, static obstacles can include, but are not limited to, other vehicles parked on the roadside, roadblocks or signs placed for road construction. An obstacle can be identified as a static obstacle if its moving speed is zero and its position is relatively fixed.

[0051] S203, based on obstacle avoidance information corresponding to the obstacle type in obstacle information and road information, determine the obstacle avoidance strategy for the target vehicle.

[0052] One possible implementation involves using dynamic obstacles as obstacle avoidance information. This information includes the motion state of the dynamic obstacle and the real-time distance between the obstacle and the target vehicle. The motion state of the dynamic obstacle and the real-time distance between the obstacle and the target vehicle are extracted from the obstacle information. Based on the motion state information and road information, the target vehicle's speed is dynamically adjusted according to a preset speed adjustment algorithm to ensure that the real-time distance between the target vehicle and the dynamic obstacle remains within a safe distance range. This preset safe distance range is determined based on the target vehicle's current speed, braking performance, and road information.

[0053] Specifically, when the obstacle type is determined to be a dynamic obstacle, the motion state information of the dynamic obstacle is extracted from the obstacle information. This can include parameters such as the moving speed, acceleration, and direction of motion of the dynamic obstacle, as well as the real-time distance between the dynamic obstacle and the target vehicle. Based on the acquired motion state information and real-time distance, the target vehicle's target speed is dynamically adjusted according to a preset speed adjustment algorithm. This preset speed adjustment algorithm comprehensively considers factors such as the target vehicle's current speed, braking performance, and road information to ensure that the adjusted speed keeps the real-time distance between the target vehicle and the dynamic obstacle within a preset safe distance range.

[0054] For example, if a dynamic obstacle (such as a vehicle in front) suddenly decelerates, the target vehicle can quickly calculate the degree to which it needs to decelerate based on the magnitude of the deceleration and its current state, allowing it to follow the vehicle in front smoothly within a safe distance and effectively avoid rear-end collisions.

[0055] Another possible implementation involves using static obstacles. The obstacle avoidance information includes the road marking type on the bypass side and the lateral distance between the obstacle and the centerline of the structured narrow road. If the road information indicates the structured narrow road is not an intersection, the road marking type on the bypass side and the lateral distance between the obstacle and the centerline of the structured narrow road are extracted from the road information. If the road marking type is dashed and the lateral distance is greater than or equal to the traversable distance, the obstacle avoidance route and obstacle avoidance control parameters for the target vehicle are determined based on the obstacle information and the road information.

[0056] Furthermore, obstacle information includes the location and shape information of static obstacles on the structured narrow road. Based on the location and shape information and the path planning algorithm, a bypass route and bypass control parameters are determined so that the target vehicle, under the control of the bypass control parameters, bypasses the static obstacle from the current lane through the bypass lane.

[0057] After determining the obstacle avoidance route and obstacle avoidance control parameters, the vehicle is controlled to travel along the obstacle avoidance route so that the target vehicle can perform the obstacle avoidance operation.

[0058] Specifically, when the obstacle type is determined to be a static obstacle, and the road information indicates that the structured narrow road is not an intersection scenario, the target vehicle extracts the road marking type on the obstacle bypass side and the lateral distance of the obstacle from the road centerline from the road information. If the road marking type is a dashed line, and the lateral distance of the obstacle from the road centerline is greater than or equal to a preset detour distance (this distance can be preset based on factors such as vehicle size and safety requirements), the obstacle bypass route and obstacle bypass control parameters of the target vehicle will be determined using a path planning algorithm based on the obstacle's location and shape information.

[0059] The obstacle avoidance control parameters can include steering angle and speed adjustment during obstacle avoidance, ensuring that the target vehicle smoothly and safely bypasses the static obstacle from the current lane via the obstacle avoidance lane. For example, when a vehicle is traveling on a narrow two-way road, if there is a parked car (static obstacle) in the right lane ahead, the system analyzes its position and shape, plans an obstacle avoidance route from the left dashed lane, and controls the vehicle to bypass the car according to the obstacle avoidance route.

[0060] Furthermore, when other vehicles are present in the obstacle avoidance lane, their driving status information is acquired. The lateral distance between the target vehicle and the obstacle avoidance lane, as well as the obstacle avoidance acceleration (a key obstacle avoidance control parameter), are obtained. Based on the driving status information, lateral distance, and obstacle avoidance acceleration of other vehicles, the relative motion trend between the target vehicle and adjacent vehicles during the obstacle avoidance maneuver is predicted. If the relative motion trend indicates that a collision between the target vehicle and adjacent vehicles will not occur, the target vehicle is controlled to travel according to the obstacle avoidance route and obstacle avoidance control parameters to perform the obstacle avoidance maneuver.

[0061] When the relative motion trend indicates that the target vehicle will collide with an adjacent vehicle, the obstacle avoidance strategy is determined to be to stop and avoid a static obstacle.

[0062] Specifically, when other vehicles are present in the obstacle avoidance lane, their driving status information can be obtained, including their speed and direction of travel. Simultaneously, the lateral distance between the target vehicle and the obstacle avoidance lane, as well as the obstacle avoidance acceleration in the obstacle avoidance control parameters, will also be acquired. Based on the speed and direction of travel of other vehicles, the lateral distance between the target vehicle and the obstacle avoidance lane, and the obstacle avoidance acceleration in the obstacle avoidance control parameters, the relative motion trend between the target vehicle and adjacent vehicles during the obstacle avoidance maneuver can be predicted. If the prediction indicates that the target vehicle will not collide with adjacent vehicles, the target vehicle will be controlled to execute the obstacle avoidance maneuver according to the planned obstacle avoidance route and obstacle avoidance control parameters. Conversely, if the prediction indicates a collision risk, the obstacle avoidance strategy will be reassessed and determined to be stopping to avoid static obstacles to ensure the driving safety of the target vehicle.

[0063] Another possible implementation is to determine the obstacle avoidance strategy as stopping to avoid static obstacles when the road marking type is solid line, the lateral distance is less than the detour distance, or the road information indicates that the narrow road is a structured intersection.

[0064] Specifically, when the road markings are solid lines, or the lateral distance between the obstacle and the road centerline is less than the allowable detour distance, or the road information indicates a structured narrow road at an intersection, the obstacle avoidance strategy is determined to be stopping and yielding to static obstacles. In this process, when the road markings are solid lines, stopping and yielding to obstacles prevents vehicles from changing lanes on solid lines, thus avoiding traffic violations. Simultaneously, it avoids situations where the obstacle is too close to the road centerline, resulting in insufficient detour space and potentially leading to a collision or other dangerous behavior if forced to detour. Furthermore, in intersection scenarios, due to the complex road conditions, such as multiple vehicles intersecting, detours may cause traffic accidents. In this case, by controlling the target vehicle to smoothly decelerate until it stops, it ensures that the target vehicle's driving complies with traffic rules while maintaining a sufficient safe distance from static obstacles, thus avoiding collisions.

[0065] Furthermore, when the obstacle avoidance time for the target vehicle to avoid static obstacles reaches the preset obstacle avoidance time, the latest obstacle information and the latest road information of the structured narrow road are obtained based on multiple sensors of the target vehicle. Based on the latest obstacle and road information, the obstacle avoidance strategy of the target vehicle is updated. The target vehicle is then controlled according to the updated obstacle avoidance strategy to avoid the obstacle.

[0066] Among them, the obstacle avoidance time threshold can be a preset time threshold based on factors such as the average processing speed of the target vehicle and traffic flow.

[0067] Specifically, during the process of the target vehicle avoiding a static obstacle, the target vehicle will monitor the obstacle avoidance time in real time. When the obstacle avoidance time reaches the preset time, the target vehicle will again obtain the latest obstacle information and the latest road information of the structured narrow road based on multiple sensors of the target vehicle.

[0068] During this process, the state of obstacles and road conditions change over time; for example, obstacles may be removed, roads may be cleared, or traffic conditions may be alleviated. By acquiring the latest obstacle and road information, the target vehicle can reassess its obstacle avoidance strategy based on this updated information and determine its next obstacle avoidance strategy accordingly.

[0069] For example, if the obstacle has disappeared or road conditions allow continued driving, the system will control the target vehicle to resume normal driving. If the obstacle still exists and road conditions do not improve, the system will continue to implement the stop-and-avoidance strategy or replan the obstacle avoidance route to ensure that the target vehicle passes through the narrow road as quickly as possible while ensuring safety.

[0070] S204, according to the obstacle avoidance strategy, controls the target vehicle to avoid obstacles.

[0071] Specifically, based on the determined obstacle avoidance strategy, the target vehicle is precisely controlled. Under the dynamic obstacle avoidance strategy, the cruise function is triggered. By adjusting the vehicle's power output or braking system, the speed of the target vehicle can be precisely controlled, ensuring that it maintains a safe distance from the dynamic obstacle while following it as closely as possible, thus maintaining traffic flow.

[0072] In a static obstacle avoidance strategy, the vehicle's steering and power systems can be controlled to guide the target vehicle along a planned obstacle avoidance route. This process calculates the target vehicle's steering angle and speed to ensure the vehicle can smoothly switch from its current lane to the obstacle avoidance lane during the avoidance process, and safely return to its original lane or continue along the planned route after bypassing the obstacle.

[0073] When the obstacle avoidance strategy is parking obstacle avoidance, the target vehicle can be controlled to smoothly decelerate until it comes to a complete stop, maintaining vehicle stability during the parking process. During parking obstacle avoidance, changes in the surrounding environment can be continuously monitored, and once the obstacle disappears or road conditions allow the vehicle to continue driving, the target vehicle will be promptly controlled to resume normal driving.

[0074] The above primarily describes the solutions provided in this application from the perspective of the device's working principle. It is understood that, to achieve the aforementioned functions, the vehicle avoidance device based on structured narrow roads includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the algorithm steps of the examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0075] This application embodiment can divide the vehicle avoidance device based on structured narrow roads into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module.

[0076] It should be noted that the module division in this embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. When dividing functional modules according to their respective functions, Figure 3 A schematic diagram of a possible composition of the vehicle avoidance device based on structured narrow roads involved in the above and embodiments is shown. Figure 3 As shown, the vehicle avoidance device 300 based on structured narrow roads may include: an acquisition module 301, an identification module 302, a determination module 303, and a control module 304.

[0077] The acquisition module 301 is used to support the execution of the vehicle avoidance device 300 based on structured narrow roads. Figure 2 S201 in the illustrated vehicle avoidance method based on structured narrow roads.

[0078] Recognition module 302 is used to support the execution of vehicle avoidance device 300 based on structured narrow roads. Figure 2 S202 in the illustrated vehicle avoidance method based on structured narrow roads.

[0079] Module 303 is used to support the execution of vehicle avoidance device 300 based on structured narrow roads. Figure 2 S203 in the illustrated vehicle avoidance method based on structured narrow roads.

[0080] Control module 304 is used to support the execution of vehicle avoidance device 300 based on structured narrow roads. Figure 2 S204 in the illustrated vehicle avoidance method based on structured narrow roads.

[0081] One possible implementation involves using dynamic obstacles as obstacle avoidance information, including the motion state information of the dynamic obstacle and the real-time distance between the dynamic obstacle and the target vehicle. Specifically, the vehicle avoidance device based on structured narrow roads extracts the motion state information of the dynamic obstacle and the real-time distance between the dynamic obstacle and the target vehicle from the obstacle information. Based on the motion state information and road information, the target vehicle's speed is dynamically adjusted according to a preset speed adjustment algorithm to ensure that the real-time distance between the target vehicle and the dynamic obstacle remains within a safe distance range. The preset safe distance range is determined based on the target vehicle's current speed, braking performance, and road information.

[0082] One possible implementation involves using a static obstacle as the obstacle avoidance information, including the road marking type on the bypass side and the lateral distance between the obstacle and the centerline of the structured narrow road. Specifically, the vehicle avoidance device based on the structured narrow road is used to extract the road marking type on the bypass side and the lateral distance between the obstacle and the centerline of the structured narrow road from the road information when the road information indicates the structured narrow road is not an intersection. When the road marking type is a dashed line and the lateral distance is greater than or equal to the dodgeable distance, the obstacle avoidance route and obstacle avoidance control parameters of the target vehicle are determined based on the obstacle information and road information. The vehicle is controlled to travel along the obstacle avoidance route to perform the obstacle avoidance operation. And / or, when the road marking type is a solid line, the lateral distance is less than the dodgeable distance, or the road information indicates the structured narrow road is an intersection, the obstacle avoidance strategy is determined to be stopping and avoiding the static obstacle.

[0083] One possible implementation involves using obstacle information that includes the location and shape of static obstacles on a structured narrow road. Specifically, the vehicle avoidance device based on the structured narrow road is used to determine an obstacle avoidance route and obstacle avoidance control parameters based on the location and shape information and a path planning algorithm. This allows the target vehicle to bypass the static obstacle from its current lane via an obstacle avoidance lane under the control of the obstacle avoidance control parameters.

[0084] In one possible implementation, when other vehicles are present in the obstacle avoidance lane, the vehicle avoidance device based on structured narrow roads also acquires the driving status information of other vehicles. This includes acquiring the lateral distance between the target vehicle and the obstacle avoidance lane, as well as the obstacle avoidance acceleration of the obstacle avoidance control parameters. Based on the driving status information, lateral distance, and obstacle avoidance acceleration of other vehicles, the device predicts the relative motion trend between the target vehicle and adjacent vehicles during the obstacle avoidance maneuver. If the relative motion trend indicates that a collision between the target vehicle and adjacent vehicles will not occur, the device controls the target vehicle to travel according to the obstacle avoidance route and obstacle avoidance control parameters to enable the target vehicle to perform the obstacle avoidance maneuver. And / or, if the relative motion trend indicates that a collision between the target vehicle and adjacent vehicles will occur, the obstacle avoidance strategy is determined to be stopping to avoid a static obstacle.

[0085] One possible implementation involves a vehicle avoidance device based on structured narrow roads that, when the obstacle avoidance time for a target vehicle to avoid a static obstacle reaches a preset avoidance time, acquires the latest obstacle information and the latest road information of the structured narrow road based on multiple sensors of the target vehicle. Based on the latest obstacle and road information, the obstacle avoidance strategy of the target vehicle is updated. The target vehicle is then controlled according to the updated obstacle avoidance strategy to ensure it avoids the obstacle.

[0086] One possible implementation is that the vehicle avoidance device based on structured narrow roads is specifically used to determine the obstacle type as a dynamic obstacle when the moving speed of the obstacle is not zero in multiple consecutive obstacle information determinations. And / or, when the moving speed of the obstacle is zero and the obstacle position in the obstacle information is relatively fixed, the obstacle type is determined as a static obstacle.

[0087] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0088] The vehicle avoidance device 300 based on structured narrow roads provided in this application embodiment is used to perform the above-mentioned... Figure 2 The vehicle avoidance method based on structured narrow roads shown can therefore achieve the same effect as the vehicle avoidance method based on structured narrow roads described above.

[0089] This application also provides a vehicle avoidance device based on structured narrow roads, which can perform the vehicle avoidance method and related steps based on structured narrow roads in the above method embodiments.

[0090] This application also provides a computer-readable storage medium storing instructions that, when executed, perform the vehicle avoidance method and related steps based on structured narrow roads in the above method embodiments.

[0091] This application also provides a computer program product that, when run on a computer, causes the computer to execute the vehicle avoidance method and related steps based on structured narrow roads described in the above method embodiments.

[0092] In some embodiments, the methods shown in this application can be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of art.

[0093] This application also provides a vehicle avoidance system 400 based on structured narrow roads, such as... Figure 4 As shown, the vehicle avoidance system 400 based on structured narrow roads includes at least one processor 401 and at least one interface circuit 402.

[0094] As an example, when the vehicle avoidance system 100 based on structured narrow roads includes a processor and an interface circuit, the processor can be... Figure 4 The processor 401 shown in the solid box (or the processor 401 shown in the dashed box) can be an interface circuit. Figure 4 The interface circuit 402 is shown in the solid box (or the dashed box). When the vehicle avoidance system 100 based on structured narrow roads includes two processors and two interface circuits, then the two processors include... Figure 4 The processor 401 shown in the solid box and the processor 401 shown in the dashed box, these two interface circuits include Figure 4 Interface circuit 402 is shown in both solid and dashed boxes. No limitations are imposed on this.

[0095] Processor 401 and interface circuit 402 can be interconnected via a line. For example, interface circuit 402 can be used to receive signals. Alternatively, interface circuit 402 can be used to send signals to other devices (e.g., processor 401). For instance, interface circuit 402 can read computer instructions stored in memory and send those instructions to processor 401. Processor 401 executes the instructions and, in conjunction with input / output devices, implements the various steps in the above embodiments, such as implementing... Figure 2 The various steps performed in any of the method embodiments shown herein. Of course, this vehicle avoidance system based on structured narrow roads may also include other discrete components, which are not specifically limited in this application.

[0096] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0098] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0100] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to it, or all or part of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A vehicle obstacle avoidance method based on structured narrow roads, characterized in that, Applied to a target vehicle traveling on a structured narrow road; the method includes: When an obstacle is detected in front of the target vehicle, obstacle information and road information of the structured narrow road are obtained based on multiple sensors of the target vehicle. Based on the obstacle information, the obstacle type of the obstacle is identified; Based on the obstacle information and the obstacle avoidance information corresponding to the obstacle type in the road information, the obstacle avoidance strategy of the target vehicle is determined; According to the obstacle avoidance strategy, the target vehicle is controlled to avoid the obstacle.

2. The method according to claim 1, characterized in that, When the obstacle type is a dynamic obstacle, the obstacle avoidance information includes the motion state information of the dynamic obstacle and the real-time distance between the dynamic obstacle and the target vehicle; determining the obstacle avoidance strategy of the target vehicle based on the obstacle information and the obstacle avoidance information corresponding to the obstacle type in the road information includes: The motion state information of the dynamic obstacle and the real-time distance between the dynamic obstacle and the target vehicle are extracted from the obstacle information. Based on the motion state information and the road information, the target speed of the target vehicle is dynamically adjusted according to a preset speed adjustment algorithm so that the real-time distance between the target vehicle and the dynamic obstacle is within a safe distance range; the safe distance range is determined based on the current speed of the target vehicle, the braking performance of the target vehicle, and the road information.

3. The method according to claim 1, characterized in that, When the obstacle type is a static obstacle, the obstacle avoidance information includes the road marking type on the bypass side and the lateral distance of the obstacle from the centerline of the structured narrow road; determining the obstacle avoidance strategy of the target vehicle based on the obstacle information and the obstacle avoidance information corresponding to the obstacle type in the road information includes: When the road information indicates that the structured narrow road is a non-intersection scenario, the road marking type on the obstacle bypass side and the lateral distance of the obstacle from the road centerline of the structured narrow road are extracted from the road information. When the road marking type is dashed and the lateral distance is greater than or equal to the detour distance, the obstacle avoidance route and obstacle avoidance control parameters of the target vehicle are determined based on the obstacle information and the road information. Control the vehicle to travel along the obstacle avoidance route so that the target vehicle can perform obstacle avoidance operations; And / or, if the road marking type is a solid line, or the lateral distance is less than the detour distance, or the road information indicates that the structured narrow road is an intersection scenario, the obstacle avoidance strategy is determined to be stopping to avoid the static obstacle.

4. The method according to claim 3, characterized in that, The obstacle information includes the location information and shape information of the static obstacle on the structured narrow road; determining the obstacle avoidance route and obstacle avoidance control parameters of the target vehicle based on the obstacle information and the road information includes: The obstacle avoidance route and obstacle avoidance control parameters are determined based on the location information, the shape information, and the path planning algorithm, so that the target vehicle, under the control of the obstacle avoidance control parameters, bypasses the static obstacle from the current lane through the obstacle avoidance lane based on the obstacle avoidance route.

5. The method according to claim 4, characterized in that, When other vehicles are present in the obstacle avoidance lane, the method further includes: Obtain the driving status information of the other vehicles; The lateral distance between the target vehicle and the obstacle avoidance lane, as well as the obstacle avoidance acceleration of the obstacle avoidance control parameters, are obtained. Based on the driving status information of other vehicles, the lateral distance, and the obstacle avoidance acceleration, predict the relative motion trend of the target vehicle with the adjacent vehicles when performing obstacle avoidance operations; When the relative motion trend indicates that the target vehicle will not collide with the adjacent vehicle, the target vehicle is controlled to drive according to the obstacle avoidance route and obstacle avoidance control parameters so that the target vehicle can perform obstacle avoidance operation; And / or, if the relative motion trend indicates that the target vehicle will collide with the adjacent vehicle, the obstacle avoidance strategy is determined to be to stop and avoid the static obstacle.

6. The method according to claim 3 or 5, characterized in that, The method further includes: When the obstacle avoidance time of the target vehicle reaches the preset obstacle avoidance time, the latest obstacle information of the obstacle and the latest road information of the structured narrow road are obtained based on multiple sensors of the target vehicle. The obstacle avoidance strategy of the target vehicle is updated based on the latest obstacle information and the latest road information. The target vehicle is controlled to avoid the obstacle based on the updated obstacle avoidance vehicle.

7. The method according to claim 1, characterized in that, The step of identifying the obstacle type based on the obstacle information includes: If the moving speed of an obstacle is not zero after multiple consecutive determinations of the obstacle information, the obstacle type is determined to be a dynamic obstacle. And / or, if it is determined that the moving speed of the obstacle is zero and the obstacle position of the obstacle information is relatively fixed, the obstacle type of the obstacle is determined to be a static obstacle.

8. A vehicle obstacle avoidance method and device based on structured narrow roads, characterized in that, Applied to a target vehicle traveling on a structured narrow road; the device includes: The acquisition module is used to acquire obstacle information of the obstacle and road information of the structured narrow road based on multiple sensors of the target vehicle when an obstacle is detected in front of the target vehicle. The identification module is used to identify the obstacle type of the obstacle based on the obstacle information; The determination module is used to determine the obstacle avoidance strategy of the target vehicle based on the obstacle information and the obstacle avoidance information corresponding to the obstacle type in the road information; The control module is used to control the target vehicle to avoid the obstacle according to the obstacle avoidance strategy.

9. A vehicle obstacle avoidance device based on structured narrow roads, characterized in that, The vehicle obstacle avoidance device based on structured narrow roads includes a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor, the processor executing the machine-executable instructions to implement the vehicle obstacle avoidance method based on structured narrow roads according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when invoked and executed by a processor, cause the processor to implement the vehicle obstacle avoidance method based on any one of claims 1 to 7.

Images