Artificial potential field method obstacle avoidance method and system based on self-adaptive weight adjustment, and environmental sanitation vehicle

Abstract

The invention relates to a self-adaptive weight adjustment artificial potential field method obstacle avoidance method and system and a sanitation vehicle. The method comprises the steps that a laser radar and an ultrasonic sensor are used for collecting environment data around the vehicle; carrying out denoising, fusion and normalization processing on the collected data; establishing an attraction potential field and a repulsion potential field between the target and the obstacle; dynamically adjusting the weight of the attraction potential field and the weight of the rejection potential field according to the current position of the vehicle and the environment information; calculating a total resultant force field according to the adjusted weight, the attraction potential field and the rejection potential field, and searching an optimal path from the current position to the target point by using a path search algorithm based on the total resultant force field; and controlling the driving direction and speed of the vehicle according to the calculated optimal path. According to the invention, the weights of the attraction potential field and the repulsion potential field are dynamically adjusted, so that the vehicle can make an optimal obstacle avoidance decision according to the current environment and state, and the obstacle avoidance efficiency and safety are improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an adaptive weight-adjusted artificial potential field obstacle avoidance method, system and sanitation vehicle. Background Art

[0002] With the rapid development of autonomous driving technology, autonomous vehicles such as sanitation vehicles have become important tools for urban cleaning and maintenance. When performing tasks such as cleaning and garbage collection, these vehicles must have efficient and reliable obstacle avoidance capabilities to ensure the safety and efficiency of the operation process. At present, the obstacle avoidance technology of autonomous driving vehicles mainly relies on the artificial potential field method, which has been widely used in the field of autonomous driving due to its intuitiveness and ease of implementation.

[0003] The traditional artificial potential field method is an obstacle avoidance strategy based on a virtual force field. By treating the target point and the obstacle as positive and negative charges (or gravitational sources and repulsive sources), respectively, an attractive potential field and a repulsive potential field are constructed to guide the movement of the vehicle. The attractive potential field is emitted from the target point, exerting a continuous attraction on the vehicle, allowing the vehicle to move in the direction of reduced potential energy (i.e., toward the target point). The repulsive potential field is formed around the obstacle, exerting a repulsive force on the vehicle approaching the obstacle, thereby preventing the vehicle from colliding with the obstacle.

[0004] Although the traditional artificial potential field method has certain effects in obstacle avoidance, its limitations are becoming increasingly prominent in practical applications:

[0005] (1) Unreachable target and local minimum problem: In a complex environment, multiple obstacles may form a complex repulsive potential field, which may cause the vehicle to be unable to find the best path to the target in some cases, or even fall into a local minimum and be unable to move forward.

[0006] (2) Repulsive potential field conflict: When multiple obstacles exist at the same time, the repulsive potential fields generated by them may conflict with each other, causing the vehicle to fall into a "wandering" state and be unable to successfully cross the obstacle area.

[0007] (3) Motion mutation problem: When a vehicle approaches an obstacle, the repulsive force will increase sharply, which may cause a sudden change in the vehicle's motion, affecting the smoothness and safety of driving.

[0008] (4) Insufficient flexibility due to fixed weights: In traditional artificial potential field methods, the weights of the attractive potential field and the repulsive potential field are usually fixed and cannot be dynamically adjusted according to the actual environment and vehicle status. This fixed weight limits the flexibility and adaptability of the obstacle avoidance strategy, making it impossible for the vehicle to make the best obstacle avoidance decision when facing different situations.

[0009] In summary, the traditional artificial potential field method has many limitations in obstacle avoidance, especially in complex environments, where its obstacle avoidance efficiency and safety are difficult to guarantee. Therefore, it is particularly important to develop a new method that can overcome these defects and improve obstacle avoidance efficiency and safety. Summary of the invention

[0010] The purpose of the present invention is to provide an artificial potential field obstacle avoidance method, system and sanitation vehicle with adaptive weight adjustment, which can dynamically adjust the weights of the attractive potential field and the repulsive potential field so that the vehicle can make the best obstacle avoidance decision according to the current environment and status to improve the obstacle avoidance efficiency and safety.

[0011] In a first aspect, the present invention provides an obstacle avoidance method using an artificial potential field method with adaptive weight adjustment, comprising the following steps:

[0012] Data collection: Use lidar and ultrasonic sensors to collect environmental data around the vehicle, including the location, size, and shape of obstacles;

[0013] Data preprocessing: denoising, fusion and normalization of collected data;

[0014] Establishing artificial potential field: establishing attractive potential field and repulsive potential field between the target and the obstacle, where the attractive potential field is used to guide the vehicle to move toward the target point, and the repulsive potential field is used to prevent the vehicle from colliding with the obstacle;

[0015] Adaptive weight adjustment: dynamically adjust the weight of the attractive potential field and the weight of the repulsive potential field according to the vehicle's current position and environmental information;

[0016] Path calculation: Calculate the total resultant force field based on the adjusted weights, the attractive potential field and the repulsive potential field, and use the path search algorithm to search for the optimal path from the current position to the target point based on the total resultant force field;

[0017] Vehicle driving control: Control the vehicle's driving direction and speed based on the calculated optimal path.

[0018] Optionally, the calculation formula of the attractive potential field is:

[0019]

[0020] Among them, U a is the attractive potential field, k a is the constant of the attractive potential field, d target is the distance from the vehicle to the target point.

[0021] Optionally, the calculation formula of the repulsive potential field is:

[0022]

[0023] Among them, U r is the repulsive potential field, k r is the constant of the repulsive potential field, d obstacle is the distance from the vehicle to the nearest obstacle.

[0024] Optionally, the method for dynamically adjusting the weight of the attractive potential field is:

[0025]

[0026] Among them, W a is the weight of the attractive potential field, k a is the constant of the attractive potential field, d target is the distance from the vehicle to the target point, d current is the current distance of the vehicle.

[0027] Optionally, the method for dynamically adjusting the weight of the repulsive potential field is:

[0028]

[0029] Among them, W r is the weight of the repulsive potential field, k r is the constant of the repulsive potential field, d obstacle is the distance from the vehicle to the nearest obstacle, d threshold is the safety distance threshold.

[0030] Optionally, in the path calculation step, the calculation formula of the total resultant force field is:

[0031] U=W a ·U a +W r ·U r

[0032] Among them, U is the total force field, W a is the weight of the attractive potential field, U a is the attractive potential field, W r is the weight of the repulsive potential field, U r It is a repulsive potential field.

[0033] Optionally, the vehicle driving control step further includes:

[0034] Monitor the vehicle's driving status and changes in the surrounding environment in real time, and adjust the vehicle's driving direction and speed based on feedback.

[0035] Optionally, the vehicle driving control step also includes: when encountering an emergency situation, calculating a new obstacle avoidance path and controlling the vehicle to perform emergency obstacle avoidance.

[0036] In the third aspect, an obstacle avoidance system using an artificial potential field method with adaptive weight adjustment described in the present invention comprises a memory and a controller, wherein the memory stores a computer-readable program, and when the computer-readable program is called by the controller, it can execute the steps of the obstacle avoidance method using an artificial potential field method with adaptive weight adjustment described in the present invention.

[0037] In a third aspect, a sanitation vehicle described in the present invention adopts an artificial potential field obstacle avoidance system with adaptive weight adjustment as described in the present invention.

[0038] Beneficial effects of the present invention:

[0039] (1) The present invention significantly improves the safety of the obstacle avoidance path:

[0040] The present invention can dynamically adjust the weights of the attractive potential field and the repulsive potential field according to the actual environment and vehicle status, so that the system can intelligently respond to environmental changes and optimize the obstacle avoidance path; it effectively avoids the common problems of unreachable targets and falling into local minima in traditional artificial potential field methods. This dynamic adjustment capability enables sanitation vehicles to maintain a smooth and safe driving path when facing emergencies or complex obstacle distribution, reduces the risk of collision with obstacles, and ensures the safety of operators and equipment.

[0041] (2) The present invention improves the efficiency of the obstacle avoidance path:

[0042] The present invention can quickly find the optimal path by accurately calculating the resultant force field and using an advanced path search algorithm. The present invention shortens the obstacle avoidance time and path length, thereby improving the operating efficiency of sanitation vehicles. In environments such as urban streets and industrial parks, this means that vehicles can complete cleaning tasks faster, reduce interruptions caused by obstacle avoidance, and improve the timeliness and efficiency of urban cleaning.

[0043] (3) The present invention enhances the adaptability of the system:

[0044] The adaptability of the present invention has also been significantly enhanced, and it can cope with dynamically changing environments and obstacles. For example, in areas with heavy traffic or dense pedestrians, the system can monitor and adapt to these changes in real time, adjust driving strategies, and ensure that sanitation vehicles can effectively perform cleaning operations while maintaining a safe distance. This adaptability not only improves the safety of operations, but also makes it possible for sanitation vehicles to be used in a variety of environments.

[0045] (4) The present invention reduces operating costs and improves economic benefits:

[0046] The present invention reduces economic losses caused by accidents and delays; at the same time, it improves operating efficiency, bringing about a dual increase in economic and social benefits for urban sanitation work; in addition, it enhances the competitiveness of transportation companies and makes a positive contribution to the environmental sanitation and traffic safety of the entire city.

[0047] In summary, the present invention not only improves the safety and efficiency of sanitation vehicles at the technical level, but also brings significant cost savings and efficiency improvements to transportation companies at the economic level. The realization of these technical effects not only improves the competitiveness of transportation companies, but also makes important contributions to the city's environmental sanitation and traffic safety work. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a flow chart of the obstacle avoidance method using the artificial potential field method with adaptive weight adjustment described in an embodiment of the present application;

[0049] Figure 2 It is a principle block diagram of the artificial potential field method obstacle avoidance system with adaptive weight adjustment described in the embodiment of the present application;

[0050] Figure 3 It is a functional module diagram of a computer-readable program in the artificial potential field method obstacle avoidance system with adaptive weight adjustment described in the embodiments of the present application. DETAILED DESCRIPTION

[0051] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0052] like Figure 1 As shown, in an embodiment of the present application, an obstacle avoidance method using an artificial potential field method with adaptive weight adjustment includes the following steps:

[0053] Step 1: Data Collection

[0054] Use LiDAR and ultrasonic sensors to collect environmental data around the vehicle, including the location, size, and shape of obstacles. LiDAR is used to obtain long-distance and high-precision distance information, while ultrasonic sensors are used to obtain close-range obstacles.

[0055] Step 2: Data Preprocessing

[0056] The collected data is denoised and a low-pass filter is used to remove high-frequency noise. Then, the data is fused to improve the accuracy of the data. Finally, the data is normalized to make it on the same scale for subsequent processing.

[0057] Step 3: Create an artificial potential field

[0058] An attractive potential field and a repulsive potential field are established between the target and the obstacle. The attractive potential field is used to guide the vehicle to move toward the target point, and its potential field strength is inversely proportional to the distance; the repulsive potential field is used to prevent the vehicle from colliding with the obstacle, and its potential field strength is proportional to the distance. Specifically:

[0059] 3.1. Define attractive potential field:

[0060] The attractive potential field is used to simulate the attraction of the target point to the vehicle. The attractive potential field is defined as being inversely proportional to the square of the distance from the vehicle to the target point. The calculation formula of the attractive potential field is as follows:

[0061]

[0062] Among them, U a is the attractive potential field, k a is the constant of the attractive potential field, d target is the distance from the vehicle to the target point.

[0063] 3.2. Define the repulsive potential field:

[0064] The repulsive potential field is used to simulate the repulsive force of obstacles on the vehicle. The repulsive potential field is usually defined as being proportional to the square of the distance from the vehicle to the obstacle. The calculation formula of the repulsive potential field is as follows:

[0065]

[0066] Among them, U r is the repulsive potential field, k r is the constant of the repulsive potential field, d obstacle is the distance from the vehicle to the nearest obstacle.

[0067] 3.3. Potential field initialization:

[0068] Before the sanitation vehicle starts to drive, the attractive potential field and the repulsive potential field are initialized according to the preset target points and the positions of known obstacles.

[0069] Step 4: Adaptive weight adjustment:

[0070] According to the current position of the vehicle and environmental information, the weight of the attractive potential field and the weight of the repulsive potential field are dynamically adjusted. The specific steps are as follows:

[0071] 4.1. Evaluate the distance between the vehicle and the target point:

[0072] Calculate the distance from the vehicle to the target point in real time, i.e. d target .

[0073] 4.2. Evaluate the distance between the vehicle and the obstacle:

[0074] Calculate the distance from the vehicle to the nearest obstacle in real time, i.e. d obstacle .

[0075] 4.3. Dynamically adjust weights:

[0076] Dynamic Adjustment W a and W r The weight adjustment strategy is as follows:

[0077]

[0078] Among them, W a is the weight of the attractive potential field, W r is the weight of the repulsive potential field, d current is the current distance of the vehicle, d threshold is the safety distance threshold.

[0079] Step 5: Path calculation:

[0080] The total resultant force field is calculated based on the adjusted weights, the attractive potential field and the repulsive potential field, where the calculation formula for the total resultant force field is as follows:

[0081] U=W a ·U a +W r ·U r ;

[0082] Among them, U is the resultant force field;

[0083] Based on the total force field, a path search algorithm is used to search for the optimal path from the current position of the car to the target point.

[0084] In the embodiment of the present application, searching for the optimal path from the current position of the vehicle to the target point using a path search algorithm based on the total resultant force field is a prior art and will not be described in detail here.

[0085] Step 6: Vehicle Driving Control:

[0086] According to the calculated optimal path, the vehicle's driving direction and speed are controlled, including:

[0087] 6.1. Direction control:

[0088] Based on the optimal path, the next target point of the vehicle is calculated, and control instructions are generated to guide the vehicle to the target point.

[0089] 6.2. Speed ​​control: Dynamically adjust the vehicle's speed based on the distance between the vehicle and obstacles and the curvature of the driving path to ensure safety and comfort.

[0090] 6.3. Real-time feedback adjustment: monitor the vehicle's driving status and changes in the surrounding environment in real time, and adjust the vehicle's driving direction and speed based on the feedback.

[0091] 6.4. Emergency obstacle avoidance: In case of emergency, such as the sudden appearance of an obstacle, the system can quickly calculate a new obstacle avoidance path and control the vehicle to perform emergency obstacle avoidance.

[0092] This method can effectively avoid obstacles when sanitation vehicles perform cleaning tasks, ensuring safe and efficient arrival at the target point. This method optimizes the obstacle avoidance path by dynamically adjusting the weights of the attractive potential field and the repulsive potential field, avoiding falling into the local minimum, thereby improving the safety and efficiency of obstacle avoidance.

[0093] The following examples illustrate the embodiments of the present application:

[0094] For example, a sanitation vehicle is performing a cleaning task on a busy city street. The goal is to navigate safely and efficiently from point A to point B while avoiding obstacles along the way. Point A is at the beginning of the street, and point B is at the other end of the street, with a straight-line distance of 100 meters between them. The sanitation vehicle needs to smoothly pass through narrow streets while maintaining a safe distance from pedestrians and parked vehicles.

[0095] In the step of establishing the artificial potential field, we first define the attractive potential field and the repulsive potential field. Assume that the attractive potential field constant k a =100, target point distance d target = 100 meters, according to the formula The attractive potential field is calculated:

[0096]

[0097] For the repulsive potential field, assume that the constant k of the repulsive potential field is r =1000, safety distance threshold d threshold = 0.5 m, the distance d from the vehicle to the nearest obstacle obstacle = 0.3 m, according to the formula The repulsive potential field U is calculated r ≈11111.11. These potential fields will guide the sanitation vehicle to avoid obstacles and move towards the target point.

[0098] In the adaptive weight adjustment step, the weights of the attractive and repulsive potential fields are dynamically adjusted according to the vehicle’s real-time position and environmental information. a =0.01, k r =0.01, current distance dcurrent =50 meters, safety distance threshold d threshold =0.5 m.

[0099] According to the formula:

[0100]

[0101] Calculate W a =0.623 and W r =0.998.

[0102] In the path calculation step, the total resultant force field is calculated based on the adjusted weights, the attractive potential field and the repulsive potential field, and the optimal path of the vehicle is calculated.

[0103] According to the formula U=W a ·U a +W r ·U r , we can calculate:

[0104] U=0.623×0.01+0.998×11111.11=11088.89.

[0105] Then, a path search algorithm is used to search for the optimal path from point A to point B.

[0106] Finally, the vehicle's driving direction and speed are controlled according to the calculated optimal path.

[0107] Through the above method, the present invention can effectively avoid obstacles when sanitation vehicles perform cleaning tasks, ensuring safe and efficient arrival at the target point. This adaptive weight-adjusted artificial potential field method obstacle avoidance algorithm and its system optimize the obstacle avoidance path by dynamically adjusting the weights of the attraction and repulsion potential fields, avoiding falling into the local minimum, thereby improving the safety and efficiency of obstacle avoidance.

[0108] As shown in 2, in an embodiment of the present application, an obstacle avoidance system using an artificial potential field method with adaptive weight adjustment includes a memory and a controller. A computer-readable program is stored in the memory. When the computer-readable program is called by the controller, the steps of the obstacle avoidance method using an artificial potential field method with adaptive weight adjustment can be executed as described in the embodiment of the present application.

[0109] like Figure 3As shown, in the embodiment of the present application, the computer-readable program is divided according to the functional modules, which include: a data acquisition module, a data preprocessing module, an artificial potential field establishment module, an adaptive weight adjustment module, a path calculation module and a vehicle control module, wherein: the data acquisition module is used to obtain the environmental data around the vehicle collected by the laser radar and the ultrasonic sensor. The data preprocessing module is used to denoise, fuse and normalize the collected data. The artificial potential field establishment module is used to establish an attractive potential field and a repulsive potential field between the target and the obstacle. The adaptive weight adjustment module is used to dynamically adjust the weight of the attractive potential field and the weight of the repulsive potential field according to the current position of the vehicle and the environmental information. The path calculation module is used to calculate the total resultant force field according to the adjusted weights, the attractive potential field and the repulsive potential field, and use the path search algorithm to search for the optimal path from the current position to the target point according to the total resultant force field. The vehicle control module is used to control the driving direction and speed of the vehicle according to the calculated optimal path.

[0110] In an embodiment of the present application, a sanitation vehicle adopts an artificial potential field obstacle avoidance system with adaptive weight adjustment as described in the embodiment of the present application.

[0111] The above-mentioned embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above-mentioned embodiments. Any other changes, modifications, substitutions, combinations and simplifications made without departing from the spirit and principle of the present invention shall be equivalent replacement modes and shall be included in the protection scope of the present invention.

Claims

1. An artificial potential field obstacle avoidance method with adaptive weight adjustment, characterized in that: The following steps are involved: Data collection: Use lidar and ultrasonic sensors to collect environmental data around the vehicle, including the location, size, and shape of obstacles; Data preprocessing: denoising, fusion and normalization of collected data; Establishing artificial potential field: establishing attractive potential field and repulsive potential field between the target and the obstacle, where the attractive potential field is used to guide the vehicle to move toward the target point, and the repulsive potential field is used to prevent the vehicle from colliding with the obstacle; Adaptive weight adjustment: Dynamically adjust the weight of the attractive potential field and the weight of the repulsive potential field according to the vehicle's current position and environmental information; Path calculation: Calculate the total resultant force field based on the adjusted weights, the attractive potential field and the repulsive potential field, and use the path search algorithm to search for the optimal path from the current position to the target point based on the total resultant force field; Vehicle driving control: Control the vehicle's driving direction and speed based on the calculated optimal path.

2. The obstacle avoidance method using artificial potential field method with adaptive weight adjustment according to claim 1, characterized in that: The calculation formula of the attractive potential field is: Among them, U a is the attractive potential field, k a is the constant of the attractive potential field, d target is the distance from the vehicle to the target point.

3. The obstacle avoidance method using artificial potential field method with adaptive weight adjustment according to claim 1, characterized in that: The calculation formula of the repulsive potential field is: Among them, U r is the repulsive potential field, k r is the constant of the repulsive potential field, d obstacle is the distance from the vehicle to the nearest obstacle.

4. The obstacle avoidance method using artificial potential field method with adaptive weight adjustment according to claim 1, characterized in that: The method to dynamically adjust the weight of the attractive potential field is: Among them, W a is the weight of the attractive potential field, k a is the constant of the attractive potential field, d target is the distance from the vehicle to the target point, d current is the current distance of the vehicle.

5. The obstacle avoidance method using artificial potential field method with adaptive weight adjustment according to claim 1, characterized in that: The method to dynamically adjust the weight of the repulsive potential field is: Among them, W r is the weight of the repulsive potential field, k r is the constant of the repulsive potential field, d obstacle is the distance from the vehicle to the nearest obstacle, d threshold is the safety distance threshold.

6. The obstacle avoidance method using artificial potential field method with adaptive weight adjustment according to claim 1, characterized in that: In the path calculation step, the calculation formula for the total resultant force field is: U=W a ·U a +W r ·U r Among them, U is the total force field, W a is the weight of the attractive potential field, U a is the attractive potential field, W r is the weight of the repulsive potential field, U r It is a repulsive potential field.

7. The obstacle avoidance method using artificial potential field method with adaptive weight adjustment according to claim 1, characterized in that: The vehicle driving control step further includes: Monitor the vehicle's driving status and changes in the surrounding environment in real time, and adjust the vehicle's driving direction and speed based on feedback.

8. The obstacle avoidance method using artificial potential field method with adaptive weight adjustment according to claim 1, characterized in that: The vehicle driving control step also includes: when encountering an emergency situation, calculating a new obstacle avoidance path and controlling the vehicle to perform emergency obstacle avoidance.

9. An artificial potential field obstacle avoidance system with adaptive weight adjustment, characterized in that: It comprises a memory and a controller, wherein the memory stores a computer-readable program, and when the computer-readable program is called by the controller, it can execute the steps of the obstacle avoidance method using the artificial potential field method with adaptive weight adjustment as claimed in any one of claims 1 to 8.

10. A sanitation vehicle, characterized in that: An obstacle avoidance system using an artificial potential field method with adaptive weight adjustment as described in claim 9.

Images