Bumpy road unmanned equipment control method and device and storage medium

Abstract

The present application relates to the technical field of unmanned equipment control, and specifically discloses a bumpy road unmanned equipment control method, device and storage medium, comprising: acquiring road environment information in front of the unmanned equipment and self state information; determining a road disturbance area according to the road environment information in front; predicting a passing posture and passing risk according to the road disturbance area and the self state information, obtaining an active pre-look control strategy; determining that the unmanned equipment executes the strategy when entering the road disturbance area within a preset time; when the unmanned equipment is entering or passing through the road disturbance area, determining a passive feedback correction strategy according to real-time posture response information, and dynamically fusing the active pre-look control strategy to determine a control instruction. The bumpy road unmanned equipment control method provided by the present application effectively improves the passing stability, safety and task execution reliability of the unmanned equipment on a bumpy road without relying on an active suspension and without changing the suspension structure of an ordinary vehicle.

Description

Technical Field

[0001] This invention relates to the field of unmanned equipment control technology, and in particular to a method, device and storage medium for controlling unmanned equipment on bumpy roads. Background Technology

[0002] With the development of unmanned driving, unmanned inspection, unmanned transportation, and field operation equipment, ground-based unmanned equipment is increasingly being used in scenarios such as park inspection, mining transportation, agricultural operations, emergency rescue, slope inspection, military reconnaissance, and passage through complex unstructured environments. In these scenarios, ground roads are usually not ideally smooth surfaces, but rather contain complex road disturbances such as potholes, bumps, gravel, ditches, steps, soft soil, continuous wavy surfaces, and abrupt changes in slope. When unmanned equipment passes through bumpy roads at high speeds, it is prone to significant problems such as vehicle pitch, roll, vertical impact, and unstable wheel-ground contact. This not only reduces the stability and safety of passage, but may also lead to blurred sensor imaging, decreased positioning accuracy, mission payload jitter, and increased control command execution errors. In severe cases, it may even cause unmanned equipment to become unstable, yaw, skid, bottom out, collide, or interrupt the mission.

[0003] In existing technologies, one type of method uses external sensing devices such as cameras, LiDAR, and depth cameras to identify road conditions ahead. Based on road images, point clouds, or depth information, it determines whether there are potholes, bumps, obstacles, or other uneven areas ahead. When obvious bumps or obstacles are detected ahead, the unmanned equipment is controlled to slow down, detour, or issue an alarm. For example, Chinese patent document CN111516692A discloses a method for detecting bumpy road areas. This type of method belongs to the pre-aiming control mode based on external perception, which can improve the unmanned equipment's ability to perceive changes in the road ahead to a certain extent. Another type of method collects the unmanned equipment's own state information through inertial measurement units, accelerometers, gyroscopes, wheel speed sensors, and drive motor current sensors. When the unmanned equipment travels on bumpy roads, it determines whether the road surface is bumpy based on information such as the vehicle's vertical acceleration, pitch angle, roll angle, angular velocity, and wheel speed fluctuations. Based on the determination, it reduces the vehicle speed or adjusts the control strategy. For example, Chinese patent document CN113370982A discloses a control system and method for vehicles traveling on potholed roads. This type of method belongs to the feedback control method based on vehicle body response and can reflect the actual road impact experienced by the unmanned equipment.

[0004] However, the aforementioned existing technologies all have the following drawbacks:

[0005] (1) The pre-aiming control method based on external perception mainly relies on the recognition results of external sensors and is easily affected by environmental conditions. In the case of strong light, backlight, night, rain, fog, sand and dust, water accumulation, weeds, or unclear road texture, the camera recognition results are unstable. Under the conditions of sparse point cloud, low reflectivity, or long-distance detection, the lidar also has errors in recognizing small-scale potholes and low protrusions.

[0006] (2) The pre-aiming control method based on external perception usually only decelerates or detours in advance based on the road recognition results ahead. It lacks feedback correction of the changes in vehicle posture when the unmanned equipment actually passes through the bumpy area. When the pre-aiming recognition results are inconsistent with the actual road excitation, the system is difficult to correct the control strategy in time, and problems such as insufficient deceleration, unreasonable detour or overly conservative control are likely to occur.

[0007] (3) Feedback control based on vehicle body response can only judge the degree of road disturbance based on the changes in vehicle body attitude and chassis response after the unmanned equipment has contacted or entered the bumpy area. There is obvious control lag and it is impossible to adjust the speed, trajectory and driving and braking status in advance before entering the bumpy area. For deep potholes, high bumps, continuous wave road surfaces or high speed traffic scenarios, relying solely on attitude feedback control cannot take effective measures before the impact occurs. It is easy to cause the unmanned equipment to generate large pitch, roll or vertical impact, affecting traffic safety and mission execution stability.

[0008] (4) Existing bumpy road control methods usually focus on active suspension or suspension parameter adjustment, while ordinary unmanned equipment usually does not have active suspension, semi-active suspension or adjustable suspension structure, which limits the applicability of the solution; and existing methods do not give enough consideration to the stable operation of task modules such as sensors, communication equipment, and work loads.

[0009] Therefore, how to dynamically integrate the forward road disturbance prediction and vehicle attitude feedback correction without relying on active suspension or changing the suspension structure of ordinary vehicles, so as to enable unmanned equipment to control in advance before reaching bumpy areas and make real-time corrections when passing through bumpy areas, thereby improving the travel stability, safety and mission execution reliability of unmanned equipment on bumpy roads, has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0010] This invention provides a method, device, and storage medium for controlling unmanned equipment on bumpy roads, aiming to solve at least one of the problems in related technologies, such as unstable identification of road disturbances ahead, delayed control response, large impact on vehicle posture, and significant disturbance to mission load during travel on bumpy roads.

[0011] As a first aspect of the present invention, a method for controlling unmanned equipment on bumpy roads is provided, comprising:

[0012] Acquire information about the road environment ahead of the unmanned equipment and the equipment's own status.

[0013] Based on the road environment information ahead, a road disturbance area in the road ahead is determined. The road disturbance area includes at least one of the following: pothole area, raised area, ditch area, step area, gravel area, continuous undulation area, abrupt slope area, and soft and subsided area.

[0014] Based on the road disturbance area and its own state information, the passage attitude and passage risk of the road disturbance area are predicted to obtain an active pre-aiming control strategy.

[0015] When it is determined that the unmanned equipment enters the road disturbance area within a preset time, the unmanned equipment is controlled to execute the active pre-aiming control strategy.

[0016] When the unmanned equipment is entering or passing through the road disturbance area, a passive feedback correction strategy is determined based on the real-time attitude response information of the unmanned equipment, and the control command of the unmanned equipment is determined after dynamic fusion of the passive feedback correction strategy and the active pre-aiming control strategy.

[0017] Furthermore, based on the road disturbance area and its own state information, the traffic attitude and traffic risk in the road disturbance area are predicted to obtain an active pre-aiming control strategy, including:

[0018] The road disturbance area is converted into a road disturbance event, and the road disturbance event includes at least the disturbance type, disturbance spatial location, disturbance geometric parameters, disturbance severity, expected contact time, and identification confidence.

[0019] Based on the road disturbance event and the unmanned equipment's own state information, predict the attitude response and passage risk of the unmanned equipment when passing through the road disturbance area. The attitude response includes at least one of pitch change trend, roll change trend, vertical impact intensity and wheel-ground contact change. The passage risk includes at least one of slip risk, bottoming out risk, yaw risk and mission load disturbance risk.

[0020] An active anti-aiming control strategy is generated based on the predicted results of both the attitude response and the traffic risk when the unmanned equipment passes through the road disturbance area. The active anti-aiming control strategy includes at least one of the following: speed pre-adjustment control, trajectory pre-adjustment control, driving force pre-adjustment control, braking force pre-adjustment control, steering pre-adjustment control, and mission status pre-adjustment control.

[0021] Furthermore, an active pre-aiming control strategy is generated based on the predicted results of both the attitude response and traffic risk of the unmanned equipment when passing through the road disturbance area, including:

[0022] The severity of the disturbance in the road disturbance area is determined based on the disturbance height or depth, disturbance slope, disturbance width, and the speed of the unmanned equipment.

[0023] The control strength of the active pre-aiming control strategy is determined based on the severity of the disturbance, the confidence level of the identification, and the expected contact time.

[0024] When the severity of the disturbance is greater than or equal to a preset severity threshold, the target speed of the unmanned equipment passing through the road disturbance area is reduced, and when the severity of the disturbance is less than the preset severity threshold, the target speed of the unmanned equipment is maintained.

[0025] Based on the spatial location of the road disturbance area and the traffic area information, the local driving trajectory adjustment amount is determined;

[0026] Based on the attitude response and traffic risk prediction results of the unmanned equipment when passing through the road disturbance area, the pre-adjustment control quantities of driving force, braking force, steering angle and mission status are determined.

[0027] The active aiming control strategy is generated based on at least one of the target speed of the unmanned equipment, the local driving trajectory adjustment amount, the driving force pre-adjustment control amount, the braking force pre-adjustment control amount, the steering angle pre-adjustment control amount, and the mission state pre-adjustment control amount.

[0028] Furthermore, a passive feedback correction strategy is determined based on the real-time attitude response information of the unmanned equipment, including:

[0029] The real-time attitude response information of the unmanned equipment during the process of passing through the road disturbance area is obtained. The real-time attitude response information includes at least one of pitch angle, roll angle, yaw angle, vertical acceleration, lateral acceleration, longitudinal acceleration, angular velocity and wheel speed change.

[0030] Calculate the deviation between the real-time attitude response information and the predicted attitude response, wherein the predicted attitude response is the predicted result of the attitude response of the unmanned equipment when it passes through the road disturbance area;

[0031] When the deviation exceeds a preset deviation threshold, the control strength of the passive feedback correction strategy is increased. The passive feedback correction strategy includes at least one of the following: reducing the target vehicle speed, limiting subsequent acceleration, increasing the safe tracking distance, adjusting the local trajectory, correcting the driving force distribution, correcting the braking force distribution, correcting the steering control amount, and pausing or reducing the task action.

[0032] Furthermore, the control commands for the unmanned equipment are determined by dynamically fusing the passive feedback correction strategy and the active pre-aiming control strategy, including:

[0033] Based on the recognition reliability of the road disturbance area and the deviation between the real-time attitude response information and the predicted attitude response, the fusion weight of the active aiming control strategy and the passive feedback correction strategy is determined.

[0034] The final control quantity of the unmanned equipment is determined based on the fusion weight of the active pre-aiming control strategy and the passive feedback correction strategy.

[0035] Further, determining the fusion weights of the active anti-aiming control strategy and the passive feedback correction strategy includes:

[0036] When the recognition confidence of the road disturbance area is greater than a preset confidence threshold and the deviation is less than a preset deviation threshold, the control weight of the active pre-aiming control strategy in the fusion weight is increased.

[0037] When the recognition confidence of the road disturbance area is less than or equal to the preset confidence threshold, or the deviation is greater than or equal to the preset deviation threshold, the control weight of the passive feedback correction strategy in the fusion weight is increased.

[0038] Furthermore, the expression for the final control quantity is:

[0039] ,

[0040] in, This represents the control quantity for an active anti-aiming control strategy. This represents the control quantity of a passive feedback correction strategy. This represents the final control quantity. The control weights of the active anti-aiming control strategy are represented by the following expression:

[0041] ,

[0042] in, This represents the confidence level of identifying the j-th road disturbance event. This represents the deviation between the actual attitude response and the predicted attitude response. This represents the attitude deviation adjustment coefficient. This indicates a positive number set to prevent the denominator from being zero;

[0043] The final control quantity includes at least one of the following: target speed, target acceleration, steering angle, driving torque, braking torque, local trajectory adjustment, and mission load control.

[0044] Furthermore, it also includes:

[0045] After the unmanned equipment passes through the road disturbance area, the road disturbance area, the active pre-aiming control strategy, the passive feedback correction strategy, the control command of the unmanned equipment, the real-time attitude response information and the passage result are associated and stored, and at least one of the road disturbance identification model, bump severity assessment model, attitude response prediction model and local road map is updated.

[0046] As another aspect of the present invention, a control device for unmanned equipment on bumpy roads is provided for implementing the unmanned equipment control method for bumpy roads described above, wherein the device includes:

[0047] The acquisition module is used to acquire information about the road environment ahead of the unmanned equipment and the equipment's own status information.

[0048] The road disturbance area determination module is used to determine the road disturbance area in the road ahead based on the road environment information ahead. The road disturbance area includes at least one of the following: pothole area, raised area, ditch area, step area, gravel area, continuous undulation area, abrupt slope area, and soft and subsided area.

[0049] An active anti-aiming control strategy acquisition module is used to predict the passage posture and passage risk of the road disturbance area based on the road disturbance area and its own state information, and to obtain an active anti-aiming control strategy.

[0050] The control execution module is used to control the unmanned equipment to execute the active pre-aiming control strategy when it is determined that the unmanned equipment enters the road disturbance area within a preset time.

[0051] The fusion decision module is used to determine a passive feedback correction strategy based on the real-time attitude response information of the unmanned equipment when the unmanned equipment is entering or passing through the road disturbance area, and to determine the control command of the unmanned equipment after dynamically fusing the passive feedback correction strategy with the active pre-aiming control strategy.

[0052] As another aspect of the present invention, a computer storage medium is provided, wherein computer program instructions are stored, which, when invoked, implement the unmanned equipment control method for bumpy roads as described above.

[0053] The unmanned equipment control method for bumpy roads provided by this invention combines forward aiming and identification of bumpy roads with vehicle attitude feedback correction. This allows for proactive control measures before the unmanned equipment reaches the road disturbance area, and real-time correction based on the actual attitude response when actually passing through the disturbance area. By constructing road disturbance events, the forward bumpy road information is converted into structured information including disturbance type, location, geometric parameters, expected contact time, and recognition reliability, which facilitates early decision-making by the control system. Furthermore, by dynamically adjusting the active forward aiming control and passive feedback correction based on the forward perception reliability and the deviation from the actual attitude response, the method effectively addresses these challenges. The system integrates weights to avoid misjudgments caused by relying solely on forward perception and control lag caused by relying solely on attitude feedback. Through coordinated control of speed, trajectory, driving force, braking force, steering, and mission status, it reduces the risks of pitch, roll, vertical impact, slippage, and yaw when unmanned equipment passes through bumpy roads. By updating the road disturbance identification model, attitude response prediction model, or local road map based on the results of passing through bumpy roads, it improves the stability of passing through similar road conditions in the future. Thus, without relying on active suspension or changing the suspension structure of ordinary vehicles, it improves the stability, safety, and mission execution reliability of unmanned equipment on bumpy roads. Attached Figure Description

[0054] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the following detailed description to explain the invention, but do not constitute a limitation thereof.

[0055] Figure 1 A flowchart of the control method for unmanned equipment on bumpy roads provided by the present invention.

[0056] Figure 2 The flowchart illustrates the active aiming control strategy provided by this invention.

[0057] Figure 3 The flowchart below illustrates the specific process for generating an active anti-aiming control strategy provided by this invention.

[0058] Figure 4 A flowchart illustrating the determination of a passive feedback correction strategy provided by this invention.

[0059] Figure 5 A flowchart for determining control commands for unmanned equipment provided by the present invention.

[0060] Figure 6This is a schematic diagram of the active-passive fusion control architecture provided by the present invention.

[0061] Figure 7 The structural block diagram of the unmanned equipment control device for bumpy roads provided by the present invention.

[0062] Figure 8 This is a structural block diagram of the electronic device provided by the present invention. Detailed Implementation

[0063] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0064] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0065] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0066] This embodiment provides a method for controlling unmanned equipment on bumpy roads. Figure 1 This is a flowchart of a method for controlling unmanned equipment on bumpy roads according to an embodiment of the present invention, such as... Figure 1 As shown, it includes:

[0067] S100: Obtain information about the road environment ahead of the unmanned equipment and the status information of the unmanned equipment itself.

[0068] In this embodiment of the invention, the unmanned equipment collects road environment information ahead using at least one of the following sensors: lidar, camera, depth camera, millimeter-wave radar, and ultrasonic radar. The road environment information ahead includes at least one of the following: road image, point cloud data, depth information, obstacle information, road surface texture information, road boundary information, and passable area information.

[0069] Meanwhile, the unmanned equipment collects its own status information through at least one of the following: inertial measurement unit, wheel speed sensor, drive motor sensor, steering angle sensor, braking status sensor, positioning module, and vehicle attitude sensor. This status information includes at least one of the following: vehicle speed, acceleration, steering angle, wheel speed, drive current, drive torque, braking status, pitch angle, roll angle, yaw rate, vertical acceleration, current position, and direction of travel.

[0070] S200. Determine the road disturbance area in the road ahead based on the road environment information ahead. The road disturbance area includes at least one of the following: pothole area, raised area, ditch area, step area, gravel area, continuous undulation area, abrupt slope area, and soft and subsided area.

[0071] In this embodiment of the invention, the road environment information ahead is processed to identify road disturbance areas that may cause bumps to the unmanned equipment. Road disturbance areas include at least one of the following: potholes, ridges, ditches, steps, gravel, continuous undulations, abrupt slope changes, and soft, subsided areas.

[0072] It should be understood that the recognition process can employ rule-based algorithms, geometric detection algorithms, machine learning algorithms, deep learning algorithms, or multi-sensor fusion algorithms. For example, road surface elevation differences can be extracted based on point cloud height changes, potholes can be identified based on image texture and shadow changes, bumps and grooves can be identified based on depth map abrupt changes, and the stability of road disturbance areas can be determined based on continuous frame detection results.

[0073] S300. Based on the road disturbance area and its own state information, predict the passage posture and passage risk of the road disturbance area to obtain an active pre-aiming control strategy.

[0074] Specifically, based on the identified road disturbance area and the unmanned equipment's own state information, the system predicts the unmanned equipment's travel attitude and risks when passing through the road disturbance area, and generates an active pre-aiming control strategy based on the prediction results. This active pre-aiming control strategy is used to adjust the unmanned equipment's driving state in advance before it actually reaches the road disturbance area, thereby reducing the bumps and impacts it experiences when passing through the area.

[0075] S400: When it is determined that the unmanned equipment enters the road disturbance area within a preset time, control the unmanned equipment to execute the active pre-aiming control strategy;

[0076] Specifically, based on the current position, speed, and location of the road disturbance area of ​​the unmanned equipment, the arrival time of the unmanned equipment to the road disturbance area is estimated. When the estimated arrival time is less than or equal to a preset time, it is determined that the unmanned equipment will enter the road disturbance area within the preset time. At this time, the unmanned equipment is controlled to execute an active pre-aiming control strategy, that is, according to the strategy, pre-aiming control commands are sent to the chassis control module, speed control module, steering control module, drive control module, braking control module, or mission load control module of the unmanned equipment, so that the unmanned equipment completes the necessary speed, trajectory, drive and braking, and mission status adjustments before actually contacting the road disturbance area, thereby reducing subsequent bumps and impacts.

[0077] S500: When the unmanned equipment is entering or passing through the road disturbance area, a passive feedback correction strategy is determined based on the real-time attitude response information of the unmanned equipment, and the control command of the unmanned equipment is determined after dynamic fusion of the passive feedback correction strategy and the active pre-aiming control strategy.

[0078] Specifically, when unmanned equipment is entering or passing through a road disturbance area, real-time attitude response information, such as the vehicle's posture and chassis response, is collected. This real-time attitude response information reflects the actual impact of road disturbances on the unmanned equipment. A passive feedback correction strategy is determined based on the real-time attitude response information, and this strategy is used to correct the unmanned equipment's current driving state in real time. Then, the passive feedback correction strategy is dynamically integrated with an active anti-aiming control strategy. Based on the anti-aiming planning results and the actual attitude response, control commands for the unmanned equipment are comprehensively determined and issued to the equipment's actuators for execution, enabling the unmanned equipment to smoothly pass through the road disturbance area in a manner that balances anti-aiming planning and real-time feedback.

[0079] Therefore, the unmanned equipment control method for bumpy roads provided by this invention achieves early perception of bumpy roads by acquiring the road environment information ahead and the unmanned equipment's own state information, and determining the road disturbance area based on the road environment information ahead; by predicting the travel attitude and travel risk based on the road disturbance area and the unmanned equipment's own state information and obtaining an active pre-aiming control strategy, and executing this strategy when it is determined that the unmanned equipment will enter the road disturbance area within a preset time, it achieves early adjustment of the travel state before the unmanned equipment reaches the road disturbance area, avoiding the control response lag caused by making corrections after entering the bumpy area; When unmanned equipment is entering or passing through areas of road disturbance, a passive feedback correction strategy is determined based on real-time attitude response information. This strategy can correct the driving state in real time according to the actual road impacts experienced by the unmanned equipment, avoiding the impact of recognition errors on control performance when relying solely on forward perception. By dynamically fusing the passive feedback correction strategy with the active anti-aiming control strategy to determine the control command, the system balances the advance capability of anti-aiming control with the real-time capability of feedback control. This effectively improves the stability, safety, and mission reliability of unmanned equipment on bumpy roads without relying on active suspension or changing the suspension structure of ordinary vehicles.

[0080] In this embodiment of the invention, based on the road disturbance area and its own state information, the traffic posture and traffic risk of the road disturbance area are predicted to obtain an active pre-aiming control strategy, such as... Figure 2 As shown, it includes:

[0081] S310. Convert the road disturbance area into a road disturbance event, wherein the road disturbance event includes at least the disturbance type, disturbance spatial location, disturbance geometric parameters, disturbance severity, expected contact time, and identification confidence.

[0082] In this embodiment of the invention, regarding the generation of road disturbance events, after determining the road disturbance area, the road disturbance area is converted into a road disturbance event. The road disturbance event includes at least the disturbance type, disturbance spatial location, disturbance geometric parameters, disturbance severity, expected contact time, and identification confidence level. The disturbance type includes potholes, bumps, ditches, steps, gravel, continuous wavy roads, abrupt slope changes, and soft soil subsidence, etc.; the disturbance spatial location includes the distance, orientation, lateral position, and longitudinal position of the road disturbance area relative to the unmanned equipment; the disturbance geometric parameters include the length, width, height, depth, slope, edge change rate, and roughness of the disturbance area; the disturbance severity characterizes the impact of the road disturbance on the unmanned equipment's travel stability; the expected contact time characterizes the expected time for the unmanned equipment's front wheel, rear wheel, left wheel, right wheel, or track contact area to reach the road disturbance area; and the identification confidence level characterizes the reliability of the current road disturbance identification result. Recognition confidence can be assessed based on sensor data integrity, image sharpness, point cloud density, recognition model output confidence, multi-sensor consistency, continuous frame stability, and historical data. Figure 1 At least one of the following must be determined: consistency.

[0083] S320. Based on the road disturbance event and the unmanned equipment's own state information, predict the attitude response and passage risk of the unmanned equipment when passing through the road disturbance area. The attitude response includes at least one of pitch change trend, roll change trend, vertical impact intensity, and wheel-ground contact change. The passage risk includes at least one of slippage risk, bottoming out risk, yaw risk, and mission load disturbance risk.

[0084] Specifically, the input parameters for constructing the attitude response prediction model are based on at least one of the disturbance type, disturbance geometry parameters, and disturbance severity in the road disturbance event, as well as the current speed, acceleration, and attitude information of the unmanned equipment. Let the first... The prediction input for each road disturbance event is: Then it can be expressed as:

[0085] ,

[0086] in, Indicates the height or depth of road disturbance. Indicates the width of the road disturbance. Indicates the slope of road disturbance. Indicates the severity of road disturbance. and These represent the current speed and acceleration of the unmanned equipment, respectively. and These represent the current pitch and roll angles of the unmanned equipment, respectively. The above parameters can be selected according to different types of unmanned equipment and different types of road disturbances; not all of them are required to participate in attitude response prediction simultaneously.

[0087] Furthermore, the predicted input is input into a pre-established attitude response prediction model to obtain the predicted attitude response of the unmanned equipment when passing through the road disturbance area:

[0088] ,

[0089] in, This represents the attitude response prediction model. This refers to the predicted attitude response. In embodiments of the present invention, the predicted attitude response may include at least one of the predicted pitch response, predicted roll response, and predicted vertical acceleration, for example:

[0090] ,

[0091] In this embodiment of the invention, the attitude response prediction model can be at least one of a vehicle dynamics model, a mapping model based on historical traffic data, or a pre-calibrated lookup table model. For different types of unmanned equipment, corresponding attitude response prediction models can be pre-established based on vehicle parameters such as vehicle mass, wheelbase, track width, suspension parameters, and center of gravity position to obtain vehicle attitude response prediction results under road disturbance conditions.

[0092] After obtaining the predicted attitude responses, the traffic risk is determined based on the relationship between each predicted attitude response and its corresponding preset safety threshold. When at least one of the predicted pitch response, predicted roll response, predicted vertical acceleration, or predicted wheel-to-ground contact state reaches or exceeds its corresponding preset safety threshold, the corresponding traffic risk level is increased. For example, when the predicted vertical acceleration satisfies the following formula, a high vertical impact risk is determined for the vehicle:

[0093] ,

[0094] in, This represents a preset vertical acceleration safety threshold. Similarly, the risks of bottoming out, yaw, slippage, or mission load disturbance can be determined based on the relationship between the predicted pitch response, predicted roll response, predicted wheel-to-ground contact state, and their corresponding safety thresholds. An active pre-aiming control strategy is generated based on the predicted attitude response and passage risks, enabling the unmanned equipment to pre-adjust at least one of the following: speed, trajectory, driving force, braking force, steering, or mission status, before reaching the road disturbance area.

[0095] S330. Generate an active anti-aiming control strategy based on the predicted results of the attitude response and traffic risk of the unmanned equipment when passing through the road disturbance area. The active anti-aiming control strategy includes at least one of speed pre-adjustment control, trajectory pre-adjustment control, driving force pre-adjustment control, braking force pre-adjustment control, steering pre-adjustment control and mission status pre-adjustment control.

[0096] In this embodiment of the invention, the active anti-aiming control strategy includes at least one of speed pre-adjustment control, trajectory pre-adjustment control, driving force pre-adjustment control, braking force pre-adjustment control, steering pre-adjustment control, and mission status pre-adjustment control. Among them, speed pre-adjustment control is used to reduce the target vehicle speed or limit acceleration and deceleration before reaching the road disturbance area, so that the unmanned equipment can pass through at a relatively smooth speed; trajectory pre-adjustment control is used to adjust the local driving trajectory according to the spatial location of the disturbance and the passable area, so that the wheels or tracks can avoid the severely disturbed areas as much as possible; drive force pre-adjustment control is used to adjust the drive force output before entering the road disturbance area to avoid sudden acceleration that would cause the vehicle to pitch more sharply; braking force pre-adjustment control is used to avoid sudden braking in the road disturbance area, reducing the pitch impact and wheel-ground adhesion changes caused by braking; steering pre-adjustment control is used to limit sharp turns or high angular velocity turns in the road disturbance area, reducing the risk of roll and lateral instability; mission status pre-adjustment control is used to adjust the mission execution status before entering the road disturbance area when the unmanned equipment is equipped with cameras, radar, gimbals, robotic arms, spraying devices, detection equipment or other mission payloads, so as to reduce the impact of bumps on mission stability.

[0097] More specifically, an active pre-aiming control strategy is generated based on the predicted results of both the attitude response and traffic risk of the unmanned equipment when passing through the road disturbance area, such as... Figure 3 As shown, it includes:

[0098] S331. Determine the severity of the disturbance in the road disturbance area based on the disturbance height or depth, disturbance slope, disturbance width, and the speed of the unmanned equipment.

[0099] S332. Determine the control strength of the active pre-aiming control strategy based on the severity of the disturbance, the confidence level of the identification, and the expected contact time;

[0100] S333. When the severity of the disturbance is greater than or equal to a preset severity threshold, reduce the target speed of the unmanned equipment passing through the road disturbance area, and when the severity of the disturbance is less than the preset severity threshold, maintain the target speed of the unmanned equipment.

[0101] In this embodiment of the invention, let the first... The severity of each road disturbance event is: The preset severity threshold is The saturation severity corresponding to the maximum rate of decrease is First, the severity of disturbances exceeding the threshold is normalized to obtain the normalized severity coefficient. :

[0102] ,

[0103] in, Indicates the variable Limited to Within the range. When hour, ;when hour, .

[0104] Furthermore, the target speed of the unmanned equipment passing through the road disturbance area is determined based on the normalized severity coefficient:

[0105] ,

[0106] in, This represents the initial target speed of the unmanned equipment under current road conditions. This indicates the minimum target speed that can be set when passing through areas of road disturbance. This represents the maximum deceleration rate, and its value range can be set to [value range missing]. .

[0107] When the severity of the disturbance is below the threshold ,at this time Maintain the original target speed; as the severity of the disturbance increases, The target speed is gradually increased and continuously decreased, thus avoiding the use of a binary control method that simply "decelerates uniformly when the threshold is exceeded".

[0108] S334. Based on the spatial location of the road disturbance area and the traffic area information, determine the local driving trajectory adjustment amount;

[0109] S335. Based on the attitude response and traffic risk prediction results of the unmanned equipment when passing through the road disturbance area, determine the driving force pre-adjustment control quantity, braking force pre-adjustment control quantity, steering angle pre-adjustment control quantity and mission status pre-adjustment control quantity.

[0110] S336. Generate the active pre-aiming control strategy based on at least one of the target speed of the unmanned equipment, the local driving trajectory adjustment amount, the driving force pre-adjustment control amount, the braking force pre-adjustment control amount, the steering angle pre-adjustment control amount, and the mission state pre-adjustment control amount.

[0111] Specifically, the severity of road disturbance It can be determined by a combination of the disturbance height or depth, the change in disturbance slope, the disturbance width, and the current speed of the unmanned equipment. For example:

[0112] ,

[0113] in, , , , All represent weighting coefficients, used to characterize the impact of disturbance height or depth, slope change, disturbance width, and vehicle speed on the severity of bumps. Since the impact degree when unmanned equipment passes through a bumpy area is usually related to the vehicle's speed, therefore... As a speed-related factor, it is used to improve the risk assessment value when passing through bumpy areas at high speeds.

[0114] Based on the severity of road disturbance It can determine the target speed when unmanned equipment passes through the road disturbance area. ,For example:

[0115] ,

[0116] in, This represents the initial target speed of the unmanned equipment under current road conditions. This indicates the permissible road disturbance risk threshold. This is a very small positive number set to prevent the denominator from being zero. The formula indicates that when the road disturbance is minor, the unmanned equipment maintains its original target speed; when the road disturbance is significant, the unmanned equipment reduces its target speed in advance to minimize the impact of bumps.

[0117] It should be noted that when it is determined that the unmanned equipment is about to reach a road disturbance area, and the credibility of the road disturbance event recognition meets the preset conditions, a pre-aiming control command is sent to the chassis control, speed control, steering control, drive control, braking control, or mission load control in advance. This step enables the unmanned equipment to complete the necessary speed, trajectory, drive and braking, and mission status adjustments before actually contacting the bumpy area, thereby reducing the subsequent impact of bumps.

[0118] In this embodiment of the invention, a passive feedback correction strategy is determined based on the real-time attitude response information of the unmanned equipment, such as... Figure 4 As shown, it includes:

[0119] S510a. Obtain real-time attitude response information of the unmanned equipment during the process of passing through the road disturbance area. The real-time attitude response information includes at least one of pitch angle, roll angle, yaw angle, vertical acceleration, lateral acceleration, longitudinal acceleration, angular velocity, and wheel speed change.

[0120] S520a. Calculate the deviation between the real-time attitude response information and the predicted attitude response, wherein the predicted attitude response is the predicted result of the attitude response when the unmanned equipment passes through the road disturbance area.

[0121] S530a. When the deviation is greater than a preset deviation threshold, the control strength of the passive feedback correction strategy is increased. The passive feedback correction strategy includes at least one of the following: reducing the target vehicle speed, limiting subsequent acceleration, increasing the safe tracking distance, adjusting the local trajectory, correcting the driving force distribution, correcting the braking force distribution, correcting the steering control amount, and pausing or reducing the task action.

[0122] Specifically, when the deviation between the actual attitude response and the predicted attitude response exceeds a preset deviation threshold, a feedback correction strength coefficient η is determined based on the degree to which the deviation exceeds the threshold. This coefficient is then used to adjust the target vehicle speed, subsequent acceleration, safe tracking distance, and other control variables. The larger the deviation, the stronger the feedback correction.

[0123] Let the attitude response deviation be The preset deviation threshold is The deviation corresponding to the maximum intensity of feedback correction is ,but:

[0124] ,

[0125] in, The value range is 0 to 1. When the deviation just exceeds the threshold, a small feedback correction is used; as the deviation increases, the correction magnitude is gradually increased; when the deviation reaches... At that time, the preset maximum feedback correction intensity is used.

[0126] In this embodiment of the invention, the specific method for improving the control strength of the passive feedback correction strategy is as follows:

[0127] (1) Target velocity correction. Based on the target velocity given by the active aiming control, the target velocity is further reduced according to the feedback correction intensity:

[0128] ,

[0129] in, This indicates the target speed during the active aiming phase. This indicates the maximum allowable additional deceleration during the feedback phase. This indicates the minimum permissible target speed.

[0130] (2) Subsequent acceleration limits. The greater the feedback correction strength, the smaller the maximum allowable subsequent acceleration of the vehicle:

[0131] ,

[0132] in, This indicates the original maximum permissible acceleration. Indicates the maximum limit quantity. This indicates the lower limit of the allowed acceleration setting.

[0133] (3) Other control quantity corrections. The safe tracking distance can be adjusted accordingly. Increase accordingly; local trajectory, driving force, braking force, steering control amount, and task actions can also be adjusted accordingly. The magnitude of the control input is proportionally adjusted, and each control input is limited within a preset safety range. This ensures that increased control strength is reflected in specific changes in the control input, rather than simply switching control states.

[0134] It should be understood that when the deviation exceeds a preset deviation threshold, the actual bump impact is determined to be stronger than expected, thus increasing the control strength of the passive feedback correction strategy. The passive feedback correction strategy includes at least one of the following: reducing the target vehicle speed, limiting subsequent acceleration, increasing the safe tracking distance, adjusting the local trajectory, correcting the drive force distribution, correcting the braking force distribution, correcting the steering control amount, and pausing or reducing task actions. Among these, pausing or reducing task actions is suitable for tasks requiring high stability, such as high-speed photography, precision inspection, and robotic arm operation.

[0135] Specifically, during the actual passage of the unmanned equipment through a bumpy area, the deviation between the actual attitude response and the predicted attitude response is calculated. Let the predicted attitude response be... The actual attitude response is Then the attitude response deviation It can be represented as:

[0136] ,

[0137] in, and It may include at least one of pitch angle, roll angle, vertical acceleration, pitch rate, roll rate, wheel speed fluctuation, and heading deviation.

[0138] Furthermore, the attitude response deviation can also be expressed in a weighted form:

[0139] ,

[0140] in, and These represent the actual pitch angle and the predicted pitch angle, respectively. and These represent the actual roll angle and the predicted roll angle, respectively. and These represent the actual vertical acceleration and the predicted vertical acceleration, respectively. and These represent the actual angular velocity and the predicted angular velocity, respectively. , , , All of these are weighting coefficients.

[0141] when Greater than the preset threshold When the actual turbulence is determined to be stronger than expected, the intensity of the passive feedback correction control is increased.

[0142] In this embodiment of the invention, the control command for the unmanned equipment is determined by dynamically fusing the passive feedback correction strategy and the active pre-aiming control strategy, such as... Figure 5 As shown, it includes:

[0143] S510b: Based on the recognition reliability of the road disturbance area and the deviation between the real-time attitude response information and the predicted attitude response, determine the fusion weight of the active pre-aiming control strategy and the passive feedback correction strategy.

[0144] Specifically, the fusion weights of the active anti-aiming control strategy and the passive feedback correction strategy are determined, such as... Figure 6 As shown, it includes:

[0145] 1) When the recognition confidence of the road disturbance area is greater than the preset confidence threshold and the deviation is less than the preset deviation threshold, increase the control weight of the active pre-aiming control strategy in the fusion weight;

[0146] 2) When the recognition confidence of the road disturbance area is less than or equal to the preset confidence threshold, or the deviation is greater than or equal to the preset deviation threshold, the control weight of the passive feedback correction strategy in the fusion weight is increased.

[0147] It should be noted that when the road disturbance recognition reliability is high, the expected contact time is sufficient, and the road information ahead is continuous and stable, the control weight of the active anti-aiming control strategy is increased, enabling the unmanned equipment to pass smoothly in a pre-planned manner. When the road information ahead is missing, sensors are obstructed, the recognition reliability is low, the recognition results of multiple sensors are inconsistent, or the actual attitude response deviation exceeds a preset threshold, the weight of the passive feedback correction strategy is increased, enabling the unmanned equipment to make rapid corrections based on the actual vehicle body response. When a continuous inconsistency is detected between the anti-aiming recognition result and the actual attitude response, it is determined that there is an error in the current road disturbance model, reducing the reliability of anti-aiming control for subsequent similar road disturbance events and increasing the control weight of attitude feedback correction.

[0148] S520b: Determine the final control quantity of the unmanned equipment based on the fusion weight of the active pre-aiming control strategy and the passive feedback correction strategy.

[0149] In this embodiment of the invention, the expression for the final control quantity is:

[0150] ,

[0151] in, This represents the control quantity for an active anti-aiming control strategy. This represents the control quantity of a passive feedback correction strategy. This represents the final control quantity. The control weights of the active anti-aiming control strategy are represented by the following expression:

[0152] ,

[0153] in, This represents the confidence level of identifying the j-th road disturbance event. This represents the deviation between the actual attitude response and the predicted attitude response. This represents the attitude deviation adjustment coefficient. This indicates a positive number set to prevent the denominator from being zero. Specifically, it can be represented as a tiny positive number set to prevent the denominator from being zero.

[0154] The final control quantity includes at least one of the following: target speed, target acceleration, steering angle, driving torque, braking torque, local trajectory adjustment, and mission load control.

[0155] It should be noted that, This is the weight for active aiming control, with a value ranging from 0 to 1. When The larger the value, the more the final control quantity depends on the forward road disturbance prediction and identification results; when The smaller the value, the more the final control quantity depends on the actual attitude feedback correction result.

[0156] As can be seen from the above formula, when the road disturbance recognition reliability is high and the attitude response deviation is small, The current is relatively large, and active pre-aiming control is mainly used; when the reliability of the road ahead recognition is low or the actual attitude response deviation is large, Reduce and increase the proportion of passive feedback correction control.

[0157] It should be understood that the final control command is generated based on the integrated control strategy and sent to at least one execution module among the chassis control system, speed control system, steering control system, drive system, braking system, and mission load control system of the unmanned equipment.

[0158] The final control command includes at least one of the following: target speed, target acceleration, target trajectory, steering angle, steering angular velocity, driving torque, braking torque, mission load working status, sensor gimbal angle, or mission pause command.

[0159] In this embodiment of the invention, the unmanned equipment control method for bumpy roads further includes:

[0160] After the unmanned equipment passes through the road disturbance area, the road disturbance area, the active pre-aiming control strategy, the passive feedback correction strategy, the control command of the unmanned equipment, the real-time attitude response information and the passage result are associated and stored, and at least one of the road disturbance identification model, bump severity assessment model, attitude response prediction model and local road map is updated.

[0161] In this embodiment of the invention, after the unmanned equipment passes through a bumpy area, it associates and stores the road disturbance event, the active pre-aiming control strategy, the passive feedback correction strategy, the final control command, the actual attitude response, and the passage result.

[0162] The aforementioned data can be used to update road disturbance identification models, bump severity assessment models, attitude response prediction models, or local road maps. By continuously accumulating actual traffic data, the accuracy of bump identification and control stability under similar road conditions can be improved. Data recording and model updates can be performed online or through offline training followed by redeployment.

[0163] In this embodiment of the invention, the unmanned equipment can be a wheeled unmanned vehicle, a tracked unmanned vehicle, a wheel-tracked hybrid unmanned vehicle, or other unmanned ground mobile equipment; forward road perception can be achieved using a single sensor or by fusing multiple sensors; the road disturbance identification method can be a rule-based geometric detection method or a machine learning or deep learning-based identification method; the estimated contact time can be calculated based on the unmanned equipment's current speed, heading angle, trajectory planning results, and the location of the disturbance area, or it can be estimated based on the vehicle's kinematics model, trajectory prediction model, or historical traffic data; the fusion weights can be determined using a rule-based threshold method, or they can be determined using fuzzy control, model predictive control, reinforcement learning, adaptive control, or a neural network model; this invention can be deployed on the unmanned equipment's main controller, or on a remote control platform, edge computing device, or vehicle-road cooperative system.

[0164] It should also be noted that this invention assumes the unmanned equipment uses a standard vehicle suspension. This invention does not require the vehicle to have active suspension, semi-active suspension, air suspension, adjustable damping suspension, or adjustable height suspension. The core of this invention lies in achieving stable passage control on bumpy roads under standard chassis conditions through forward-looking identification of road disturbances and feedback correction of vehicle posture.

[0165] Therefore, the unmanned equipment control method for bumpy roads provided in this embodiment of the invention achieves stable passage control on bumpy roads under ordinary suspension conditions by organically combining forward road disturbance prediction and vehicle posture feedback correction: it realizes structured forward decision-making by constructing road disturbance events, achieves complementary advantages of active and passive control by dynamically fusing weights, and continuously improves control performance by associating and storing passage data and updating the model, thereby effectively improving the passage stability, safety and mission execution reliability of unmanned equipment on bumpy roads.

[0166] In summary, compared with the prior art, the present invention has at least the following beneficial effects:

[0167] (1) This invention combines forward aiming recognition of bumpy roads with vehicle attitude feedback correction, which can take control measures in advance before the unmanned equipment reaches the bumpy area, and can make real-time corrections based on the actual attitude response when actually passing through the bumpy area.

[0168] (2) This invention does not rely on active suspension, semi-active suspension or adjustable suspension structure, and is applicable to unmanned equipment under ordinary vehicle suspension conditions, and has better engineering applicability and promotion value.

[0169] (3) By constructing road disturbance events, the present invention converts information about bumpy roads ahead into structured information containing disturbance type, location, geometric parameters, expected contact time and recognition credibility, which is beneficial for the control system to make advance decisions.

[0170] (4) Based on the reliability of forward perception and the actual attitude response deviation, the present invention dynamically adjusts the fusion weight between active pre-aiming control and passive feedback correction, so as to avoid misjudgment caused by relying solely on forward perception and control lag caused by relying solely on attitude feedback.

[0171] (5) This invention reduces the risks of pitch, roll, vertical impact, slippage and yaw when unmanned equipment passes through bumpy roads by coordinating control of speed, trajectory, driving force, braking force, steering and mission status.

[0172] (6) The present invention can update the road disturbance identification model, attitude response prediction model or local road map based on the results of bumpy road travel, thereby improving the travel stability under similar road conditions in the future.

[0173] (7) This invention not only focuses on the safety of unmanned equipment itself, but also on the stability of the task loads such as sensors, gimbals, robotic arms, and detection equipment, which can improve the reliability of unmanned equipment in complex road environments.

[0174] As another embodiment of the present invention, a control device 100 for unmanned equipment on bumpy roads is provided to implement the unmanned equipment control method for bumpy roads described above, wherein, as Figure 7 As shown, it includes:

[0175] The acquisition module 110 is used to acquire information about the road environment ahead of the unmanned equipment and the status information of the unmanned equipment itself.

[0176] The road disturbance area determination module 120 is used to determine the road disturbance area in the road ahead based on the road environment information ahead. The road disturbance area includes at least one of the following: pothole area, raised area, ditch area, step area, gravel area, continuous undulation area, abrupt slope area, and soft and subsided area.

[0177] The active anti-aiming control strategy acquisition module 130 is used to predict the passage posture and passage risk of the road disturbance area based on the road disturbance area and its own state information, and to obtain an active anti-aiming control strategy.

[0178] The control execution module 140 is used to control the unmanned equipment to execute the active pre-aiming control strategy when it is determined that the unmanned equipment enters the road disturbance area within a preset time.

[0179] The fusion decision module 150 is used to determine a passive feedback correction strategy based on the real-time attitude response information of the unmanned equipment when the unmanned equipment is entering or passing through the road disturbance area, and to determine the control command of the unmanned equipment after dynamically fusing the passive feedback correction strategy with the active pre-aiming control strategy.

[0180] The unmanned equipment control device for bumpy roads provided by this invention acquires information about the road environment ahead and the unmanned equipment's own state, and determines the road disturbance area based on the road environment information, thus achieving early perception of bumpy roads ahead. By predicting the travel attitude and travel risk based on the road disturbance area and the unmanned equipment's own state information, and obtaining an active pre-aiming control strategy, this strategy is executed when it is determined that the unmanned equipment will enter the road disturbance area within a preset time. This allows for early adjustment of the travel state before the unmanned equipment reaches the road disturbance area, avoiding the control response lag caused by post-entry corrections after entering the bumpy area. When unmanned equipment is entering or passing through areas of road disturbance, a passive feedback correction strategy is determined based on real-time attitude response information. This strategy can correct the driving state in real time according to the actual road impact experienced by the unmanned equipment, avoiding the impact of recognition errors on control performance when relying solely on forward perception. By dynamically fusing the passive feedback correction strategy with the active anti-aiming control strategy to determine the control command, the advance capability of anti-aiming control and the real-time capability of feedback control are taken into account. Thus, without relying on active suspension or changing the suspension structure of ordinary vehicles, the stability, safety, and mission execution reliability of unmanned equipment on bumpy roads are effectively improved.

[0181] As another embodiment of the present invention, a computer storage medium is provided, wherein computer program instructions are stored, and when the computer program instructions are invoked, the unmanned equipment control method for bumpy roads described above is implemented.

[0182] In this embodiment of the invention, a non-transitory computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can execute the unmanned equipment control method for bumpy roads described in any of the above method embodiments. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0183] As another embodiment of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory is communicatively connected to the processor;

[0184] The memory is used to store program instructions;

[0185] The processor is used to call and execute the program instructions to implement the unmanned equipment control method for bumpy roads described above.

[0186] like Figure 8 As shown, the electronic device 10 may include: at least one processor 11, such as a CPU (Central Processing Unit), at least one communication interface 13, a memory 14, and at least one communication bus 12. The communication bus 12 is used to enable communication between these components. The communication interface 13 may include a display screen or a keyboard; optionally, the communication interface 13 may also include a standard wired interface or a wireless interface. The memory 14 may be high-speed RAM (Random Access Memory) or non-volatile memory, such as at least one disk drive. Optionally, the memory 14 may also be at least one storage device located remotely from the aforementioned processor 11. The memory 14 stores application programs, and the processor 11 calls the program code stored in the memory 14 to execute any of the aforementioned method steps.

[0187] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 12 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0188] The memory 14 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 14 may also include a combination of the above types of memory.

[0189] The processor 11 can be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP.

[0190] The processor 11 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0191] Optionally, memory 14 is also used to store program instructions. Processor 11 can invoke program instructions to implement the present invention. Figure 1 The embodiment illustrates the control method for unmanned equipment on bumpy roads.

[0192] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of the present invention, and the present invention is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A control method for unmanned equipment on bumpy roads, characterized in that, include: Acquire information about the road environment ahead of the unmanned equipment and the equipment's own status. Based on the road environment information ahead, a road disturbance area in the road ahead is determined. The road disturbance area includes at least one of the following: pothole area, raised area, ditch area, step area, gravel area, continuous undulation area, abrupt slope area, and soft and subsided area. Based on the road disturbance area and its own state information, the passage attitude and passage risk of the road disturbance area are predicted to obtain an active pre-aiming control strategy. When it is determined that the unmanned equipment enters the road disturbance area within a preset time, the unmanned equipment is controlled to execute the active pre-aiming control strategy. When the unmanned equipment is entering or passing through the road disturbance area, a passive feedback correction strategy is determined based on the real-time attitude response information of the unmanned equipment, and the control command of the unmanned equipment is determined after dynamic fusion of the passive feedback correction strategy and the active pre-aiming control strategy.

2. The control method for unmanned equipment on bumpy roads according to claim 1, characterized in that, Based on the road disturbance area and its own state information, the traffic posture and traffic risk of the road disturbance area are predicted to obtain an active pre-aiming control strategy, including: The road disturbance area is converted into a road disturbance event, and the road disturbance event includes at least the disturbance type, disturbance spatial location, disturbance geometric parameters, disturbance severity, expected contact time, and identification confidence. Based on the road disturbance event and the unmanned equipment's own state information, predict the attitude response and passage risk of the unmanned equipment when passing through the road disturbance area. The attitude response includes at least one of pitch change trend, roll change trend, vertical impact intensity and wheel-ground contact change. The passage risk includes at least one of slip risk, bottoming out risk, yaw risk and mission load disturbance risk. An active anti-aiming control strategy is generated based on the predicted results of both the attitude response and the traffic risk when the unmanned equipment passes through the road disturbance area. The active anti-aiming control strategy includes at least one of the following: speed pre-adjustment control, trajectory pre-adjustment control, driving force pre-adjustment control, braking force pre-adjustment control, steering pre-adjustment control, and mission status pre-adjustment control.

3. The method for controlling unmanned equipment on bumpy roads according to claim 2, characterized in that, An active pre-aiming control strategy is generated based on the predicted results of both the attitude response and the traffic risk of the unmanned equipment when passing through the road disturbance area, including: The severity of the disturbance in the road disturbance area is determined based on the disturbance height or depth, disturbance slope, disturbance width, and the speed of the unmanned equipment. The control strength of the active pre-aiming control strategy is determined based on the severity of the disturbance, the confidence level of the identification, and the expected contact time. When the severity of the disturbance is greater than or equal to a preset severity threshold, the target speed of the unmanned equipment passing through the road disturbance area is reduced, and when the severity of the disturbance is less than the preset severity threshold, the target speed of the unmanned equipment is maintained. Based on the spatial location of the road disturbance area and the traffic area information, the local driving trajectory adjustment amount is determined; Based on the attitude response and traffic risk prediction results of the unmanned equipment when passing through the road disturbance area, the pre-adjustment control quantities of driving force, braking force, steering angle and mission status are determined. The active aiming control strategy is generated based on at least one of the target speed of the unmanned equipment, the local driving trajectory adjustment amount, the driving force pre-adjustment control amount, the braking force pre-adjustment control amount, the steering angle pre-adjustment control amount, and the mission state pre-adjustment control amount.

4. The control method for unmanned equipment on bumpy roads according to claim 1, characterized in that, A passive feedback correction strategy is determined based on the real-time attitude response information of the unmanned equipment, including: The real-time attitude response information of the unmanned equipment during the process of passing through the road disturbance area is obtained. The real-time attitude response information includes at least one of pitch angle, roll angle, yaw angle, vertical acceleration, lateral acceleration, longitudinal acceleration, angular velocity and wheel speed change. Calculate the deviation between the real-time attitude response information and the predicted attitude response, wherein the predicted attitude response is the predicted result of the attitude response of the unmanned equipment when it passes through the road disturbance area; When the deviation exceeds a preset deviation threshold, the control strength of the passive feedback correction strategy is increased. The passive feedback correction strategy includes at least one of the following: reducing the target vehicle speed, limiting subsequent acceleration, increasing the safe tracking distance, adjusting the local trajectory, correcting the driving force distribution, correcting the braking force distribution, correcting the steering control amount, and pausing or reducing the task action.

5. The control method for unmanned equipment on bumpy roads according to claim 4, characterized in that, The control commands for the unmanned equipment are determined by dynamically fusing the passive feedback correction strategy and the active pre-aiming control strategy, including: Based on the recognition reliability of the road disturbance area and the deviation between the real-time attitude response information and the predicted attitude response, the fusion weight of the active aiming control strategy and the passive feedback correction strategy is determined. The final control quantity of the unmanned equipment is determined based on the fusion weight of the active pre-aiming control strategy and the passive feedback correction strategy.

6. The control method for unmanned equipment on bumpy roads according to claim 5, characterized in that, Determining the fusion weights of the active anti-aiming control strategy and the passive feedback correction strategy includes: When the recognition confidence of the road disturbance area is greater than a preset confidence threshold and the deviation is less than a preset deviation threshold, the control weight of the active pre-aiming control strategy in the fusion weight is increased. When the recognition confidence of the road disturbance area is less than or equal to the preset confidence threshold, or the deviation is greater than or equal to the preset deviation threshold, the control weight of the passive feedback correction strategy in the fusion weight is increased.

7. The method for controlling unmanned equipment on bumpy roads according to claim 5, characterized in that, The expression for the final control quantity is: ， in, This represents the control quantity for an active anti-aiming control strategy. This represents the control quantity of a passive feedback correction strategy. This represents the final control quantity. The control weights of the active anti-aiming control strategy are represented by the following expression: ， in, This represents the confidence level of identifying the j-th road disturbance event. This represents the deviation between the actual attitude response and the predicted attitude response. This represents the attitude deviation adjustment coefficient. This indicates a positive number set to prevent the denominator from being zero; The final control quantity includes at least one of the following: target speed, target acceleration, steering angle, driving torque, braking torque, local trajectory adjustment, and mission load control.

8. The control method for unmanned equipment on bumpy roads according to claim 1, characterized in that, Also includes: After the unmanned equipment passes through the road disturbance area, the road disturbance area, the active pre-aiming control strategy, the passive feedback correction strategy, the control command of the unmanned equipment, the real-time attitude response information and the passage result are associated and stored, and at least one of the road disturbance identification model, bump severity assessment model, attitude response prediction model and local road map is updated.

9. A control device for unmanned equipment on bumpy roads, used to implement the control method for unmanned equipment on bumpy roads as described in any one of claims 1 to 8, characterized in that, include: The acquisition module is used to acquire information about the road environment ahead of the unmanned equipment and the equipment's own status information. The road disturbance area determination module is used to determine the road disturbance area in the road ahead based on the road environment information ahead. The road disturbance area includes at least one of the following: pothole area, raised area, ditch area, step area, gravel area, continuous undulation area, abrupt slope area, and soft and subsided area. An active anti-aiming control strategy acquisition module is used to predict the passage posture and passage risk of the road disturbance area based on the road disturbance area and its own state information, and to obtain an active anti-aiming control strategy. The control execution module is used to control the unmanned equipment to execute the active pre-aiming control strategy when it is determined that the unmanned equipment enters the road disturbance area within a preset time. The fusion decision module is used to determine a passive feedback correction strategy based on the real-time attitude response information of the unmanned equipment when the unmanned equipment is entering or passing through the road disturbance area, and to determine the control command of the unmanned equipment after dynamically fusing the passive feedback correction strategy with the active pre-aiming control strategy.

10. A computer storage medium, characterized in that, Used to store computer program instructions, which, when invoked, implement the unmanned equipment control method for bumpy roads as described in any one of claims 1 to 8.

Images