Vehicle control method and related products

Abstract

A vehicle control method and related products are applied to the technical field of intelligent vehicles. A computing device receives perception data of a first sensor of a vehicle, which can reflect a contact state between a second vehicle body moved by a first vehicle body and an obstacle. The computing device obtains control information of the vehicle based on the perception data of the first sensor. By perceiving the contact between the moved second vehicle body and the obstacle, accurate motion control of the vehicle can be achieved, effectively avoiding excessive extrusion and collision of the obstacle due to inertia. Especially in the scene where a parking limiting device is set, whether the predetermined parking position is reached can be determined by perceiving the contact with the special limiting obstacle, thereby improving the accuracy, safety and automation level of vehicle parking. The application also provides a device, a chip, a computing device, a vehicle control system, a vehicle, a readable storage medium and a program product for executing the method.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle technology, and in particular to a vehicle control method and related products. Background Technology

[0002] Vehicles with dual bodies, such as heavy-duty trucks (hereinafter referred to as "heavy trucks"), are widely used in logistics transportation, port operations, mining, and other fields. To meet transportation needs, heavy trucks typically tow trailers, with trailer lengths reaching over 20 meters. In scenarios such as parking lots, freight stations, and warehouses, heavy trucks need to reverse into parking spaces or park at designated loading and unloading positions. Due to the long body and large load capacity of heavy trucks, the parking space provided by parking lots or loading and unloading platforms is relatively limited. Therefore, parking heavy trucks relies heavily on the driver's experience, and the driver can only observe the parking space behind the trailer through the rearview mirror, which is often not very accurate when judging the extreme positions.

[0003] To solve this problem, a common practice is to place tires on the wall as mechanical stopping devices. When reversing, the driver gradually moves the rear of the vehicle closer to and eventually touches the tire, judging whether the intended stopping position has been reached by the physical obstruction of the tire and the impact sound. However, heavy trucks have greater inertia when loaded, which can easily damage the tires, leading to frequent tire replacements.

[0004] In summary, improving the accuracy of parking decisions in reversing scenarios for large vehicles with dual bodies is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This application provides a vehicle control method and related products that can automatically, accurately, and reliably detect the contact state between a mobile platform (such as a vehicle with a dual-body structure) and an obstacle, and perform precise motion control based on this, effectively avoiding excessive compression and collision with obstacles due to inertia.

[0006] In a first aspect, this application provides a vehicle control method that can be executed by a device with computing capabilities, and it is convenient to describe the execution subject using a computing device as an example.

[0007] The vehicle control method includes: a computing device receiving perception data from a first sensor of the vehicle. The vehicle includes at least a first body and a second body, the first body being used to move the second body (e.g., a tractor unit moving a trailer). The perception data from the first sensor is used to indicate the contact state of the second body with an obstacle. Based on the perception data from the first sensor, the computing device obtains control information for the vehicle. If the perception data from the first sensor indicates that the second body has made contact with an obstacle, the vehicle control information includes a braking indication.

[0008] The above-described solution can perceive the contact state between the vehicle body and obstacles in real time and generate control commands, including braking instructions, based on this. Unlike conventional vehicle control, this solution issues braking instructions only after sensing that the second body has made contact with the obstacle. This is because a vehicle consists of a first body and a second body with different functions, and parking is usually determined by the second body contacting the limit device. Furthermore, since the second body is separate from the first body, information such as the speed and acceleration of the second body cannot be directly obtained through the sensors of the first body. Therefore, this solution uses sensors to perceive the contact state between the second body and the obstacle.

[0009] The above solution changes the traditional vehicle control method that relies on the driver's subjective feeling, achieving precise control of the vehicle's movement process and improving the accuracy, safety, and automation of vehicle parking limit. Especially for heavy trucks and other vehicles with large inertia and poor visibility, the above solution can trigger braking in a very short time after contact, effectively avoiding excessive compression of obstacles due to inertia.

[0010] In one possible implementation of the first aspect, the obstacle is used to limit the vehicle's movement when it stops. Exemplarily, the obstacle can be a resilient limiting device such as a tire, rubber mat, or cushioning pad. The above implementation is applicable to specific scenarios such as parking, and by sensing contact with the limiting device to determine whether a predetermined parking position has been reached, it improves the accuracy, safety, and automation of vehicle parking.

[0011] In some other cases, if the vehicle does not come into contact with a pre-set specific limiting device, but instead collides with an unexpected limiting device, such as a traffic cone or storage box in front of the tires, the computing device may also determine that the vehicle has come into contact with an obstacle based on the perception data and issue a braking instruction to brake.

[0012] In another possible implementation of the first aspect, the first sensor is disposed on the second vehicle body. For example, for a heavy truck comprising a tractor unit and a trailer (or cargo box), the first sensor may be disposed at the rear of the trailer. Since the rear of the trailer is the first part to come into contact with an obstacle behind it during reversing, placing the sensor directly there allows for more direct and timely detection of the contact state, reducing signal transmission delay.

[0013] Furthermore, the main control platform (such as an intelligent driving domain controller) can be located on the tractor unit. In some cases, the first sensor and the main control platform are connected wirelessly to overcome the fragility and wiring difficulties of the physical connection (such as wiring harness) between the tractor unit and the trailer. In other cases, the first sensor and the main control platform are connected via wired wiring harnesses, for example, through wired communication interfaces on the tractor unit and the trailer, which can ensure the reliability and stability of transmission.

[0014] In one possible implementation of the first aspect, the sensing data of the first sensor includes data indicating the acceleration of the second vehicle body within a first time window. When the sensing data of the first sensor satisfies a first condition, it is considered that the second vehicle body has made contact with the obstacle. The first condition can be designed according to requirements and has multiple possible scenarios.

[0015] In one scenario, the first condition includes: the acceleration direction of the second vehicle body within the first time window is negative (i.e., the deceleration direction), and the acceleration value of the second vehicle body within the first time window shows an increasing trend. This utilizes the physical characteristic that a vehicle experiences a gradually increasing negative acceleration after contacting an elastic obstacle. The computing device uses features in the acceleration dimension to determine the contact state, which is intuitive and computationally inefficient.

[0016] In another scenario, the first condition includes: the time-domain waveform of the acceleration of the second vehicle body within a first time window, and the matching of the acceleration waveform when the second vehicle body is compressed against the obstacle. Specifically, the computing device can acquire a contact waveform template after the vehicle contacts the elastic obstacle, and match the real-time collected acceleration waveform with this template, such as calculating a correlation coefficient to obtain the matching degree. If the matching degree exceeds a threshold, it is determined that the vehicle is in contact with the obstacle. This waveform matching method has strong anti-interference capabilities, can effectively distinguish the difference between real contact collisions and acceleration fluctuations caused by road bumps, and has high accuracy.

[0017] In another possible implementation of the first aspect, the sensing data of the first sensor includes elastic wave data from the elastic wave sensor within a first time window. The elastic wave sensor is extremely sensitive to weak contact and can distinguish elastic waves generated by different materials.

[0018] In this embodiment, contact is determined when the sensing data from the first sensor meets a first condition.

[0019] For example, the first condition includes: the elastic wave intensity within the first time window has an increasing trend, and / or, the maximum or average intensity of the elastic wave within the first time window exceeds the first elastic wave intensity threshold.

[0020] Furthermore, the first condition may also include: within the first time window, the intensity of the elastic wave in the first frequency band of the first elastic wave data satisfies the second condition. The first frequency band is the frequency band in which the elastic wave generated when the obstacle deforms. For example, the elastic wave generated by tire deformation is mainly concentrated in a specific frequency band. By analyzing the energy proportion of this frequency band, it can be confirmed that the object in contact is indeed the expected obstacle (such as an elastic obstacle) and not other hard objects, thereby avoiding false triggering of the function.

[0021] In yet another possible implementation of the first aspect, the obstacle comprises an elastic material (such as a tire). The sensing data from the first sensor includes data from a second time window and data from a third time window, the second time window preceding the third time window.

[0022] When the data in the second time window indicates that the second vehicle body has begun to make contact with the obstacle, the computing device determines that the second vehicle body is subjected to a rebound force based on the data in the third time window. Because an elastic obstacle undergoes a rebound process after being compressed, this process has unique characteristics in the acceleration or elastic wave signal. For example, the absolute value of negative acceleration increases and the rate of change of acceleration decreases, or negative acceleration gradually changes into positive acceleration. By detecting the rebound characteristics in the acceleration or elastic wave signal, a dual confirmation mechanism can be formed, greatly improving the reliability of the detection and confirming that the object in contact is indeed the expected obstacle, and not some other hard object, thereby avoiding false triggering of the function.

[0023] In yet another possible implementation of the first aspect, the computing device further acquires perception data from a second sensor of the vehicle. The perception data from the second sensor is used to indicate the distance between the vehicle and the obstacle. Before the second vehicle body contacts the obstacle, speed limit information of the vehicle is obtained based on the perception data from the second sensor; the speed limit information is used to indicate a speed limit for the vehicle.

[0024] The above implementation introduces a mid-to-long-range ranging sensor (such as millimeter-wave radar, camera, etc.), which can actively limit the vehicle speed based on the distance before the vehicle comes into contact with the obstacle, creating safer low-speed conditions for subsequent contact braking, thereby further reducing the possibility of the vehicle hitting the obstacle.

[0025] Furthermore, prior to the second vehicle body contacting the obstacle, the vehicle's speed is negatively correlated with the distance between the vehicle and the obstacle. Pre-planning ensures that the instantaneous speed at the moment of contact is low, thereby limiting the impact force of the collision.

[0026] In another possible implementation of the first aspect, the computing device further instructs adjustments to the attitude of the second vehicle body based on perception data from the second sensor. The environmental perception data is used to indicate the attitude of the second vehicle body relative to the obstacle. For example, a camera or radar at the rear of the vehicle can detect whether the rear of the trailer is facing the obstacle. If the system detects that the vehicle is approaching the obstacle at an angle, it can automatically or prompt the driver to adjust the direction of the vehicle to straighten the trailer, ensuring frontal contact between the vehicle and the obstacle, thus preventing damage to the vehicle body or the obstacle (such as a limiting device) when the vehicle is parked at an angle.

[0027] In another possible implementation of the first aspect, the sensing data of the first sensor includes elastic wave data from multiple elastic wave sensors. The elastic wave data from the multiple elastic wave sensors is used to indicate the relative posture of the second vehicle body when it contacts the obstacle. For example, multiple elastic wave sensors are horizontally positioned at the rear of the trailer. When contact occurs, the timing and intensity of the impact detected by different sensors will vary depending on the location of the contact point. By analyzing these differences (such as time difference, intensity ratio, etc.), the computing device can determine the position of the contact point in the width direction of the trailer, and thus determine whether the contact is frontal or tilted. Based on this, the vehicle control information may include posture adjustment instructions, such as slightly steering the vehicle to adjust the angle of the next contact, making the force on the contact surface more uniform.

[0028] In another possible implementation of the first aspect, the computing device further instructs the display of the attitude of the second vehicle body relative to the obstacle. Specifically, the computing device may instruct the display unit to display the attitude of the second vehicle body relative to the obstacle, or the computing device may output information for display, which can be used by the display unit to display the attitude of the second vehicle body relative to the obstacle. For example, the computing device may visually present information such as contact position and deflection angle (e.g., "right rear contact, deflection angle approximately 3 degrees") on an in-vehicle display screen, providing intuitive feedback to the driver.

[0029] In another possible implementation of the first aspect, the computing device further determines, based on the input data, that the vehicle's driving intention is to park. In other words, the aforementioned control methods (such as automatic braking, speed limit control, etc.) are only activated when the driver's intention is clearly identified as being to perform a parking operation, thus avoiding false triggering during normal driving or unexpected operations (such as accidentally engaging reverse gear or sudden acceleration to avoid danger), thereby improving the intelligence and safety of the system.

[0030] For example, the input data includes vehicle driving operation data and / or information about obstacles around the vehicle (such as continuously decreasing radar range). The vehicle driving operation data includes one or more of the following: gear position, power control information, or vehicle steering angle information. The power control information includes one or more of the following: throttle opening information, braking control information, and acceleration information. The vehicle steering information includes one or more of the following: steering wheel angle or wheel deflection angle.

[0031] Secondly, this application provides a vehicle control device, which includes units for implementing the method described in the first aspect or any of its embodiments, such as an acquisition unit and a processing unit.

[0032] Thirdly, this application provides a chip including a processor and a communication interface, wherein the communication interface is used for inputting and / or outputting data, and the processor is used for calling computer instructions to implement the method of the first aspect or any embodiment thereof.

[0033] Fourthly, this application provides a computing device including a processor and a memory, the memory for storing computer instructions, and the processor for calling the computer instructions stored in the memory to cause the computing device to implement the method described in the first aspect or any of its embodiments.

[0034] Fifthly, this application provides a vehicle control system, which includes a first sensor, and the vehicle control device of the second aspect, or the chip of the third aspect, or the computing device of the fourth aspect.

[0035] Sixthly, this application provides a vehicle that includes the vehicle control device of the second aspect, the chip of the third aspect, the computing device of the fourth aspect, or the vehicle control system of the fifth aspect.

[0036] In a seventh aspect, this application provides a computer-readable storage medium for storing computer program instructions that, when executed by a processor, cause an apparatus including a processor to implement the method described in the first aspect or any of its embodiments.

[0037] Eighthly, this application provides a computer program product including computer program instructions that, when executed by a processor, cause a device including a processor to implement the method described in the first aspect or any of its embodiments.

[0038] The beneficial effects of aspects two through eight mentioned above can be referred to the beneficial effects of aspect one, and will not be elaborated on here. Attached Figure Description

[0039] The accompanying drawings used in the embodiments of this application are described below.

[0040] Figure 1 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application; Figure 2 This is a schematic flowchart of a vehicle control method provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating the signal characteristics of a vehicle's acceleration during a contact process, provided in an embodiment of this application. Figure 4 This is a schematic diagram of a posture adjustment scenario provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application; Figure 7 This is a functional block diagram of an intelligent driving device provided in an embodiment of this application. Detailed Implementation

[0041] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0042] To facilitate understanding, we will first introduce some technical terms that may be involved in the embodiments of this application.

[0043] A mobile platform generally refers to a mechanical device capable of autonomous or controlled movement. For example, a mobile platform can be a passenger vehicle, a freight vehicle, an automated guided vehicle (AGV), or an autonomous mobile robot (AMR). Freight vehicles include articulated vehicles, such as heavy-duty trucks that include a tractor and a trailer (the definition of a heavy-duty truck can be found in industry standards). For ease of explanation, some embodiments in this application are described using heavy-duty trucks as examples; however, those skilled in the art should understand that the technical solutions of this application are equally applicable to other types of mobile platforms.

[0044] Articulated vehicles typically consist of at least two functionally distinct body sections. The first body section serves as the power source and control unit, driving the entire vehicle's movement. The second body section comprises the load-bearing or operational units (such as trailers / trailers) towed by the first body section. In integrated mobile platforms, the first and second body sections can be considered integrated as a single unit, with sensors located at a specific part of the platform (e.g., the rear). Alternatively, for non-vehicle mobile platforms, such as multi-segment robotic arms, this can be replaced by multi-segment main bodies. These main bodies refer to each independent structural unit constituting the mobile platform, and can also be referred to as segments, components, etc.

[0045] An obstacle is an object that impedes the movement of a mobile platform. In some embodiments, the obstacle may include components made of elastic materials, such as used tires or rubber bumpers. Furthermore, the obstacle may serve as a limiting device pre-installed at the end of the target docking location, acting as a physical docking marker.

[0046] An accelerometer (ACC) is a sensing device that measures the acceleration (including inertial force) experienced by an object during its motion.

[0047] An inertial measurement unit (IMU) is an inertial sensing device that typically integrates a three-axis accelerometer and a three-axis gyroscope. The three-axis accelerometer measures the linear acceleration of an object in three orthogonal directions (X, Y, and Z axes). The three-axis gyroscope measures the angular velocity (i.e., rotational rate) of the object about its three axes, thereby calculating the object's pitch, roll, and yaw angles in real time.

[0048] An elastic wave sensor is a sensing device used to detect high-frequency elastic stress waves released by a material due to deformation or fracture. The elastic wave sensor can be installed at a predetermined location on a moving platform. When the moving platform comes into contact with an obstacle (especially an elastic body), elastic waves are generated at the contact interface. By analyzing the intensity changes, time-domain waveform, and spectral distribution of the elastic wave signal, it is possible to determine whether contact has occurred and even identify the material of the contacting object.

[0049] The above explanations of the terminology can be applied to the embodiments described below.

[0050] With the rapid development of automation and intelligent technologies, various mobile platforms are widely used in logistics, manufacturing, and service industries. These mobile platforms often need to be precisely docked at designated locations. For example, heavy trucks need to back into small parking garages or unloading points, automated guided vehicles need to precisely dock with charging stations, and warehouse robots need to dock at precise points in front of shelves.

[0051] In these parking scenarios, a common challenge is accurately determining whether the mobile platform has reached the intended final parking position. This is especially true for mobile platforms consisting of multiple sections (such as heavy-duty trucks with tractor and trailer units). The main control system is typically located on only one section (e.g., the tractor unit), and these sections are not rigidly connected. This makes it difficult for operators of the main control or active systems to accurately ascertain the overall status of the platform, ultimately resulting in the mobile platform failing to park precisely at the designated location. Taking heavy-duty truck parking as an example, one solution is to install physical limiting devices (such as tires or blocks) at the target parking position. The driver relies on sensing the mechanical impact or displacement signal transmitted through the hinges to the tractor unit when the trailer hits the limiting device to determine if the heavy-duty truck has parked correctly and then controls the vehicle to stop accordingly.

[0052] This human-sensing approach has significant drawbacks. First, for heavy trucks with extremely high inertia, by the time the driver senses a collision, the vehicle has often already excessively compressed the limiting device. Second, heavy trucks have an articulated, long structure, resulting in a significant inner wheel difference when reversing, making it difficult for the driver to predict the trailer's rear posture and accurately determine whether it has parked in the intended position. Finally, this approach relies entirely on the driver's experience, without involving automated assistance or closed-loop control, leading to a low parking success rate, high collision risk, and inability to meet the large-scale, standardized parking needs of heavy trucks. Furthermore, for unmanned mobile platforms (such as driverless work vehicles), human sensing is completely unacceptable.

[0053] In view of this, this application provides a vehicle control method and related products that can automatically, accurately and reliably detect the contact state between the mobile platform and obstacles (such as limit devices), and perform precise motion control based on this, effectively avoiding excessive compression of obstacles due to inertia.

[0054] Especially in heavy truck parking scenarios, since heavy trucks are usually judged to be parked based on the second body contact with the limit device, the above solution can trigger braking in a very short time after contact, effectively preventing the heavy truck from hitting the limit device behind when parking.

[0055] The system architecture involved in the embodiments of this application is described below. Please refer to... Figure 1 , Figure 1 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle 100 in this embodiment is illustrated as an articulated vehicle including a tractor unit (i.e., a first body 11) and a trailer (i.e., a second body 12). Figure 1 As shown, the vehicle 100 includes a first body 11, a second body 12, a computing device 13, a first sensor 14, an ultrasonic radar 15, and a camera 16. Among them, The first body 11 includes a power source that drives the first body and the entire vehicle. The second body 12 serves as a load-bearing or operational component, capable of loading and performing operational functions. In parking scenarios, the rear and sides of the second body 12 are areas prone to contact with other objects during parking, and are therefore areas requiring close attention.

[0056] The computing device 13 is a device with computing capabilities, including hardware modules and / or software modules with computing capabilities.

[0057] As an example of a hardware implementation, computing device 13 may include at least one processor. In one implementation, the processor includes circuitry with instruction fetching and execution capabilities, such as a central processing unit (CPU), microprocessor, microcontroller unit (MCU), graphics processing unit (GPU), etc. In another implementation, the processor implements its functions through logical relationships of hardware circuitry, such as application-specific integrated circuits (ASICs) and / or programmable logic devices (PLDs), such as field-programmable gate arrays (FPGAs). In yet another implementation, the processor includes hardware circuitry designed for artificial intelligence, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. Computing device 13 includes at least one processor integrated as a system-on-chip (SOC), commonly referred to as an SOC by those skilled in the art. When a SoC includes multiple processors, the types of processors can be different, such as including CPU and NPU, or including MCU, CPU and DPU.

[0058] For example, the computing device 13 includes, but is not limited to, a domain controller (DC), a mobile data center (MDC), an electronic control unit (ECU), and a vehicle intranet unit (VIU). The DC may include a vehicle domain controller (VDC).

[0059] The computing device 13 is typically located on the first body 11 and is used to process sensor data and generate control commands.

[0060] The first sensor 14 is disposed on the second vehicle body 12 and is used to sense the contact state between the second vehicle body 12 and the obstacle. Exemplarily, the first sensor 14 can be disposed at the rear of the second vehicle body 12, or on the left and right sides of the second vehicle body 12, or both at the rear and on the sides. The first sensor 14 includes one or more combinations of an accelerometer (ACC), an inertial measurement unit (IMU), and an elastic wave sensor. The accelerometer is used to measure acceleration. The IMU integrates a three-axis accelerometer and a three-axis gyroscope, and can output linear acceleration, angular velocity, and attitude angle, etc., for more accurate sensing of the motion state and attitude of the second vehicle body 12. The elastic wave sensor is used to detect the stress wave released by material deformation upon contact, and has high sensitivity to weak contact.

[0061] In some implementations, the computing device 13 is wirelessly connected to the first sensor 14 to avoid damage to the wiring harness caused by repeated detachment and reattachment between the first vehicle body 11 and the second vehicle body 12.

[0062] Ultrasonic radar 15 and camera 16 serve as examples of second sensors used to acquire information about the vehicle 100 and its surrounding environment. Ultrasonic radar 15 can be positioned at the rear of the second vehicle body 12 to measure the distance between the second vehicle body 12 and obstacles. Camera 16 can be positioned on either the first vehicle body 11 or the second vehicle body 12 to acquire images of the environment behind the vehicle. Furthermore, the second sensor may also include millimeter-wave radar, lidar, etc., to achieve longer-range or higher-precision ranging and sensing. The second sensor communicates with the computing device 13 via a wired (e.g., controller area network bus, Ethernet) or wireless connection.

[0063] An obstacle refers to an object that the vehicle 100 may come into contact with in its driving environment. In some embodiments of this application, the obstacle is a pre-set limiting device placed at the end of the target parking position as a physical parking marker, such as an edge of a wall or loading dock. To cushion the impact and protect the vehicle upon contact, the obstacle may be made of a resilient material, such as tires or rubber buffer pads. Figure 1 As shown, when the rear of the second vehicle body 12 contacts the obstacle hanging on the wall, it indicates that the vehicle has stopped in place.

[0064] In some cases, vehicles also include one or more of the following: a gear shifter, an accelerator, and a steering system. The gear shifter changes the vehicle's gear position, such as P, R, and D. The accelerator controls the amount of power output from the vehicle and, in some cases, can trigger functions such as regenerative braking. The steering system controls the vehicle's direction of travel and includes wheel actuators and, more specifically, a steering wheel.

[0065] It should be understood that Figure 1The architecture diagram shown is for illustrative purposes only. In actual applications, components in vehicle 100 can be added or removed according to specific requirements. Figure 1 This should not be construed as a limitation on the embodiments of this application. The vehicle 100 described above can be an articulated vehicle such as a heavy truck or a tractor-trailer. In addition to vehicles, this application can also be applied to other mobile platforms, such as automated guided vehicles, autonomous mobile robots, and unmanned forklifts.

[0066] The method provided in the embodiments of this application is described below. Please refer to... Figure 2 , Figure 2 This is a schematic flowchart illustrating a vehicle control method provided in an embodiment of this application. Optionally, this vehicle control method can be implemented in the aforementioned vehicle 100, for example, executed by a computing device 13. For ease of understanding, the following description uses a computing device as the executing entity. Figure 2 The vehicle control method shown may include steps S21 to S22. The order of steps here is merely an example, and the embodiments of this application are also applicable to other order of steps, multiple executions of a particular step, etc. S21 to S22 are as follows: S21, the computing device receives the sensing data from the first sensor.

[0067] Computing devices (e.g.) Figure 1 The computing device 13) is a device with computing capabilities, such as MDC, VDC, etc.

[0068] The first sensor is mounted on the second body of the vehicle (such as a trailer), for example, at the rear or side of the second body. The sensing data from the first sensor is used to indicate the contact status between the second body and the obstacle. In some cases, the obstacle is a pre-placed limiting device at the end of the parking target position, such as a component made of elastic material like a used tire or a rubber bumper.

[0069] The first sensor can be of various types, and correspondingly, the content of the sensed data will also differ. Several possible sensor designs are described below: Sensor design 1: The first sensor includes a sensor that senses speed and / or acceleration. The data output by the first sensor can indicate the acceleration of the second vehicle body. For example, for a speed-sensing sensor, acceleration can be calculated from the speed over a period of time. Alternatively, ACC can directly sense the acceleration of the second vehicle body.

[0070] Taking an acceleration sensor as an example, when the second vehicle body comes into contact with an obstacle, the acceleration sensor can capture the acceleration data during the contact period between the second vehicle body and the obstacle, and provide the acceleration data to the computing device.

[0071] In some cases, the first sensor is an IMU (Integrated Measurement Unit), and the data from the IMU may include linear acceleration data of the second vehicle body. Furthermore, the data from the IMU may also include angular velocity data and attitude angle data, which can comprehensively describe the motion state of the second vehicle body. For example, by measuring three-axis acceleration using an accelerometer and three-axis angular velocity using a gyroscope, the pitch, roll, and yaw angles of the second vehicle body can be calculated.

[0072] Sensor design 2: The first sensor includes an elastic wave sensor, and the sensed data includes elastic wave data within a first time window. The elastic wave sensor is also sensitive to weak contact and can detect stress waves released by material deformation. When the second vehicle body comes into contact with an obstacle, an elastic wave is generated at the contact point, and the elastic wave sensor can convert the elastic wave at the contact point into signal data output.

[0073] In some cases, the first sensor includes a combination of the aforementioned sensors. For example, an acceleration sensor and an elastic wave sensor are simultaneously deployed at the rear of the second vehicle body. The data detected by the acceleration sensor and the elastic wave sensor are fused together for judgment, or the results of the two are cross-checked, to improve the reliability and sensitivity of contact state detection.

[0074] Optionally, the computing device can receive the sensed data in either continuous real-time reception or polling reception at a preset frequency. The sensed data typically carries a timestamp so that the computing device can analyze the data characteristics within different time windows.

[0075] In some cases, the first sensor is included in the sensing device. The sensing device also includes an adsorption component for releasably adsorbing the sensing device onto an object (such as a vehicle, a second body, etc.). In other words, the sensing device achieves a releasable connection with the object through the adsorption component, and the first sensor within the sensing device can collect sensing data to indicate the contact state between the second body and the obstacle. Thus, there is no need to fix the sensor to the object; the sensing device is attached by adsorption to supplement the sensing capability when it is needed, which is particularly suitable for mobile platforms such as heavy trucks that require temporary replacement of the second body. Exemplarily, the adsorption component may include at least one electromagnet and / or at least one permanent magnet.

[0076] S22, the computing device obtains control information for the vehicle based on the perception data from the first sensor.

[0077] Control information includes one or more of the following: braking instruction, speed limit instruction, and attitude adjustment instruction. Specifically, when the computing device determines, based on perception data, that the second vehicle body has made contact with an obstacle, the generated control information includes a braking instruction. This braking instruction is sent to the vehicle's braking system, triggering braking to decelerate and stop the vehicle. When the computing device determines that the second vehicle body has not yet made contact with the obstacle, the generated control information may include information instructing the vehicle to continue moving (e.g., maintaining the current speed or acceleration), or may not include a braking command.

[0078] Specifically, the computing device detects whether the vehicle has made contact with an obstacle based on the perception data from the first sensor, and obtains control information for the vehicle based on the detection results. In some cases, when the perception data from the first sensor meets a first condition, it is considered that the second vehicle body has made contact with the obstacle. The first condition can be designed according to requirements and has multiple possible scenarios.

[0079] The following details how computing devices determine contact status based on different types of sensing data, namely, several contact status determination methods.

[0080] Method 1 for determining contact status: The computing device determines the contact status based on acceleration data.

[0081] When the first sensor is an accelerometer, the computing device can analyze the acceleration data of the second vehicle body within a time window (such as the first time window), that is, analyze the characteristics of acceleration in the time domain. During the contact process between the second vehicle body and the obstacle, the acceleration signal will exhibit characteristic changes, and the computing device can detect whether specific characteristic changes are present by analyzing the acceleration data over a period of time, thereby determining the contact state between the second vehicle body and the obstacle.

[0082] For example, combined Figure 3 During the contact process between a vehicle and an elastic component (such as a tire), the following stages occur: First, an impact peak occurs (the impact stage), during which the acceleration direction is negative and the acceleration value increases. Subsequently, the acceleration value enters the compression stage, where the acceleration value fluctuates around a certain position. Finally, the acceleration gradually returns to positive and increases (i.e., the rebound stage), and then gradually decays.

[0083] The following describes two methods for detecting characteristic changes in acceleration data: Based on acceleration detection method 1, the computing device identifies contact through threshold judgment. When the acceleration direction of the second vehicle body within the first time window is detected to be negative (i.e., deceleration direction), and the absolute value of the acceleration shows an increasing trend, contact is determined to have occurred. For example, the computing device continuously samples three time points (i.e.,... Figure 3The acceleration values ​​a1, a2, and a3 (t1, t2, and t3) shown are for illustrative purposes only. If the absolute values ​​of a1, a2, and a3 increase sequentially and their directions are negative, then the first condition is met, and contact is determined to have occurred. In other words, the first condition includes: the acceleration direction of the second vehicle body within the first time window is negative, and the acceleration value of the second vehicle body within the first time window shows an increasing trend (sub-condition 1). This judgment method is intuitive and computationally inefficient, making it suitable for scenarios with high real-time requirements.

[0084] Based on acceleration detection method 2, the computing device uses waveform matching to identify contact. For example, the computing device can acquire a contact waveform template, which is a typical acceleration time-domain waveform of the second vehicle body when it is pressed against an obstacle, obtained through prior experiments or simulations. The computing device performs cross-correlation calculations between the acquired acceleration waveform and the template to calculate the matching degree. When the matching degree exceeds a preset threshold (e.g., 0.85), it is determined that the vehicle is in contact with the first obstacle. In other words, the first condition includes: the time-domain waveform of the acceleration of the second vehicle body within a first time window, and the matching of the acceleration waveform of the second vehicle body when it is pressed against the obstacle (sub-condition 2).

[0085] It should be noted that the two acceleration-based detection methods described above can be combined. As an example of combination, satisfying either of the two sub-conditions (sub-condition 1 and sub-condition 2) is considered to satisfy the first condition. In some cases, both sub-conditions must be satisfied for the first condition to be satisfied.

[0086] The second method for determining the contact status involves a computing device that determines the contact status based on elastic wave data.

[0087] When the first sensor is an elastic wave sensor, the elastic wave intensity will suddenly increase at the instant the second vehicle body contacts the obstacle. Therefore, the computing device can detect whether the elastic wave intensity has an increasing trend, or whether the maximum or average value of the elastic wave intensity exceeds a first elastic wave intensity threshold. If the above conditions are met, it is preliminarily determined that contact has occurred. For example, the first condition includes: the elastic wave intensity within a first time window has an increasing trend, and / or, the maximum or average value of the elastic wave intensity within the first time window exceeds the first elastic wave intensity threshold.

[0088] To confirm that the contact object is the expected obstacle (such as a tire) and not another hard object, the computing device can also perform frequency domain analysis on the data from the first sensor to confirm that the contact object is the expected obstacle. As a possible design, the first condition may also include: within the first time window, the intensity of the elastic wave in the first frequency band (i.e., the characteristic frequency band where the elastic wave generated when the obstacle deforms) satisfies the second condition. The first frequency band is the frequency band where the elastic wave generated when the obstacle deforms. The second condition here refers to the characteristic condition that the intensity of the elastic wave in the first frequency band must satisfy; this condition can be designed or automatically determined according to requirements. For example, the second condition may include that the intensity is the strongest among multiple frequency bands (one sub-condition). Another example is that the energy proportion of the first frequency band exceeds a certain threshold (yet another sub-condition). Yet another example is that the energy value of the first frequency band exceeds an energy intensity threshold, etc. (yet another sub-condition). Of course, in the specific implementation process, the second condition can be designed with more sub-conditions. When the second condition includes multiple sub-conditions, the multiple sub-conditions can be connected by "OR", "AND", or partially connected by "AND" and partially by "OR". The multiple sub-conditions can also be set to have a sequential relationship or be designed as parallel sub-conditions.

[0089] For example, the computing device can determine the energy percentage of a first frequency band in the elastic wave data based on the elastic wave data. If the energy percentage of this frequency band exceeds a certain threshold (e.g., 60%), the contact object is confirmed as an elastic obstacle, and the contact is deemed valid. This material-based recognition method can effectively avoid false triggering of non-limiting objects.

[0090] Whether using an accelerometer or an elastic wave sensor, since obstacles contain elastic materials (such as tires), they will rebound after being compressed upon contact. The computing device can use this characteristic to perform double verification to determine that the object in contact with the vehicle body is the expected elastic object, thereby eliminating interference from road bumps, flying stone impacts, and other situations that may cause similar contact.

[0091] As one possible design, the perception data includes data from two time windows. The data from the first time window is used to determine the start of contact, while the data from the second time window is used to reflect whether there is a rebound characteristic (i.e., to determine that the vehicle is subjected to a rebound force). Using the data from these two time windows, it is possible to determine that the object in contact with the vehicle is the expected elastic object, and to perform subsequent vehicle control accordingly, thereby avoiding false triggering of functions.

[0092] For example, the sensing data includes data from a second time window (the contact detection phase) and data from a third time window (the elastic action detection phase), with the second time window preceding the third time window. When the computing device determines that contact has begun based on the data from the second time window, it does not immediately trigger braking. Instead, it opens a short monitoring window, the third time window (e.g., 10ms, 20ms), and analyzes the data within this window to look for rebound characteristic signals. For example, for acceleration or IMU data, the rebound signal manifests as a slowing rate of increase in negative acceleration or the negative acceleration reaching its peak. For elastic wave data, the rebound generates a new elastic wave pulse with a weaker intensity than that of the first time window. If a rebound signal matching the characteristics is detected within the third time window, true contact is confirmed, and braking is executed. Otherwise, it is determined to be interference, and braking is not executed.

[0093] Considering the enormous inertia of mobile platforms such as heavy trucks, there is still a considerable distance required from triggering braking to a complete stop. If the speed at contact is too high, even if braking is triggered, it may cause excessive compression of the obstacle. To further reduce the impact force on the obstacle at contact, the computing device can combine the distance perception results to perform speed planning.

[0094] As one possible design, the computing device also acquires perception data from a second sensor of the vehicle. This second sensor could be, for example, ultrasonic radar, millimeter-wave radar, lidar, or a camera. The perception data from the second sensor can reflect the distance between the second vehicle body and an obstacle; specifically, the perception data from the second sensor may include one or more of the following: the distance between the second vehicle body and the obstacle, the time position of the echo, and the position of the obstacle relative to the vehicle. Before the second vehicle body makes contact with the obstacle, the computing device can generate speed limit information based on the distance to limit the vehicle's speed.

[0095] Furthermore, prior to contact with the obstacle, the vehicle's speed is negatively correlated with the distance between the vehicle and the obstacle. That is, the closer the distance, the lower the permissible maximum speed tends to be. For example, when the distance between the vehicle and the obstacle falls within a first distance range (e.g., 1.5 meters to 3 meters), the speed limit is a first value (e.g., 5 km / h). When the distance falls within a second distance range (e.g., 0.5 meters to 1.5 meters), the speed limit is a lower second value (e.g., 2 km / h).

[0096] Vehicles may not always approach obstacles in an ideal posture (such as facing them directly). Figure 4As shown in part (a), during the initial stage of parking, the second body may approach the limiting device at an angle. If the vehicle reverses directly at this time, the second body will not be able to make frontal contact with the limiting device. On the one hand, the second body may hit the wall or loading platform, causing the body to be impacted. On the other hand, the limiting device may be knocked off course, deviating from its original fixed position or even damaged.

[0097] To avoid the aforementioned problems, in some implementations, the computing device also instructs adjustments to the attitude of the second vehicle body based on perception data from a second sensor (such as a camera or radar). The perception data from the second sensor can indicate the attitude of the second vehicle body relative to an obstacle, such as whether it is tilted. If the second vehicle body is detected approaching an obstacle at a tilt angle, the computing device can generate an attitude adjustment instruction. Combined with... Figure 4 In part (b), the computing device can control the first vehicle body to turn slightly so that the second vehicle body is straightened so that the second vehicle body can make frontal contact with the obstacle in a way that faces the obstacle directly, thus avoiding damage to the limiting device.

[0098] In some cases, the sensor used to detect the vehicle's attitude relative to the obstacle can be the same sensor used to detect the distance between the vehicle and the obstacle, such as ultrasonic radar or a camera. In other cases, the sensor used to detect the vehicle's attitude relative to the obstacle can be a different sensor from the sensor used to detect the distance between the vehicle and the obstacle, for example, using ultrasonic radar to detect distance and using a camera on the second or first vehicle body to detect vehicle attitude.

[0099] In addition to using additional sensors besides the first sensor, another approach involves the computing device using data from an elastic wave sensor to detect the attitude of the second vehicle body relative to the obstacle. However, in this case, adjustments to the vehicle body's attitude must be made only after the second vehicle body has made contact with the obstacle (i.e., elastic wave data reflecting the attitude of the second vehicle body has been acquired).

[0100] As one possible implementation example, the first sensor includes multiple elastic wave sensors, such as three elastic wave sensors evenly spaced horizontally at the rear of the trailer. When contact occurs, the sensors at different locations detect differences in the timing and intensity of the impact. By analyzing these differences (such as time difference of arrival and intensity ratio), the computing device calculates the position of the contact point in the second vehicle width direction, thereby determining the relative pose (such as the deflection angle). Based on this, the control information can include attitude adjustment instructions, such as slightly steering the vehicle to adjust the angle of the next contact. Simultaneously, the computing device can also instruct the onboard display to show this relative pose (such as "Right rear contact, deflection angle approximately 3 degrees"), providing intuitive feedback to the driver.

[0101] Figure 2 In the illustrated embodiment, the computing device only issues a braking command after sensing contact with an obstacle. This function may conflict with other functions, such as emergency braking. To ensure that the triggering scenarios meet user needs, some solutions also determine the vehicle's driving intention as a stop based on input data. Only when the driving intention is clearly identified as a stop operation are the aforementioned contact detection, automatic braking, and speed limit control functions activated. This avoids false triggering during normal driving or unexpected operations, improving the system's intelligence and safety.

[0102] Optionally, the input data may include driving operation data and / or obstacle information around the vehicle. The driving operation data includes one or more of the following: gear position, power control information, or vehicle steering angle information. The power control information includes one or more of the following: throttle opening information, braking control information, and acceleration information. The vehicle steering information includes one or more of the following: steering wheel angle or wheel deflection angle.

[0103] For example, when it detects that "the gear is in reverse, the throttle opening is stable and small, the steering wheel is slightly adjusted and the distance between the vehicle and the obstacle tends to decrease", the computing device determines that the current driving intention is to park the vehicle.

[0104] In summary, based on the perception data from the first sensor, the computing device accurately determines the contact state between the second vehicle body and the obstacle through various judgment logics (such as threshold judgment, waveform matching, double confirmation, and material recognition). In the case of contact, it generates control information including braking instructions, achieving precise, safe, and automated control of the vehicle parking process. Furthermore, the computing device also combines data from the second sensor and environmental perception sensors to generate control information including speed limit information and attitude adjustment instructions.

[0105] It should be understood that the various judgment methods and control strategies described above can be combined or selected according to actual needs, and the embodiments of this application do not limit this. Figure 2 The steps shown are for illustrative purposes only; in practical applications, some steps may be added or omitted as needed.

[0106] The methods of the embodiments of this application have been described in detail above. The apparatus of the embodiments of this application is provided below.

[0107] It should be understood that the division of units in the apparatus provided in this application embodiment is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units in the apparatus can be implemented by a processor calling software. For example, the apparatus includes a processor connected to a memory, which stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit of the apparatus. The processor is, for example, a general-purpose processor, such as a CPU or MPU, and the memory is either internal or external to the apparatus.

[0108] Alternatively, the units in the device can be implemented as hardware circuits. The functionality of some or all of the units can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functionality of some or all of the above units is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD (Programmable Logic Controller). Taking an FPGA as an example, it can include a large number of logic gates, and the connection relationships between these logic gates are configured through configuration files to achieve the functionality of some or all of the above units.

[0109] In the embodiments of this application, each unit in the device may be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, neural network processing unit (NPU), tensor processing unit (TPU), MPU, digital signal processor (DSP), ASIC, FPGA, or a combination of at least two of these processor forms.

[0110] Furthermore, the units in the above devices can be fully or partially integrated together, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a System-on-a-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as including a CPU, an NPU, and an MCU; or including a CPU and an MCU; or including a CPU and a GPU, etc.

[0111] Several possible devices are listed below.

[0112] Please see Figure 5 , Figure 5This is a schematic diagram of a vehicle control device provided in an embodiment of this application. Optionally, the vehicle control device 200 can be a standalone device, such as a controller, processor, SOC, server, etc. Alternatively, the vehicle control device 200 can be a component within a standalone device, such as a chip, integrated circuit, software module (cloud service, AI model), etc. The vehicle control device 200 is used to implement the aforementioned method, such as... Figure 2 The vehicle control method shown.

[0113] The vehicle control device 200 includes an acquisition unit 201 and a processing unit 202. The acquisition unit 201 is used to acquire data, such as data from a first sensor, data from a second sensor, etc., and optionally, it is also used to implement other operations involved in the aforementioned method embodiments. The processing unit 202 is used to process data and optionally, it is also used to implement other operations involved in the aforementioned method embodiments. It should be understood that the unit division and naming here are only illustrative; in specific implementations, some units may be combined together, or one unit may be split into multiple units.

[0114] In one possible implementation, the acquisition unit 201 is used to receive perception data from a first sensor of the vehicle. The processing unit 202 is used to obtain control information for the vehicle based on the perception data from the first sensor. Exemplarily, the acquisition unit 201 may include a wired communication interface and / or a wireless module. The acquisition unit 201 may be directly connected to the first sensor, or the perception data from the first sensor may be received by the acquisition unit 201 after passing through one or more intermediate devices.

[0115] In another possible implementation, the processing unit 202 analyzes the sensing data from the first sensor to determine whether the second vehicle body has made contact with the obstacle. For example, the processing unit determines whether the sensor's sensing data meets a first condition, and if the first condition is met, it determines that the second vehicle body has made contact with the obstacle.

[0116] In another possible implementation, the acquisition unit 201 is further configured to acquire perception data from the vehicle's second sensor. The processing unit 202 is further configured to obtain vehicle speed limit information based on the perception data from the second sensor, in order to limit the vehicle's speed.

[0117] In another possible implementation, the processing unit 202 is further configured to instruct the adjustment of the attitude of the second vehicle body based on the perception data from the second sensor. For example, it may instruct the control system to adjust the attitude of the second vehicle body, or instruct the display of a prompt message to prompt the driver to adjust the attitude of the second vehicle body.

[0118] In another possible implementation, the processing unit 202 is also used to indicate and display the attitude of the second vehicle body relative to the obstacle.

[0119] In another possible implementation, the processing unit 202 is also configured to determine, based on the input data, that the driving intention of the vehicle is to park.

[0120] For details on the operations performed by the vehicle control device 200, please refer to the above description of the system architecture, scenarios, and method embodiments.

[0121] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application, such as... Figure 6 The computing device 13 shown can be a standalone device, such as an MDC, GPU, or server. Alternatively, the computing device 13 can be a component within a standalone device, such as a chip, integrated circuit, or software module (e.g., cloud service, AI model). The computing device 13 is used to implement the aforementioned methods, such as... Figure 2 The vehicle control method shown.

[0122] The computing device 13 includes at least one processor and at least one memory. Optionally, the computing device 13 also includes a communication interface. Further optionally, the computing device 13 also includes connection lines, wherein the processor, communication interface, and / or memory are connected via the connection lines, and / or communicate with each other via the connection lines to transmit control signals and / or data signals. Wherein: A processor is a module with computing capabilities, including one or more of the following: arithmetic operations, logical operations, image-related operations, and artificial intelligence-related operations. Memory provides storage space, which can store data such as the operating system and computer programs. Memory can be one or a combination of several of the following: random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).

[0123] A communication interface can be used to provide information input or output to at least one processor, and / or to receive and / or send signals to externally transmitted signals. For example, a computing device may be a package containing chips or circuitry, and its communication interface may include interface circuitry. Alternatively, a computing device may be a communication-enabled device, and its communication interface may include data transmission interfaces such as Ethernet interfaces, serial data interfaces, and parallel data interfaces, and / or wireless link interfaces (Wi-Fi, Bluetooth, general wireless transmission, vehicular short-range communication technology, and other short-range wireless communication technologies). In some cases, the functionality of the communication interface is implemented through transceiver circuitry or dedicated transceiver chips.

[0124] The functions and operations of each module or unit in the computing device 13 listed above are merely illustrative examples.

[0125] The functional units in the computing device can be used to implement the aforementioned method, such as Figure 2 The vehicle control methods shown are examples of such methods.

[0126] Optionally, the processor is a processor specifically designed to perform the aforementioned methods (referred to as a dedicated processor for easy distinction), or a processor that performs the aforementioned methods by invoking a computer program (referred to as a dedicated processor for easy distinction). Optionally, at least one processor may include both dedicated processors and general-purpose processors.

[0127] Optionally, if the computing device includes at least one memory, and the processor implements the aforementioned control method by calling a computer program, the computer program may be stored in the memory.

[0128] The following describes, exemplarily, an intelligent driving device that may be involved in the embodiments of this application. See also Figure 7 , Figure 7 This is a functional block diagram of an intelligent driving device provided in an embodiment of this application. For example... Figure 7 As shown, the intelligent driving device 400 may include a sensing system 41, a display device 42, and a computing platform 43. The intelligent driving device 400 can be an intelligent mobile platform such as a vehicle, drone, or logistics vehicle.

[0129] The perception system 41 may include one or more sensors for sensing information about the environment surrounding the intelligent driving device 400. In this embodiment, the perception system 41 may include... Figure 1The first sensor 14 shown may further include sensors for sensing the vehicle's surrounding environment (such as obstacle distance) and the vehicle's attitude relative to obstacles in the environment. For example, the perception system 41 may include one or more of an IMU, lidar, millimeter-wave radar, ultrasonic radar, and a camera device. As another example, the perception system 41 may include a positioning system, which may be a global navigation satellite system (GNSS), such as the Global Positioning System (GPS), BeiDou system, etc.

[0130] Display device 42 belongs to the category of interactive devices and may include in-vehicle displays, projection equipment, etc.

[0131] Some or all of the functions of the intelligent driving device 400 can be controlled by a computing platform 43. The computing platform 43 may include processors 431, 432 to 43n (the number of n can be designed according to requirements), each processor being a circuit with signal processing capabilities (see the previous introduction to processors). Furthermore, the computing platform 43 may include a memory for storing instructions, some or all of which can call the instructions in the memory to implement corresponding functions. In some embodiments, the computing platform 43 can run the intelligent driving system.

[0132] Figure 7 The intelligent driving device 400 or computing platform 43 shown can be used to implement the vehicle control method described above, such as Figure 2 The vehicle control methods shown are examples of such methods.

[0133] This application also provides a chip, which includes logic circuitry and a communication interface. The communication interface is used to receive and / or send information, or to input and / or output information, and the logic circuitry is used to process the information. This chip is used to implement the aforementioned vehicle control method, such as... Figure 2 The vehicle control methods shown are examples of such methods.

[0134] This application also provides a computer-readable storage medium storing instructions that, when executed on at least one processor, cause a device including the processor to implement the aforementioned vehicle control method.

[0135] This application also provides a computer program product, which includes computer instructions for implementing the aforementioned vehicle control method.

[0136] This application also provides a mobile platform, which includes the aforementioned vehicle control device 200, computing device 13, intelligent driving device 400, the aforementioned chip, or the aforementioned computer-readable storage medium, or includes the aforementioned computer program product. Here, "mobile platform" broadly refers to various electronic devices (or terminals), and in some scenarios, "terminal" is used to refer to both mobile platforms and electronic devices.

[0137] In addition, a few additional points need to be made regarding this application: I. The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to depart from the protection scope of the technical solutions of the embodiments of this application.

[0138] 2. Unless otherwise stated, “multiple” means two or more.

[0139] 3. Unless otherwise specified or in case of logical conflict, the terms and / or descriptions in different embodiments of this application are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0140] IV. The various numerical designations used in this application are merely for descriptive convenience and are not intended to limit the scope of protection of this application. Unless otherwise specified, the order of the serial numbers used in this application does not imply the sequence of execution; the execution order of each process should be determined by its function and internal logic. For example, the terms "first," "second," and other various terminology (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0141] Furthermore, any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0142] V. 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 device that includes a series of steps or modules is not necessarily limited to those steps or modules that are expressly listed, but may include other steps or modules that are not expressly listed or that are inherent to such process, method, product or device.

[0143] VI. Unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. In this application, "and / or" is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0144] VII. Unless otherwise stated, the names of systems, devices, apparatuses, modules and other information in the embodiments of this application are merely examples, and apparatuses, devices and modules are used to represent possible entities that implement a certain function, and the meanings of the three can be interchanged.

[0145] 8. The design scope and operating conditions of the intelligent driving function in this application can be designed to comply with relevant laws and regulations. The control operations of the vehicle are also designed to comply with relevant regulations during specific implementation.

Claims

1. A vehicle control method, characterized in that, The method includes: The vehicle receives perception data from a first sensor, wherein the vehicle includes at least a first body and a second body, the first body being used to drive the second body to move, and the perception data from the first sensor being used to indicate the contact state between the second body and an obstacle. Based on the sensing data from the first sensor, control information for the vehicle is obtained; When the sensing data from the first sensor indicates that the second vehicle body has come into contact with the obstacle, the vehicle's control information includes a braking instruction.

2. The method according to claim 1, characterized in that, The obstacle is used to limit the movement of the vehicle when it is parked.

3. The method according to claim 1 or 2, characterized in that, The first sensor is located on the second vehicle body.

4. The method according to any one of claims 1-3, characterized in that, The sensing data from the first sensor includes data indicating the acceleration of the second vehicle body within a first time window; When the sensing data of the first sensor meets the first condition, the sensing data of the first sensor indicates that the second vehicle body has come into contact with the obstacle; The first condition includes: Within the first time window, the acceleration direction of the second vehicle body is negative, and the acceleration value of the second vehicle body within the first time window shows an increasing trend.

5. The method according to any one of claims 1-3, characterized in that, The sensing data from the first sensor includes data indicating the acceleration of the second vehicle body within a first time window; When the sensing data of the first sensor meets the first condition, the sensing data of the first sensor indicates that the second vehicle body has come into contact with the obstacle; The first condition includes: The time-domain waveform of the acceleration of the second vehicle body within the first time window is matched with the acceleration waveform of the second vehicle body when it is squeezed between the obstacle.

6. The method according to any one of claims 1-3, characterized in that, The sensing data of the first sensor includes elastic wave data from the elastic wave sensor within a first time window; When the sensing data of the first sensor meets the first condition, the sensing data of the first sensor indicates that the second vehicle body has come into contact with the obstacle; The first condition includes: The elastic wave intensity within the first time window has an increasing trend, and / or the maximum or average intensity of the elastic wave within the first time window exceeds the first elastic wave intensity threshold.

7. The method according to claim 6, characterized in that, The first condition also includes: Within the first time window, the intensity of the elastic wave in the first frequency band satisfies the second condition, where the first frequency band is the frequency band of the elastic wave generated when the obstacle deforms.

8. The method according to any one of claims 1-7, characterized in that, The obstacle comprises an elastic material; The sensing data from the first sensor includes data from a second time window and data from a third time window, wherein the second time window is located before the third time window; The method further includes: If the data in the second time window indicates that the second vehicle body has begun to make contact with the obstacle, the data in the third time window determines that the second vehicle body is subjected to a rebound force.

9. The method according to any one of claims 1-8, characterized in that, The method includes: Acquire perception data from the vehicle's second sensor, the perception data from the second sensor being used to indicate the distance between the vehicle and the obstacle; Before the second vehicle body comes into contact with the obstacle, the vehicle's speed limit information is obtained based on the perception data of the second sensor, and the speed limit information is used to indicate a speed limit for the vehicle.

10. The method according to claim 9, characterized in that, Before the second vehicle body comes into contact with the obstacle, the speed of the vehicle is negatively correlated with the distance between the vehicle and the obstacle.

11. The method according to any one of claims 1-10, characterized in that, The method further includes: Based on perception data from a second sensor, the attitude of the second vehicle body is adjusted, wherein the environmental perception data is used to indicate the attitude of the second vehicle body relative to the obstacle.

12. The method according to any one of claims 1-10, characterized in that, The sensing data of the first sensor includes elastic wave data from multiple elastic wave sensors, which are used to indicate the relative pose of the second vehicle body when it comes into contact with the obstacle. The vehicle's control information includes attitude adjustment instructions.

13. The method according to claim 11 or 12, characterized in that: The indicator displays the attitude of the second vehicle body relative to the obstacle.

14. The method according to any one of claims 1-13, characterized in that, The method further includes: Based on the input data, the driving intention of the vehicle is determined to be to park. The input data includes the vehicle's driving operation data and / or information about obstacles around the vehicle.

15. The method according to claim 14, characterized in that, The vehicle's driving operation data includes the vehicle's gear position, power control information, and / or vehicle steering angle information.

16. A vehicle control device, characterized in that, The vehicle control device includes an acquisition unit and a processing unit, and the vehicle control device is used to implement the method according to any one of claims 1-15.

17. A chip, characterized in that, The chip includes a processor and a communication interface, the communication interface being used for inputting and / or outputting data; The processor is used to invoke computer instructions to implement the method described in any one of claims 1-15.

18. A computing device, characterized in that, Including processor and memory, The memory is used to store computer instructions. The processor is configured to invoke computer instructions stored in the memory to cause the computing device to implement the method according to any one of claims 1-15.

19. A vehicle control system, characterized in that, The vehicle control system includes a first sensor. in, The vehicle control system further includes the vehicle control device as described in claim 16. Alternatively, the vehicle control system may further include the chip of claim 17. Alternatively, the vehicle control system may further include the computing device of claim 18.

20. A vehicle, characterized in that, The vehicle includes the vehicle control device of claim 16, or the chip of claim 17, or the computing device of claim 18, or the vehicle control system of claim 19.

21. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes computer program instructions. When the computer program instructions are invoked by a processor, the apparatus including the processor performs the method according to any one of claims 1-15.

22. A computer program product, characterized in that, The computer program product includes computer program instructions. When the computer program instructions are invoked by a processor, the apparatus including the processor performs the method according to any one of claims 1-15.

Images