Remote parking method, microcontroller and storage medium

Abstract

The application relates to the field of intelligent vehicle control, in particular to a remote parking method, a microcontroller and a storage medium, and aims to solve the problems of long response link, slow instruction response and insufficient control real-time performance of an existing remote parking scheme in a standby or dormant state of a vehicle. The method is applied to the microcontroller, after receiving a remote parking instruction sent by a user through a terminal device, the current state parameters of the vehicle are quickly acquired, and control decisions are made in combination with the instruction, corresponding vehicle execution control information is generated and output, so that the vehicle can complete the corresponding parking-in or parking-out action. By completing the remote control instruction processing, state determination and control generation on the microcontroller side, the start-up and processing link can be shortened, resource competition and time delay can be reduced, the response speed, control timeliness, stability and use convenience of the remote parking can be improved, and the driving safety in a complex parking environment can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle control technology, and in particular to a remote parking method, a microcontroller, and a storage medium. Background Technology

[0002] In remote-controlled straight-in and straight-out parking, existing solutions typically involve an onboard controller receiving remote commands and combining them with attitude perception, environmental perception, positioning, planning, and execution control to complete the automatic parking or exit of the vehicle.

[0003] However, when the vehicle is in a power-off sleep state, existing solutions generally rely on highly integrated control chips to complete the wake-up, initialization and algorithm loading of relevant modules, resulting in a long command response chain. At the same time, the centralized processing of perception, localization, planning and control tasks makes it susceptible to resource contention, making it difficult to balance startup latency and real-time response capabilities.

[0004] Therefore, improving the response speed of remote parking commands in vehicle sleep / standby scenarios has become a technical problem that needs to be solved. Summary of the Invention

[0005] This application provides a remote parking method, a microcontroller, and a storage medium to solve the aforementioned technical problems. This method addresses the remote parking needs of vehicles in sleep / standby scenarios. After receiving a remote control command issued by a user through a terminal device, it makes control decisions based on the vehicle's current state information and generates and executes corresponding control commands accordingly. This improves the vehicle's response efficiency to remote control commands while ensuring the remote parking function is implemented and also maintains the real-time performance of the control process.

[0006] In a first aspect, embodiments of this application provide a remote parking method applied to a microcontroller, the method comprising:

[0007] Obtain the first remote control command, which is issued by the user through the terminal device;

[0008] Determine the vehicle's initial status information;

[0009] Based on the first remote control command and the first status information, a first control command is generated;

[0010] Execute the first control command.

[0011] In one possible embodiment, the microcontroller is communicatively connected to an inertial sensor, and the first state information includes inertial data output by the inertial sensor.

[0012] In one possible embodiment, the operating mode of the first remote control command is either a straight-in parking mode or a straight-out driving mode.

[0013] In one possible embodiment, the microcontroller is communicatively connected to an ultrasonic sensor, and the first state information also includes environmental information output by the ultrasonic sensor.

[0014] In one possible embodiment, the environmental information includes at least one of static obstacle information, dynamic obstacle information, and pedestrian information.

[0015] In one possible embodiment, the first state information also includes vehicle wheel speed information.

[0016] In one possible embodiment, the first state information further includes second state information, which is determined based on inertial data, vehicle wheel speed information, and visual inertial odometer calculation.

[0017] In one possible embodiment, it also includes:

[0018] Obtain the stop command; the stop command is used to instruct the execution of the first control command to stop.

[0019] Execute the stop command.

[0020] In one possible embodiment, obtaining the stop command includes:

[0021] When the first fault identifier is determined, a stop command is obtained. The first fault identifier is used to indicate a microcontroller failure or that the first control command cannot be executed.

[0022] In one possible embodiment, it also includes:

[0023] When the first fault indicator indicates a microcontroller fault, the first remote control command and the first status information are sent to the on-chip system.

[0024] In one possible embodiment, when executing the first control command, the method further includes:

[0025] The first notification information is determined, which includes at least one of the following: vehicle start-up first status information, parking progress information, driving out progress information, vehicle speed information, vehicle position information, and vehicle attitude information;

[0026] The first notification information is sent to the terminal device.

[0027] In one possible embodiment, a first control command is generated based on a first remote control command and first status information, including:

[0028] The first remote control command and the first status information are input into the first algorithm to obtain the first control command. The first algorithm includes a straight-in-straight-out path planning algorithm and / or an obstacle rapid identification and avoidance algorithm.

[0029] Secondly, embodiments of this application provide a microcontroller, including: a memory and a processor;

[0030] The memory stores the instructions that the computer executes;

[0031] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0032] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0033] The remote parking method, microcontroller, and storage medium provided in this application embodiment can obtain the first remote control command issued by the user through the terminal device and determine the first state information of the vehicle. Based on the remote control requirements and the current state of the vehicle, the method can generate and execute the first control command, thereby shortening the remote parking command response link in the vehicle's sleep standby scenario, improving the command response speed, and taking into account the real-time performance and stability of parking control. Attached Figure Description

[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0035] Figure 1 This is a schematic diagram of the hardware architecture of the remote parking system provided in the embodiments of this application;

[0036] Figure 2 A flowchart illustrating the remote parking method provided in this application embodiment;

[0037] Figure 3 This is a schematic diagram of the structure of the remote parking device provided in the embodiments of this application;

[0038] Figure 4 This is a schematic diagram of the structure of the microcontroller provided in an embodiment of this application.

[0039] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0040] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0041] Remote parking technology falls under the field of intelligent vehicle control and is primarily used in scenarios where it is inconvenient for drivers to directly complete the actions of getting in and out of the vehicle, such as underground parking lots, narrow parking spaces, and parking spaces near walls or pillars. Related systems typically consist of terminal equipment, onboard controllers, and vehicle actuators, and combine attitude perception, environmental perception, positioning, path planning, and driving control to automatically park or exit the vehicle.

[0042] In existing remote-controlled direct-in / direct-out parking solutions, after the user issues a remote control command via a terminal device, the onboard controller needs to acquire information such as the vehicle's attitude, surrounding obstacles, and vehicle operating status. Based on this information, it then determines the path, generates control commands, and drives the vehicle to perform the corresponding actions. This type of solution typically integrates perception, localization, planning, and control tasks into a highly integrated control chip. When the vehicle is in a power-down sleep state, it also needs to complete chip wake-up, module initialization, and algorithm loading before entering the control execution phase.

[0043] Because the existing processing chain is relatively long, vehicles often cannot respond immediately after receiving remote control commands, causing users to experience a noticeable sense of waiting. At the same time, multiple tasks are processed on the same control platform, and resource contention may occur during the startup and execution phases, resulting in additional delays between status acquisition, control decisions, and command issuance. In complex parking environments, this can also affect the real-time performance and stability of remote parking, making it difficult to balance ease of operation and driving safety.

[0044] Therefore, improving the response speed of remote parking commands and ensuring the timeliness of the control process while the vehicle is in standby or sleep mode has become a technical problem that needs to be solved. To address this issue, a remote parking method based on a microcontroller is provided. After receiving the first remote control command issued by the user through a terminal device, the method determines the first state information of the vehicle, generates a first control command based on the first remote control command and the first state information, and then executes the first control command. This shortens the command response chain and improves the real-time control performance of remote parking.

[0045] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0046] Figure 1 This is a schematic diagram of the hardware architecture of the remote parking system provided in the embodiments of this application, as shown below. Figure 1 As shown, it includes:

[0047] The top-level module is a system-on-a-chip (SoC). The core hardware in the middle layer is a microcontroller, which integrates the remote parking program. It is the sole computing and control core of the entire remote parking system. All logical calculation tasks, such as perception data parsing, vehicle pose calculation, parking trajectory calculation, and actuator control command generation, are independently completed by the parking program inside the microcontroller. The bottom layer is a serial communication bus, which in the vehicle scenario is the controller local area network (LAN) bus. The bus serves as a unified data transmission channel, and four types of bottom-level hardware terminals are connected below it: remote terminal devices, ultrasonic sensors, inertial sensors, and vehicle-end actuators. All signals acquired and output by the bottom-level hardware are transmitted and received through this bus.

[0048] Figure 2 This is a flowchart illustrating the remote parking method provided in an embodiment of this application. The method provided in this application is applicable to any microcontroller. Figure 2 As shown, the method includes:

[0049] S101. Obtain the first remote control command, which is issued by the user through the terminal device.

[0050] In this application, the microcontroller is the executing entity of the method. The microcontroller is equipped with standby monitoring capabilities, instruction parsing capabilities, and control output capabilities connected to the vehicle communication link, used to maintain monitoring of remote parking trigger events when the vehicle is in standby or sleep mode. The first remote control command is a remote operation input initiated by the user through a terminal device. The terminal device serves as the carrier for establishing remote interaction between the user and the vehicle; in this application, it is specifically a mobile terminal with a remote parking application installed. After receiving the user's trigger operation, the terminal device generates the first remote control command. This command may carry information to support command recognition and processing, enabling the microcontroller to complete command attribution and validity confirmation upon receipt.

[0051] In practice, the terminal device sends the first remote control command to the vehicle via a wireless communication module. This module can use a Bluetooth link or a WiFi (Wireless Fidelity) link. The microcontroller is electrically connected to this wireless communication module or connected via the vehicle's local communication bus. When the vehicle is in a power-down sleep state, the microcontroller maintains its monitoring task. Upon receiving a data frame from the wireless communication module, it first reads the data frame header and identifies whether it is a remote parking service message. If the identification result is yes, it continues to parse the relevant fields in the message. After successful parsing, the message is identified as the first remote control command and written to the microcontroller's internal buffer, simultaneously triggering subsequent status acquisition tasks. If message verification fails, session times out, or field anomalies are found during parsing, the microcontroller directly terminates the current control process and keeps the vehicle's actuators inactive. Based on this processing method, the first remote control command does not need to be transmitted to the on-chip system and wait for it to complete wake-up, algorithm loading, and task scheduling. Instead, it is directly received and parsed by the microcontroller. The command entry point switches from a highly integrated control platform to a fast-starting control unit, compressing the initial response time of remote parking from the receiving link.

[0052] In one possible embodiment, the first remote control command may include operating mode information, such as a straight-in parking mode or a straight-out driving mode. For example, after acquiring the first remote control command, the microcontroller may also send a reception confirmation message back to the terminal device. This confirmation message indicates that the vehicle has entered the remote parking processing flow. It should be understood that the above examples are merely illustrative and not limiting. The specific communication medium, message structure, and verification method for acquiring the first remote control command can be adjusted according to the vehicle's communication architecture, as long as the microcontroller can directly receive the remote parking command issued by the user through the terminal device.

[0053] S102. Determine the vehicle's first state information.

[0054] In this application, the first state information is a set of vehicle current state data established by the microcontroller before generating control output, used to characterize the vehicle's current state related to remote parking control. The first state information at least covers the key variables that can support real-time remote parking control.

[0055] In practice, after parsing the first remote control command, the microcontroller initiates the state acquisition process, sending read requests to relevant interfaces according to a preset sampling period, or retrieving the latest data from the corresponding interface interrupt cache. Subsequently, the microcontroller performs necessary processing on the acquired vehicle current state data and forms a unified record of the first state information at a given moment. Based on the above analysis, it can be seen that the first state information is not an isolated reading, but a set of states formed to meet the needs of remote parking control. After receiving the first remote control command, the microcontroller directly completes the key state acquisition and integration, reducing the waiting time caused by cross-control platform forwarding and centralized scheduling, and ensuring that subsequent control calculations are based on the effective vehicle state at the current moment.

[0056] In one possible embodiment, the first state information may further include gear position, braking status, or steering angle feedback value. The microcontroller reads these operating states through the vehicle control network to determine whether the actuator meets the action conditions when generating subsequent control commands. Based on the above analysis, the first state information can be adjusted according to the vehicle platform configuration, as long as it reflects the current state of the vehicle and supports the generation of subsequent control commands.

[0057] S103. Generate a first control command based on the first remote control command and the first status information.

[0058] In this application, the first control command is the control result output by the microcontroller to the vehicle actuators, used to convert the user's remote control intention into executable power, steering, and braking actions of the vehicle. The generation process of the first control command involves determining the control target using the first remote control command, determining the current constraints and real-time state using the first state information, and completing the control quantity calculation within the microcontroller. The first state information is used to limit the control quantity boundaries and determine whether continued driving, speed reduction, maintaining steering, or direct braking is permitted at the current moment.

[0059] In practice, the microcontroller internally invokes control logic that matches the current control objective. This control logic first determines the target driving intention based on the first remote control command and calculates the basic motion command based on the first state information. The basic motion command includes at least the target vehicle speed and the target steering adjustment trend. Then, it performs a risk assessment based on the current state information. When it is determined that there is a risk affecting the execution of remote parking, the microcontroller modifies the basic motion command into a deceleration command or a braking command. The first control command may include at least one of a drive request value, a steering execution request value, and a braking request value. At any given moment, it may only include a braking request value to indicate that the vehicle needs to stop immediately.

[0060] In one possible embodiment, the microcontroller can adjust the target vehicle speed or steering control quantity based on the deviation between the current vehicle state and the target control requirements, so that the first control command includes execution condition judgment and real-time correction results when it is generated. By jointly processing the first remote control command and the first state information within the microcontroller, the first control command does not need to rely on the on-chip system to complete centralized planning before being issued, thus enabling the control closed-loop update to be completed in a shorter cycle.

[0061] S104, Execute the first control command.

[0062] In this application, executing the first control command includes the microcontroller sending the generated control result to the vehicle execution system and continuously refreshing the control output based on the feedback status until the current remote parking task is completed or the stop condition is triggered. The execution link of the first control command is established based on the in-vehicle communication link. After sending the control information, the microcontroller does not exit, but continues to collect the first status information and form the input data for the next control cycle, thus constituting a cyclical processing process of receiving commands, updating status, generating control, and executing control.

[0063] In practical implementation, the microcontroller outputs the first control command according to a fixed control cycle, and refreshes the first state information in each control cycle. If the stopping condition is not met, the corrected first control command continues to be output; if the stopping condition is met, the first control command is switched to the corresponding stop control command and the vehicle is kept in a safe state. Based on the above analysis, it can be seen that this application enables the key control closed loop of remote parking to run on a fast-start control platform by having the microcontroller directly complete the control output and continuously update the execution results. From the receipt of the first remote control command, the establishment of the first state information, the generation of the first control command to the execution of the first control command, a short-link processing flow is formed. In the vehicle standby or hibernation scenario, it can directly enter the control state, shorten the waiting time after the user issues a remote parking request, and enable the control command to be quickly corrected according to the real-time state. It should be understood that the above example is only for demonstration and not a limitation. The specific message format, control cycle, and actuator interface form of the first control command can also be varied according to the execution system configuration of the vehicle platform, as long as the remote parking method of this application can be implemented.

[0064] Based on the above analysis, this application provides a remote parking method applied to a microcontroller, comprising: acquiring a first remote control command, which is issued by a user through a terminal device; determining the first state information of the vehicle; generating a first control command based on the first remote control command and the first state information; and executing the first control command. In this application, the microcontroller directly undertakes the tasks of receiving commands, acquiring states, making control decisions, and executing outputs for remote parking. The control link, which was originally handled by the on-chip system after startup, is moved forward to the standby control unit. Upon receiving the remote control command issued by the user through the terminal device, the microcontroller can enter the control flow, combine it with the current state of the vehicle to form first state information, further generate the first control command, and drive the vehicle to execute system actions through the in-vehicle communication link. Therefore, remote parking can still establish a short response link even when the vehicle is in standby or sleep mode, and the control output can be quickly refreshed with the real-time state, meeting the timeliness and safety control requirements in remote parking scenarios.

[0065] In one possible implementation, the microcontroller is communicatively connected to an inertial sensor, and the first state information includes inertial data output by the inertial sensor.

[0066] In this embodiment, the microcontroller is a low-power control unit for receiving, processing, and outputting control commands. The inertial sensor is an attitude sensing device installed on the vehicle, and its output inertial data is used to characterize the vehicle's motion state in the longitudinal, lateral, or pitch directions. The inertial sensor can integrate an accelerometer, a gyroscope, or a combination of both, and establish a communication connection with the microcontroller through a serial bus, parallel interface, or other electrical connection methods to directly send the collected inertial data to the microcontroller. The communication connection can be implemented in a wired manner, and the connection port can include any of SPI (Serial Peripheral Interface), I2C (Inter-Integrated Circuit), and UART (Universal Asynchronous Receiver / Transmitter). The specific interface form is configured according to the hardware layout of the vehicle controller. In practical applications, other models of this component can also be selected, and this application does not limit this.

[0067] Upon receiving the first remote control command, the microcontroller can directly read the inertial data output by the inertial sensor and use this inertial data as part of the first state information for subsequent control decisions. The inertial data may include at least one of acceleration and angular velocity data, or it may be a combination of data after filtering, calibration, or coordinate transformation. Based on this, the microcontroller can quickly determine the current attitude change trend of the vehicle, thereby acquiring information related to the vehicle's motion state. Because the inertial data from the inertial sensor is directly input to the microcontroller, the microcontroller can form the first state information without relying on on-chip system intervention, and based on this, continue to generate control commands that match the vehicle's current state.

[0068] In this operating mode, the inertial sensor continuously outputs inertial data reflecting changes in vehicle attitude. After the communication connection is established, the microcontroller receives this inertial data in real time and performs state analysis. The analysis result is used as part of the first state information in remote parking control. This structure allows the microcontroller to independently acquire attitude-related states even when the vehicle is in standby or sleep mode, and directly use the inertial data for control decisions.

[0069] By adopting this method, the acquisition link of vehicle attitude-related information is shortened, and the microcontroller can obtain the inertial data in the first state information without going through a long system wake-up process, thereby improving the timeliness of remote parking command response and maintaining good continuity and stability of the control process.

[0070] In one possible implementation, the first remote control command operates in either a straight-in parking mode or a straight-out driving mode.

[0071] In one implementation, the straight-in parking mode corresponds to a control scenario where a vehicle moves straight into the target parking space from its current position along a drivable lane. After recognizing this mode, the microcontroller generates a control command to guide the vehicle into the parking space, based on the first state information. The straight-out driving mode corresponds to a control scenario where a vehicle moves straight out of the parking space from its current position along a preset lane. After recognizing this mode, the microcontroller generates a control command to guide the vehicle out of the parking space, based on the first state information. The operation mode information can be written using a mode selection control on the terminal interface. The microcontroller parses the received command frame, extracts the mode field, and calls the corresponding path planning and driving control parameters accordingly. The encoding format of the mode field can be carried by an enumeration code, a flag bit, or a predefined frame segment. In practical applications, other models or equivalent forms of encoding structures can also be selected, and this application does not limit this.

[0072] By limiting the first remote control command to either a straight-in parking mode or a straight-out driving mode, the microcontroller can directly enter the corresponding control branch after receiving the command, without having to make additional inferences about the command type. This ensures that the generated first control command corresponds one-to-one with the vehicle's entry or exit target, and improves the determinism and response consistency of the remote parking control process.

[0073] In one possible implementation, the microcontroller is communicatively connected to the ultrasonic sensor, and the first state information also includes environmental information output by the ultrasonic sensor.

[0074] During operation, after receiving the first remote control command, the microcontroller synchronously acquires the environmental information output by the ultrasonic sensor and incorporates it into the first state information to participate in the generation of subsequent control commands. Since the environmental information can directly reflect the distribution of obstacles around the vehicle, the microcontroller can use this information to determine whether the parking lane is passable and whether there is interference with the target trajectory, and generate a first control command that matches the current environment, thereby driving the vehicle to perform a straight-in parking mode or a straight-out driving mode.

[0075] Using the above method, the microcontroller can directly acquire the surrounding environment state without relying on the complex initialization of a highly integrated control chip. This allows the first state information to simultaneously include both the vehicle's motion state and the environmental state, thereby improving the completeness of the control decision-making basis. The environmental information output by the ultrasonic sensor is input to the microcontroller with low latency, which helps to shorten the remote parking response chain and improve the timeliness and reliability of control command generation in complex parking environments.

[0076] Based on the foregoing embodiments, the environmental information further includes at least one of static obstacle information, dynamic obstacle information, and pedestrian information.

[0077] In practical implementation, ultrasonic sensors can be deployed along the front, sides, or rear of the vehicle. The sensor probes are connected to the vehicle body via fixed brackets, which can be made of injection-molded engineering plastic parts. The sensor body is installed in the brackets using screws or clips to maintain probe orientation stability. The microcontroller determines whether an obstacle is within a preset distance threshold based on the ranging values ​​returned by each probe, and combines multiple consecutive frames of ranging results to identify whether the target is stationary or has moved. When multiple probes output stable and continuous near-range echoes in adjacent sampling periods, the microcontroller classifies it as static obstacle information. When the echo distance changes continuously over time and the target outline shifts, it is classified as dynamic obstacle information. When a target is detected entering the vehicle's preset avoidance zone and meets the distance change pattern corresponding to human characteristics, it is classified as pedestrian information. The above discrimination results are written into the first state information by the microcontroller and used for subsequent control command generation.

[0078] With this environmental information configuration, the microcontroller can directly acquire perception results related to surrounding risks before parking control, and distinguish between fixed obstacles, moving obstacles and pedestrians near the vehicle, so that the first state information covers more complete environmental elements, thereby supporting environmental judgment and control decisions during remote parking.

[0079] Based on the aforementioned embodiments, the first state information further includes vehicle wheel speed information.

[0080] When the vehicle is in standby or hibernation recovery phase, the microcontroller receives the vehicle's wheel speed information and determines whether the vehicle is stationary, crawling at low speed, or continuously moving based on wheel speed thresholds. This determination is then matched with the operating mode corresponding to the first remote control command to generate a first control command adapted to the current vehicle state. Since wheel speed information directly represents the vehicle's current motion, the microcontroller can complete state confirmation without waiting for a more complex full-vehicle state reconstruction, allowing wheel speed information to support control decisions in conjunction with other state information.

[0081] By incorporating vehicle wheel speed information into the first state information, the microcontroller obtains a more complete vehicle state dimension. The vehicle wheel speed information, inertial data, and environmental information can form a mutual verification relationship, making the generation of the first control command more closely match the vehicle's actual motion state. Therefore, in remote-controlled straight-in parking or straight-out driving scenarios, the vehicle's response to user commands is more consistent, and the matching accuracy between control commands and the vehicle's current driving state is correspondingly improved.

[0082] Based on the aforementioned embodiments, the first state information further includes second state information, which is determined based on inertial data, vehicle wheel speed information, and visual inertial odometer calculation.

[0083] In this specific implementation, the second state information characterizes the vehicle's motion or pose state at the current moment. Inertial data is output by inertial sensors mounted on the vehicle, and wheel speed information is collected by the vehicle wheel speed detection unit. Both serve as inputs to the visual inertial odometry (VIO) algorithm. After receiving the inertial data and wheel speed information, the microcontroller performs time synchronization, outlier removal, and scale unification processing. The processed data is then input into the VIO algorithm to complete fusion estimation and output the second state information. The VIO algorithm can run within the microcontroller or be executed by a computation module connected to the microcontroller and return the result. Its calculation process combines inertial data with wheel speed information to determine the vehicle's attitude change, displacement increment, or overall motion state. Because wheel speed information can constrain inertial integral drift, the second state information has a more stable state representation capability when outputting and can be incorporated into the first state information for subsequent control command generation.

[0084] Inertial data is the raw motion information reflecting changes in vehicle acceleration and angular velocity, while wheel speed information is the operating parameter reflecting the rotational speed of each wheel. When combined with the visual inertial odometry method, the microcontroller can continuously estimate the short-term trajectory of the vehicle. In this application, the visual inertial odometry method can employ a fusion estimation model suitable for an in-vehicle embedded platform, outputting second state information by jointly solving for the inertial data and wheel speed information. In practical applications, other algorithmic forms suitable for vehicle state estimation can also be selected, and this application does not limit this choice.

[0085] By incorporating the second state information, determined based on inertial data and vehicle wheel speed information, into the first state information, the microcontroller can obtain a more complete description of the vehicle's state. This improves the matching accuracy of the vehicle's current motion state when generating subsequent first control commands, making the judgment of the vehicle's attitude and motion trend more accurate during remote parking, thereby enhancing the consistency and stability of the control response.

[0086] One possible implementation also includes:

[0087] Obtain the stop command; the stop command is used to instruct the execution of the first control command to stop.

[0088] Execute the stop command.

[0089] In practical implementation, the stop command can be sent to the microcontroller by the terminal device after receiving a user interruption operation, or it can be triggered by the vehicle control interface and transmitted to the microcontroller via a communication link. Upon recognizing the stop command, the microcontroller stops outputting the control signal corresponding to the first control command to the actuator and cancels the cached control parameters, preventing the current control action from continuing to act on the vehicle. Executing the stop command can manifest as closing the parking control channel, clearing the pending control queue, releasing the occupied resources associated with the first control command, and switching the vehicle to a hold brake or neutral hold state. The communication module used by the microcontroller to receive the stop command can use Bluetooth, Wi-Fi, or a dedicated short-range vehicle communication link. In practical applications, other models can also be selected for this component, and this application does not limit this choice.

[0090] During operation, the microcontroller continuously listens for stop signals while executing the first control command. Upon receiving a stop command, it immediately interrupts the current control output and executes the corresponding stop control logic, causing the vehicle to terminate the current remote parking action. This process allows the execution of the first control command to be remotely terminated, maintaining the vehicle in a controllable and safe state.

[0091] With the above settings, the current remote parking task can be terminated in time after the user issues a stop command. The first control command will no longer drive the vehicle to perform subsequent actions, the duration of the control output is limited, and the vehicle state can quickly return to a stable state, thereby realizing remote interruption control of the remote parking process.

[0092] In one possible implementation, obtaining the stop instruction includes:

[0093] When the first fault identifier is determined, a stop command is obtained. The first fault identifier is used to indicate a microcontroller failure or that the first control command cannot be executed.

[0094] In practical implementation, upon receiving a stop command, the microcontroller immediately ceases control output to the drive motor, steering actuator, or brake actuator, clears the current control buffer, or freezes the current control state, thus halting the parking action corresponding to the first control command. The microcontroller can be a single-chip control chip or a controller with anomaly monitoring function; other models can also be selected in practical applications, and this application does not limit this choice. By associating the first fault identifier with the stop command trigger, the control process can be terminated promptly upon detecting a microcontroller malfunction or the inability to execute the first control command, thereby maintaining the remote parking process under control and reducing the risk of continuous abnormal control output.

[0095] Based on the foregoing embodiments, it further includes: when the first fault indicator indicates a microcontroller fault, sending a first remote control command and first status information to the on-chip system.

[0096] When the microcontroller detects the first fault indicator, it still encapsulates the currently stored first remote control command and first status information into a data frame, and sends it along with a timestamp, message identifier, and verification information to the system-on-a-chip (SoC) so that the SoC can obtain the control context at the time of the fault. After receiving the data frame, the SoC can maintain the vehicle control state, execute a safe takeover, or complete fault log recording based on the first remote control command and first status information, thereby ensuring that the control information is not interrupted when the microcontroller fails.

[0097] By adopting the above method, when the microcontroller fails, the first remote control command and the first status information can be transferred to the on-chip system in a timely manner, so that the control context before and after the failure can be preserved. The on-chip system can then perform subsequent processing or recording based on this, thereby improving the fault tolerance and control continuity of the remote parking system.

[0098] In one possible implementation, when executing the first control command, the method further includes: determining first notification information, the first notification information including at least one of vehicle start-up first state information, parking progress information, driving out progress information, vehicle speed information, vehicle position information, and vehicle attitude information; and sending the first notification information to the terminal device.

[0099] In practical implementation, while executing the first control command, the microcontroller continuously reads the vehicle's operating status variables and selects the corresponding feedback content based on whether it is currently in straight-in parking mode or straight-out driving mode. When the vehicle just enters the control execution phase, the microcontroller can send the vehicle's initial status information to the terminal device; when the vehicle is in the parking process, it can simultaneously output parking progress information, vehicle speed information, vehicle position information, and vehicle attitude information; when the vehicle is in the driving process, it can simultaneously output driving progress information and position and attitude information corresponding to the driving trajectory. The first notification information can be sent to the terminal device via Bluetooth, Wi-Fi, or cellular communication. After receiving it, the terminal device displays the vehicle's current status on the interface, allowing the user to monitor the vehicle's execution progress in real time.

[0100] During the execution of the first control command, the microcontroller generates the first notification information and sends it to the terminal device. This enables the terminal device to continuously receive status feedback such as vehicle start-up, parking, exiting, speed, position, and attitude, thus forming a status feedback mechanism synchronized with the control execution process. This method allows users to promptly know the current stage and motion status of the vehicle and determine whether remote parking is being executed correctly, improving the visualization of the control process and the timeliness of status feedback.

[0101] In one possible implementation, a first control command is generated based on a first remote control command and first status information, including: inputting the first remote control command and first status information into a first algorithm to obtain the first control command, wherein the first algorithm includes a straight-in-straight-out path planning algorithm and / or an obstacle rapid identification and avoidance algorithm.

[0102] In practical implementation, after the microcontroller sends the first remote control command and the first state information into the first algorithm, it first generates a driving trajectory corresponding to the target mode based on the direct-in-direct-out path planning algorithm. Then, it combines the obstacle rapid recognition and avoidance algorithm to make a real-time judgment on the obstacle risk in the trajectory neighborhood, and jointly solves the vehicle speed, steering angle, and braking amount, thereby outputting the first control command. This first control command can be output to the vehicle execution link in the form of discrete control quantity, or it can be output to the steering, drive, and braking components directly in the form of continuous control quantity.

[0103] When the first algorithm runs within the microcontroller, it can quickly match a preset path template with an obstacle threshold table and perform local corrections based on the current first state information. For the straight-in / straight-out path planning part, the algorithm determines the central axis driving trajectory based on the vehicle wheelbase, current vehicle attitude information, and target travel direction, and generates an executable path within the parking space boundary constraints. For the obstacle rapid identification and avoidance part, the algorithm jointly judges the ultrasonic echo distance, changes in vehicle wheel speed information, and attitude deviation. When an obstacle is detected approaching, the algorithm adjusts the path offset or speed limit parameters to adapt the first control command to the current environment.

[0104] By directly inputting the first remote control command and the first state information into the first algorithm for calculation, the microcontroller can complete path planning and obstacle avoidance decisions within a short processing link, and output the first control command that matches the current state of the vehicle. This enables the vehicle to obtain continuous and executable control quantities in straight-in or straight-out scenarios, thereby improving the real-time performance and stability of remote parking control.

[0105] Figure 3 This is a schematic diagram of the structure of the remote parking device provided in the embodiments of this application, as shown below. Figure 3 As shown, the remote parking device 30 provided in this embodiment includes an acquisition module 301, a processing module 302, and an execution module 303.

[0106] The acquisition module 301 is used to acquire a first remote control command, which is issued by the user through a terminal device;

[0107] Processing module 302 is used to determine the first state information of the vehicle;

[0108] The processing module 302 is also used to generate a first control command based on the first remote control command and the first status information;

[0109] Execution module 303 is used to execute the first control instruction.

[0110] In one possible embodiment, the microcontroller is communicatively connected to an inertial sensor, and the first state information includes inertial data output by the inertial sensor.

[0111] In one possible embodiment, the operating mode of the first remote control command is either a straight-in parking mode or a straight-out driving mode.

[0112] In one possible embodiment, the microcontroller is communicatively connected to an ultrasonic sensor, and the first state information also includes environmental information output by the ultrasonic sensor.

[0113] In one possible embodiment, the environmental information includes at least one of static obstacle information, dynamic obstacle information, and pedestrian information.

[0114] In one possible embodiment, the first state information also includes vehicle wheel speed information.

[0115] In one possible embodiment, the first state information further includes second state information, which is determined based on inertial data, vehicle wheel speed information, and visual inertial odometer calculation.

[0116] In one possible embodiment, it also includes:

[0117] Obtain the stop command; the stop command is used to instruct the execution of the first control command to stop.

[0118] Execute the stop command.

[0119] In one possible embodiment, obtaining the stop command includes:

[0120] When the first fault identifier is determined, a stop command is obtained. The first fault identifier is used to indicate a microcontroller failure or that the first control command cannot be executed.

[0121] In one possible embodiment, it also includes:

[0122] When the first fault indicator indicates a microcontroller fault, the first remote control command and the first status information are sent to the on-chip system.

[0123] In one possible embodiment, when executing the first control command, the method further includes:

[0124] The first notification information is determined, which includes at least one of the following: vehicle start-up first status information, parking progress information, driving out progress information, vehicle speed information, vehicle position information, and vehicle attitude information;

[0125] The first notification information is sent to the terminal device.

[0126] In one possible embodiment, a first control command is generated based on a first remote control command and first status information, including:

[0127] The first remote control command and the first status information are input into the first algorithm to obtain the first control command. The first algorithm includes a straight-in-straight-out path planning algorithm and / or an obstacle rapid identification and avoidance algorithm.

[0128] The remote parking device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0129] Figure 4 This is a schematic diagram of the microcontroller provided in an embodiment of this application. Figure 4 As shown, the microcontroller 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the microcontroller 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus.

[0130] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0131] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0132] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0133] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0134] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0135] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0136] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0137] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0138] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0139] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0140] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0142] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0143] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0144] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A remote-controlled parking method, characterized in that, Applied to a microcontroller, the method includes: Obtain a first remote control command, wherein the first remote control command is issued by the user through a terminal device; Determine the vehicle's initial status information; Based on the first remote control command and the first status information, a first control command is generated; Execute the first control instruction.

2. The method according to claim 1, characterized in that, The microcontroller is communicatively connected to the inertial sensor, and the first state information includes the inertial data output by the inertial sensor.

3. The method according to claim 1, characterized in that, The operation mode of the first remote control command is either straight-in parking mode or straight-out driving mode.

4. The method according to claim 1, characterized in that, The microcontroller is communicatively connected to the ultrasonic sensor, and the first status information also includes environmental information output by the ultrasonic sensor.

5. The method according to claim 4, characterized in that, The environmental information includes at least one of static obstacle information, dynamic obstacle information, and pedestrian information.

6. The method according to claim 2, characterized in that, The first status information also includes vehicle wheel speed information.

7. The method according to claim 6, characterized in that, The first state information also includes second state information, which is determined based on the inertial data, the vehicle wheel speed information, and the visual inertial odometer calculation method.

8. The method according to claim 1, characterized in that, Also includes: Obtain a stop instruction, the stop instruction being used to instruct the execution of the first control instruction to stop; Execute the stop command.

9. The method according to claim 8, characterized in that, The process of obtaining the stop command includes: When a first fault identifier is determined, a stop command is obtained. The first fault identifier is used to indicate that the microcontroller is faulty or that the first control command cannot be executed.

10. The method according to claim 9, characterized in that, Also includes: When the first fault identifier indicates a fault in the microcontroller, the first remote control command and the first status information are sent to the system on-chip.

11. The method according to claim 1, characterized in that, When executing the first control instruction, the method further includes: The first notification information is determined, which includes at least one of the following: vehicle start-up first status information, parking progress information, driving out progress information, vehicle speed information, vehicle position information, and vehicle attitude information; The first notification information is sent to the terminal device.

12. The method according to claim 1, characterized in that, The step of generating a first control command based on the first remote control command and the first status information includes: The first remote control command and the first status information are input into the first algorithm to obtain the first control command. The first algorithm includes a straight-in-straight-out path planning algorithm and / or an obstacle rapid identification and avoidance algorithm.

13. A microcontroller, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-12.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-12.

Images