Method for controlling an unmanned vehicle outside the vehicle and electronic device

Abstract

The application discloses an off-vehicle control method of an unmanned vehicle and electronic equipment, and is applied to the field of vehicle control. The unmanned vehicle is provided with a vehicle-mounted camera which shoots a view field towards the outside of the vehicle. The off-vehicle control method of the unmanned vehicle comprises the following steps: acquiring a shooting image of the vehicle-mounted camera, wherein the shooting image comprises image content of a control gesture performed by an off-vehicle controller; identifying the control gesture performed by the off-vehicle controller and first position information representing a position of the off-vehicle controller from the shooting image; if second position information from a positioning device held by the off-vehicle controller is acquired, and the first position information is consistent with the second position information, the unmanned vehicle is controlled to run according to the control gesture of the off-vehicle controller. The application solves the technical problem that the unmanned vehicle cannot run off a congested road section.

Description

Technical Field

[0001] This invention belongs to the field of autonomous driving technology, and particularly relates to an external control method and electronic device for an unmanned vehicle. Background Technology

[0002] Autonomous driving is divided into six levels, L0 to L5, namely, no driver assistance, driver-assisted, partial driver assistance, combined driver assistance, highly automated driving, and fully automated driving. Level 4 autonomous driving has been achieved so far, meaning unmanned driving within a specific area.

[0003] However, autonomous vehicles may "paralyze" in dense traffic, meaning they may struggle to move due to having to avoid other vehicles and remain stationary, unable to automatically leave the congested area. Summary of the Invention

[0004] The external control method and electronic device for an unmanned vehicle provided by the embodiments of the present invention at least to some extent solve the technical problem that unmanned vehicles cannot leave congested road sections.

[0005] In a first aspect of the invention, an external control method for an autonomous vehicle is provided, wherein the autonomous vehicle is equipped with an onboard camera whose field of view faces outwards, the method comprising: acquiring images captured by the onboard camera, the captured images including image content of an external operator performing control gestures; identifying from the captured images the control gestures performed by the external operator and first location information representing the location of the external operator; and if second location information is acquired from a positioning device, and the first location information is consistent with the second location information, controlling the autonomous vehicle to drive according to the control gestures of the external operator.

[0006] In conjunction with the first aspect, in some embodiments, identifying the control gestures performed by the operator outside the vehicle and the first location information representing the location of the operator outside the vehicle from the captured image includes: inputting the captured image into a trained target detection model; detecting the operator outside the vehicle from the captured image through the target detection model, and identifying the control gestures performed by the operator outside the vehicle and the first location information representing the location of the operator outside the vehicle.

[0007] In conjunction with the first aspect, in some embodiments, a fixing device for locking the positioning device is also installed on the autonomous vehicle. Before acquiring the image captured by the vehicle-mounted camera, the method further includes: acquiring an external control request when the positioning device is locked to the fixing device, the external control request being initiated after the vehicle identification information of the autonomous vehicle and / or the identity identification information of the external operator has been verified; in response to the external control request, controlling the autonomous vehicle to enter an interactive control mode; and in response to the external control request, unlocking the fixing device to change the positioning device from a state locked to the fixing device to a usable state.

[0008] In conjunction with the first aspect, in some embodiments, obtaining the external control request includes: obtaining the identity information of the external operator; verifying the identity information; and generating the external control request if the identity information is verified.

[0009] In conjunction with the first aspect, in some embodiments, obtaining the external control request includes: receiving an external control request initiated by a server, wherein the external control request is initiated after the server verifies the vehicle identification information of the autonomous vehicle and / or the identity identification information of the external operator.

[0010] In conjunction with the first aspect, in some embodiments, the method further includes: during the process of controlling the autonomous vehicle to drive according to the control gestures of the operator outside the vehicle, if it is detected that the operator outside the vehicle has left the field of view of the vehicle-mounted camera, controlling the positioning device to issue a reminder message, the reminder message being used to remind the operator outside the vehicle that they have left the field of view of the vehicle-mounted camera and / or to remind them to put the positioning device back at the fixed device; controlling the autonomous vehicle to automatically drive to the parking area and then stop.

[0011] In conjunction with the first aspect, in some embodiments, after controlling the autonomous vehicle to automatically drive to the parking area and stop, the method further includes: detecting whether the positioning device has been returned to the fixing device; if so, controlling the fixing device to lock, and controlling the autonomous vehicle to exit the interactive control mode so that the autonomous vehicle can continue the autonomous driving task.

[0012] In conjunction with the first aspect, in some embodiments, obtaining the second location information from the positioning device includes: receiving a positioning wave signal emitted by the positioning device, wherein the positioning wave signal is emitted by the positioning device under the operation of the operator outside the vehicle; and parsing the positioning wave signal to obtain second location information characterizing the location of the operator outside the vehicle.

[0013] In conjunction with the first aspect, in some embodiments, controlling the autonomous vehicle to drive according to the control gestures of the operator outside the vehicle includes: converting the identified control gestures performed by the operator outside the vehicle into vehicle control commands; controlling the autonomous vehicle to drive according to the vehicle control commands and driving parameters configured for the interactive control mode; wherein the driving parameters include a first driving speed limit and / or a first safe distance from surrounding obstacles, the first driving speed limit being lower than a second driving speed limit configured for the autonomous driving mode, and the first safe distance being lower than the second safe distance configured for the autonomous driving mode.

[0014] In a second aspect of the invention, an electronic device is provided, comprising: a processor, and a memory communicatively connected to the processor; the memory storing computer-executable instructions; the processor executing the computer-executable instructions stored in the memory to implement the external control method for an unmanned vehicle as described in any embodiment of the first aspect.

[0015] According to one or more technical solutions provided in the embodiments of the present invention, at least the following technical effects or advantages are achieved:

[0016] By identifying the control gestures performed by an external operator and the first location information representing the operator's location from images captured by the vehicle's onboard camera, and if a second location information is obtained from a positioning device, the autonomous vehicle will drive according to the identified control gestures if the first and second location information match. This allows the autonomous vehicle to automatically leave congested road sections under the external control of the operator. Furthermore, since the autonomous vehicle only drives according to the control gestures identified from the captured images when the first and second location information match, the autonomous vehicle is only controlled by a specific person, avoiding interference from pedestrian gestures and improving the reliability of external control of the autonomous vehicle. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0018] Figure 1 A flowchart of an external control method for an autonomous vehicle according to some embodiments of the present invention is shown;

[0019] Figure 2 The basis is shown Figure 1The interaction process of external control methods for autonomous vehicles;

[0020] Figure 3 A schematic diagram of the structure of an electronic device according to some embodiments of the present invention is shown. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] First, it should be clarified that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0023] This invention provides an external control method for an autonomous vehicle, applicable to autonomous vehicles. The autonomous vehicle is equipped with an onboard camera whose field of view faces outwards. The autonomous vehicle also features an independent positioning device capable of emitting positioning wave signals. Furthermore, the autonomous vehicle is equipped with a signal receiving device for receiving the positioning wave signals emitted by the positioning device.

[0024] In some embodiments, the positioning device and the signal receiving device communicate via any one of RFID, Bluetooth, and UWB (Ultra Wide Band) communication methods. In some embodiments, the vehicle-mounted camera can be installed on the windshield of the autonomous vehicle with its field of view facing forward.

[0025] like Figure 1 As shown, the external control method for unmanned vehicles provided in this embodiment of the invention includes the following steps S101 to S103.

[0026] In step S101: Acquire images captured by the vehicle-mounted camera, including images of the operator outside the vehicle performing control gestures.

[0027] Understandably, the images captured by the vehicle-mounted camera can be video footage or at least a single photograph of a person operating the vehicle outside the vehicle performing control gestures. The vehicle-mounted camera captures the control gestures performed by the person operating the vehicle outside the vehicle, within the camera's field of view.

[0028] It is understandable that the control gestures performed by the operator outside the vehicle can be preset control gestures, which can include various types of traffic control gestures such as: going straight, turning left, waiting to turn left, turning right, waiting to turn right, changing lanes, and parking on the side of the road.

[0029] In step S102: Identify the control gestures performed by the operator outside the vehicle and the first location information representing the location of the operator outside the vehicle from the captured image.

[0030] In some embodiments, identifying control gestures performed by an operator outside the vehicle and first location information representing the location of the operator outside the vehicle from the captured image includes: inputting the captured image into a trained target detection model; detecting the operator outside the vehicle from the captured image using the target detection model, and identifying the control gestures performed by the operator outside the vehicle and the first location information representing the location of the operator outside the vehicle.

[0031] In some embodiments, the object detection model can be a deep learning-based neural network model, such as R-CNN (Region-based Convolutional Neural Networks, an algorithm that applies deep learning to object detection), Mask R-CNN (Mask Region-based Convolutional Neural Network, a multi-task deep learning model for object detection and instance segmentation), or Fast R-CNN (Fast Region-based Convolutional Network), etc., which are region-based convolutional neural networks.

[0032] It is understood that the external operator is one or more authorized personnel with the authority to operate the autonomous vehicle, such as traffic police or park management personnel. In some embodiments, the external operator has distinctive features compared to other personnel. It is understood that distinctive features include one or more of clothing color, clothing texture, and clothing logos. An image set is used to train a deep learning-based neural network model to obtain an object detection model, wherein each image in the image set includes an image of a person wearing distinctive clothing performing standard control gestures.

[0033] In other embodiments, preprocessing operations such as denoising and enhancement are performed on the captured images to improve the accuracy and efficiency of subsequent processing. Feature extraction is then performed on the preprocessed images to extract key image features that characterize the control gestures of the operator outside the vehicle. These key image features include shape, color, and texture. The extracted key image features are then matched with various pre-stored standard gesture templates to identify the control gestures performed by the operator outside the vehicle.

[0034] In step S103: If the second position information from the positioning device is obtained, and the first position information is consistent with the second position information, the driverless vehicle is controlled to drive according to the control gestures of the operator outside the vehicle.

[0035] Understandably, by combining the first location information identified from images captured by the vehicle's onboard camera with the second location information obtained through the positioning device for fusion positioning, the two positioning methods must be consistent to improve the accuracy and robustness of locating the operator outside the vehicle. The positioning device is mounted on the autonomous vehicle and is available for the operator to access when the autonomous vehicle requires external control.

[0036] In some embodiments, a positioning wave signal emitted by a positioning device held by an operator outside the vehicle is received by a signal receiving device. The autonomous vehicle analyzes the positioning wave signal received by the signal receiving device to extract second location information representing the location of the operator outside the vehicle. Both the extracted second location information and the first location information include the distance between the operator outside the vehicle and the autonomous vehicle, and the angle of the operator outside the vehicle relative to the autonomous vehicle.

[0037] To improve the safety of operating autonomous vehicles from outside the vehicle, the positioning device may also include an activation button operated by an external operator. The positioning device only emits a positioning wave signal when the external operator operates the activation button, and will not emit a positioning wave signal if the external operator does not operate the activation button.

[0038] To enhance communication security between the positioning device and the autonomous vehicle, wireless encryption is used to ensure secure communication and prevent unauthorized access and operation. In some embodiments, the positioning device integrates an encryption chip that generates one or more unique encryption keys during manufacturing. When an operator outside the vehicle presses the activation button on the positioning device, it generates a positioning wave signal. This signal is encrypted using a pre-generated encryption key before transmission, employing symmetric, asymmetric, or hybrid encryption modes. The encrypted signal is then transmitted to the autonomous vehicle via radio waves (such as RFID signals) at frequencies in the megahertz range (e.g., 300MHz to 450MHz) to ensure stable and reliable transmission. The encrypted signal is received by a signal receiving device installed on the autonomous vehicle, which uses a corresponding decryption key to decrypt the received signal and reconstruct the positioning wave signal.

[0039] In some embodiments, the autonomous vehicle may be configured with an autonomous driving mode and an interactive control mode. The interactive control mode is a mode in which the autonomous vehicle is controlled through interaction between an operator outside the vehicle and the autonomous vehicle. The autonomous driving mode is a mode in which the vehicle drives itself without human intervention. The autonomous vehicle is also equipped with a fixing device for locking the positioning device onto the vehicle. When the autonomous vehicle is in autonomous driving mode, the positioning device is locked by the fixing device and cannot be retrieved.

[0040] It is understood that the external control method for unmanned vehicles provided in the embodiments of the present invention may further include: controlling the unmanned vehicle to drive according to the control gestures of the external operator when the first location information and the second location information are inconsistent.

[0041] It is understandable that the positioning accuracy of the positioning device is higher than that of the vehicle camera. Determining whether the first location information and the second location information are consistent includes: determining whether the second location information is within the positioning range of the first location information. If so, the first location information and the second location information are consistent; otherwise, the first location information and the second location information are inconsistent.

[0042] In some embodiments, when the first location information and the second location information are inconsistent, it indicates that the control gesture is not a control gesture performed by an operator outside the vehicle, ensuring that the vehicle is only controlled by the control gestures of specific personnel, and the vehicle does not recognize the gestures of other pedestrians, thereby improving the reliability of external control.

[0043] In some embodiments, if the operator outside the vehicle does not operate the activation button, the second location information from the positioning device cannot be obtained, and if the second location information cannot be obtained, the driverless vehicle is controlled to stop.

[0044] In some embodiments, before acquiring the image captured by the vehicle-mounted camera, the method further includes: acquiring an external control request when the positioning device is locked to a fixed device, wherein the external control request is initiated after the vehicle identification information of the autonomous vehicle and / or the identity identification information of the external operator has been verified; in response to the external control request, controlling the autonomous vehicle to enter an interactive control mode; and in response to the external control request, unlocking the fixed device to change the positioning device from a locked state to a usable state.

[0045] In some embodiments, the step of obtaining an external control request includes: obtaining the identification information of the external operator and verifying the obtained identification information; if the identification information is verified, generating an external control request.

[0046] In some embodiments, an input device is installed on the autonomous vehicle for users to input identity verification information. The input device may be located on the B-pillar or C-pillar of the autonomous vehicle.

[0047] In some embodiments, acquiring and verifying the identity information of the external operator includes: the autonomous vehicle acquiring, via an input device, identity information representing the identity of the external operator, such as a personnel number, ID card number, or the last six digits of the ID card, which uniquely identifies the external operator; the autonomous vehicle verifying the input identity information using pre-stored information locally on the vehicle; if verification is successful, an external control request is generated. It is understood that verification succeeds if the input identity information exists in the pre-stored information, and fails if the input identity information does not exist in the pre-stored information. The pre-stored information includes the identity information of each operator authorized to control the deployed autonomous vehicle from outside.

[0048] The system verifies the input identity information using pre-stored information locally on the autonomous vehicle. If verification passes, an external control request is generated. Essentially, verification succeeds if the input identity information exists in the pre-stored information, and fails if it does not. The pre-stored information contains the identity information of all personnel authorized to control the autonomous vehicle from outside.

[0049] In other embodiments, obtaining an external control request includes receiving an external control request initiated by a server, wherein the external control request is initiated by the server after verifying the vehicle identification information of the autonomous vehicle and the identity identification information of the external operator.

[0050] In some embodiments, receiving an external control request initiated by the server includes: after the autonomous vehicle obtains the identity information representing the identity of the external operator input by the external operator through an input device on the autonomous vehicle, the autonomous vehicle reports the vehicle identification information of the autonomous vehicle and the input identity information to the system for managing autonomous vehicles, so that the server can verify the received identity information using pre-stored information. After successful verification, the server issues an external control request to the corresponding autonomous vehicle based on the vehicle identification information.

[0051] In other embodiments, receiving an external control request initiated by the server includes: the user terminal obtaining the vehicle identification information of the autonomous vehicle, which can be a VIN (Vehicle Identification Number) code. This can be obtained by scanning the QR code corresponding to the VIN code displayed on the autonomous vehicle through an APP installed on the user terminal, or by the external operator manually entering the VIN code of the autonomous vehicle into the APP. The user terminal then obtains the vehicle identification information of the autonomous vehicle and sends it to the server used to manage the autonomous vehicles. The server then verifies the vehicle identification information reported by the user terminal using pre-stored information. If the verification is successful, the server issues an external control request to the corresponding autonomous vehicle based on the vehicle identification information.

[0052] In some other embodiments, a video call with the back-end management personnel can be initiated through the video call interface of the user terminal or the video call interface of the autonomous vehicle. The identity of the person operating the vehicle outside the vehicle can be manually verified through the video call. In response to the authorization operation by the back-end management personnel after the identity of the person operating the vehicle outside the vehicle is manually verified, the server issues an external control request to the autonomous vehicle.

[0053] In some embodiments, to improve the reliability of controlling the autonomous vehicle from outside the vehicle, after receiving an external control request initiated by the server, it is determined whether the distance between the user terminal and the autonomous vehicle is less than a preset distance threshold. If so, in response to the external control request, the autonomous vehicle is controlled to enter an interactive control mode; in response to the external control request, the fixing device is unlocked, so that the positioning device changes from a locked state to a usable state. It is understood that the preset distance threshold can be within the range of 10 to 50 meters, for example, the preset distance setting is set to 10m, 20m, or 50m.

[0054] Through any of the above implementation methods, control of the autonomous vehicle can be released to the operator outside the vehicle, so that the autonomous vehicle can enter the interactive control mode and unlock the fixing device, thereby making it easier for the operator outside the vehicle to take the positioning device for use when the operator outside the vehicle controls the autonomous vehicle.

[0055] In some embodiments, the external control method for an autonomous vehicle provided by the present invention may further include: monitoring whether the external operator leaves the field of view of the onboard camera while controlling the autonomous vehicle to drive according to the control gestures of the external operator; if the external operator is detected to have left the field of view of the onboard camera, controlling the positioning device to issue a reminder message, the reminder message being used to remind the external operator that they have left the field of view of the onboard camera and / or to remind them to put the positioning device back at the fixed device; and controlling the autonomous vehicle to automatically drive to a parking area and then stop. It is understood that the parking area can be a lane at the edge of a road.

[0056] In some embodiments, the external control method for an autonomous vehicle provided by the present invention may further include: after controlling the autonomous vehicle to automatically drive to a parking area and stop, detecting whether the positioning device has been returned to the fixed device; if the positioning device is detected to have been returned to the fixed device, controlling the fixed device to lock, and also controlling the autonomous vehicle to exit the interactive control mode and return to the autonomous driving mode, so that the autonomous vehicle can continue to perform autonomous driving tasks, thereby enabling the autonomous vehicle to continue autonomous driving after leaving the congested road section through external control, thus improving the intelligence of the autonomous vehicle.

[0057] In some embodiments, controlling an autonomous vehicle to drive according to the control gestures of an external operator includes: converting the recognition result of the control gestures into vehicle control commands; and controlling the autonomous vehicle to drive according to the indicated direction of the vehicle control commands and the driving parameters set for the external control mode.

[0058] In some embodiments, the driving parameters set for the external control mode include a first driving speed limit and / or a first safe distance from surrounding obstacles, wherein the first driving speed limit is lower than the second driving speed limit of the driverless vehicle in the autonomous driving mode, and the first safe distance is lower than the second safe distance of the driverless vehicle in the autonomous driving mode.

[0059] Understandably, the first driving speed limit can be set within the range of 5 to 15 km / h. For example, the first driving speed limit can be set to 5 km / h, 10 km / h, or 15 km / h. The first safety distance can be set within the range of 8 to 12 m. For example, the first safety distance can be set to 8 m, 10 m, or 12 m.

[0060] Figure 2 The basis is shown Figure 1 The interaction process of the external control method for autonomous vehicles. For a better understanding of the external control method for autonomous vehicles provided in this embodiment, please refer to... Figure 2 The interaction process of the external control method for autonomous vehicles in some embodiments of the present invention is given:

[0061] Step S01: The driverless vehicle is in a road with heavy traffic, and the driverless vehicle can no longer drive automatically;

[0062] Step S02: The operator outside the vehicle applies for external control by inputting their identification information into the input device on the driverless vehicle.

[0063] Step S03: The driverless vehicle verifies the identity information entered by the operator outside the vehicle. If the verification is successful, the fixing device used to lock the positioning device is unlocked.

[0064] Step S04: The operator outside the vehicle retrieves the positioning device;

[0065] Step S05: The operator outside the vehicle holds the positioning device in hand, presses or holds the activation button on the positioning device, and performs the control gesture for external control of the driverless vehicle. The positioning device emits a positioning wave signal when the operator outside the vehicle presses the activation button.

[0066] Step S061: The signal receiving device installed on the unmanned vehicle receives the positioning wave signal;

[0067] Step S062: The onboard camera installed on the driverless vehicle captures the control gestures performed by the operator outside the vehicle to obtain images;

[0068] Step S071: The autonomous vehicle analyzes the received positioning wave information to extract the second location information representing the location of the operator outside the vehicle;

[0069] Step S072: The autonomous vehicle uses a pre-trained target detection model to perform image recognition on the captured images to identify the operator outside the vehicle, the first location information representing the location of the operator outside the vehicle, and the control gestures performed by the operator outside the vehicle.

[0070] Step S08: Compare whether the first location information and the second location information are consistent. If they are, proceed to step S09.

[0071] Step S09: Convert the recognized control gestures into vehicle control commands, and control the autonomous vehicle to drive according to the vehicle control commands.

[0072] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 3 A schematic diagram of the structure of an electronic device according to some embodiments of the present invention is shown. For example... Figure 3 As shown, the electronic device includes one or more memories 304, one or more processors 302, and at least one computer program (program code) stored in the memory 304 and executable on the processor 302. When the processor 302 executes the computer program, it implements the external control method of the unmanned vehicle of any of the above embodiments.

[0073] Among them, Figure 3 In this document, a bus architecture (represented by bus 300) is used. Bus 300 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.

[0074] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, the computer program including executable instructions, which, when executed by a processor, implements a method for outputting vehicle interpretation information according to any of the above embodiments.

[0075] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0080] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An external control method for an unmanned vehicle, characterized in that, The autonomous vehicle is equipped with an onboard camera with its field of view facing outwards, and the autonomous vehicle is also equipped with an independent positioning device; the method includes: Acquire images captured by the vehicle-mounted camera, the images including images of an operator outside the vehicle performing control gestures; The control gestures performed by the operator outside the vehicle and the first location information representing the location of the operator outside the vehicle are identified from the captured images. If second location information is obtained from the positioning device, and the first location information is consistent with the second location information, the driverless vehicle is controlled to drive according to the control gestures of the operator outside the vehicle. The positioning wave signal emitted by the positioning device is received, and the positioning wave signal is emitted by the positioning device under the operation of the operator outside the vehicle. The positioning wave signal is analyzed to obtain second location information representing the location of the operator outside the vehicle. Both the second location information and the first location information include the distance between the operator outside the vehicle and the driverless vehicle and the angle of the operator outside the vehicle relative to the driverless vehicle.

2. The method as described in claim 1, characterized in that, The step of identifying the control gestures performed by the operator outside the vehicle and the first location information representing the location of the operator outside the vehicle from the captured image includes: The captured image is input into the trained target detection model; The target detection model detects the operator outside the vehicle from the captured image, identifies the control gestures performed by the operator, and identifies the first location information representing the location of the operator.

3. The method as described in claim 1, characterized in that, The autonomous vehicle is also equipped with a fixing device for locking the positioning device, and before acquiring the image captured by the vehicle-mounted camera, it further includes: When the positioning device is locked to the fixed device, an external control request is obtained. The external control request is initiated after the vehicle identification information of the unmanned vehicle and / or the identity identification information of the external operator are verified. In response to the external control request, the driverless vehicle is controlled to enter the interactive control mode; In response to the external control request, the fixing device is unlocked so that the positioning device changes from a state where it is locked to the fixing device to a state where it is accessible.

4. The method as described in claim 3, characterized in that, The process of obtaining external control requests includes: Obtain the identification information of the person operating the vehicle outside; The identity information is verified; If the identity verification information is successful, the external control request is generated.

5. The method as described in claim 3, characterized in that, The process of obtaining external control requests includes: Receive an external control request initiated by the server, wherein the external control request is initiated after the vehicle identification information of the autonomous vehicle and / or the identity identification information of the external operator are verified by the server.

6. The method as described in claim 3, characterized in that, Also includes: During the process of controlling the unmanned vehicle to drive according to the control gestures of the operator outside the vehicle, if it is detected that the operator outside the vehicle has left the field of view of the vehicle-mounted camera, the positioning device is controlled to issue a reminder message. The reminder message is used to remind the operator outside the vehicle that they have left the field of view of the vehicle-mounted camera and / or to remind them to put the positioning device back at the fixed device. The driverless vehicle is controlled to automatically drive to the parking area and then stop.

7. The method as described in claim 6, characterized in that, After controlling the driverless vehicle to automatically drive to the parking area and stop, the method further includes: Detect whether the positioning device has been returned to the fixing device; If so, the fixed device is locked, and the autonomous vehicle is exited the interactive control mode so that the autonomous vehicle can continue its autonomous driving mission.

8. The method as described in claim 1, characterized in that, Controlling the driverless vehicle to drive according to the control gestures of the operator outside the vehicle includes: The identified control gestures performed by the operator outside the vehicle are converted into vehicle control commands; Control the autonomous vehicle to drive according to the vehicle control command and the driving parameters configured for the interactive control mode; The driving parameters include a first driving speed limit and / or a first safe distance from surrounding obstacles, wherein the first driving speed limit is lower than a second driving speed limit configured for the autonomous driving mode, and the first safe distance is lower than a second safe distance configured for the autonomous driving mode.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the external control method for the unmanned vehicle as described in any one of claims 1-8.

Images