Collision risk warning methods, devices, and vehicles for remote-controlled vehicle driving
By identifying obstacles around the vehicle and generating risk level warning images, the problem of remote drivers being unable to identify collision risks in a timely manner is solved, improving risk identification efficiency and decision-making accuracy, and enhancing the safety of remote driving.
Patent Information
- Application Number
- CN202510600732.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-09
- Publication Date
- 2026-11-10
Smart Images

Figure CN123072228A_ABST
Abstract
Description
Technical Field
[0001] This specification relates to the field of remote driving technology, and in particular to a collision risk warning method, device and vehicle for remotely controlled driving of a vehicle. Background Technology
[0002] As an important branch of intelligent driving, remote driving technology relies on 5G communication technology to achieve human-vehicle separation control. This means a remote driver can control a vehicle remotely through a remote driving platform, demonstrating significant application value in scenarios such as intelligent transportation, industrial automation, and emergency rescue. However, because remote drivers can only independently judge the collision risk of a vehicle based on image information, and due to factors such as image perspective and quality, remote drivers cannot promptly understand and assess the vehicle's collision risk, ultimately affecting the safety of remote driving.
[0003] In existing technologies, remote driving platforms typically display images in a fixed driving direction based on the remote driver's actions. For example, when the vehicle is in drive (D) mode, it displays the image data from the forward-facing camera; or when the remote driver is preparing to change lanes to the right, it displays the image data from the right-facing and right-facing side-facing cameras. However, this method cannot promptly indicate the location of potential collision risk areas and provide corresponding images. This results in the driver in the cabin being unable to locate collision risk areas and make decisions in complex driving scenarios, leading to decreased risk identification efficiency and decision-making accuracy, and ultimately reducing the safety of remote driving. Summary of the Invention
[0004] In view of this, this specification provides a collision risk warning method, a computer-readable storage medium, and a program product for remote-controlled driving of a vehicle to address the deficiencies in related technologies.
[0005] Specifically, this specification is implemented through the following technical solution:
[0006] According to a first aspect of this specification, a collision risk warning method for remotely controlled driving of a vehicle is provided, applicable to a vehicle remotely driven by a remote driver via a remote driving platform, the method comprising:
[0007] If an obstacle is detected around the vehicle, the collision risk level between the vehicle and the obstacle is determined based on the vehicle motion information and the obstacle description information.
[0008] Determine the orientation information of the obstacle relative to the vehicle, and generate a warning image for the obstacle based on the orientation information, wherein the warning image is matched with the collision risk level;
[0009] The alarm image is sent to the remote driving platform for display to the remote driver.
[0010] According to a second aspect of this specification, a device for calculating the remaining driving range of a vehicle is provided, applicable to a vehicle remotely driven by a remote driver via a remote driving platform, the device comprising:
[0011] The collision risk level determination unit is used to determine the collision risk level between the vehicle and the obstacle based on vehicle motion information and obstacle description information when an obstacle is detected around the vehicle.
[0012] The alarm image determination unit is used to determine the orientation information of the obstacle relative to the vehicle, and generate an alarm image for the obstacle based on the orientation information, wherein the alarm image is matched with the collision risk level;
[0013] The alarm image display unit is used to send the alarm image to the remote driving platform for display to the remote driver.
[0014] According to a third aspect of this specification, a vehicle is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of any of the methods described in the first aspect.
[0015] According to a fourth aspect of this specification, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.
[0016] According to a fifth aspect of this specification, a computer program product includes a computer program / instructions that, when executed by a processor, implement the steps of the method described in the first aspect.
[0017] When a vehicle detects an obstacle in its vicinity, it can determine the collision risk level between itself and the obstacle based on vehicle motion information and obstacle description information. Then, based on the obstacle's relative positional information, it generates a warning image for the obstacle and sends this warning image to the remote driving platform for display to the remote driver. This application achieves risk-oriented visual enhancement interaction by dynamically sensing the collision risk level and positional information of obstacles around the vehicle, generating a warning image matching the risk level, and pushing it to the remote driving platform. This compensates for the blind spot perception deficiencies caused by fixed viewing angles, and enables the remote driver to quickly locate and quantify the collision threat, thereby significantly improving the efficiency of risk identification and decision-making accuracy in complex scenarios, and enhancing the active safety capabilities of remote driving. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in this specification, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of this specification, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.
[0019] Figure 1 This is a schematic diagram of the architecture of a collision risk warning system for remote-controlled driving of a vehicle, as shown in the embodiments disclosed in this specification.
[0020] Figure 2 This is a flowchart illustrating a collision risk warning method for remote-controlled vehicle driving as shown in the embodiments disclosed in this specification;
[0021] Figure 3 This is a schematic diagram of a vehicle ultrasonic radar sensor shown in the embodiments disclosed in this specification;
[0022] Figure 4 This is a schematic diagram illustrating a vehicle camera according to an embodiment disclosed in this specification;
[0023] Figure 5 This is a schematic diagram illustrating a vehicle collision risk level classification according to the embodiments disclosed in this specification;
[0024] Figures 6a-6c This is a schematic diagram illustrating a remote driving platform displaying alarm images according to an embodiment disclosed in this specification;
[0025] Figure 7 This is a schematic structural diagram of an electronic device shown in the embodiments of this specification;
[0026] Figure 8 This is a block diagram illustrating a collision risk warning device for remote-controlled vehicle driving, as shown in the embodiments of this specification. Detailed Implementation
[0027] 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 specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification.
[0028] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” as used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.
[0029] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."
[0030] The following describes in detail, with reference to the accompanying drawings, embodiments of the collision risk warning method for remote-controlled vehicle driving described in this specification.
[0031] Figure 1 This is a schematic diagram illustrating the architecture of a collision risk warning system for remote-controlled vehicle driving, as shown in the embodiments disclosed in this specification. Figure 1 As shown, the system may include a vehicle 11 and a remote driving platform 12.
[0032] Vehicle 11 serves as the execution terminal of the aforementioned collision risk warning system. Through the collaborative operation of the corresponding environmental perception module and alarm generation module, it achieves dynamic identification and visual warning of collision risks. Specifically, the environmental perception module can use sensors such as LiDAR, millimeter-wave radar, and multiple cameras to identify and collect descriptive and directional information of obstacles around the vehicle in real time. Based on vehicle motion information such as vehicle speed, steering angle, and acceleration, along with the aforementioned descriptive information, it constructs a collision risk assessment model and calculates the collision risk level. Furthermore, as a remotely controlled object, vehicle 11 can be further adapted to different scenarios such as passenger cars, commercial vehicles, or special-purpose vehicles; this specification does not limit its application to these applications.
[0033] The remote driving platform 12 serves as the core interactive interface for the remote driver. Besides assisting the remote driver in controlling the vehicle 11, it can also receive alarm images pushed by the vehicle 11 based on the alarm generation module via a low-latency communication link. Simultaneously, the remote driving platform also supports subsequent operations such as touch marking or voice feedback on the alarm images displayed on the platform, thus forming a closed loop for risk management. Of course, the remote driving platform can present the aforementioned core interactive interface through devices such as simulators, virtual reality glasses, mobile phones, and tablets; this specification does not impose any limitations on this.
[0034] Figure 2 This is a flowchart illustrating a collision risk warning method for remotely controlled driving of a vehicle, provided in an exemplary embodiment. The method is applied to a vehicle remotely driven by a remote driver via a remote driving platform and may include the following steps:
[0035] Step S202: If an obstacle is detected around the vehicle, the collision risk level between the vehicle and the obstacle is determined based on the vehicle motion information and the obstacle description information.
[0036] When a remote driver remotely controls a vehicle through a remote driving platform, the vehicle can use a perception network composed of, for example, lidar, millimeter-wave radar, and multiple cameras to identify and collect obstacle description information of surrounding obstacles in real time, such as distance, relative speed, and trajectory data. It can also obtain its own vehicle motion information, such as speed, steering angle, and acceleration, through corresponding motion sensors, thereby determining the collision risk level of the vehicle to facilitate the subsequent generation of warning images for the corresponding obstacles.
[0037] The following is based on Figure 3 For example, the process of identifying obstacles and obtaining obstacle description information can be implemented using the ultrasonic radar sensor shown in the diagram. Figure 3As shown, the ultrasonic radar sensors at the vehicle end are arranged as follows: Two long-range ultrasonic (LRU) radar sensors are deployed on the front side of the vehicle (Front Left Side, FLS and Front Right Side, FRS), and four short-range ultrasonic (SRU) radar sensors are deployed on the front left (FL), front left middle (FLM), front right middle (FRM), and front right (FR). Two LRU-type ultrasonic radar sensors are deployed on the rear side of the vehicle (Rear Left Side, RLS and Rear Right Side, RRS), and four SRU-type ultrasonic radar sensors are deployed on the rear left (RL), rear left middle (RLM), rear right middle (RRM), and rear right (RR). In other words, the vehicle can be composed of 4 LRU and 8 SRU type ultrasonic radar sensors, which are installed at equal angles on the front and rear bumpers and side skirts of the vehicle. Based on the ultrasonic pulse echo ranging principle, the vehicle can detect obstacles 180 degrees on the front and rear sides of the vehicle through multi-sensor collaboration.
[0038] Of course, in addition to ultrasonic radar, the aforementioned vehicles can also achieve obstacle detection based on image recognition by deploying systems such as a SurroundView Camera System (SVCS). For example, six high-resolution wide-angle cameras are configured around the vehicle body—Front View (FV), Left Front View (LFV), Right Front View (RFV), Left Rear View (LRV), Right Rear View (RRV), and Rear View (RV)—forming a 360° visual coverage without blind spots. Each camera acquires images at a frame rate of 30fps, and uses deep learning models such as YOLOv7 or Faster R-CNN to perform target detection in real time, accurately identifying obstacle types and their outlines, such as pedestrians, vehicles, and roadblocks. Combined with stereo vision algorithms, obstacle distances can be calculated using the parallax of the binocular cameras, and cross-validated with the ranging results of the ultrasonic radar to improve detection accuracy.
[0039] After acquiring vehicle motion information and obstacle description information, the vehicle can calculate the relative distance between the vehicle and the obstacle through multi-source data fusion, thereby determining the aforementioned collision risk level.
[0040] In one embodiment, the vehicle can obtain the relative distance between itself and the obstacle based on the vehicle motion information and the obstacle description information, and determine the collision risk level based on the relative distance. The degree of danger represented by the collision risk level is negatively correlated with the distance. Besides directly determining the relative distance using single sensor data, multiple sensor data can be aligned using algorithms such as the Extended Kalman Filter (EKF) to eliminate single sensor errors, such as radar noise or visual false detections, ensuring the reliability of the relative distance. The collision risk level can be directly divided into multiple levels based on the relative distance, following the core rule: the closer the distance, the higher the degree of danger represented by the risk level; the farther the distance, the lower the degree of danger represented by the risk level. In the specific classification process, the collision risk level of obstacles at different relative distances can be determined based on preset classification thresholds. For example, when the relative distance is greater than 0m and less than or equal to 0.3m, a Level 1 alarm can be triggered; when the relative distance is greater than 0.3m and less than or equal to 0.6m, a Level 2 alarm can be triggered; and when the relative distance is greater than 0.6m and less than or equal to 1.0m, a Level 3 alarm can be triggered. The collision risk level corresponding to Level 1, Level 2, and Level 3 alarms represents a progressively lower degree of danger. In other words, the collision risk level of a Level 1 alarm is higher than that of a Level 2 alarm, and the collision risk level of a Level 2 alarm is higher than that of a Level 3 alarm.
[0041] Furthermore, the aforementioned classification can automatically adjust the classification threshold based on vehicle speed and road conditions. For example, on icy or snowy roads with low friction coefficients, the high-risk threshold dynamically increases from 3 meters to 5 meters, triggering an early warning. This feature is not described in this manual.
[0042] Step S204: Determine the orientation information of the obstacle relative to the vehicle, and generate a warning image for the obstacle based on the orientation information, wherein the warning image is matched with the collision risk level.
[0043] While determining the collision risk level, the vehicle can generate a warning image matching the collision risk level based on the obstacle's relative positional information, such as azimuth angle and distance. The content of this positional information can be formatted uniformly based on preset positional regions, thereby achieving refined positional zoning to adapt to the sensitivity requirements of different driving scenarios. Figure 4For example, spatial risk gradient perception can be achieved through a 30° sector division. This involves dividing the monitoring area at the front of the vehicle into six directional regions: Fa (0°–30°), Fb (30°–60°), Fc (60°–90°), Fd (90°–120°), Fe (120°–150°), and Ff (150°–180°), each covering a 30° sector. Specifically, Fa / Ff only supports Level 1 alarms; Fb / Fe supports Level 1 and Level 2 alarms; and Fc / Fd supports Level 1, Level 2, and Level 3 alarms. Simultaneously, the monitoring area at the rear of the vehicle can be divided into six directional zones: Ra (180°~210°), Rb (210°~240°), Rc (240°~270°), Rd (270°~300°), Re (300°~330°), and Rf (330°~360°). The angle division rules are the same as those for the front. Among these, Ra / Rf only supports Level 1 alarms; Rb / Re supports Level 1 and Level 2 alarms; and Rc / Rd supports Level 1, Level 2, and Level 3 alarms. Obstacles within the same directional zone can be identified as belonging to the corresponding directional zone.
[0044] It is worth mentioning that when the obstacle is located in the transition zone between the first and second orientations, the orientation information can be determined based on the historical orientation of the obstacle relative to the vehicle. The transition zone can be understood as a threshold transition zone with a preset transition angle between every two adjacent orientations. For example, when the preset transition angle between Fa and Fb is 3°, the Fa-Fb transition zone is 28.5° to 31.5°. When an obstacle's orientation corner enters this transition zone, the most recently stable historical orientation can be used as the orientation information. For example, an obstacle previously identified as Fa will retain its Fa identifier when entering the Fa-Fb transition zone. Furthermore, if the obstacle continues to move to an adjacent orientation for more than 1 second, it can be updated to a new orientation identifier, thereby improving the accuracy of the orientation information and avoiding the obstacle recognition jitter problem.
[0045] The obstacle recognition described above can also be linked to the vehicle's gear position, thus eliminating the need for collision risk warnings for obstacles in unnecessary directions. For example, when the vehicle is in reverse (R gear), collision risk warnings are only issued for obstacles in the six directions Ra, Rb, Rc, Rd, Re, and Rf. When the vehicle is not in R gear, collision risk warnings are only issued for obstacles in the six directions Fa, Fb, Fc, Fd, Fe, and Ff. This manual does not impose any limitations on this.
[0046] Depending on the number of obstacles, this manual also provides corresponding alarm image generation schemes.
[0047] In one embodiment, when a single obstacle is detected around the vehicle, the obstacle's position relative to the vehicle can be used to generate a warning image for that obstacle. In this case, the obstacle can be considered as an object posing a collision risk to the vehicle.
[0048] In another embodiment, when multiple obstacles are identified around the vehicle, at least one obstacle with a relatively higher collision risk level can be identified. The orientation information of each obstacle relative to the vehicle is then determined, and a warning image is generated for each obstacle based on this orientation information. Here, the "relatively higher obstacle" can be considered as one or more obstacles with the highest collision risk level. In warnings of the same level, the orientation of the closest obstacle can be selected as the orientation information. Furthermore, different orientation weights can be configured to improve the accuracy of the orientation information; for example, the warning priority for the directly forward area (Fc / Fd or Rc / Rd) is set higher than that for the side areas.
[0049] Of course, depending on the actual usage scenario and needs, a risk level threshold can be preset. For example, the default setting is a level 2 alarm, which will only trigger a collision risk alarm when the actual collision risk level is greater than the preset risk level, thereby generating an alarm image for the obstacle based on the aforementioned location information. The preset risk level threshold can be a fixed preset risk level or a dynamic preset risk level, which is adjusted in real time according to network bandwidth, driver operation status, and vehicle speed.
[0050] The actual generation process of the aforementioned alarm images can be closely integrated with the aforementioned directional information. The following will illustrate this process. Figure 5 Taking an example, the process of generating alarm images will be explained. Figure 5 As shown, assume the vehicle provides connected camera sensors to upload the surrounding environment to a remote driving platform. These camera sensors may include a front wide-angle camera, a rear wide-angle camera, a right-side front-view camera, a right-side rear-view camera, a left-side front-view camera, a left-side rear-view camera, a front fisheye camera, a right-side fisheye camera, a rear-side fisheye camera, and a left-side fisheye camera. These camera sensors can provide omnidirectional coverage of the vehicle. Depending on the location information, different camera sensors can be used to capture the aforementioned warning images. Specifically, assuming a collision risk warning is triggered, multiple display areas can be generated to form a warning image. These areas can respectively display the left fisheye camera image, a stitched Around View Monitor (AVM) image, the right fisheye camera image, the first warning image, and the second warning image, such as... Figure 6aAreas 1, 2, 3, 4, and 5 are shown. The above AVM image can be stitched together from the images of the front, right, rear, and left fisheye cameras. The first and second alarm images can be dynamically adjusted according to the obstacle risk level and the location information mentioned above, for example, using the following dynamic adjustment strategy:
[0051]
[0052]
[0053] Except for specific locations where shooting is impossible due to viewing angle limitations (corresponding to the black images in the table above), the first warning image can display images from either a front-view wide-angle or a rear-view wide-angle camera, and the second warning image can display images from either a left-side front-view, left-side rear-view, right-side front-view, or right-side rear-view camera. In short, when the aforementioned location information corresponds to one camera on the vehicle, the warning image can be captured based on that camera; or, when the aforementioned location information corresponds to multiple cameras on the vehicle, the warning image can be constructed from multiple images taken from different perspectives by the multiple cameras, or from corresponding stitched images, thereby ensuring that the warning image is applicable to a variety of vehicle camera configurations. Those skilled in the art will understand that the above... Figure 6c And the following text Figure 6b , 6c The layout of each display area can be changed and adjusted according to actual needs, and this manual does not impose any restrictions on this.
[0054] Of course, in addition to warning images, the vehicle can also generate a default normal driving image if no collision risk is triggered, thus ensuring that the remote driver can correctly control the vehicle via the remote driving platform. For example, when the vehicle is in reverse (R), three display areas are generated to form the aforementioned normal driving image, with each area displaying the left, rear, and right fisheye camera views, respectively. Figure 6a As shown in areas 1, 2, and 3; when the vehicle is not in reverse (R), three display areas are generated to form the above-mentioned normal driving image, with the corresponding areas displaying the left, front, and right fisheye camera images, respectively. Figure 6b Regions 1, 2, and 3 are shown.
[0055] Regarding the warning image itself, an image style can be generated based on the collision risk level. The visual prominence of this image style is positively correlated with the degree of danger represented by the collision risk level; that is, the higher the collision risk level, the stronger the visual prominence of the image style, and vice versa. The aforementioned image style can be determined based on design principles positively correlated with the collision risk level, considering multiple dimensions such as color saturation, dynamic frequency, and information density. For example, a low-collision-risk warning image can use a light blue semi-transparent border and static distance text markings; a medium-collision-risk warning image can use an overlaid yellow gradient animated border with embedded directional arrows and a distance countdown indicator; a high-collision-risk warning image can use a bright red dynamic border, high-frequency pulse warning indicators, and a full-screen mask, supplemented by 3D directional projection to enhance spatial perception and ensure timely detection by the remote driver.
[0056] Step S206: Send the alarm image to the remote driving platform to display it to the remote driver.
[0057] After generating an alarm image, the vehicle can send it over the network to a remote driving platform, where it will be displayed to the remote driver. The alarm image can be efficiently compressed into video using encoding standards such as H.264, and low-latency streaming can be achieved using network protocols to ensure high real-time display. Furthermore, hardware encoding, such as NVIDIA NVENC, can be used to reduce CPU load and increase encoding speed, ensuring a stable video stream frame rate of 30fps. A dynamic bitrate strategy is also introduced to combat weak network environments encountered in actual use. Network transmission can prioritize UDP to reduce transmission latency, while integrating dynamic jitter buffering and a reconnection mechanism within 5 seconds to ensure streaming stability in weak network environments.
[0058] Of course, the aforementioned vehicle may choose to send the aforementioned warning image and the aforementioned location information to the aforementioned remote driving platform, so that the aforementioned remote driving platform can display the corresponding warning image according to the location information. For example, the aforementioned warning image may be displayed in the remote driving platform interface at the location corresponding to the aforementioned location information, and the location information may be described in the form of text, pictures, etc.; or, the aforementioned warning image and other images may be stitched together according to the location information, and the stitched image may be sent to the aforementioned remote driving platform, so that the remote driving platform can display the stitched image. The other images include, but are not limited to, normal environmental images, and do not depend on the footage captured by the camera.
[0059] Figure 7 This is a schematic structural diagram of an electronic device according to an exemplary embodiment. Please refer to... Figure 7At the hardware level, the electronic device includes a processor 702, an internal bus 710, a network interface 704, memory 706, and non-volatile memory 708, and may also include other necessary hardware. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it, forming a risk code detection device at the logical level. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.
[0060] Figure 8 This specification illustrates a block diagram of a collision risk warning device for remote-controlled vehicle driving. (See also...) Figure 8 As shown, the device, applied to a vehicle remotely driven by a remote driver via a remote driving platform, may include:
[0061] The collision risk level determination unit 802 is used to determine the collision risk level between the vehicle and the obstacle based on vehicle motion information and obstacle description information when an obstacle is detected around the vehicle.
[0062] The alarm image determination unit 804 is used to determine the orientation information of the obstacle relative to the vehicle, and generate an alarm image for the obstacle based on the orientation information, wherein the alarm image is matched with the collision risk level.
[0063] The alarm image display unit 806 is used to send the alarm image to the remote driving platform for display to the remote driver.
[0064] Optionally, the collision risk level determination unit 802 is specifically used for:
[0065] The relative distance between the vehicle and the obstacle is obtained based on the vehicle motion information and the obstacle description information;
[0066] The collision risk level is determined based on the relative distance, and the degree of danger represented by the collision risk level is negatively correlated with the distance.
[0067] Optionally, the alarm image determination unit 804 is specifically used for:
[0068] When the obstacle is located in the transition area between the first and second orientations, the orientation information is determined based on the historical orientation of the obstacle corresponding to the vehicle.
[0069] Optionally, the alarm image determination unit 804 is specifically used for:
[0070] If multiple obstacles are detected around the vehicle, at least one obstacle with a relatively higher collision risk level is identified among the multiple obstacles.
[0071] The orientation information of the at least one obstacle relative to the vehicle is determined, and an alarm image for each obstacle is generated based on the orientation information.
[0072] Optionally, the alarm image determination unit 804 is specifically used for:
[0073] If the collision risk level is greater than a preset risk level, an alarm image for the obstacle is generated based on the location information.
[0074] Optionally, the alarm image determination unit 804 is specifically used for:
[0075] If the location information corresponds to a camera on the vehicle, the warning image is captured based on that camera;
[0076] When the location information corresponds to multiple cameras of the vehicle, multiple images taken from different perspectives by the multiple cameras are used as the alarm image, and the multiple images or the corresponding stitched image are used as the alarm image.
[0077] Optionally, the alarm image determination unit 804 is specifically used for:
[0078] The image style of the warning image is generated based on the collision risk level, and the prominence of the image style is positively correlated with the degree of danger represented by the collision risk level.
[0079] Optionally, the alarm image display unit 806 is specifically used for:
[0080] The alarm image and the location information are sent to the remote driving platform, so that the remote driving platform can display the alarm image based on the location information; or...
[0081] The alarm image and other images are stitched together according to the location information, and the stitched image is sent to the remote driving platform so that the remote driving platform can display the stitched image.
[0082] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.
[0083] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.
[0084] Based on the same concept as the methods described above, this specification also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor performs the steps of the method as described in any of the above embodiments by executing the executable instructions.
[0085] Based on the same concept as the methods described above, this specification also provides a vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method as described in any of the above embodiments.
[0086] Based on the same concept as the methods described above, this specification also provides a computer-readable storage medium having computer instructions stored thereon that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.
[0087] Based on the same concept as the methods described above, this specification also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the methods as described in any of the above embodiments.
[0088] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.
[0089] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.
[0090] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.
[0091] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.
[0092] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.
[0093] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
[0094] Therefore, specific embodiments of the subject matter have been described. Furthermore, the processes depicted in the figures are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.
[0095] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.
Claims
1. A collision risk warning method for remote-controlled vehicle driving, characterized in that, Applied to vehicles remotely driven by a remote driver via a remote driving platform, the method includes: If an obstacle is detected around the vehicle, the collision risk level between the vehicle and the obstacle is determined based on the vehicle motion information and the obstacle description information. Determine the orientation information of the obstacle relative to the vehicle, and generate a warning image for the obstacle based on the orientation information, wherein the warning image is matched with the collision risk level; The alarm image is sent to the remote driving platform for display to the remote driver.
2. The method according to claim 1, characterized in that, Determining the collision risk level between the vehicle and the obstacle based on vehicle motion information and obstacle description information includes: The relative distance between the vehicle and the obstacle is obtained based on the vehicle motion information and the obstacle description information; The collision risk level is determined based on the relative distance, and the degree of danger represented by the collision risk level is negatively correlated with the distance.
3. The method according to claim 1, characterized in that, Determining the orientation information of the obstacle relative to the vehicle includes: When the obstacle is located in the transition area between the first and second orientations, the orientation information is determined based on the historical orientation of the obstacle corresponding to the vehicle.
4. The method according to claim 1, characterized in that, The method involves determining the orientation information of the obstacle relative to the vehicle and generating an alarm image for the obstacle based on the orientation information. If multiple obstacles are detected around the vehicle, at least one obstacle with a relatively higher collision risk level is identified among the multiple obstacles. The orientation information of the at least one obstacle relative to the vehicle is determined, and an alarm image for each obstacle is generated based on the orientation information.
5. The method according to claim 1, characterized in that, The alarm image for the obstacle is generated based on the location information; If the collision risk level is greater than a preset risk level, an alarm image for the obstacle is generated based on the location information.
6. The method according to claim 1, characterized in that, The step of generating an alarm image for the obstacle based on the location information includes: If the location information corresponds to a camera on the vehicle, the warning image is captured based on that camera; When the location information corresponds to multiple cameras of the vehicle, multiple images taken from different perspectives by the multiple cameras are used as the alarm image, and the multiple images or the corresponding stitched image are used as the alarm image.
7. The method according to claim 1, characterized in that, The step of generating an alarm image for the obstacle based on the location information includes: The image style of the warning image is generated based on the collision risk level, and the prominence of the image style is positively correlated with the degree of danger represented by the collision risk level.
8. The method according to claim 1, characterized in that, Sending the alarm image to the remote driving platform includes: The alarm image and the location information are sent to the remote driving platform, so that the remote driving platform can display the alarm image based on the location information; or... The alarm image and other images are stitched together according to the location information, and the stitched image is sent to the remote driving platform so that the remote driving platform can display the stitched image.
9. A device for calculating the remaining driving range of a vehicle, characterized in that, The device, applicable to vehicles remotely driven by a remote driver via a remote driving platform, includes: The collision risk level determination unit is used to determine the collision risk level between the vehicle and the obstacle based on vehicle motion information and obstacle description information when an obstacle is detected around the vehicle. The alarm image determination unit is used to determine the orientation information of the obstacle relative to the vehicle, and generate an alarm image for the obstacle based on the orientation information, wherein the alarm image is matched with the collision risk level; The alarm image display unit is used to send the alarm image to the remote driving platform for display to the remote driver.
10. A vehicle, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the method as described in any one of claims 1 to 8.
11. A computer-readable storage medium, characterized in that, It stores computer instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 8.
12. A computer program product, characterized in that, Includes a computer program / instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 8.
