Man-machine co-driving control right switching method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a man-machine co-driving control right switching method and device, electronic equipment and a storage medium, and belongs to the technical field of intelligent driving. The method comprises the following steps: carrying out driving index prediction on a target vehicle to obtain predicted driving index data; identifying the driving state of the target vehicle based on the predicted driving index data and a preset driving safety index boundary to obtain a target driving state domain; wherein the target driving state domain comprises any one of a target driving safety domain, a target driving danger domain and a target driving recoverable domain; and switching the driving right between the target unmanned system and the target driver based on the target driving state domain. According to the method, the target driving state domain of the vehicle is determined based on the predicted driving index, so that the driving right switching between the target unmanned system and the target driver is carried out, the accuracy of anti-collision driving evaluation of the target vehicle is improved, and the man-machine co-driving control right switching accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent driving, in particular to a method and device for switching control right of man-machine co-driving, an electronic device and a storage medium. BACKGROUND

[0002] At present, the traditional method for switching control right of man-machine co-driving usually analyzes the safety indicators (such as acceleration, headway time) of the vehicle, and combines rules or algorithm to analyze the driving right attribution under different vehicle driving states. For example, in intelligent driving, the acceleration of the intelligent driving vehicle and the headway time between the intelligent driving vehicle and the obstacle vehicle in the same lane are analyzed, and the intelligent driving vehicle and the driver are identified for driving right attribution according to the obstacle avoidance rules, so as to realize the switching of driving right between the intelligent driving vehicle and the driver. However, this method only designs safety indicators for a single lane, that is, only considers the obstacles in the current lane of the vehicle, and the influence of other lanes on intelligent driving, which makes the collision avoidance driving evaluation of the vehicle inaccurate, resulting in low accuracy of switching control right of man-machine co-driving. Therefore, how to improve the accuracy of switching control right of man-machine co-driving has become a problem to be solved. SUMMARY

[0003] The present application aims to provide a method and device for switching control right of man-machine co-driving, an electronic device and a storage medium to solve the problems raised in the background.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a method for switching control right of man-machine co-driving, comprising the following steps: Step 1: predicting the driving indicators of the target vehicle to obtain multi-dimensional predicted driving indicator data; the predicted driving indicator data at least covers two or more of the predicted latest reaction time, the predicted latest collision time and the predicted headway time, so as to fully reflect the interactive safety state of the target vehicle and the surrounding environment; Step 2: based on the obtained predicted driving indicator data, combining the preset driving safety indicator boundary, dynamically identifying the driving state to which the target vehicle currently belongs, and determining the target driving state domain; wherein the target driving state domain is any one of the target driving safety domain, the target driving danger domain and the target driving recoverable domain, and different driving state domains correspond to different safety risk levels of the target vehicle; Step 3: according to the specific type of the identified target driving state domain, performing adaptive switching operation of driving right between the target unmanned system and the target driver, ensuring that the switching decision matches the current safety risk level of the vehicle, and ensuring driving safety.

[0005] Preferably, the predicted driving indicator data includes the predicted latest reaction time; the prediction and processing of the driving indicators of the target vehicle to obtain the predicted driving indicator data specifically includes: The first step is to obtain the obstacle movement area of ​​the target obstacle within a preset target time period. The target obstacle covers other vehicles, pedestrians, non-motorized vehicles and fixed roadblocks within a multi-lane range around the target vehicle. The obstacle movement area is generated by fusing obstacle motion parameters collected by lidar, camera and millimeter-wave radar. The obstacle motion parameters include the obstacle's speed, acceleration and heading angle, and are predicted by combining Kalman filter algorithm to ensure that the movement range of surrounding potential obstacles can be fully covered. The second step is to obtain the safe movement area of ​​the target vehicle within the target time period. The safe movement area is determined jointly based on the dynamic constraints of the target vehicle, road topology information, and traffic rules to ensure that the area range meets the vehicle's driving capabilities and road regulations. The dynamic constraints include maximum acceleration, maximum deceleration, and steering angle limits. The road topology information includes lane width, curvature, and speed limit signs. The traffic rules include, but are not limited to, no-lane-change zones and stop-and-yield requirements. The third step involves using set operations (the difference between the safe movement area and the obstacle movement area) and a trajectory planning algorithm (A) based on the safe movement area and the obstacle movement area. Algorithm or RRT The algorithm identifies the vehicle reachability set of the target vehicle at a preset target time; the vehicle reachability set is used to characterize the set of safe driving states (position, speed, heading angle) of the target vehicle at the target time, excluding driving states that collide with obstacles; The fourth step is to determine the predicted latest response time based on the target time and the vehicle reachable set. If the vehicle reachable set at the target time is not empty, it indicates that the vehicle still has a safe driving path, and the prediction of the vehicle reachable set at the next time continues iteratively. If the vehicle reachable set is empty, it indicates that the vehicle has no safe driving path, and the time difference between the current time and the initial prediction time is the predicted latest response time.

[0006] Preferably, the predicted driving index data includes the predicted latest collision time; the step of predicting the driving index of the target vehicle to obtain the predicted driving index data includes: The first step is to obtain the vehicle's driving trajectory (generated by the path planning module of the target unmanned system) within a preset driving time period, and to determine the vehicle's driving range based on the vehicle's driving trajectory and its own size. The vehicle's driving range is a set of rectangular areas formed by expanding each point on the driving trajectory according to the vehicle's size, which completely covers the space that the vehicle may occupy during its driving process. The second step is to obtain the obstacle's trajectory during the travel time (predicted through sensor data fusion), and determine the obstacle's travel range based on the obstacle's trajectory and obstacle size. The obstacle's travel range is a set of rectangular areas formed by expanding each point on the obstacle's trajectory according to the obstacle's size, accurately reflecting the space that the obstacle may occupy during its travel. The third step is to perform a time-axis synchronous comparison between the vehicle's driving range and the obstacle's driving range, and detect whether there is an overlap between the two at each moment to determine the collision state of the target vehicle and obtain the target collision state data; if there is an overlap between the two at a certain moment, the moment is determined to be a potential collision moment, and the corresponding overlap area, collision moment and other information are the target collision state data. The fourth step is to select the earliest collision time from all potential collision times included in the target collision state data and determine it as the predicted latest collision time, so as to provide a basis for judging the urgency of vehicle collision risk.

[0007] Preferably, the predicted driving index data includes the predicted headway time; the step of predicting the driving index of the target vehicle to obtain the predicted driving index data includes: The first step is to obtain road map information (high-precision electronic map, including lane lines, traffic signs, and intersection locations) of the route traveled by the target vehicle, and based on the road map information, determine the absolute position information of obstacles around the target vehicle in the map coordinate system through lidar point cloud matching and camera image recognition technology to ensure accurate obstacle positioning. The second step involves combining the obstacle location information with the road map information to analyze the correlation between the obstacle and the target vehicle's trajectory, and to filter target obstacles. Priority is given to identifying obstacles that intersect with the target vehicle's trajectory and are closest to it as target obstacles, focusing on obstacles that have the greatest impact on vehicle driving safety. The third step is to measure the longitudinal distance between the target obstacle and the target vehicle along the driving trajectory, i.e., the target vehicle distance, to avoid interference from the lateral distance on the safety judgment. The ratio of the target vehicle distance to the current driving speed of the target vehicle is determined as the predicted headway time, which intuitively reflects the safe distance relationship between the vehicle and the obstacle in front.

[0008] Preferably, the step of switching driving rights between the target unmanned system and the target driver based on the target driving state domain includes: If the target vehicle is in the target driving danger zone (with a direct collision risk), a forward switching of driving authority is immediately triggered, i.e., switching from the target unmanned system to the target driver. At the same time, a takeover notification is sent to the driver through multimodal prompts (steering wheel vibration, instrument panel visual warning, and voice reminder "Please take over the vehicle immediately") to ensure that the driver is aware of the takeover in a timely manner. The target unmanned system is also controlled to maintain basic assistance functions (maintain current lane, briefly decelerate) for 0.5s-1.0s to provide a buffer time for the driver to take over and avoid loss of vehicle control during the takeover process. If the target vehicle is in the target driving recoverable domain (with minor safety hazards), the driving authority remains with the target unmanned system; the target unmanned system performs targeted avoidance operations based on the predicted driving index data (appropriately decelerating to increase the distance between the vehicle and the obstacle in front, and finely adjusting the heading angle to move away from surrounding obstacles), gradually transferring the vehicle state towards the target driving safety domain; at the same time, it monitors changes in the predicted driving index in real time, and if the index deteriorates to the target driving danger domain, it immediately triggers a forward switch; If the target vehicle is within the target driving safety domain (no collision risk), the driving authority remains with the target unmanned system. The target unmanned system drives stably according to the preset path planning and speed control strategy, updating the predicted driving index data every 2 seconds to ensure timely monitoring of changes in the vehicle's safety status. If the predicted driving index drops to the target driving recoverable domain due to sudden environmental changes (such as sudden road obstacles), the control logic corresponding to the target driving recoverable domain is automatically activated to ensure that the vehicle continues to be in a safe driving state.

[0009] Preferably, the driving state of the target vehicle is identified based on the predicted driving index data and the preset driving safety index boundary to obtain the target driving state domain, including: If the predicted driving index data is not within the driving safety index boundary, then the driving state of the target vehicle is determined to be the target driving hazard domain. If the predicted driving index data at the current moment and the next moment are within the driving safety index boundary, then the driving state of the target vehicle is determined to be the target driving recoverable domain. If the driving state of the target vehicle is in the target driving recoverable domain within a preset future time period, then the driving state of the target vehicle is determined to be the target driving safe domain.

[0010] Preferably, the driving safety index boundary includes a safe to warning interval and a warning to danger interval; before identifying the driving state of the target vehicle based on the predicted driving index data and the preset driving safety index boundary to obtain the target driving state domain, the method further includes: The first step is to collect historical driving index data of the target vehicle under different driving scenarios (highway lane change, ramp merging, roundabout driving, driving in rainy weather, driving in snowy weather, and driving at night). The historical driving index data covers index data for safe driving scenarios (no collision risk, no emergency operation by the driver) and index data for dangerous scenarios (near collision event, driver performing emergency braking / steering operation), ensuring that the data covers all types of driving conditions. The second step is to use the percentile method to perform statistical analysis on the historical driving index data to eliminate abnormal data interference: the maximum value of the index data under 90% safe scenarios is determined as the safe index value (representing the basic safety threshold), and the maximum value of the index data under 95% safe scenarios is determined as the warning index value (representing the high safety threshold). The third step is to divide the specific range of the driving safety index boundary based on the safety index value and the warning index value: [minimum index value, safety index value] is determined as the safe to warning range, corresponding to the state of the vehicle with a slight safety hazard; [safety index value, warning index value] is determined as the warning to danger range, corresponding to the safe state of the vehicle with no collision risk, providing a clear judgment standard for subsequent driving status identification.

[0011] Preferably, the human-machine co-driving control switching device includes: The driving index prediction module is used to predict the driving index of the target vehicle and output multi-dimensional predicted driving index data. The driving index prediction module includes an obstacle movement area prediction unit (which generates obstacle movement areas by fusing multi-sensor data and algorithms), a safe movement area calculation unit (which determines the safe movement area by combining vehicle dynamics and road rules), a vehicle reachability set solving unit (which solves the vehicle reachability set through set operations and trajectory planning algorithms), a latest reaction time determination unit (which iteratively calculates and predicts the latest reaction time based on the vehicle reachability set), a vehicle driving range generation unit (which expands the trajectory according to the vehicle size to obtain the driving range), an obstacle driving range generation unit (which expands the trajectory according to the obstacle size to obtain the driving range), a collision state detection unit (which detects collision states by synchronously comparing the range), a latest collision time determination unit (which selects the earliest collision time to obtain the predicted latest collision time), an obstacle location unit (which determines the obstacle position through multi-technology fusion), a target obstacle screening unit (which analyzes correlations to screen target obstacles), and a vehicle headway time calculation unit (which calculates the ratio of vehicle distance to speed to obtain the predicted vehicle headway time). All units work together to ensure that the prediction data is comprehensive and accurate. The driving status recognition module receives the predicted driving index data output by the driving index prediction module, combines it with preset driving safety index boundaries, dynamically identifies the driving status of the target vehicle, and outputs a target driving status domain (one of the following: target driving safety domain, target driving danger domain, and target driving recoverable domain). The driving status recognition module includes a historical data acquisition unit (collecting historical driving index data under multiple scenarios), an index value statistics unit (calculating safety index values ​​and warning index values ​​using the percentile method), a safety boundary determination unit (dividing the safety to warning interval and the warning to danger interval based on index values), and a status domain judgment unit (determining the target driving status domain based on index data and interval matching), providing a status basis for driving authority switching. The driving control switching module is used to receive the target driving state domain output by the driving state recognition module and perform adaptive driving control switching according to its type. The driving control switching module includes a switching trigger unit (which determines whether to trigger switching and the switching direction based on the state domain type), a multimodal prompt unit (which sends multi-form takeover reminders to the driver), and an auxiliary takeover unit (which controls the unmanned system to provide basic auxiliary functions during the switching process) to ensure that the driving control switching is safe, timely, and smooth.

[0012] Preferably, an electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the human-machine co-driving control switching method.

[0013] Preferably, a computer-readable storage medium stores a computer program that, when executed by a processor, implements the human-machine co-driving control switching method.

[0014] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention, through its proposed human-machine co-driving control switching method, device, electronic equipment, and storage medium, predicts the driving indicators of a target vehicle to obtain predicted driving indicator data; based on the predicted driving indicator data and preset driving safety indicator boundaries, it identifies the driving state of the target vehicle to obtain a target driving state domain; wherein the target driving state domain includes any one of the following: a target driving safety domain, a target driving danger domain, and a target driving recoverable domain; based on the target driving state domain, it performs a driving control switch between the target unmanned system and the target driver. This application determines the target driving state domain of the vehicle based on predicted driving indicators to facilitate a driving control switch between the target unmanned system and the target driver, which helps improve the accuracy of the target vehicle's collision avoidance driving assessment, thereby improving the accuracy of the human-machine co-driving control switching. Attached Figure Description

[0015] Figure 1This is a flowchart of the human-machine co-driving control switching method provided in the embodiments of this application; Figure 2 yes Figure 1 The flowchart of step S101 in the text; Figure 3 yes Figure 1 Another flowchart of step S101 in the process; Figure 4 yes Figure 1 Another flowchart of step S101 in the process; Figure 5 This is another flowchart of the human-machine co-driving control switching method provided in the embodiments of this application; Figure 6 yes Figure 1 The flowchart of step S102 in the document; Figure 7 yes Figure 1 The flowchart of step S103 in the process; Figure 8 This is a schematic diagram of the human-machine co-driving control switching device provided in the embodiments of this application; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0016] 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, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0019] This application provides a method and apparatus for switching control in human-machine co-driving, an electronic device and a storage medium, which aim to improve the accuracy of switching control in human-machine co-driving.

[0020] The human-machine co-driving control switching method, apparatus, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the human-machine co-driving control switching method in this application embodiment is described.

[0021] The human-machine co-driving control switching method provided in this application relates to the field of intelligent driving technology. This method can be applied to a terminal, a server, or software running on either the terminal or the server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the human-machine co-driving control switching method, but is not limited to the above forms.

[0022] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0023] Figure 1 This is an optional flowchart of the human-machine co-driving control switching method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S103.

[0024] Step S101: Predict the driving indicators of the target vehicle to obtain the predicted driving indicator data.

[0025] Step S102: Based on the predicted driving index data and the preset driving safety index boundary, the driving state of the target vehicle is identified to obtain the target driving state domain; wherein, the target driving state domain includes any one of the following: target driving safety domain, target driving danger domain, and target driving recoverable domain.

[0026] Step S103: Based on the target driving state domain, switch driving authority between the target unmanned system and the target driver.

[0027] Steps S101 to S103 of this application embodiment involve predicting the driving indicators of the target vehicle to obtain predicted driving indicator data; identifying the driving state of the target vehicle based on the predicted driving indicator data and preset driving safety indicator boundaries to obtain a target driving state domain; wherein the target driving state domain includes any one of the following: a target driving safety domain, a target driving danger domain, and a target driving recoverable domain; and switching driving rights between the target unmanned system and the target driver based on the target driving state domain. This application determines the target driving state domain of the vehicle based on predicted driving indicators to switch driving rights between the target unmanned system and the target driver, which helps improve the accuracy of the target vehicle's collision avoidance driving assessment, thereby improving the accuracy of human-machine co-driving control switching.

[0028] In step S101 of some embodiments, specifically, the predicted driving index data refers to the driving index data of the target vehicle during its driving process. This may include, but is not limited to, predicted acceleration, predicted headway time, predicted latest collision time, and predicted latest reaction time.

[0029] Specifically, acceleration prediction can be achieved by collecting vehicle speed data and its corresponding timestamp data from the vehicle's speed sensors. The collected speed and timestamp data are then filtered and denoised to eliminate potential measurement errors. Furthermore, the speed and timestamp data are fitted to obtain a function expression relating speed and time. This function expression is then differentiated to obtain the acceleration function expression. At a specific time point, the vehicle's acceleration can be determined by calculating the derivative of the function at that time point.

[0030] Please see Figure 2 In some embodiments, step S101 includes, but is not limited to, steps S201 to S203: Step S201: Obtain road map information of the target vehicle, and obtain obstacle location information of the target vehicle based on the road map information.

[0031] Step S202: Determine the target obstacle based on the obstacle location information and road map information.

[0032] Step S203: Obtain the target distance between the target obstacle and the target vehicle, and determine the predicted headway time based on the target distance.

[0033] In step S201 of some embodiments, specifically, the road map information refers to the surrounding map information when the target vehicle is driving on the road. The road map information may include, but is not limited to, lane lines, traffic signs, traffic light positions, roadblocks and other vehicle position information.

[0034] Furthermore, obstacle location information can be obtained by using the target vehicle's sensors (such as LiDAR, cameras, etc.) to detect and identify the types of obstacles around the vehicle (including other vehicles, pedestrians, bicycles, roadblocks, etc.) and data such as the distance, direction, and relative speed of the obstacles. Combining the data collected by the sensors with road map information can accurately identify and locate the position of obstacles.

[0035] In step S202 of some embodiments, specifically, the target obstacle can be other vehicles located in front of the target vehicle.

[0036] Specifically, by combining road map information and obstacle location information, we can more accurately understand the position of the target vehicle on the road and the relative position of surrounding obstacles, so as to determine the precise location and possible trajectory of the obstacles, thereby filtering out other vehicles that are most likely to collide with the target vehicle as target obstacles.

[0037] In step S203 of some embodiments, specifically, the target vehicle distance refers to the distance on the actual driving path between the target vehicle and the obstacle in front.

[0038] Specifically, the predicted headway time is the ratio of the distance between the target vehicle and the vehicle in front to the speed of the target vehicle, and is used to assess the safe distance between vehicles.

[0039] Specifically, by dividing the target distance by the target vehicle's speed, we can obtain the predicted headway time during the target vehicle's journey, which indicates how long it will take for the target vehicle to reach the location of the target obstacle at its current speed.

[0040] In this embodiment, the predicted headway time is determined based on the target vehicle distance, which enables the acquisition of the predicted headway time of the target vehicle. This facilitates the subsequent assessment of the safe distance between the unmanned system and the vehicle in front, and allows for appropriate switching of driving authority when necessary to avoid vehicle collisions.

[0041] Please see Figure 3 In some embodiments, step S101 may include, but is not limited to, steps S301 to S304: Step S301: Obtain the vehicle's driving trajectory within a preset driving time period, and determine the vehicle's driving range based on the vehicle's driving trajectory.

[0042] Step S302: Obtain the obstacle's travel trajectory during the travel time period, and determine the obstacle's travel range based on the obstacle's travel trajectory.

[0043] Step S303: Based on the vehicle's travel range and the obstacle's travel range, perform collision state detection on the target vehicle to obtain target collision state data.

[0044] Step S304: Determine the predicted latest collision time based on the target collision state data.

[0045] In step S301 of some embodiments, specifically, the preset driving time period refers to the future driving time period of the target vehicle, that is, the time period from the current moment to the end of the collision planning.

[0046] Specifically, the unmanned system can obtain the vehicle's location information for the next period of time from the target vehicle's sensor data, and based on this information, it can predict the vehicle's trajectory for a period of time in the future.

[0047] For example, the target vehicle is The predicted location at time ( ) If the target vehicle's trajectory can be determined based on all predicted positions from the current moment to the end of the collision planning process, then the trajectory of the target vehicle can be determined.

[0048] Specifically, the vehicle's driving range refers to all the driving locations that a target vehicle, based on its own length and width, may pass through within a certain period of time.

[0049] In step S302 of some embodiments, specifically, the obstacle's trajectory can be determined by reading the driving position information of the surrounding obstacles from the target vehicle's sensors, and the trajectory of the surrounding obstacles in the future can be predicted using this information.

[0050] For example, the predicted position of the obstacle at time t is ( If the obstacle's trajectory can be determined based on all predicted positions from the current moment to the end of the collision planning process, then the obstacle's trajectory can be determined.

[0051] Specifically, the obstacle travel range refers to all the travel positions that an obstacle, based on its length and width, may pass through within a certain period of time.

[0052] In this embodiment, by acquiring the obstacle's trajectory and range, the influence of other lanes on the target vehicle's driving state can be considered, rather than being limited to the same lane, which helps improve the accuracy of vehicle collision avoidance assessment.

[0053] In step S303 of some embodiments, specifically, the target collision state data refers to the state data at the moment when the target vehicle collides with the obstacle.

[0054] Specifically, this step involves comparing the trajectory and range of the target vehicle and the obstacle to determine whether a collision is likely to occur between them within a preset travel time period.

[0055] Furthermore, the length and width of the obstacle are obtained as ( ), and obtain the length and width of the target vehicle as ( ), can calculate the target vehicle in The position of the vehicle's length and width edges at any given time, and the position of the obstacle's length and width edges.

[0056] Furthermore, if the length and width of the target vehicle coincide with the length and width of the obstacle, then the target vehicle is... The vehicle is constantly colliding with obstacles; if the length and width of the target vehicle do not overlap with the length and width of the obstacle, then it is judged... Whether the target vehicle will collide with the obstacle at any given time. If the target vehicle will not collide with the obstacle until the planned end time, it means that the target vehicle will not collide with the obstacle from the current time to the planned end time.

[0057] In this embodiment, collision state detection of the target vehicle is performed based on the vehicle's driving range and the obstacle's driving range to obtain target collision state data. This provides predictive information about the time and location of potential future collisions, which helps the unmanned system to more accurately assess traffic conditions and the driving environment, and facilitates subsequent improvements in the accuracy of human-machine co-driving control switching.

[0058] In step S304 of some embodiments, specifically, predicting the latest collision time means predicting the time when the target vehicle will collide with the obstacle, assuming the target vehicle's current speed and travel path remain unchanged.

[0059] Specifically, from the current moment to the end of the planning process, the system iterates backward step by step to determine when the target vehicle and the obstacle will enter a collision state, and takes the first collision time as the latest collision time.

[0060] In this embodiment, the predicted latest collision time is determined based on the target collision state data, enabling the unmanned system to issue an early warning when a collision risk is predicted, providing valuable reaction time for the driver or the unmanned system and improving vehicle driving safety. Furthermore, it not only considers obstacles in the current lane of the unmanned system, but also obstacles around the target vehicle can be prevented from colliding by predicting the latest collision time.

[0061] Please see Figure 4 In some embodiments, step S101 may include, but is not limited to, steps S401 to S404: Step S401: Obtain the obstacle movement area of ​​the target obstacle within the preset target time period.

[0062] Step S402: Obtain the safe movement area of ​​the target vehicle within the target time period.

[0063] Step S403: Based on the safe movement area and the obstacle movement area, identify the vehicle reachability set of the target vehicle at a preset target time; the vehicle reachability set is used to characterize the set of states in which the target vehicle is safely driving at the target time.

[0064] Step S404: Determine the latest predicted response time based on the target time and the vehicle reachability set.

[0065] In step S401 of some embodiments, the target time period can be a time period consistent with the preset driving time period, that is, the time period from the current moment to the collision planning termination moment.

[0066] Specifically, the obstacle movement area refers to the path area along which the obstacle travels within the target time period.

[0067] Specifically, the position, speed, acceleration, and obstacle trajectory information of the target vehicle can be predicted from vehicle sensor data within a target time period. Based on this information, a Frenet coordinate system is established, and the coordinates of the obstacles and their future predicted trajectories are transformed into the corresponding Frenet coordinate system, thereby calculating the obstacle movement area within the target time period.

[0068] In step S402 of some embodiments, specifically, the safe movement area refers to the movement area where the target vehicle will not collide with obstacles within a target time period. The safe movement area is derived from the reachability set. 1. The safe movement region at the initial moment is the initial reachable set; 2. Derive the safe movement region in the next time step from the initial reachable set; 3. Subtract the obstacle movement area from the safe movement area in the next moment to obtain the reachable set in the next moment; 4. Repeat steps 1, 2, and 3 to derive the reachable set at each time step until the program terminates.

[0069] Specifically, the initial position, initial speed, and maximum acceleration of the target vehicle can be obtained from the target vehicle's sensors to determine the safe movement area of ​​the target vehicle at the current moment, and the safe movement area of ​​the vehicle at the next moment can be determined in the same way, so as to finally determine the safe movement area of ​​the target vehicle within the target time period.

[0070] In step S403 of some embodiments, specifically, the vehicle reachability set describes the set of all locations that a vehicle can safely reach without a collision under given initial conditions and dynamic constraints on safe vehicle movement. It can be used to characterize the set of states in which the target vehicle is safely driving at the target time.

[0071] Specifically, starting from the next moment, the safe movement area can be subtracted from the obstacle movement area at the corresponding moment to determine whether the vehicle reachable set exists at that moment. If the vehicle reachable set exists, this process can be repeated to obtain the vehicle reachable set corresponding to each moment until the vehicle reachable set corresponding to the collision planning termination moment is obtained, so as to obtain all vehicle reachable sets within the target time period. If the vehicle reachable set does not exist at that moment, it means that the vehicle safe movement area does not exist at that moment, and there may be a risk of vehicle collision.

[0072] In this embodiment, based on the safe movement area and the obstacle movement area, the vehicle reachable set of the target vehicle at the preset target time is identified, which can determine all possible states that the target vehicle can safely reach at the target time, thereby providing a safe driving state space for the target vehicle, which facilitates subsequent precise control of the vehicle to avoid collisions.

[0073] In step S404 of some embodiments, specifically, predicting the latest reaction time refers to the longest time required from recognizing a potential collision between the target vehicle and the obstacle to initiating a collision avoidance response.

[0074] Specifically, if If a vehicle reachable set exists at a given time, it indicates that the latest reaction time of the unmanned system is at that time. Afterwards; if If the vehicle reachability set does not exist at a given time, it means that the latest reaction time of the unmanned system is at that time. Before.

[0075] Specifically, the latest predicted response time can be determined using the following formula: in, Indicates the predicted latest response time. Indicates the latest reaction time. Represents the set of real numbers. Indicates the current moment. Indicates the end time of the plan. This indicates the collision avoidance maneuvers performed on the target vehicle. This represents all the operational actions of the target vehicle. This indicates the driving status of the target vehicle. This indicates the initial state of the target vehicle's movement. This indicates the pre-planned trajectory of the target vehicle; express The set of collision states at any given moment.

[0076] In this embodiment, the latest predicted reaction time is determined based on the target time and the vehicle reachability set, which can ensure that the target vehicle can make a timely reaction before the collision occurs, thereby improving the safety of vehicle driving.

[0077] Please see Figure 5 In some embodiments, prior to step S102, the human-machine co-driving control switching method further includes, but is not limited to, steps S501 to S503: Step S501: Obtain historical driving index data of the target vehicle under different driving conditions.

[0078] Step S502: Statistically analyze historical driving indicator data to obtain safety indicator values ​​and warning indicator values.

[0079] Step S503: Determine the safe to warning range and the warning to danger range based on the safety index value and the warning index value.

[0080] In step S501 of some embodiments, specifically, historical driving index data refers to the driving index data of the target vehicle within a historical time period, including but not limited to the target vehicle's speed, acceleration, headway time, latest collision time, and latest reaction time within the historical time period.

[0081] Specifically, different driving situations may include, but are not limited to, driving in the rain, driving in the snow, driving on rural roads, changing lanes on highways, merging on ramps, and driving in roundabouts.

[0082] Specifically, historical driving data can be collected from the vehicle's sensors.

[0083] In step S502 of some embodiments, specifically, the safety index value is used to characterize the division value of the driving index data of the target vehicle during driving within a safe range. The safety index value includes, but is not limited to, acceleration safety index value, headway time safety index value, latest collision time safety index value, and latest reaction time safety index value.

[0084] Specifically, the warning index value is used to characterize the driving index data of the target vehicle during the driving process as a further division value within the safe range. The warning index value has a higher safety indication than the safety index value. The warning index value includes, but is not limited to, the acceleration warning index value, the headway time warning index value, the latest collision time warning index value, and the latest reaction time warning index value.

[0085] Specifically, the safety index values ​​can be determined based on the mean or median of various historical driving index data and driving scenarios.

[0086] Specifically, the warning indicator values ​​can be determined based on the average values ​​of various historical driving indicator data and driving scenarios within the standard deviation range.

[0087] For example, the safety index value for acceleration can be -1.46 (m / s²) when changing lanes at high speed, 0.46 (m / s²) when merging on a ramp, and -1.3 (m / s²) when in a roundabout; the safety index value for headway time can be 0.55 (s) when changing lanes at high speed, 1.07 (s) when merging on a ramp, and 0.59 (s) when in a roundabout; the safety index value for latest collision time can be 1.5 (s) when changing lanes at high speed, 1.6 (s) when merging on a ramp, and 4.2 (s) when in a roundabout; and the safety index value for latest reaction time can be 3.5 (s) when changing lanes at high speed, 4.6 (s) when merging on a ramp, and 6.2 (s) when in a roundabout.

[0088] Furthermore, the examples above are only to illustrate that each driving indicator data has a corresponding safety indicator value, and are not restrictions on the safety indicator values.

[0089] In step S503 of some embodiments, specifically, the driving safety indicator boundaries include the safe to warning range and the warning to danger range.

[0090] Specifically, the interval between safety indicator values ​​and warning indicator values ​​is defined as the safety-to-warning interval. Since each driving indicator data corresponds to a different safety indicator value, each driving indicator data also corresponds to a different safety-to-warning interval. That is, the safety-to-warning interval may include, but is not limited to, the acceleration safety-to-warning interval, the headway-time safety-to-warning interval, the latest collision time safety-to-warning interval, and the latest reaction time safety-to-warning interval.

[0091] Specifically, the data range exceeding the warning index value will be designated as the warning to danger range. This warning to danger range includes, but is not limited to, the acceleration warning to danger range, the headway time warning to danger range, the latest collision time warning to danger range, and the latest reaction time warning to danger range.

[0092] Specifically, the safe to warning range is used to indicate that the vehicle's driving indicators are within the safe driving range, meaning that the vehicle is still driving within a safe and controllable range.

[0093] Specifically, the warning to danger zone is used to indicate that the vehicle's driving indicators fall within a safer driving range.

[0094] For example, if the safe driving index boundary for acceleration when merging into a ramp is 0.46 to 2.74 (m / s²), and the warning to danger range is 1.62 to 2.74 (m / s²), then it means that the safety of the vehicle when driving in the range of 1.62 to 2.74 (m / s²) is higher than the safety of driving in the range of 0.46 to 2.74 (m / s²).

[0095] In this embodiment, by dividing the safe to warning zone and the warning to danger zone, it is convenient to divide the corresponding driving state domain according to the safety requirements of different driving indicators when the vehicle is driving, instead of just being limited to collision avoidance assessment of obstacles in the same lane, which helps to further improve the accuracy of human-machine co-driving control switching.

[0096] Please see Figure 6 In some embodiments, step S102 includes, but is not limited to, steps S601 to S603: Step S601: If the predicted driving index data is not within the driving safety index boundary, then the driving state of the target vehicle is determined as the target driving hazard zone.

[0097] Step S602: If the predicted driving index data at the current time and the next time are within the driving safety index boundary, then the driving state of the target vehicle is determined as the target driving recoverable domain.

[0098] Step S603: If the driving state of the target vehicle is in the target driving recoverable domain within the preset future time period, then the driving state of the target vehicle is determined to be the target driving safe domain.

[0099] In step S601 of some embodiments, specifically, the target driving hazard domain indicates that the predicted driving index of the target vehicle has exceeded the driving safety index boundary.

[0100] Specifically, if any of the predicted driving indicators (such as predicted acceleration, predicted headway time, predicted latest collision time, or predicted latest reaction time) exceeds the driving safety indicator boundary, it indicates that the target vehicle is in a dangerous state during driving. The set of all dangerous states of the target vehicle constitutes the target driving hazard domain.

[0101] Furthermore, when the target vehicle's driving state falls within the target driving hazard zone, it means that the target vehicle may face a high risk of collision and needs to take immediate evasive action (such as slowing down or changing lanes) to avoid a potential collision.

[0102] Specifically, the target driving hazard zone can be determined using the following formula: in, express The target driving danger zone at any time Indicates the target vehicle is in The driving status at any given moment. This indicates the driving status of all target vehicles. express Real-time driving safety data.

[0103] Furthermore, in The data between any target vehicle's driving status and any driving safety indicator data at any given time is not empty, indicating that... The target vehicle's driving status at any given time falls within the target driving hazard zone.

[0104] In this embodiment, by determining the driving state of the target vehicle as the target driving hazard zone, the potential collision risks of the vehicle can be identified in a timely manner. This facilitates the implementation of avoidance measures through subsequent human-machine co-driving control switching, thereby avoiding or mitigating possible collisions and ensuring the safe driving of the target vehicle.

[0105] In step S602 of some embodiments, specifically, the target driving recoverable domain means that all predicted driving indicators of the target vehicle are within the warning to danger range of the driving safety indicator boundary.

[0106] Specifically, if all predicted driving indicators of the target vehicle are within the safe to dangerous range at the current moment, and all predicted driving indicators are within the warning to dangerous range at the next moment, it means that the driving status of the target vehicle is within the target driving recoverable range, that is, the target vehicle is driving within a safe and controllable range at both the current moment and the next moment.

[0107] Specifically, the target driving recoverable domain can be determined using the following formula: in, This represents the recoverable domain of the target driving at time t. Indicates the target vehicle is in The driving status at any given moment. express The target driving danger zone at any time Indicates the target vehicle is in The driver's control actions at all times; It is a state transition function, representing the state transition function of the target vehicle. Execute in state The state after the action.

[0108] Furthermore, in The driving status of any target vehicle at any given time and The target driving hazard zones at any given time do not overlap, and the vehicle driver is... The control actions at each moment ensure that the target vehicle's driving state remains within the recoverable domain in the next moment, indicating that... The driving state of the target vehicle at any given time belongs to the target driving recoverable domain.

[0109] In this embodiment, by determining the driving state of the target vehicle as the target driving recoverable domain, it is possible to ensure that the target vehicle is driving in a safe and controllable state, which provides data support for the subsequent realization of intelligent driving.

[0110] In step S603 of some embodiments, specifically, the target driving safety domain means that all predicted driving indicators of the target vehicle are within the warning to danger range of the driving safety indicator boundary.

[0111] Specifically, if the target vehicle's driving status is within the target driving recoverable domain at the current moment and at any time in the future, it means that the target vehicle's driving status at the current moment is within the target driving safe domain. In other words, the target vehicle is driving within a safe and controllable range at the current moment and in the future, and there is no risk of collision.

[0112] Specifically, the target driving safety zone can be determined using the following formula: in, express The target driving safety domain at any given time Indicates the target vehicle is in The driving status at any given moment. Indicates a preset future time period. Indicates the target vehicle is in The driving status at any given moment. Indicates the target vehicle is in The control actions of the unmanned system at all times express The target driving recoverable domain at any given time Furthermore, within the target vehicle's driving state at time t, for The real-time driving status of the target vehicle is monitored by an unmanned system. The control actions at any given time ensure that the target vehicle's driving state remains within the recoverable domain for a period of time in the future, indicating that... The driving status of the target vehicle at any given time belongs to the target driving safety domain.

[0113] In this embodiment, by determining the driving state of the target vehicle as the target driving safety domain, it can be ensured that the vehicle's driving will be safe and controllable for a period of time in the future, providing important data support for the subsequent switching of human-machine co-driving control.

[0114] Please see Figure 7 In some embodiments, step S103 includes, but is not limited to, steps S701 to S703: Step S701: When the target vehicle is in the target driving danger zone, the driving authority is assigned to the target driver.

[0115] Step S702: When the target vehicle is in the target driving recoverable domain, the driving authority is assigned to the target unmanned system.

[0116] Step S703: When the target vehicle is in the target driving safety zone, the driving authority is assigned to the target unmanned system.

[0117] In step S701 of some embodiments, specifically, when the driving rights of the target vehicle belong to the unmanned system, if the target vehicle is in the target driving danger zone at the next moment, a forward switch is triggered to allocate the driving rights to the target driver.

[0118] Specifically, the forward transfer of driving rights can be represented by the following formula: in, Indicates the forward switching condition. Indicates the target vehicle is in The driving status at any given moment. Indicates a preset future time period. Indicates the target vehicle is in The control actions of the unmanned system at all times Indicates target driving .

[0119] Furthermore, if the target vehicle's driving state at time t and the control actions of the unmanned system result in the vehicle's state at the next time not falling within the target driving recoverable domain, then a forward switching condition is triggered, which means transferring driving control from the unmanned system to the target driver.

[0120] In this embodiment, when the target vehicle is in the target driving danger zone, the driving authority is assigned to the target driver. This ensures that during human-machine co-driving, if the unmanned system cannot guarantee safety, the risk of vehicle collision can be avoided by assigning the driving authority to the target driver for vehicle control, thereby improving the safety of vehicle driving.

[0121] In step S702 of some embodiments, specifically, when the driving rights of the target vehicle belong to the target driver, if the driving status of the target vehicle is within the target driving recoverable domain or the target driving safe domain, it is determined whether the driving rights will trigger a forward switch in a preset future time period. If the forward switch will not be triggered in the preset future time period, a reverse switch is triggered and the driving rights are transferred to the unmanned system.

[0122] Specifically, the reverse switching of driving rights can be represented by the following formula: in, Indicates the reverse switching condition. Indicates the target vehicle is in The driving status at any given moment. Indicates a preset future time period, Invert the forward switching condition. Indicates logical NOT. Indicates the target vehicle is in The driving status at any given moment. Indicates the target vehicle is in The control actions of the unmanned system at all times Indicates the target vehicle is in The driving status at any given moment. Indicates the target vehicle is in The driving status at any given moment.

[0123] Furthermore, for all from Time's up The target vehicle within the time period If neither the forward switching condition for the driving status at any given time nor the control action of the unmanned system is met, then the reverse switching condition is met.

[0124] In this embodiment, when the target vehicle is in the target driving safety zone, the driving rights are assigned to the target unmanned system. This ensures that the vehicle is in the driving safety zone and that no forward switching will be triggered in the future time period, thus guaranteeing an accurate switch of driving rights between the target driver and the unmanned system and further improving the safety of vehicle driving.

[0125] In step S703 of some embodiments, specifically, when the driving rights of the target vehicle belong to the target driver, if the driving state of the target vehicle is in the target driving recoverable domain, it is determined whether the driving rights will trigger a forward switch in the future period of time. If the forward switch will not be triggered in the future period of time, a reverse switch is triggered and the driving rights are transferred to the unmanned system.

[0126] In this embodiment, when the target vehicle is within the target driving safety zone, the driving authority is assigned to the target unmanned system, indicating that the vehicle's driving state is safe and there is no risk of collision. By transferring the driving authority to the unmanned system, the vehicle's driving safety is ensured while improving the vehicle's driving efficiency.

[0127] This application's embodiments predict the driving indicators of a target vehicle to obtain predicted driving indicator data; based on the predicted driving indicator data and preset driving safety indicator boundaries, the driving state of the target vehicle is identified to obtain a target driving state domain; wherein, the target driving state domain includes any one of the following: a target driving safety domain, a target driving danger domain, and a target driving recoverable domain; based on the target driving state domain, driving control is switched between the target unmanned system and the target driver. This application determines the target driving state domain of the vehicle based on predicted driving indicators to switch driving control between the target unmanned system and the target driver, which helps improve the accuracy of the target vehicle's collision avoidance driving assessment, thereby improving the accuracy of human-machine co-driving control switching.

[0128] Please see Figure 8 This application also provides a human-machine co-driving control switching device, which can realize the above-mentioned human-machine co-driving control switching method. The device includes: The driving index prediction module is used to predict the driving index of the target vehicle and obtain the predicted driving index data. The driving state recognition module is used to identify the driving state of the target vehicle based on predicted driving index data and preset driving safety index boundaries, and obtain the target driving state domain; wherein, the target driving state domain includes any one of the following: target driving safety domain, target driving danger domain, and target driving recoverable domain; The driving control switching module is used to switch driving control between the target unmanned system and the target driver based on the target driving state domain.

[0129] The specific implementation of the human-machine co-driving control switching device is basically the same as the specific implementation of the human-machine co-driving control switching method described above, and will not be repeated here.

[0130] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described human-machine co-driving control switching method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0131] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the processing system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 to execute the human-machine co-driving control switching method of the embodiments of this application. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0132] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described human-machine co-driving control switching method.

[0133] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0134] The human-machine co-driving control switching method, apparatus, electronic device, and storage medium provided in this application predict the driving indicators of a target vehicle to obtain predicted driving indicator data; based on the predicted driving indicator data and preset driving safety indicator boundaries, the driving state of the target vehicle is identified to obtain a target driving state domain; wherein the target driving state domain includes any one of the following: a target driving safety domain, a target driving danger domain, and a target driving recoverable domain; based on the target driving state domain, driving control is switched between the target unmanned system and the target driver. This application determines the target driving state domain of the vehicle based on predicted driving indicators to switch driving control between the target unmanned system and the target driver, which helps improve the accuracy of the target vehicle's collision avoidance driving assessment, thereby improving the accuracy of human-machine co-driving control switching.

[0135] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0136] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0137] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; 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 this embodiment according to actual needs.

[0138] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0139] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0140] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and 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. The coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, or indirect coupling or communication connection between the apparatus or units, and may be electrical, mechanical, or other forms.

[0142] The units described above 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.

[0143] Furthermore, the functional units in the various embodiments of this application 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0144] If the integrated unit 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 application, in essence, or the part that contributes to the prior art, or all or 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 multiple 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 application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0145] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for switching control in human-machine co-driving, characterized in that, Includes the following steps: Step 1: Predict the driving indicators of the target vehicle and obtain multi-dimensional predicted driving indicator data; the predicted driving indicator data shall cover at least two or more of the following: predicted latest reaction time, predicted latest collision time, and predicted headway time, so as to comprehensively reflect the interactive safety status of the target vehicle and the surrounding environment. Step 2: Based on the acquired predicted driving index data and combined with the preset driving safety index boundary, dynamically identify the current driving state of the target vehicle and determine the target driving state domain; wherein, the target driving state domain is any one of the target driving safety domain, the target driving danger domain, and the target driving recoverable domain, and different driving state domains correspond to different safety risk levels of the target vehicle; Step 3: Based on the specific type of the identified target driving state domain, perform an adaptive switching operation of driving rights between the target unmanned system and the target driver to ensure that the switching decision matches the current safety risk level of the vehicle and ensure driving safety.

2. The human-machine co-driving control switching method according to claim 1, characterized in that: The predicted driving index data includes the predicted latest reaction time; the process of predicting the driving index of the target vehicle to obtain the predicted driving index data specifically includes: The first step is to obtain the obstacle movement area of ​​the target obstacle within a preset target time period. The target obstacle covers other vehicles, pedestrians, non-motorized vehicles and fixed roadblocks within a multi-lane range around the target vehicle. The obstacle movement area is generated by fusing obstacle motion parameters collected by lidar, camera and millimeter-wave radar. The obstacle motion parameters include the obstacle's speed, acceleration and heading angle, and are predicted by combining Kalman filter algorithm to ensure that the movement range of surrounding potential obstacles can be fully covered. The second step is to obtain the safe movement area of ​​the target vehicle within the target time period. The safe movement area is determined jointly based on the dynamic constraints of the target vehicle, road topology information, and traffic rules to ensure that the area range meets the vehicle's driving capabilities and road regulations. The dynamic constraints include maximum acceleration, maximum deceleration, and steering angle limits. The road topology information includes lane width, curvature, and speed limit signs. The traffic rules include, but are not limited to, no-lane-change zones and stop-and-yield requirements. The third step involves identifying the vehicle reachability set of the target vehicle at a preset target time based on the safe movement area and the obstacle movement area, using set operations and trajectory planning algorithms. The vehicle reachability set is used to characterize the set of states in which the target vehicle can safely drive at the target time, excluding driving states that collide with obstacles. The fourth step is to determine the predicted latest response time based on the target time and the vehicle reachable set. If the vehicle reachable set at the target time is not empty, it indicates that the vehicle still has a safe driving path, and the prediction of the vehicle reachable set at the next time continues iteratively. If the vehicle reachable set is empty, it indicates that the vehicle has no safe driving path, and the time difference between the current time and the initial prediction time is the predicted latest response time.

3. The human-machine co-driving control switching method according to claim 1, characterized in that: The predicted driving index data includes the predicted latest collision time; the process of predicting the driving index of the target vehicle to obtain the predicted driving index data includes: The first step is to obtain the vehicle's driving trajectory within a preset driving time period, and based on the vehicle's driving trajectory and the vehicle's own size, determine the vehicle's driving range; the vehicle's driving range is a set of rectangular areas formed by expanding each point on the driving trajectory according to the vehicle's size, which completely covers the space that the vehicle may occupy during the driving process. The second step is to obtain the obstacle's trajectory during the travel time period, and determine the obstacle's travel range based on the obstacle's trajectory and the obstacle's size. The obstacle's travel range is a set of rectangular areas formed by expanding each point on the obstacle's trajectory according to the obstacle's size, accurately reflecting the space that the obstacle may occupy during its travel. The third step is to perform a time-axis synchronous comparison between the vehicle's driving range and the obstacle's driving range, and detect whether there is an overlap between the two at each moment to determine the collision state of the target vehicle and obtain the target collision state data; if there is an overlap between the two at a certain moment, the moment is determined to be a potential collision moment, and the corresponding overlap area, collision moment and other information are the target collision state data. The fourth step is to select the earliest collision time from all potential collision times included in the target collision state data and determine it as the predicted latest collision time, so as to provide a basis for judging the urgency of vehicle collision risk.

4. The human-machine co-driving control switching method according to claim 1, characterized in that: The predicted driving index data includes the predicted headway time; the process of predicting the driving index of the target vehicle to obtain the predicted driving index data includes: The first step is to obtain road map information of the route traveled by the target vehicle, and based on the road map information, determine the absolute position information of the obstacles around the target vehicle in the map coordinate system through lidar point cloud matching and camera image recognition technology, so as to ensure accurate obstacle positioning. The second step involves combining the obstacle location information with the road map information to analyze the correlation between the obstacle and the target vehicle's trajectory, and to filter target obstacles. Priority is given to identifying obstacles that intersect with the target vehicle's trajectory and are closest to it as target obstacles, focusing on obstacles that have the greatest impact on vehicle driving safety. The third step is to measure the longitudinal distance between the target obstacle and the target vehicle along the driving trajectory, i.e., the target vehicle distance, to avoid interference from the lateral distance on the safety judgment. The ratio of the target vehicle distance to the current driving speed of the target vehicle is determined as the predicted headway time, which intuitively reflects the safe distance relationship between the vehicle and the obstacle in front.

5. The human-machine co-driving control switching method according to any one of claims 1-4, characterized in that: The step of switching driving authority between the target unmanned system and the target driver based on the target driving state domain includes: If the target vehicle is in the target driving danger zone, the forward switching of driving rights is immediately triggered, that is, switching from the target unmanned system to the target driver. At the same time, a takeover notification is sent to the driver through multimodal prompts to ensure that the driver is aware of it in time. The target unmanned system is controlled to maintain basic auxiliary functions for 0.5s-1.0s to provide a buffer time for the driver to take over and avoid loss of vehicle control during the takeover process. If the target vehicle is in the target driving recoverable domain, the driving authority remains with the target unmanned system; the target unmanned system performs targeted risk avoidance operations based on the predicted driving index data, gradually transferring the vehicle state to the target driving safety domain; at the same time, it monitors changes in the predicted driving index in real time, and if the index deteriorates to the target driving danger domain, it immediately triggers a forward switch. If the target vehicle is within the target driving safety domain, the driving authority remains with the target unmanned system. The target unmanned system drives stably according to the preset path planning and speed control strategy, updating the predicted driving index data every 2 seconds to ensure timely monitoring of changes in the vehicle's safety status. If a sudden environmental change causes the predicted driving index to drop to the target driving recoverable domain, the control logic corresponding to the target driving recoverable domain is automatically activated to ensure the vehicle remains in a safe driving state.

6. The human-machine co-driving control switching method according to any one of claims 1-4, characterized in that: Based on the predicted driving index data and the preset driving safety index boundaries, the driving state of the target vehicle is identified to obtain the target driving state domain, including: If the predicted driving index data is not within the driving safety index boundary, then the driving state of the target vehicle is determined to be the target driving hazard domain. If the predicted driving index data at the current moment and the next moment are within the driving safety index boundary, then the driving state of the target vehicle is determined to be the target driving recoverable domain. If the driving state of the target vehicle is in the target driving recoverable domain within a preset future time period, then the driving state of the target vehicle is determined to be the target driving safe domain.

7. The human-machine co-driving control switching method according to any one of claims 1-4, characterized in that: The driving safety index boundary includes a safe to warning interval and a warning to danger interval; before identifying the driving state of the target vehicle based on the predicted driving index data and the preset driving safety index boundary to obtain the target driving state domain, the method further includes: The first step is to collect historical driving indicator data of the target vehicle under different driving scenarios; the historical driving indicator data includes indicator data for safe driving scenarios and indicator data for dangerous scenarios, ensuring that the data covers all types of driving conditions; The second step is to use the percentile method to perform statistical analysis on the historical driving index data to eliminate abnormal data interference: the maximum value of the index data in 90% safe scenarios is determined as the safe index value, and the maximum value of the index data in 95% safe scenarios is determined as the warning index value. The third step is to divide the specific range of the driving safety index boundary based on the safety index value and the warning index value: [minimum index value, safety index value] is determined as the safe to warning range, corresponding to the state of the vehicle with a slight safety hazard; [safety index value, warning index value] is determined as the warning to danger range, corresponding to the safe state of the vehicle with no collision risk, providing a clear judgment standard for subsequent driving status identification.

8. A human-machine co-driving control switching device, characterized in that: The device includes: The driving index prediction module is used to predict the driving index of the target vehicle and output multi-dimensional predicted driving index data. The driving index prediction module includes an obstacle movement area prediction unit, a safe movement area calculation unit, a vehicle reachability set solution unit, a latest reaction time determination unit, a vehicle driving range generation unit, an obstacle driving range generation unit, a collision state detection unit, a latest collision time determination unit, an obstacle positioning unit, a target obstacle screening unit, and a vehicle headway time calculation unit. All units work together to ensure that the prediction data is comprehensive and accurate. The driving status recognition module is used to receive the predicted driving index data output by the driving index prediction module, and dynamically identify the driving status of the target vehicle in combination with the preset driving safety index boundary, and output the target driving status domain. The driving status recognition module includes a historical data acquisition unit, an index value statistics unit, a safety boundary determination unit and a status domain judgment unit, which provides a status basis for driving authority switching. The driving control switching module is used to receive the target driving state domain output by the driving state recognition module and perform adaptive driving control switching according to its type. The driving control switching module includes a switching trigger unit, a multimodal prompt unit, and an auxiliary takeover unit to ensure safe, timely, and smooth driving control switching.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the human-machine co-driving control switching method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the human-machine co-driving control switching method as described in any one of claims 1 to 7.

Images