Self-adaptive auxiliary driving system and method based on navigation

Abstract

The invention relates to a navigation-based self-adaptive auxiliary driving system and method.The system comprises a navigation unit, an inductor set, a control unit and an interpersonal interaction interface, the inductor set is in one-way data connection with the control unit, and the inductor set is used for sending acquired induction data to the control unit; the navigation unit is in one-way data connection with the control unit, the control unit is used for sending control data to a vehicle chassis, the navigation unit is in one-way data connection with the control unit, the navigation unit is used for sending data to the control unit, and the control unit is in two-way communication with the interpersonal interaction interface. The problem that in the actual driving process, frequent manual opening and closing of the auxiliary driving function may cause adverse effects on driving in some driving scenes is solved, the method can well cooperate with a driver to carry out urgent danger avoiding operation, and the safety of vehicle driving is improved.

Description

Technical Field

[0001] The present invention relates to the field of assisted driving technology, and in particular to a navigation-based adaptive assisted driving system and method. Background Art

[0002] Assisted driving technology refers to the technology that provides assistance to the driver through technical means such as sensors, computers and communication equipment inside the vehicle to improve driving safety and driving comfort. With the continuous development of science and technology, assisted driving technology has been widely used in the automotive industry.

[0003] Assisted driving technology can be divided into many types, including but not limited to adaptive cruise control (ACC), lane keeping assist system (LKA), automatic emergency braking system (AEB), blind spot monitoring system (BSM). The development of assisted driving technology aims to improve driving safety, reduce the accident rate, and provide a more convenient and comfortable driving experience. With the continuous advancement of artificial intelligence, sensor technology and communication technology, assisted driving technology will continue to develop and provide important support for the construction of future intelligent transportation systems and the realization of autonomous driving technology.

[0004] In the prior art, common vehicle assisted driving functions are often independent of each other, and the functions generally need to be turned on and off by the driver. However, in the actual driving process, frequent manual switching of assisted driving functions may have an adverse effect on driving in certain driving scenarios. Summary of the invention

[0005] In view of the above deficiencies in the prior art, the present invention provides a navigation-based adaptive assisted driving system and method, which not only solves the problem that frequent manual switching of assisted driving functions may have an adverse effect on driving in certain driving scenarios during actual driving, but also can well cooperate with the driver to perform emergency avoidance operations, thereby improving the safety of driving the vehicle.

[0006] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: A navigation-based adaptive assisted driving system, the system comprising: a navigation unit, a sensor group, a control unit and a human interaction interface, the sensor group being connected to the control unit in a one-way data manner, the sensor group being used to send collected sensing data to the control unit, the navigation unit being connected to the control unit in a one-way data manner, the control unit being used to send control data to a vehicle chassis, the navigation unit being connected to the control unit in a one-way data manner, the navigation unit being used to send data to the control unit, and the control unit being in two-way communication with the human interaction interface.

[0007] Furthermore, the sensor group includes at least one of a millimeter wave radar, a camera and a laser SLAM.

[0008] Furthermore, the human-computer interaction interface includes at least a touch screen, a voice recognition system, an on-board HUD and multi-function steering wheel control buttons.

[0009] Furthermore, the control unit has multiple assisted driving functions, which include at least adaptive cruise control function, lane keeping assist function, automatic emergency braking function and blind spot monitoring function. The control unit is provided with a corresponding switch and priority for each assisted driving function.

[0010] In order to achieve the above-mentioned object and other related objects, the present invention further provides a navigation-based adaptive assisted driving method, which is applied to any of the navigation-based adaptive assisted driving systems described above, and the method comprises: The sensor group collects scene data and determines the current driving scene based on the scene data; Different assisted driving functions are enabled based on different driving scenarios. When the driving scenarios change, the assisted driving functions are switched. The driving scenarios include at least highway scenarios, curve and ramp scenarios, and urban driving and intersection scenarios.

[0011] Furthermore, in a highway scenario, the adaptive cruise control function, lane keeping assist function and automatic emergency braking function are activated at the same time, among which the automatic emergency braking function has a higher priority than the lane keeping assist function, and the lane keeping assist function has a higher priority than the adaptive cruise control function.

[0012] Furthermore, in curve and slope scenarios, the lane keeping assist function and the automatic emergency braking function are activated at the same time. When a sharp bend and / or slope is detected ahead on the road, the lane keeping assist function is exited.

[0013] Furthermore, in urban driving and intersection scenarios, the automatic emergency braking function and blind spot monitoring function are activated at the same time.

[0014] Furthermore, an interface for configuring the assisted driving function is provided on the human-computer interaction interface, on which the assisted driving function can be increased or decreased, and the parameters of the assisted driving function can be set.

[0015] Furthermore, in the interface for configuring the assisted driving function, a navigation information adjustment option is provided for the adaptive cruise control function; a trigger threshold adjustment option is provided for the automatic emergency braking function; and an option for adjusting the distance between the vehicle and the center line of the vehicle is provided for the lane keeping assist function.

[0016] The present invention has the following positive effects: 1. Based on navigation and perception data, the present invention adaptively manages the assisted driving function during vehicle driving according to the user's parameter settings, reducing the driver's switch operations during driving. At the same time, the driving experience and driving safety are improved through the coordinated work of multiple assisted driving functions and the priority mechanism.

[0017] 2. The present invention enables different assisted driving functions based on different driving scenarios, and switches the assisted driving functions when the driving scenarios change. This not only solves the problem that frequent manual switching of assisted driving functions may have an adverse effect on driving in certain driving scenarios during actual driving, but also can well cooperate with the driver to perform emergency risk avoidance operations, thereby improving the safety of driving the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is an architecture diagram of the navigation-based adaptive assisted driving system of the present invention; Figure 2 It is a functional structure diagram of the assisted driving switching system of the present invention. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0020] Example 1: Figure 1 As shown, an adaptive assisted driving system based on navigation includes: a navigation unit, a sensor group, a control unit and a human interaction interface, the sensor group is connected to the control unit in a one-way data manner, the sensor group is used to send the collected sensing data to the control unit, the navigation unit is connected to the control unit in a one-way data manner, the control unit is used to send control data to the vehicle chassis, the navigation unit is connected to the control unit in a one-way data manner, the navigation unit is used to send data to the control unit, and the control unit has two-way communication with the human interaction interface.

[0021] In this embodiment, the sensor group includes at least one of a millimeter wave radar, a camera and a laser SLAM.

[0022] In this embodiment, the human-computer interaction interface includes at least a touch screen, a voice recognition system, a vehicle-mounted HUD, and multi-function steering wheel control buttons.

[0023] In this embodiment, the control unit has multiple assisted driving functions, which include at least adaptive cruise control function, lane keeping assist function, automatic emergency braking function and blind spot monitoring function. The control unit is provided with a corresponding switch and priority for each assisted driving function.

[0024] In this embodiment, the present invention provides a navigation-based adaptive assisted driving method, which is applied to any one of the navigation-based adaptive assisted driving systems, and the method includes: The sensor group collects scene data and determines the current driving scene based on the scene data; Different assisted driving functions are enabled based on different driving scenarios. When the driving scenarios change, the assisted driving functions are switched. The driving scenarios include at least highway scenarios, curve and ramp scenarios, and urban driving and intersection scenarios.

[0025] In this embodiment, in a highway scenario, the adaptive cruise control function, the lane keeping assist function and the automatic emergency braking function are activated simultaneously, wherein the automatic emergency braking function has a higher priority than the lane keeping assist function, and the lane keeping assist function has a higher priority than the adaptive cruise control function.

[0026] In this embodiment, in curve and ramp scenarios, the lane keeping assist function and the automatic emergency braking function are activated simultaneously, and when a sharp bend and / or a ramp is detected ahead on the road, the lane keeping assist function is exited.

[0027] In this embodiment, in urban driving and intersection scenarios, the automatic emergency braking function and the blind spot monitoring function are activated at the same time.

[0028] In this embodiment, an interface for configuring the assisted driving function is provided on the human-computer interaction interface, on which the assisted driving function can be increased or decreased, and the parameters of the assisted driving function can be set.

[0029] In this embodiment, in the interface for configuring the assisted driving function, a navigation information adjustment option is provided for the adaptive cruise control function; a trigger threshold adjustment option is provided for the automatic emergency braking function; and an option for adjusting the distance between the vehicle and the center line of the vehicle is provided for the lane keeping assist function.

[0030] Embodiment 2: Based on the navigation-based adaptive assisted driving system and method of Embodiment 1, the present invention is further illustrated and described below.

[0031] like Figure 1As shown, an adaptive assisted driving system based on navigation includes: a navigation unit, a sensor group, a control unit and a human interaction interface, the sensor group is connected to the control unit in a one-way data manner, the sensor group is used to send the collected sensing data to the control unit, the navigation unit is connected to the control unit in a one-way data manner, the control unit is used to send control data to the vehicle chassis, the navigation unit is connected to the control unit in a one-way data manner, the navigation unit is used to send data to the control unit, and the control unit has two-way communication with the human interaction interface.

[0032] In this embodiment, a navigation-based adaptive assisted driving method is provided. The method is implemented by a scene recognition system and a function management system in a control unit. The specific functions of the two systems are as follows: 1. Scene recognition system, which collects scene data through a sensor group and performs multi-modal data fusion to determine the current driving scene.

[0033] The driving scene is determined by the scene recognition system in the control unit in combination with the navigation data and the perception data. The scene division and judgment basis can be referred to as follows: Scene classification: congestion scene; high-speed scene; narrow road scene; curve scene; intersection scene; ramp scene. Classification basis: (1) Congestion scenario: The road section in the navigation data has a traffic speed of ≤20 km / h; (2) Highway scenario: ① The road section is clearly marked as a highway in the navigation data; ② The current scene is not a congested scene; ③The current scene is not a narrow road scene; ④The current scene is not a curve scene; ⑤The current scene is not an intersection scene; (3) Narrow road scenario: the lane width in the sensor perception data is less than or equal to 3m; (4) Curve scenario: ① The road section is clearly marked as a curve or sharp turn in the navigation data; ② The lane lines in the sensor perception data have obvious curvature; (5) Intersection scenario: There are clearly marked sections of road near intersections in the navigation data; (6) Slope scenario: ① The navigation data clearly indicates that the road section is an uphill or downhill section; ② The sensor ramp detection algorithm has output results. The core functional components of the scene recognition system can be described as follows: (1) The system adopts a hierarchical multimodal data fusion architecture to align navigation data (high-precision maps, real-time path planning) and perception data (millimeter-wave radar, camera, laser SLAM) in time and space to solve the problem of heterogeneous data synchronization. The time alignment is based on PTP (Precision Time Protocol) to achieve microsecond synchronization of sensor data and navigation data; the spatial coordinate alignment is achieved by real-time matching of the vehicle posture (6DoF) output by SLAM with the high-precision map coordinate system (UTM or WGS84), and using the extended Kalman filter (EKF) to fuse GPS / IMU data to ensure positioning accuracy ≤10cm.

[0034] (2) Dynamic scene recognition algorithm, that is, based on navigation semantic information and real-time perception data, a scene probability model is constructed and a Bayesian network is used to realize scene dynamic reasoning. The input features include but are not limited to: ① Navigation data: road type (highway / city), curvature radius, slope, and traffic sign semantics (such as intersection distance and curve marking).

[0035] ② Perception data: lane width (laser SLAM point cloud fitting), obstacle distribution (millimeter wave radar clustering), slope angle (IMU fusion).

[0036] The scenario probability calculation can refer to the formula , Among them, S i is the i-th scene, and D is the current multimodal data.

[0037] On this basis, an online learning mechanism can be introduced, for example, dynamically optimizing the scene division threshold based on the driver's historical operation data (such as adjusting the speed threshold of the congestion scene from 20km / h to the 15-25km / h range).

[0038] 2. Assisted driving function management system, such as Figure 2 As shown, different assisted driving functions are enabled based on different driving scenarios, and the assisted driving functions are switched when the driving scenarios change. Its core functional components can be described as follows: Functional algorithm architecture, the functional algorithm of the assisted driving function switching system is based on the finite state machine and event-driven model; among them, the scene recognition result is given by the scene recognition system; the event trigger will generate events according to the scene changes (such as high speed-curve) to trigger state migration; the state machine decision layer will manage the function activation status and priority rules corresponding to each scene; the function execution layer executes specific control instructions. The system's preset scene priority rules can be described as: Intersection scene > Narrow road scene > Curve scene > Ramp scene > Congestion scene > Highway scene. Further, the function activation rules in each scene are shown in Table 1. Table 1 Scenario function activation rules

[0039] (2) Scene switching logic ①State migration when switching scenes The triggering condition of scene switching can be described as when the scene recognition module detects that the confidence of the new scene exceeds the threshold (such as 90%), or the maintenance condition is not met within the duration of the current scene (such as the high-speed scene must meet the defined conditions for 5 consecutive seconds). It should be noted during the migration process that the high-priority scene should immediately terminate the active functions of the low-priority scene (such as the intersection scene terminal high-speed scene ACC), and gradually reduce the control amount of the disabled function through the ramp-down algorithm (such as the ACC target speed linearly drops to the current speed within 1 second).

[0040] ② Adjustment of function priority within the scene The function priority adjustment strategy within the scene adopts a dynamic weight calculation method, and the formula is as follows: W i =α·S critical +β·D risk +γ·U driver , Among them, S critical : Functional safety factor (AEB=1.0, LKA=0.7, ACC=0.5); D risk : Real-time risk assessment value (based on collision time, lane efficiency); U driver : Driver preference coefficient (configured through the HMI configuration interface); α, β, γ: normalized weight coefficients (α+β+γ=1).

[0041] For example, in a high-speed scenario, if a low-speed vehicle (TTC < 3s) suddenly appears in front, the AEB will increase sharply, causing its weight to exceed that of LKA, triggering ABE to completely take over braking control.

[0042] (1) Functional management strategies for each scenario The detailed functional management strategy description of each scenario is shown in Table 2 Table 2 Scene function management list

[0043] 3. Human-computer interaction system, i.e. the external information interaction interface of the overall system. It includes touch screen, voice recognition system, vehicle HUD (head-up display) and multi-function steering wheel control buttons. The system should be able to provide the driver with configurable adaptive assisted driving functions. The driver can add or reduce assisted driving functions within the system configuration functions, and can also set the parameters of the assisted driving functions. An adaptive assisted driving system based on navigation is provided in an embodiment of the present invention. Based on navigation management, it reduces the switch operations of the driver during driving. At the same time, it improves the driving experience, driving safety and perception data through the coordinated work of multiple assisted driving functions and a priority mechanism. The assisted driving function is adaptively performed during vehicle driving according to the user's parameter settings.

[0044] In the system structure, the human-machine interaction interface should be able to provide the driver with configurable adaptive assisted driving functions. The driver can add or reduce assisted driving functions within the system configuration functions, and can also set the parameters of the assisted driving functions. Parameter settings include but are not limited to the following points: ①ACC function setting: The system automatically adjusts according to navigation information or the driver manually adjusts.

[0045] ②AEB function settings: AEB trigger threshold (collision time).

[0046] ③LKA function setting: the distance between the vehicle and the center of the lane line.

[0047] ④BSM function setting: obstacle type for blind spot monitoring.

[0048] The present invention proposes an adaptive assisted driving system with wide adaptability, high safety, strong scalability and practical use significance. Based on navigation and perception data, the system adaptively manages the assisted driving function during vehicle driving according to the user's parameter settings, reduces the driver's switch operation during driving, and improves the driving experience and driving safety through the coordinated work of multiple assisted driving functions and priority mechanism.

[0049] In one embodiment, a computer device is provided, the computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented: Scene data is collected through a sensor group, and the current driving scene is determined based on the scene data; different assisted driving functions are enabled based on different driving scenes, and the assisted driving functions are switched when the driving scene changes. The driving scenes include at least highway scenes, curve and ramp scenes, and urban driving and intersection scenes.

[0050] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor performs the following steps: Scene data is collected through a sensor group, and the current driving scene is determined based on the scene data; different assisted driving functions are enabled based on different driving scenes, and the assisted driving functions are switched when the driving scene changes. The driving scenes include at least highway scenes, curve and ramp scenes, and urban driving and intersection scenes.

[0051] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0052] In summary, the present invention not only solves the problem that frequent manual switching of the assisted driving function may have an adverse effect on driving in certain driving scenarios during actual driving, but also can well cooperate with the driver to perform emergency avoidance operations and improve the safety of driving the vehicle.

[0053] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A navigation-based adaptive assisted driving system, characterized in that: The system includes: a navigation unit, a sensor group, a control unit and a human interaction interface, the sensor group is connected to the control unit in a one-way data manner, the sensor group is used to send the collected sensing data to the control unit, the navigation unit is connected to the control unit in a one-way data manner, the control unit is used to send control data to the vehicle chassis, the navigation unit is connected to the control unit in a one-way data manner, the navigation unit is used to send data to the control unit, and the control unit communicates with the human interaction interface in a two-way manner.

2. The navigation-based adaptive assisted driving system according to claim 1, characterized in that: The sensor group includes at least one of a millimeter wave radar, a camera and a laser SLAM.

3. The navigation-based adaptive assisted driving system according to claim 1, characterized in that: The human-computer interaction interface includes at least a touch screen, a voice recognition system, an on-board HUD and multi-function steering wheel control buttons.

4. The navigation-based adaptive assisted driving system according to claim 1, characterized in that: The control unit has multiple assisted driving functions, which include at least adaptive cruise control function, lane keeping assist function, automatic emergency braking function and blind spot monitoring function. The control unit is provided with a corresponding switch and priority for each assisted driving function.

5. A navigation-based adaptive assisted driving method, characterized in that: Applied to the navigation-based adaptive assisted driving system according to any one of claims 1 to 4, the method comprising: The sensor group collects scene data and determines the current driving scene based on the scene data; Different assisted driving functions are enabled based on different driving scenarios. When the driving scenarios change, the assisted driving functions are switched. The driving scenarios include at least highway scenarios, curve and ramp scenarios, and urban driving and intersection scenarios.

6. The navigation-based adaptive assisted driving method according to claim 5, characterized in that: In highway scenarios, the adaptive cruise control function, lane keeping assist function and automatic emergency braking function are activated at the same time, among which the automatic emergency braking function has a higher priority than the lane keeping assist function, and the lane keeping assist function has a higher priority than the adaptive cruise control function.

7. The navigation-based adaptive assisted driving method according to claim 5, characterized in that: In curve and slope scenarios, the lane keeping assist function and automatic emergency braking function are activated at the same time. When a sharp bend and / or slope is detected ahead on the road, the lane keeping assist function is exited.

8. The navigation-based adaptive assisted driving method according to claim 5, characterized in that: In urban driving and intersection scenarios, the automatic emergency braking function and blind spot monitoring function are activated at the same time.

9. The navigation-based adaptive assisted driving method according to claim 5, characterized in that: The human-computer interaction interface is provided with an interface for configuring the assisted driving function, on which the assisted driving function can be increased or decreased, and the parameters of the assisted driving function can be set.

10. The navigation-based adaptive assisted driving method according to claim 9, characterized in that: In the interface for configuring the assisted driving function, there is an option to adjust the navigation information for the adaptive cruise control function; there is an option to adjust the trigger threshold for the automatic emergency braking function; and there is an option to adjust the distance between the vehicle and the center line of the vehicle for the lane keeping assist function.

Images