Ice-snow road automatic driving vehicle trajectory planning method based on finite state machine

Abstract

The application relates to an ice and snow road automatic driving vehicle trajectory planning method based on a finite state machine, wherein the method comprises the following steps: determining the risk value of the surrounding environment of the current vehicle based on the collision risk field of the surrounding environment of the vehicle, identifying the collision risk state of the current ice and snow road according to the risk value and a preset risk threshold; collecting the running state of the tire of the current vehicle, determining the actual working condition of the current vehicle according to the running state; constructing a finite state machine based on the collision risk state and the actual working condition of the current vehicle, converting the actual working condition of the current vehicle by using the finite state machine, and matching the best trajectory planning algorithm according to the conversion result of the actual working condition, so as to plan the vehicle driving trajectory on the current ice and snow road according to the best trajectory planning algorithm. Therefore, the problems that reliable ice and snow road risk evaluation cannot be performed, the collision risk level of the ice and snow road cannot be selected for the bottom layer trajectory planning algorithm and the like are solved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method for autonomous vehicle trajectory planning on icy and snowy roads based on finite state machines. Background Technology

[0002] Icy and snowy roads have low and time-varying coefficients of adhesion, and are prone to traffic accidents and unexpected events, posing significant risks to the driving safety of autonomous vehicles. When making safe decisions on icy and snowy roads, autonomous vehicles need to employ decision-making methods with high precision and real-time capabilities, while comprehensively considering the characteristics of the icy and snowy road surface and the impact of other road users on the vehicle.

[0003] Existing decision-making methods for autonomous vehicles can generally be divided into three types: finite state machine-based, optimization-based, and learning-based methods. Among them, only optimization-based and learning-based methods can output specific trajectories, which are essential for icy and snowy roads. However, optimization-based algorithms have high computational costs and cannot achieve high real-time performance. At the same time, for complex scenarios such as icy and snowy roads, it is difficult to train an effective network by directly using learning-based decision-making methods such as reinforcement learning. Unlike optimization-based and learning-based methods, finite state machine-based methods are convenient to apply and have low computational costs. Although they cannot plan trajectories, they can use finite state machines for higher-level decision-making. That is, they can use finite state machines to classify the vehicle's operating conditions and consider the use of energy functions to form a driving risk field, thereby increasing the consideration of the risk of vehicle instability on icy and snowy roads. Icy and snowy roads are classified according to the level of risk. Different trajectory planning algorithms are used to output trajectories based on different operating conditions of the vehicle, other vehicles, and different risk levels of icy and snowy roads, without increasing the computational cost, while outputting safer trajectories.

[0004] Currently, technologies based on finite state machines can input the results of fuzzy reasoning into a finite state machine and output either lane-changing or free-roaming driving. In addition, these technologies can also enable vehicles to switch between six types of driving behaviors based on finite state machines and environmental factors such as TTC (Traffic Troubleshooting Control).

[0005] However, the relevant technologies are insufficient for reliable risk assessment of icy and snowy roads, and cannot select underlying trajectory planning algorithms for collision risk levels on icy and snowy roads, which urgently needs to be addressed. Summary of the Invention

[0006] This application provides a trajectory planning method for autonomous vehicles on icy and snowy roads based on finite state machines, in order to solve the problems of related technologies that make it difficult to conduct reliable risk assessments on icy and snowy roads and are unable to select the underlying trajectory planning algorithm based on the collision risk level of icy and snowy roads.

[0007] The first aspect of this application provides a trajectory planning method for autonomous vehicles on icy and snowy roads based on a finite state machine, comprising the following steps: determining the risk value of the current vehicle's surrounding environment based on a collision risk field; identifying the collision risk state of the current icy and snowy road based on the risk value and a preset risk threshold; collecting the tire operating state of the current vehicle; determining the actual operating condition of the current vehicle based on the operating state; constructing a finite state machine based on the collision risk state and the actual operating condition of the current vehicle; transforming the actual operating condition of the current vehicle using the finite state machine; and matching the optimal trajectory planning algorithm based on the transformation result of the actual operating condition to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm.

[0008] Optionally, in one embodiment of this application, before determining the risk value of the current vehicle's surrounding environment based on the collision risk field of the vehicle's surrounding environment, the method includes: detecting the lateral acceleration of other surrounding vehicles; constructing an instability risk field of other surrounding vehicles on the current icy and snowy road based on the lateral acceleration of the other surrounding vehicles and a preset instability risk threshold; obtaining the adhesion coefficient of the current icy and snowy road; generating a road adhesion coefficient risk field based on the adhesion coefficient; and constructing the collision risk field of the vehicle's surrounding environment based on the instability risk field and the road adhesion coefficient risk field.

[0009] Optionally, in one embodiment of this application, identifying the collision risk state of the current icy road based on the risk value and a preset risk threshold includes: constructing a risk area that meets preset requirements with the current vehicle's position as the center; obtaining the maximum value of the field strength of the collision risk field around the vehicle within the risk area, and using the maximum value as the risk value of the current vehicle's surrounding environment; comparing the risk value with the preset risk threshold, and if the comparison result is that the risk value is greater than or equal to the preset risk threshold, then determining that the current icy road collision risk state is a high-risk state; otherwise, determining that the current icy road collision risk state is a low-risk state.

[0010] Optionally, in one embodiment of this application, the step of collecting the current tire operating status of the vehicle and determining the actual operating condition of the vehicle based on the operating status includes: detecting the tire slip ratio of the vehicle; when the tire slip ratio of the vehicle is within a first preset range, the current actual operating condition of the vehicle is determined to be a normal operating condition; when the tire slip ratio of the vehicle is within a second preset range, the current actual operating condition of the vehicle is determined to be a transitional operating condition; when the tire slip ratio of the vehicle is within a third preset range, the current actual operating condition of the vehicle is determined to be an extreme operating condition; the maximum value of the first preset range is less than the minimum value of the second preset range, and the maximum value of the second preset range is less than the minimum value of the third preset range.

[0011] A second aspect of this application provides an autonomous vehicle trajectory planning device for icy and snowy roads based on a finite state machine, comprising: an identification module for determining the risk value of the current surrounding environment of the vehicle based on a collision risk field around the vehicle, and identifying the collision risk state of the current icy and snowy road according to the risk value and a preset risk threshold; an acquisition module for acquiring the operating state of the tires of the current vehicle and determining the actual operating condition of the current vehicle according to the operating state; and a planning module for constructing a finite state machine based on the collision risk state and the actual operating condition of the current vehicle, transforming the actual operating condition of the current vehicle using the finite state machine, and matching the optimal trajectory planning algorithm according to the transformation result of the actual operating condition, so as to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm.

[0012] Optionally, in one embodiment of this application, it further includes: a first construction module, configured to detect the lateral acceleration of other surrounding vehicles before determining the risk value of the current vehicle's surrounding environment based on the collision risk field of the vehicle's surrounding environment, and construct the instability risk field of other surrounding vehicles on the current icy and snowy road based on the lateral acceleration of the other surrounding vehicles and a preset instability risk threshold; an acquisition module, configured to acquire the adhesion coefficient of the current icy and snowy road, and generate a road adhesion coefficient risk field based on the adhesion coefficient; and a second construction module, configured to construct the collision risk field of the vehicle's surrounding environment based on the instability risk field and the road adhesion coefficient risk field.

[0013] Optionally, in one embodiment of this application, the identification module includes: a division unit, configured to construct a risk area that meets preset requirements with the current position of the vehicle as the center; a value assignment unit, configured to obtain the maximum value of the field strength of the collision risk field around the vehicle within the risk area, and use the maximum value as the risk value of the current environment around the vehicle; and a comparison unit, configured to compare the risk value with a preset risk threshold, and if the comparison result is that the risk value is greater than or equal to the preset risk threshold, then the current icy road collision risk state is determined to be a high-risk state, otherwise the current icy road collision risk state is determined to be a low-risk state.

[0014] Optionally, in one embodiment of this application, the acquisition module includes: a detection unit for detecting the slip ratio of the vehicle's tires; a first determination unit for determining that the current actual operating condition of the vehicle is a normal operating condition when the slip ratio of the vehicle's tires is within a first preset range; a second determination unit for determining that the current actual operating condition of the vehicle is a transitional operating condition when the slip ratio of the vehicle's tires is within a second preset range; and a third determination unit for determining that the current actual operating condition of the vehicle is an extreme operating condition when the slip ratio of the vehicle's tires is within a third preset range.

[0015] The comparison unit is used to determine if the maximum value of the first preset interval is less than the minimum value of the second preset interval, and if the maximum value of the second preset interval is less than the minimum value of the third preset interval.

[0016] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the autonomous vehicle trajectory planning method for icy and snowy roads based on a finite state machine as described in the above embodiments.

[0017] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for autonomous vehicle trajectory planning on icy and snowy roads based on a finite state machine.

[0018] Therefore, the embodiments of this application have the following beneficial effects:

[0019] The embodiments of this application determine the risk value of the current surrounding environment of the autonomous vehicle based on the collision risk field of the vehicle's surrounding environment, identify the collision risk state of the current icy and snowy road based on the risk value and a preset risk threshold, collect the current tire operating status of the vehicle, determine the actual operating condition of the vehicle based on the operating status, construct a finite state machine based on the collision risk state and the actual operating condition of the vehicle, use the finite state machine to transform the actual operating condition of the vehicle, and match the optimal trajectory planning algorithm according to the transformation result of the actual operating condition to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm. This application effectively ensures the real-time performance and rationality of the trajectory planning of autonomous vehicles on icy and snowy roads by conducting a comprehensive assessment of the road risk of the vehicle on icy and snowy roads, combining the vehicle's operating condition, and using a finite state machine to select the underlying trajectory planning algorithm. Therefore, it solves the problems of related technologies, such as the difficulty in conducting reliable risk assessment of icy and snowy roads and the inability to select the underlying trajectory planning algorithm based on the collision risk level of icy and snowy roads.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0022] Figure 1 This is a flowchart of an autonomous vehicle trajectory planning method based on a finite state machine for icy and snowy roads, according to an embodiment of this application.

[0023] Figure 2 A schematic diagram of a risk field and risk assessment for icy and snowy roads is provided as an embodiment of this application;

[0024] Figure 3 An input-output diagram of a finite state machine for upper-level decision-making in an autonomous vehicle is provided as an embodiment of this application;

[0025] Figure 4 A schematic diagram of a finite state machine for upper-level decision-making in an autonomous vehicle is provided as an embodiment of this application;

[0026] Figure 5 This is an example diagram of an autonomous vehicle trajectory planning device based on a finite state machine for icy and snowy roads according to an embodiment of this application;

[0027] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0028] Among them, 10-Automatic vehicle trajectory planning device based on finite state machine for icy and snowy roads, 100-Identification module, 200-Acquisition module, 300-Planning module, 601-Memory, 602-Processor, and 603-Communication interface. Detailed Implementation

[0029] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0030] The following describes an embodiment of the autonomous vehicle trajectory planning method for icy and snowy roads based on a finite state machine, with reference to the accompanying drawings. Addressing the problems mentioned in the background section, this application provides a method for autonomous vehicle trajectory planning on icy and snowy roads based on a finite state machine. In this method, the risk value of the vehicle's surrounding environment is determined based on a collision risk field; the collision risk state of the current icy and snowy road is identified based on the risk value and a preset risk threshold; the tire operating state of the current vehicle is collected, and the actual operating condition of the current vehicle is determined based on the operating state; a finite state machine is constructed based on the collision risk state and the actual operating condition of the current vehicle; the actual operating condition of the current vehicle is transformed using the finite state machine; and the optimal trajectory planning algorithm is matched based on the transformation result of the actual operating condition to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm. This application effectively ensures the real-time performance and rationality of autonomous vehicle trajectory planning on icy and snowy roads by conducting a comprehensive assessment of the road risk of the vehicle on icy and snowy roads, combining this with the vehicle's operating condition, and using a finite state machine to select the underlying trajectory planning algorithm. This solves the problems that related technologies struggle to reliably assess the risks of icy and snowy roads, and are unable to select underlying trajectory planning algorithms for the collision risk levels of icy and snowy roads.

[0031] Specifically, Figure 1 This is a flowchart illustrating an autonomous vehicle trajectory planning method for icy and snowy roads based on a finite state machine, as provided in an embodiment of this application.

[0032] like Figure 1 As shown, the trajectory planning method for autonomous vehicles on icy and snowy roads based on finite state machines includes the following steps:

[0033] In step S101, based on the collision risk field of the vehicle's surrounding environment, the risk value of the current vehicle's surrounding environment is determined, and the collision risk status of the current icy and snowy road is identified according to the risk value and the preset risk threshold.

[0034] The embodiments of this application first determine the collision risk field φ of the environment surrounding the vehicle on icy and snowy roads. r And utilize this collision risk field φ r Obtain the risk value φ of the current surrounding environment of the vehicle. max Then, based on the risk value φ of the current surrounding environment of the vehicle. max The collision risk status of the vehicle on icy and snowy roads is determined by comparing the results with a pre-set risk threshold k.

[0035] Therefore, the embodiments of this application determine the current collision risk status of icy and snowy roads based on the collision risk field of the vehicle's surrounding environment and the instability risk of surrounding vehicles, so as to conduct a comprehensive road risk assessment and provide guidance and basis for subsequent vehicle trajectory planning.

[0036] Optionally, in one embodiment of this application, before determining the risk value of the current vehicle's surrounding environment based on the collision risk field of the vehicle's surrounding environment, the method includes: detecting the lateral acceleration of other surrounding vehicles; constructing an instability risk field of other surrounding vehicles on the current icy and snowy road based on the lateral acceleration of other surrounding vehicles and a preset instability risk threshold; obtaining the adhesion coefficient of the current icy and snowy road; generating a road adhesion coefficient risk field based on the adhesion coefficient; and constructing a collision risk field of the vehicle's surrounding environment based on the instability risk field and the road adhesion coefficient risk field.

[0037] In the embodiments of this application, the collision risk field φ of the vehicle's surrounding environment r This includes the coefficient of adhesion of roads with icy or snowy surfaces and its variation (μ). i The risk field generated by the vehicle and the risk field generated by all vehicles around the vehicle (assuming there are n vehicles) are described using an energy function. These two risk fields are then superimposed to form a single energy field, namely the collision risk field φ of the vehicle's surrounding environment. r Its mathematical expression is shown in the following formula:

[0038]

[0039] The magnitude of the risk field generated by the j-th vehicle in the vicinity is related to its motion state x. j =g(d jx d jy v jx v jy M j , l j ) related, d jx d jy v represents the lateral and longitudinal distances from the j-th vehicle to its own vehicle, respectively. jx v jy M represents the longitudinal and lateral velocities of the j-th vehicle, respectively. j For the mass of the j-th vehicle, l jThe total length, width, and height of vehicle j represent the total length, width, and height of vehicle j. Therefore, every other vehicle around vehicle j will generate an energy field f2(x) in the environment around vehicle j based on an energy function. j Thus, for each of his vehicles, it is possible to achieve the desired energy field f2(x). j Based on this, the risk of vehicle instability is integrated.

[0040] It should be noted that the embodiments of this application can detect the lateral acceleration of surrounding vehicles. If the lateral acceleration of the j-th vehicle If the value exceeds a preset threshold k0, the vehicle has a high probability of instability, where k0 = μ. min b, where b is a preset value, typically set to 5, μ min Let f2(x) be the minimum adhesion coefficient of the road surface covered by the vertical projection of the j-th vehicle. If other vehicles on icy or snowy roads are in a high-risk instability state, then the field strength value f2(x) generated by them in the risk field is... j It should be multiplied by a constant k1. Since the unstable vehicle's motion is uncontrollable and the risk of collision is relatively high, k1 > 5 is required.

[0041] It is important to note that the assessment of instability risk of other vehicles must fully consider the vehicle type. For large, heavy trucks and buses, the risk threshold should be much lower than that of small passenger cars. Furthermore, the risk field f1(μ) generated by the road adhesion coefficient... i It should be negatively correlated with the adhesion coefficient, that is, the adhesion coefficient μ of this area of ​​the road. i The smaller, f1(μ) i The larger the value of ), the better.

[0042] It is understood that embodiments of this application may be based on the vehicle's lateral acceleration. To determine the instability risk of surrounding vehicles, when the surrounding vehicles are at high instability risk, the movement of the instable vehicles is often uncontrollable and will pose a great collision risk to the vehicle itself. Therefore, it is necessary to significantly increase the field strength generated by the vehicle in the risk field and superimpose the field strength generated by all vehicles to obtain the risk field of the environment around the vehicle itself.

[0043] Therefore, the embodiments of this application fully consider the low road adhesion coefficient and the change of adhesion coefficient, as well as other vehicles or obstacles around the vehicle and their motion state. Combined with the instability risk of vehicles around the vehicle's location, an environmental risk field around the vehicle is constructed, thereby realizing a comprehensive risk assessment of icy and snowy roads based on the energy length of instability risk.

[0044] Optionally, in one embodiment of this application, identifying the collision risk status of the current icy and snowy road based on the risk value and a preset risk threshold includes: constructing a risk area that meets preset requirements with the current vehicle's position as the center; obtaining the maximum value of the field strength of the collision risk field around the vehicle within the risk area, and using the maximum value as the risk value of the current vehicle's surrounding environment; comparing the risk value with the preset risk threshold, and if the comparison result is that the risk value is greater than or equal to the preset risk threshold, then the current collision risk status of the icy and snowy road is determined to be a high-risk status, otherwise the current collision risk status of the icy and snowy road is determined to be a low-risk status.

[0045] It should be noted that after forming the risk field around the vehicle, the embodiments of this application can obtain the vehicle's specific location through the vehicle's positioning system, and obtain an elliptical region centered on the vehicle's location, such as... Figure 2 As shown, the major axis of this elliptical region is the x-axis of the vehicle, and the minor axis is the y-axis of the vehicle. The length of the major axis of the ellipse is related to the longitudinal velocity v of the vehicle. x Positive correlation: The length of the minor axis is related to the lateral velocity v of the vehicle. y Positive correlation, take the risk field strength φ within the elliptical region. r maximum value φ max This is used as the risk value of the vehicle on the icy and snowy road at that moment, and this risk value is compared with a pre-set risk threshold k. If the risk field strength φ r maximum value φ max If the value is greater than k, it indicates that the current collision risk status of the icy and snowy road is high-risk; otherwise, it indicates low-risk.

[0046] Therefore, the embodiments of this application compare the risk value of the current surrounding environment of the vehicle with a preset risk threshold to obtain the current collision risk status on icy and snowy roads, enabling a comprehensive road risk assessment and providing a reliable basis for subsequent upper-level decision-making of autonomous vehicles on icy and snowy roads based on finite state machines.

[0047] In step S102, the current tire operating status of the vehicle is collected, and the actual working condition of the vehicle is determined based on the operating status.

[0048] While identifying the collision risk status of the current icy and snowy road, embodiments of this application can also collect the operating status of the vehicle's tires to determine the actual operating conditions of the vehicle.

[0049] Optionally, in one embodiment of this application, the current tire operating status of the vehicle is collected, and the actual operating condition of the vehicle is determined based on the operating status, including: detecting the slip ratio of the vehicle's tires; when the slip ratio of the vehicle's tires is within a first preset range, the current actual operating condition of the vehicle is determined to be a normal operating condition; when the slip ratio of the vehicle's tires is within a second preset range, the current actual operating condition of the vehicle is determined to be a transitional operating condition; when the slip ratio of the vehicle's tires is within a third preset range, the current actual operating condition of the vehicle is determined to be an extreme operating condition; the maximum value of the first preset range is less than the minimum value of the second preset range, and the maximum value of the second preset range is less than the minimum value of the third preset range.

[0050] It should be noted that, in the embodiments of this application, the current operating conditions of the vehicle include three types: normal operating conditions, transitional operating conditions, and extreme operating conditions.

[0051] Among them, when the vehicle tires are working in the linear region, and the tires move on the ground in pure rolling or with only a low slip ratio or slip rate, there is little difference between driving on a normal road surface and driving on a normal road surface. In this case, the vehicle is in normal operating condition.

[0052] When a vehicle's tires have a large longitudinal slip ratio, a large slewing ratio, or a large lateral slip ratio, the vehicle is in an extreme working condition. Under this condition, one or more tires of the vehicle are in a saturated state, that is, the vehicle is in a steady-state drift or slip state with a large lateral speed, which is a relatively dangerous working condition.

[0053] The transitional state between the above-mentioned normal operating conditions and extreme operating conditions is called the transitional operating condition. In this state, the vehicle's tires are close to or have reached saturation, but this state is not stable.

[0054] Therefore, the embodiments of this application determine the actual working conditions of the vehicle based on the tire's operating status, thereby providing a basis and data support for selecting the underlying trajectory planning algorithm for icy and snowy roads.

[0055] In step S103, a finite state machine is constructed based on the collision risk state and the current actual working condition of the vehicle. The finite state machine is used to transform the current actual working condition of the vehicle, and the optimal trajectory planning algorithm is matched according to the transformation result of the actual working condition, so as to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm.

[0056] The embodiments of this application primarily rely on the comprehensive results of the vehicle's risk assessment on icy and snowy roads (numerical results of the risk assessment and the set risk thresholds) and the vehicle's operating conditions to achieve upper-level decision-making for autonomous vehicles on icy and snowy roads. When the vehicle's operating conditions and the risk status of icy and snowy roads differ, the embodiments of this application can utilize a finite state machine decision-making mechanism to determine the specific offline-computed low-level trajectory planning algorithm for vehicle estimation and planning on icy and snowy roads. Figure 3 As shown.

[0057] Embodiments of this application can use a finite state machine to select a trajectory planning algorithm for a vehicle on icy and snowy roads for trajectory planning, such as... Figure 4 As shown, the specific process is as follows:

[0058] 1. When the vehicle is generally in normal operating conditions, the trajectory planning algorithm for normal operating conditions can be used based on the collision risk of the icy and snowy road surface around the vehicle (whether it is a high-risk state or a low-risk state). (The underlying trajectory planning algorithm for high-risk normal operating conditions can be obtained by modifying some parameters in the underlying trajectory planning algorithm for low-risk normal operating conditions).

[0059] 2. When a collision-free trajectory cannot be planned under normal operating conditions, or when the vehicle's lateral acceleration exceeds the acceleration safety threshold, the vehicle is likely to skid. In this case, the vehicle can enter a transitional operating condition automatically or manually. Under the transitional operating condition, if the collision risk on the icy or snowy road surface is high, the transitional operating condition trajectory planning algorithm and control module will be used to quickly bring the vehicle into the extreme operating condition. If the collision risk on the icy or snowy road surface is low, the transitional operating condition trajectory planning algorithm and control module will be used to quickly bring the vehicle into the normal operating condition.

[0060] 3. After the vehicle enters the extreme working condition, if the icy and snowy road surface remains in a high collision risk state, the vehicle can use the extreme working condition trajectory planning algorithm to plan the vehicle trajectory. When the icy and snowy road surface is reduced to a low risk state, the vehicle is controlled to return to the transition working condition, and then the trajectory planning algorithm is determined according to the change of collision risk on the icy and snowy road surface.

[0061] It is understood that the vehicle transition condition in this application embodiment is an intermediate state between normal and extreme conditions, and is not a vehicle condition that can remain stable for a long time. After entering this condition, the vehicle should quickly enter the normal or extreme conditions with the help of trajectory planning and motion control.

[0062] It should be noted that, in the embodiments of this application, the four underlying trajectory planning algorithms described above—high-risk normal working condition underlying trajectory planning algorithm, low-risk normal working condition underlying trajectory planning algorithm, extreme working condition trajectory planning algorithm, and transitional working condition trajectory planning algorithm—can use algorithms that can output trajectories, such as optimization learning or reinforcement learning, to perform vehicle trajectory planning on icy and snowy roads.

[0063] Therefore, the embodiments of this application comprehensively consider two factors: the vehicle's operating conditions and the collision risk level of icy and snowy roads, in selecting the underlying trajectory planning algorithm to ensure real-time performance while planning a reasonable trajectory.

[0064] The trajectory planning method for autonomous vehicles on icy and snowy roads based on a finite state machine, as proposed in this application, determines the risk value of the vehicle's surrounding environment based on a collision risk field. It then identifies the collision risk state of the current icy and snowy road based on the risk value and a preset risk threshold. The method collects the tire operating status of the vehicle and determines the vehicle's actual operating condition. A finite state machine is constructed based on the collision risk state and the vehicle's actual operating condition. This finite state machine is used to transform the vehicle's actual operating condition, and the optimal trajectory planning algorithm is matched based on the transformation result to plan the vehicle's trajectory on the icy and snowy road. This application effectively ensures the real-time performance and rationality of the trajectory planning for autonomous vehicles on icy and snowy roads by conducting a comprehensive assessment of the road risks and combining this with the vehicle's operating condition, and by using a finite state machine to select the underlying trajectory planning algorithm.

[0065] Secondly, with reference to the accompanying drawings, an autonomous vehicle trajectory planning device based on a finite state machine for icy and snowy roads, according to an embodiment of this application, is described.

[0066] Figure 5 This is a block diagram of an autonomous vehicle trajectory planning device for icy and snowy roads based on a finite state machine, according to an embodiment of this application.

[0067] like Figure 5 As shown, the autonomous vehicle trajectory planning device 10 for icy and snowy roads based on finite state machines includes: an identification module 100, a data acquisition module 200, and a planning module 300.

[0068] The identification module 100 is used to determine the risk value of the current surrounding environment of the vehicle based on the collision risk field of the vehicle's surrounding environment, and to identify the collision risk status of the current icy and snowy road according to the risk value and the preset risk threshold.

[0069] The data acquisition module 200 collects the current tire operating status of the vehicle and determines the actual working condition of the vehicle based on the operating status.

[0070] The planning module 300 is used to construct a finite state machine based on the collision risk state and the current actual working condition of the vehicle. The finite state machine is used to transform the current actual working condition of the vehicle, and the optimal trajectory planning algorithm is matched according to the transformation result of the actual working condition to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm.

[0071] Optionally, in one embodiment of this application, the autonomous vehicle trajectory planning device 10 for icy and snowy roads based on finite state machines in this application embodiment further includes: a first construction module, an acquisition module, and a second construction module.

[0072] The first construction module is used to detect the lateral acceleration of other surrounding vehicles before determining the risk value of the current surrounding environment of the self-vehicle based on the collision risk field of the self-vehicle's surrounding environment, and to construct the instability risk field of other surrounding vehicles on the current icy and snowy road based on the lateral acceleration of other surrounding vehicles and the preset instability risk threshold.

[0073] The acquisition module is used to obtain the adhesion coefficient of the current icy and snowy road and generate a road adhesion coefficient risk field based on the adhesion coefficient.

[0074] The second construction module is used to construct the collision risk field of the vehicle's surrounding environment based on the instability risk field and the road adhesion coefficient risk field.

[0075] Optionally, in one embodiment of this application, the identification module 100 includes: a division unit, an assignment unit, and a comparison unit.

[0076] The division unit is used to construct a risk area that meets preset requirements, centered on the current position of the vehicle.

[0077] The assignment unit is used to obtain the maximum value of the field strength of the collision risk field around the vehicle within the risk area, and to use the maximum value as the current risk value of the vehicle's surrounding environment.

[0078] The comparison unit is used to compare the risk value with the preset risk threshold. If the comparison result is that the risk value is greater than or equal to the preset risk threshold, the current collision risk status of the icy and snowy road is determined to be a high-risk status; otherwise, the current collision risk status of the icy and snowy road is determined to be a low-risk status.

[0079] Optionally, in one embodiment of this application, the acquisition module 200 includes: a detection unit, a first determination unit, a second determination unit, a third determination unit, and a comparison unit.

[0080] The detection unit is used to detect the slip rate of the vehicle's tires.

[0081] The first determination unit is used to determine that the current actual working condition of the vehicle is a normal working condition when the slip ratio of the vehicle's tires is within a first preset range.

[0082] The second determination unit is used to determine that the current actual working condition of the vehicle is a transitional working condition when the slip ratio of the vehicle's tires is within a second preset range.

[0083] The third determination unit is used to determine that the current actual working condition of the vehicle is the extreme working condition when the slip ratio of the vehicle's tires is within the third preset range.

[0084] The comparison unit is used to determine if the maximum value of the first preset interval is less than the minimum value of the second preset interval, and if the maximum value of the second preset interval is less than the minimum value of the third preset interval.

[0085] It should be noted that the foregoing explanation of the embodiment of the autonomous vehicle trajectory planning method for icy and snowy roads based on finite state machines also applies to the autonomous vehicle trajectory planning device for icy and snowy roads based on finite state machines in this embodiment, and will not be repeated here.

[0086] The autonomous vehicle trajectory planning device for icy and snowy roads based on a finite state machine, as proposed in this application, determines the risk value of the vehicle's surrounding environment based on a collision risk field, identifies the collision risk state of the current icy and snowy road based on the risk value and a preset risk threshold, collects the tire operating status of the vehicle, determines the actual operating condition of the vehicle based on the operating status, constructs a finite state machine based on the collision risk state and the actual operating condition of the vehicle, uses the finite state machine to transform the actual operating condition of the vehicle, and matches the optimal trajectory planning algorithm based on the transformation result of the actual operating condition to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm. This application effectively ensures the real-time performance and rationality of the autonomous vehicle trajectory planning on icy and snowy roads by conducting a comprehensive assessment of the road risk of the vehicle on icy and snowy roads, combining the vehicle's operating condition, and using a finite state machine to select the underlying trajectory planning algorithm.

[0087] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0088] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0089] When the processor 602 executes the program, it implements the autonomous vehicle trajectory planning method based on finite state machine for icy and snowy roads provided in the above embodiments.

[0090] Furthermore, electronic devices also include:

[0091] Communication interface 603 is used for communication between memory 601 and processor 602.

[0092] The memory 601 is used to store computer programs that can run on the processor 602.

[0093] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0094] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0095] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0096] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0097] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for autonomous vehicle trajectory planning on icy and snowy roads based on a finite state machine.

[0098] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0099] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0100] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0102] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0103] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0104] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0105] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A trajectory planning method for autonomous vehicles on icy and snowy roads based on finite state machines, characterized in that, Includes the following steps: Based on the collision risk field of the vehicle's surrounding environment, the risk value of the current vehicle's surrounding environment is determined, and the collision risk status of the current icy and snowy road is identified according to the risk value and the preset risk threshold. The system collects the current tire operating status of the vehicle, determines the actual operating condition of the vehicle based on the operating status, and... Based on the collision risk state and the current actual operating condition of the vehicle, a finite state machine is constructed. The finite state machine is used to transform the current actual operating condition of the vehicle. The optimal trajectory planning algorithm is matched according to the transformation result of the actual operating condition, so as to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm. The process of collecting the current tire operating status of the vehicle and determining the actual operating condition of the vehicle based on the operating status includes: Detect the slip ratio of the vehicle's tires; When the slip ratio of the vehicle's tires is within a first preset range, the actual operating condition of the current vehicle is determined to be a normal operating condition. When the slip ratio of the vehicle's tires is within the second preset range, the current actual operating condition of the vehicle is determined to be a transitional operating condition. When the slip ratio of the vehicle's tires is within the third preset range, the current actual working condition of the vehicle is determined to be an extreme working condition. The maximum value of the first preset interval is less than the minimum value of the second preset interval, and the maximum value of the second preset interval is less than the minimum value of the third preset interval.

2. The method according to claim 1, characterized in that, Before determining the risk value of the current surrounding environment of the vehicle based on the collision risk field of the vehicle's surrounding environment, the following steps are included: The lateral acceleration of other surrounding vehicles is detected, and based on the lateral acceleration of other surrounding vehicles and a preset instability risk threshold, an instability risk field of other surrounding vehicles on the current icy and snowy road is constructed. Obtain the adhesion coefficient of the current icy and snowy road, and generate a road adhesion coefficient risk field based on the adhesion coefficient; The collision risk field of the vehicle's surrounding environment is constructed based on the instability risk field and the road adhesion coefficient risk field.

3. The method according to claim 2, characterized in that, The step of identifying the collision risk status of the current icy and snowy road based on the risk value and the preset risk threshold includes: A risk zone that meets preset requirements is constructed centered on the current location of the vehicle. The maximum value of the field strength of the collision risk field around the vehicle within the risk area is obtained, and the maximum value is used as the risk value of the current environment around the vehicle. If the risk value is greater than or equal to the preset risk threshold, the current collision risk status of the icy road is determined to be a high-risk status; otherwise, the current collision risk status of the icy road is determined to be a low-risk status.

4. A trajectory planning device for autonomous vehicles on icy and snowy roads based on a finite state machine, characterized in that, include: The identification module is used to determine the risk value of the current surrounding environment of the vehicle based on the collision risk field of the vehicle's surrounding environment, and to identify the collision risk status of the current icy and snowy road according to the risk value and the preset risk threshold. The data acquisition module collects the current tire operating status of the vehicle, and determines the actual operating condition of the vehicle based on the operating status. The planning module is used to construct a finite state machine based on the collision risk state and the current actual operating condition of the vehicle, use the finite state machine to transform the current actual operating condition of the vehicle, and match the optimal trajectory planning algorithm according to the transformation result of the actual operating condition, so as to plan the vehicle's driving trajectory on the current icy and snowy road according to the optimal trajectory planning algorithm. The acquisition module includes: The detection unit is used to detect the slip ratio of the tires of a self-driving vehicle; The first determination unit is used to determine that the actual working condition of the current vehicle is a normal working condition when the slip ratio of the vehicle tires is within a first preset range. The second determination unit is used to determine that the current actual working condition of the vehicle is a transitional working condition when the slip rate of the vehicle tires is within a second preset range. The third determination unit is used to determine that the current actual working condition of the vehicle is an extreme working condition when the slip ratio of the vehicle tires is within a third preset range. The comparison unit is used to determine if the maximum value of the first preset interval is less than the minimum value of the second preset interval, and if the maximum value of the second preset interval is less than the minimum value of the third preset interval.

5. The apparatus according to claim 4, characterized in that, Also includes: The first construction module is used to detect the lateral acceleration of other surrounding vehicles before determining the risk value of the current surrounding environment of the self-vehicle based on the collision risk field of the self-vehicle's surrounding environment, and to construct the instability risk field of other surrounding vehicles on the current icy and snowy road based on the lateral acceleration of the other surrounding vehicles and a preset instability risk threshold. The acquisition module is used to acquire the adhesion coefficient of the current icy and snowy road and generate a road adhesion coefficient risk field based on the adhesion coefficient. The second construction module is used to construct the collision risk field of the vehicle's surrounding environment based on the instability risk field and the road adhesion coefficient risk field.

6. The apparatus according to claim 5, characterized in that, The identification module includes: A partitioning unit is used to construct a risk area that meets preset requirements, centered on the current position of the vehicle. The assignment unit is used to obtain the maximum value of the field strength of the collision risk field of the vehicle's surrounding environment within the risk area, and to use the maximum value as the risk value of the current vehicle's surrounding environment. The comparison unit is used to compare the risk value with a preset risk threshold. If the comparison result is that the risk value is greater than or equal to the preset risk threshold, the current collision risk status of the icy and snowy road is determined to be a high-risk status; otherwise, the current collision risk status of the icy and snowy road is determined to be a low-risk status.

7. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the autonomous vehicle trajectory planning method for icy and snowy roads based on a finite state machine as described in any one of claims 1-3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the autonomous vehicle trajectory planning method for icy and snowy roads based on a finite state machine as described in any one of claims 1-3.

Images