Vehicle path planning method based on thermodynamic diagram, vehicle and electronic equipment

Abstract

The invention provides a vehicle path planning method based on a thermodynamic diagram, a vehicle and electronic equipment. The method comprises the steps that passing data of a vehicle are acquired, a thermodynamic diagram matrix reflecting spatial risk distribution is generated based on the passing data, obstacle types and a safety distance rule, and the safety distance rule represents a rule set by a safety distance between the vehicle and an obstacle; the driving preference setting of the user is obtained, the weight coefficient of the thermodynamic diagram matrix of the vehicle is adjusted according to the driving preference setting, and an adjusted thermodynamic diagram is obtained; and in the path exploration process of the vehicle based on the hybrid A star algorithm, the adjustment thermodynamic diagram is used as a state transition cost correction factor of the hybrid A star algorithm, and a low-cost path of the vehicle is determined. The problems that in the prior art, path planning based on an A star algorithm is mainly embodied in static processing of environmental elements, dynamic evaluation of obstacle types and risks is lacked, and humanized decision factors are not integrated are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle routing technology, and more specifically, to a heatmap-based vehicle routing method, a vehicle, a computer-readable storage medium, and an electronic device. Background Technology

[0002] In the field of autonomous driving, path planning technology is a core component for achieving autonomous navigation. Traditional path planning algorithms, such as A* algorithm, while providing paths from start to finish, have limitations when handling dynamic and complex environments. These limitations mainly manifest in the static handling of environmental factors, the lack of dynamic assessment of obstacle types and risks, and the failure to incorporate human-centered decision-making factors. Specifically: Static obstacle handling: Traditional algorithms usually treat obstacles as fixed, without considering their type (such as pedestrians, vehicles, fixed obstacles) and potential risk level, which may lead to overly conservative path planning or insufficient response in sudden situations.

[0003] Dynamic environment adaptability: In dynamic environments, such as when pedestrians suddenly cross the road or vehicles are parked randomly, traditional algorithms have limited real-time adjustment capabilities and may need to frequently replan routes, affecting efficiency and safety.

[0004] Human-machine collaborative decision-making: When planning routes, autonomous driving systems or intelligent robots often lack interaction mechanisms with human operators or passengers, and cannot reflect personal preferences or decision-making needs in specific situations in real time. Summary of the Invention

[0005] The main objective of this application is to provide a heatmap-based vehicle path planning method, vehicle, computer-readable storage medium, and electronic device, in order to at least solve the problems of existing path planning technologies based on the A* algorithm, which mainly focus on the static processing of environmental factors, lack of dynamic assessment of obstacle types and risks, and failure to incorporate human decision-making factors.

[0006] To achieve the above objectives, according to one aspect of this application, a vehicle path planning method based on heatmaps is provided, comprising: acquiring vehicle traffic data; generating a heatmap matrix reflecting spatial risk distribution based on the traffic data, obstacle types, and safety distance rules, wherein the safety distance rules are characterized as rules for setting safety distances between the vehicle and obstacles; acquiring user driving preference settings; adjusting the weight coefficients of the vehicle's heatmap matrix according to the driving preference settings to obtain an adjusted heatmap; and during the vehicle's path exploration based on a hybrid A* algorithm, using the adjusted heatmap as a state transition cost correction factor for the hybrid A* algorithm to determine the low-cost path of the vehicle.

[0007] Optionally, generating a heatmap matrix reflecting the spatial risk distribution based on the access data, obstacle types, and safety distance rules includes: determining the diffusion distance and hazard factor of each obstacle in the heatmap based on the obstacle type; and generating the heatmap matrix reflecting the spatial risk distribution based on the access data, the diffusion distance and hazard factor corresponding to the obstacle type, and the safety distance rules.

[0008] Optionally, the adjusted heatmap is used as a state transition cost correction factor in the hybrid A* algorithm to determine the low-cost path of the vehicle, including: constructing a kinematic model of the vehicle, the kinematic model including the rear axle center coordinates, current driving angle, steering wheel angle, and road length at the next time step; simulating multiple state transition paths of the vehicle based on the kinematic model, and determining the risk value of each state transition path based on the adjusted heatmap; and determining the low-cost path of the vehicle based on the risk value of each state transition path.

[0009] Optionally, determining the low-cost path of the vehicle based on the risk value of each state transition path includes: sorting the state transition paths in ascending order of risk value to obtain a path sequence; and selecting the first preset number of state transition paths in the path sequence as the low-cost paths of the vehicle.

[0010] Optionally, after determining the risk value of each state transition path based on the adjusted heatmap, the method further includes: determining whether the risk value of each state transition path is greater than a risk threshold; marking the state transition paths whose risk values ​​are greater than the risk threshold, so as to stop using the hybrid A* algorithm to extend the exploration of the state transition paths.

[0011] Optionally, after determining the low-cost path of the vehicle, the method further includes: in the case of replanning the search path of the vehicle, obtaining the current traffic data of the vehicle, and updating the adjusted heatmap based on the current traffic data to obtain an updated heatmap.

[0012] Optionally, obtaining the user's driving preference settings includes: determining the user's selected custom area and the diffusion distance and hazard factor set for the custom area through the vehicle's in-vehicle terminal; and determining the user's driving preference settings based on the custom area and the diffusion distance and hazard factor corresponding to the custom area.

[0013] According to another aspect of this application, a vehicle is provided, comprising: a controller for executing any of the heatmap-based vehicle path planning methods described above.

[0014] According to another aspect of this application, a vehicle path planning device based on a heatmap is provided, comprising: an acquisition unit, configured to acquire vehicle traffic data, and generate a heatmap matrix reflecting spatial risk distribution based on the traffic data, obstacle type, and safety distance rules, wherein the safety distance rules are characterized as rules for setting the safety distance between the vehicle and obstacles; an adjustment unit, configured to acquire user driving preference settings, and adjust the weight coefficients of the vehicle's heatmap matrix according to the driving preference settings to obtain an adjusted heatmap; and a first determination unit, configured to use the adjusted heatmap as a state transition cost correction factor for the hybrid A* algorithm during the vehicle's path exploration based on the hybrid A* algorithm to determine the low-cost path of the vehicle.

[0015] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform any of the heatmap-based vehicle routing methods described above.

[0016] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any of the heatmap-based vehicle routing methods described above.

[0017] By applying the technical solution of this application, a heatmap matrix is ​​generated by acquiring vehicle traffic data and combining obstacle type and safety distance rules, which intuitively reflects the spatial risk distribution. The generation of the heatmap matrix not only considers the spatial occupancy risk of static obstacles, but also dynamically integrates temporary risk areas generated by real-time perception data, enhancing the multi-source fusion modeling capability of environmental risks. Furthermore, by acquiring the user's driving preference settings, this embodiment can adjust the weight coefficients of the heatmap matrix in real time to form an adjusted heatmap, thereby guiding the search process in the hybrid A* algorithm path exploration to prioritize avoiding high-risk and undesirable areas and favoring low-cost paths. In the state transition stage of the hybrid A* algorithm, the adjusted heatmap is introduced as a cost correction factor, and high-risk and infeasible search branches are eliminated in advance through a risk threshold screening mechanism, significantly reducing invalid node expansion and redundant calculations, and improving computational efficiency. This solves the problems of existing path planning based on the A* algorithm, which mainly focuses on the static processing of environmental elements, lacks dynamic assessment of obstacle types and risks, and fails to incorporate human decision-making factors. Attached Figure Description

[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 A hardware structure block diagram of a mobile terminal for performing a heatmap-based vehicle routing method is shown in an embodiment of this application. Figure 2 A schematic flowchart of a heatmap-based vehicle routing method according to an embodiment of this application is shown. Figure 3 A structural block diagram of a heatmap-based vehicle routing device provided according to an embodiment of this application is shown. Detailed Implementation

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, 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 for the embodiments of this application 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.

[0022] As described in the background section, existing path planning technologies based on the A* algorithm mainly suffer from static processing of environmental elements, lack of dynamic assessment of obstacle types and risks, and failure to incorporate human decision-making factors. To address these issues, embodiments of this application provide a heatmap-based vehicle path planning method, a vehicle, a computer-readable storage medium, and an electronic device.

[0023] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0024] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a vehicle routing method based on heatmaps, according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0025] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the heatmap-based vehicle routing method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0026] This embodiment provides a heatmap-based vehicle routing method that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 2 This is a flowchart of a heatmap-based vehicle routing method according to an embodiment of this application. Figure 2 As shown, the method includes the following steps: Step S201: Obtain vehicle traffic data, and generate a heat map matrix reflecting the spatial risk distribution based on the traffic data, obstacle type, and safety distance rules, wherein the safety distance rules are the rules for setting the safety distance between the vehicle and the obstacle. Specifically, the obstacle type and safety distance rules are set as follows (d represents the diffusion distance in the heatmap matrix, indicating the distance of risk diffusion from the edge of the obstacle outward, in meters; w represents the hazard factor in the heatmap matrix, set in the range (0~1)): The obstacle is a pillar. d is set to 0.5, indicating that it can be as close to the edge as possible. w is set to 0.5, indicating that the risk is acceptable. The obstacles are water-filled barriers or traffic cones. d is set to 0.3, indicating that it is possible to stay close to the edge as much as possible, and w is set to 0.8, indicating a higher risk. The obstacle is a temporary parking space. d is set to 3, indicating that it will extend outwards by 3.0m. w is set to 1, indicating an extremely high risk. For obstacles in special areas (such as vegetation in ground parking lots, or manhole covers in old parking lots), d is set to 0.0 and w is set to 0.5. Step S202: Obtain the user's driving preference settings, and adjust the weight coefficients of the heatmap matrix of the vehicle according to the driving preference settings to obtain the adjusted heatmap. Specifically, the vehicle-mounted system has a simple canvas that allows users or remote safety operators to select an area from above and set the grid type of that area to a custom area. Users can also adjust the weight coefficient of the custom area in the heatmap matrix.

[0028] Step S203: During the path exploration process of the vehicle based on the hybrid A* algorithm, the adjusted heatmap is used as the state transition cost correction factor of the hybrid A* algorithm to determine the low-cost path of the vehicle.

[0029] The hybrid A-star algorithm refers to a path planning method that combines the traditional A-star search algorithm with a vehicle kinematics model, and is suitable for automatic parking scenarios. The A-star algorithm is a widely used algorithm for finding the shortest path in a graph. It combines heuristic search with breadth-first search or depth-first search, guiding the search process by evaluating the estimated cost from the current node to the target node (usually called h(n)) and the known cost from the starting point to the current node (usually called g(n)).

[0030] This embodiment uses vehicle traffic data to generate a heatmap matrix based on obstacle type and safe distance rules, intuitively reflecting the spatial risk distribution. The generation of the heatmap matrix not only considers the spatial occupancy risk of static obstacles but also dynamically integrates temporary risk zones generated from real-time perception data, enhancing the multi-source fusion modeling capability of environmental risks. Furthermore, by acquiring user driving preference settings, this embodiment can adjust the weight coefficients of the heatmap matrix in real time, forming an adjusted heatmap. This guides the search process in the hybrid A* algorithm path exploration to prioritize avoiding high-risk and undesirable areas, favoring low-cost paths. During the state transition phase of the hybrid A* algorithm, the adjusted heatmap is introduced as a cost correction factor. A risk threshold screening mechanism preemptively eliminates high-risk and infeasible search branches, significantly reducing invalid node expansion and redundant calculations, thus improving computational efficiency. This addresses the problems of existing A* algorithm-based path planning technologies, which primarily focus on static processing of environmental elements, lack dynamic assessment of obstacle types and risks, and fail to incorporate human-centered decision-making factors.

[0031] In the specific implementation process, a heat map matrix reflecting the spatial risk distribution is generated based on the aforementioned traffic data, obstacle types, and safety distance rules. This includes: determining the diffusion distance and hazard factor of each obstacle in the heat map based on the aforementioned obstacle types; and generating the aforementioned heat map matrix reflecting the spatial risk distribution based on the aforementioned traffic data, the aforementioned diffusion distance and hazard factor corresponding to the aforementioned obstacle types, and the safety distance rules.

[0032] This method generates a heatmap matrix reflecting spatial risk distribution based on obstacle type, historical traffic data, and safety distance requirements. Obstacles in the environment, such as fixed pillars, traffic cones, temporarily parked vehicles, pedestrian areas, and low-adhesion surfaces, are first assigned specific heatmap parameters. These parameters are evaluated through automated fine-tuning combined with a large-scale parking dataset. For different obstacles, their corresponding heatmap values ​​reflect their own risk level and the extent of their impact on the surrounding environment, quantified by setting diffusion distances and hazard factors. The grid occupied by the obstacle and its surrounding area are assigned corresponding risk weights according to preset diffusion distances. The weights decrease as the distance increases, but will not fall below a preset minimum value. After enumerating all obstacle boundary points and calculating their diffusion range, the system determines a distance factor by calculating the Euclidean distance from each grid to the obstacle, further adjusting the grid's risk value. Ultimately, the risk value of each grid in the heatmap matrix is ​​the maximum of the risk values ​​of all influencing factors, ensuring that even if multiple factors act on the same grid simultaneously, the risk will not be underestimated. This heatmap not only captures the spatial occupancy risk of static obstacles but also dynamically overlays temporary risk zones generated from real-time sensing data, achieving multi-source fusion modeling of environmental risks. In hybrid A-planet path search, this heatmap serves as a state transition cost correction factor. By calculating the sum of costs of all grids occupied by the vehicle after its next movement, it guides the search process to avoid high-risk areas, thereby improving the safety and efficiency of path planning while ensuring path feasibility and smoothness. Furthermore, a human preference adjustment mechanism allows drivers or remote operators to set preferences for specific areas through a human-machine interface, influencing the heatmap weights to meet personalized operational needs. A risk threshold screening mechanism preemptively eliminates high-risk and infeasible search branches during the state expansion phase, ensuring the real-time nature and effectiveness of path planning. Heatmap updates and risk assessments are performed when the vehicle restarts the parking process or autonomously replans the path, ensuring the effectiveness of the threshold settings. Overall, the path planning method in this embodiment can efficiently and safely generate optimal paths that conform to safety constraints and human preferences in complex environments.

[0033] Specifically, the adjusted heatmap is used as a state transition cost correction factor for the hybrid A* algorithm to determine the low-cost path of the vehicle. This includes: constructing a kinematic model of the vehicle, which includes the rear axle center coordinates, current driving angle, steering wheel angle, and road length at the next time step; simulating multiple state transition paths of the vehicle based on the kinematic model, and determining the risk value of each state transition path based on the adjusted heatmap; and determining the low-cost path of the vehicle based on the risk value of each state transition path.

[0034] The kinematic model is defined as: `new_pos, new_heading = vehicle(pos,heading, steering, s)`, where `pos` represents the coordinates of the vehicle's rear axle center, `heading` indicates the current angle, `steering` represents the steering wheel angle, and `s` represents the distance traveled in the next step (the distance traveled in the next time step). During state transitions, hundreds of pairs of `(steering, s)` can be enumerated to obtain the vehicle's position in the next step. The total cost of all the grid cells occupied by the vehicle in the next step is also considered.

[0035] Taking the kinematic model: new_pos, new_heading = vehicle(pos, heading, steering_i, s_i) as an example, the cost of the (steering_i, s_i) pair is the sum of the costs of all the grids occupied by the vehicle after the next movement, cost_i = sum of cost of get_occupied_grids(new_pos, 0.0).

[0036] Set the calibration parameter ranking_cost = 1.0; Sort all states by cost_i in ascending order, and then perform linear interpolation based on the ranking: rank_cost_i = Lerp(0.0, 1.0, rank_i); The ranking cost for the first place is 0.0, and the ranking cost for the last place is 1.0.

[0037] Prioritize expanding states with low ranking_cost, and simultaneously add them to the g_cost accumulation for A-star.

[0038] This allows for a preference for low-risk regions during state transitions, and because it affects the accumulation of g_cost, it also influences the preference for global path exploration.

[0039] This method uses an adjusted heatmap as a state transition cost correction factor in a hybrid A* algorithm to determine the low-cost path for the vehicle. Specifically, this method constructs a kinematic model of the vehicle, encompassing key parameters such as the coordinates of the rear axle center, the current driving angle, the steering wheel angle, and the path length at the next time step. Based on this model, the system simulates multiple possible state transition paths for the vehicle and calculates the risk value of each path based on the adjusted heatmap. By comparing the risk values ​​of each path, the path with the lowest cost is selected as the vehicle's forward route. This strategy effectively utilizes heatmap information adjusted by human preferences, guiding the path-finding process towards lower-risk areas. Simultaneously, it considers the impact of vehicle motion characteristics on path cost, ensuring the safety and rationality of the path. In practical applications, a risk threshold screening mechanism further optimizes search efficiency, avoiding unnecessary path expansion, thereby quickly generating optimal paths in complex environments and meeting the needs of autonomous vehicles for rapid response and safe driving in dynamic environments. Of course, heatmap updates and risk assessments are only performed during the path replanning phase to ensure the system's real-time response capability and efficient utilization of computing resources. Through the above steps, this embodiment can significantly improve the path planning performance of the hybrid A* algorithm in complex environments, achieving a perfect combination of path planning security, efficiency, and personalized strategies.

[0040] More specifically, determining the low-cost path for the vehicle based on the risk value of each of the aforementioned state transition paths includes: sorting the state transition paths in ascending order of risk value to obtain a path sequence; and selecting the first preset number of state transition paths in the path sequence as the low-cost path for the vehicle.

[0041] The preset quantity can be set according to specific selection needs, such as 1, 2, 3, etc.

[0042] The hybrid A-path planning method of this approach assesses the risk of possible path options based on a pre-set heatmap matrix during state transitions. This process first calculates the cumulative risk value of all state transition paths, forming a sequence containing all paths and their corresponding risks. Then, the system automatically sorts the path sequence according to the risk value, with low-risk paths naturally at the beginning. Finally, a pre-set number of sorted paths are selected as the low-cost path set. These paths not only have low heatmap risk values ​​but are also feasible paths that satisfy vehicle kinematic constraints. This strategy effectively guides the search algorithm to prioritize safe and low-risk paths, thereby finding a safe and efficient path in complex operating environments.

[0043] Furthermore, after determining the risk value of each of the aforementioned state transition paths based on the adjusted heatmap, the method further includes: determining whether the risk value of each of the aforementioned state transition paths is greater than a risk threshold; marking the aforementioned state transition paths whose risk values ​​are greater than the aforementioned risk threshold, so as to stop using the aforementioned hybrid A* algorithm to extend the exploration of the aforementioned state transition paths.

[0044] The risk threshold screening mechanism is set as follows: When performing state transitions during enumeration, if the accumulated ranking_cost (risk value) is significantly higher than the risk threshold, it indicates that the current state has traversed multiple high-risk areas, and the node is directly set to close to stop further expansion. The risk threshold is related to the maximum number of expansion nodes in the A* algorithm. For example, when the number of expansion nodes in the A* search is 50,000, this risk threshold is set to 50. In this case, the risk threshold is equivalent to suppressing the endless expansion of the search layer.

[0045] This method, based on an adjustable weighted heatmap-based human-machine collaborative hybrid A / B path planning approach, further incorporates a risk threshold screening mechanism to improve the efficiency and safety of path search. Specifically, after determining the risk value of each state transition path, the system checks whether these risk values ​​exceed a pre-set risk threshold. If the risk value of a specific state transition path exceeds this threshold, the system marks the path, thus preventing the hybrid A / B algorithm from further exploring these high-risk paths. This mechanism automatically eliminates path options that pass through multiple high-risk areas, significantly reducing the expansion of invalid nodes and avoiding redundant computation, thereby improving the real-time performance and feasibility of path planning. By setting a reasonable risk threshold, this method ensures that the search process focuses on low-risk and preferred areas, generating paths that not only meet safety standards but also better align with driver preferences, thus improving the path planning performance of autonomous vehicles or intelligent robots in complex environments.

[0046] Furthermore, after determining the low-cost path for the aforementioned vehicle, the method further includes: in the case of replanning the search path for the aforementioned vehicle, obtaining the current traffic data of the aforementioned vehicle, and updating the adjusted heatmap based on the current traffic data to obtain an updated heatmap.

[0047] Among these, re-planning of search routes includes restarting the parking process or allowing the vehicle to re-plan autonomously.

[0048] This method, once the vehicle has determined a low-cost path, further enhances the system's adaptability when the search path needs to be replanned. Specifically, the vehicle continuously collects current traffic data during operation, including but not limited to real-time perception of new obstacles, environmental changes, or human intervention commands. Based on this real-time updated data, the system can dynamically adjust the heatmap, i.e., update the heatmap. This process involves recalculating the weight coefficients of each grid in the heatmap to reflect the latest environmental risks and human preferences. By rapidly responding to environmental changes and human intervention, the system ensures that path planning is always based on the most accurate information, thereby improving the real-time performance and safety of path planning. After updating the heatmap, the Hybrid A* algorithm recalculates the path using the new risk distribution, prioritizing low-risk areas and avoiding high-risk areas, ensuring that the vehicle can find the optimal driving route even in dynamic environments. This mechanism effectively avoids blind driving after environmental changes, reduces the uncertainty of path planning, enhances the vehicle's adaptability to complex environments, and provides technical support for safe and efficient human-machine cooperative driving.

[0049] Specifically, obtaining the user's driving preference settings includes: determining the user's selected custom area and the diffusion distance and hazard factor set for the custom area through the vehicle's in-vehicle terminal; and determining the user's driving preference settings based on the custom area and the diffusion distance and hazard factor corresponding to the custom area.

[0050] To more accurately respond to driver preferences, this method integrates dynamic weight adjustments for customizable regions, enabling personalized path planning strategies. Through the vehicle's in-vehicle interface, drivers can intuitively select and mark specific areas, such as vacant parking spaces or safety-sensitive areas to avoid, and then set the diffusion distance and hazard factors for these areas. This process not only enhances the ability to identify diverse environmental risks but also allows drivers to directly intervene in the risk assessment model, making it more closely aligned with actual needs. In the initial stage of path planning, the system automatically updates the weight coefficients in the heatmap matrix based on the driver's preference settings, ensuring that low-risk areas or driver-preferred areas are prioritized during the execution of the hybrid A* algorithm, thereby optimizing path selection. Especially in the state transition cost calculation stage, the preference-adjusted heatmap serves as a key correction factor, directly affecting the score of candidate paths, prompting the algorithm to proactively avoid high-risk options and prioritize exploring low-cost paths that meet the driver's expectations. Combined with a risk threshold screening mechanism, search efficiency is further improved, unnecessary high-risk area assessments are avoided, and path planning is both efficient and safe. The entire solution does not require frequent real-time updates to the heat map; it only recalculates when necessary based on new information or driver adjustments, thus maintaining system stability and efficient use of computing resources.

[0051] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the heatmap-based vehicle routing method of this application will be described in detail below with reference to specific embodiments.

[0052] This embodiment relates to a specific heatmap-based vehicle path planning method. Addressing various types of obstacles and environmental elements in the vehicle operating environment (including fixed pillars, traffic cones, temporarily parked vehicles, pedestrian areas, and low-adhesion road surfaces), it first pre-sets corresponding heatmap values ​​(weighting coefficients) based on obstacle type, historical traffic data, and safety distance requirements. This generates a heatmap matrix reflecting the spatial risk distribution. The heatmap parameters are obtained through automated fine-tuning of variable parameters combined with a large-scale parking dataset. This heatmap not only reflects the spatial occupancy risk of static obstacles but can also dynamically overlay temporary risk zones generated from real-time sensing data, thereby achieving multi-source fusion modeling of environmental risks.

[0053] Building upon this foundation, this embodiment further introduces a human preference adjustment mechanism: drivers or remote operators can set preferences for specific areas through a human-machine interface, such as reducing the path cost of vacant parking spaces to prioritize entry, or increasing the path cost of certain designated areas to avoid approaching specific targets (such as densely populated areas or construction zones). This human adjustment will be applied to the weight coefficients of the heatmap in real time, realizing the integration of human-machine co-driving and customized path strategies to meet personalized operation needs.

[0054] During the hybrid A-star path search process, the system uses a preference-adjusted heatmap as a state transition cost correction factor. By weighting the node expansion cost function, it guides the search process to prioritize avoiding high-risk or unpopular areas and favors low-cost paths. To improve real-time performance, this embodiment introduces a risk threshold screening mechanism during the node expansion stage, pruning high-risk and infeasible search branches in advance, effectively reducing invalid node expansions and redundant calculations.

[0055] This embodiment significantly improves the search efficiency and path safety of the hybrid A* algorithm in complex environments, shortens computation time, and generates optimal paths that meet safety constraints and human preferences while ensuring path feasibility and smoothness. This method is applicable to scenarios requiring real-time path planning in dynamic and complex environments, such as autonomous vehicles, automated valet parking (AVP), and mobile robots. It offers advantages such as high computational efficiency, strong path safety, support for human-machine co-driving, and customized strategies.

[0056] This application also provides a vehicle, including a controller for executing any of the above-described heatmap-based vehicle path planning methods. The controller may be an ECU.

[0057] This application also provides a heatmap-based vehicle routing planning device. It should be noted that the heatmap-based vehicle routing planning device of this application can be used to execute the heatmap-based vehicle routing planning method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0058] The following describes the vehicle routing device based on heatmaps provided in the embodiments of this application.

[0059] Figure 3 This is a schematic diagram of a heatmap-based vehicle routing device according to an embodiment of this application. Figure 3 As shown, the device includes: The acquisition unit 31 is used to acquire vehicle traffic data and generate a heat map matrix reflecting the spatial risk distribution based on the traffic data, obstacle type, and safety distance rules. The safety distance rules are characterized as the rules for setting the safety distance between the vehicle and the obstacle. The adjustment unit 32 is used to obtain the user's driving preference settings, and adjust the weight coefficients of the heat map matrix of the vehicle according to the driving preference settings to obtain the adjusted heat map. The first determining unit 33 is used to determine the low-cost path of the vehicle by using the adjusted heatmap as the state transition cost correction factor of the hybrid A* algorithm during the path exploration process of the vehicle based on the hybrid A* algorithm.

[0060] In this embodiment, an acquisition unit is used to acquire vehicle traffic data and generate a heatmap matrix reflecting the spatial risk distribution based on the traffic data, obstacle types, and safety distance rules. The safety distance rules are defined as the rules governing the safe distance between vehicles and obstacles. An adjustment unit is used to acquire user driving preference settings and adjust the weight coefficients of the vehicle's heatmap matrix according to these settings to obtain an adjusted heatmap. A first determination unit is used to use the adjusted heatmap as a state transition cost correction factor for the hybrid A* algorithm during the vehicle's path exploration process to determine the vehicle's low-cost path. By acquiring vehicle traffic data and combining obstacle types and safety distance rules to generate a heatmap matrix, the spatial risk distribution is intuitively reflected. The generation of the heatmap matrix not only considers the spatial occupancy risk of static obstacles but also dynamically integrates temporary risk areas generated from real-time perception data, enhancing the multi-source fusion modeling capability of environmental risks. Furthermore, by acquiring the user's driving preference settings, this embodiment can adjust the weight coefficients of the heatmap matrix in real time to form an adjusted heatmap. This guides the search process in the hybrid A* algorithm path exploration to prioritize avoiding high-risk and undesirable areas and favor low-cost paths. During the state transition phase of the hybrid A* algorithm, the adjusted heatmap is introduced as a cost correction factor. A risk threshold screening mechanism preemptively eliminates high-risk and infeasible search branches, significantly reducing invalid node expansion and redundant calculations, thus improving computational efficiency. This addresses the problems of existing A* algorithm-based path planning technologies, which primarily focus on static processing of environmental factors, lack of dynamic assessment of obstacle types and risks, and failure to incorporate human-centered decision-making factors.

[0061] As an optional solution, the acquisition unit includes a first determining module and a generating module; the first determining module is used to determine the diffusion distance and hazard factor of each obstacle in the heat map based on the above obstacle types; the generating module is used to generate the above heat map matrix reflecting the spatial risk distribution based on the above passage data, the above diffusion distance and hazard factor corresponding to the above obstacle types, and the safety distance rules.

[0062] In one optional scheme, the first determining unit includes a construction module, a second determining module, and a third determining module; the construction module is used to construct a kinematic model of the vehicle, the kinematic model including the rear axle center coordinates, current driving angle, steering wheel angle, and road length at the next time step; the second determining module is used to simulate multiple state transition paths of the vehicle based on the kinematic model, and determine the risk value of each state transition path based on the adjusted heatmap; the third determining module is used to determine the low-cost path of the vehicle based on the risk value of each state transition path.

[0063] In one optional scheme, the third determining module includes a sorting submodule and a selection submodule; the sorting submodule is used to sort the state transition paths in order of risk value from low to high to obtain a path sequence; the selection submodule is used to select the first preset number of state transition paths in the path sequence as the low-cost paths of the vehicle.

[0064] In one alternative embodiment, the apparatus further includes a second determining unit and a marking unit; the second determining unit is used to determine whether the risk value of each of the aforementioned state transition paths is greater than a risk threshold after determining the risk value of each of the aforementioned state transition paths based on the aforementioned adjusted heatmap; the marking unit is used to mark the aforementioned state transition paths whose risk values ​​are greater than the aforementioned risk threshold, so as to stop using the aforementioned hybrid A* algorithm to expand the exploration of the aforementioned state transition paths.

[0065] In an alternative embodiment, the apparatus further includes an updating unit, configured to, after determining the low-cost path of the vehicle and in the event of a replanning of the vehicle's search path, acquire the current traffic data of the vehicle, update the adjusted heatmap based on the current traffic data, and obtain an updated heatmap.

[0066] In one optional scheme, the adjustment unit includes a fourth determining module and a fifth determining module. The fourth determining module is used to determine the user-selected custom area and the diffusion distance and hazard factor set for the custom area through the vehicle's in-vehicle terminal. The fifth determining module is used to determine the user's driving preference settings based on the custom area and the diffusion distance and hazard factor corresponding to the custom area.

[0067] The aforementioned heatmap-based vehicle routing device includes a processor and a memory. The acquisition unit, adjustment unit, and first determination unit are all stored as program units in the memory, and the processor executes these program units to achieve their respective functions. All of the above modules reside in the same processor; alternatively, the modules may be located in different processors in any combination.

[0068] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and their parameters can be adjusted to address the shortcomings of existing path planning technologies based on the A* algorithm, which mainly suffer from static handling of environmental factors, lack of dynamic assessment of obstacle types and risks, and failure to incorporate human-centered decision-making factors.

[0069] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0070] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the heatmap-based vehicle routing method.

[0071] Specifically, heatmap-based vehicle routing methods include: Step S201: Obtain vehicle traffic data, and generate a heat map matrix reflecting the spatial risk distribution based on the traffic data, obstacle type, and safety distance rules, wherein the safety distance rules are the rules for setting the safety distance between the vehicle and the obstacle. Step S202: Obtain the user's driving preference settings, and adjust the weight coefficients of the heatmap matrix of the vehicle according to the driving preference settings to obtain the adjusted heatmap. Step S203: During the path exploration process of the vehicle based on the hybrid A* algorithm, the adjusted heatmap is used as the state transition cost correction factor of the hybrid A* algorithm to determine the low-cost path of the vehicle.

[0072] This invention provides a processor for running a program, wherein the program executes the heatmap-based vehicle routing method.

[0073] Specifically, heatmap-based vehicle routing methods include: Step S201: Obtain vehicle traffic data, and generate a heat map matrix reflecting the spatial risk distribution based on the traffic data, obstacle type, and safety distance rules, wherein the safety distance rules are the rules for setting the safety distance between the vehicle and the obstacle. Step S202: Obtain the user's driving preference settings, and adjust the weight coefficients of the heatmap matrix of the vehicle according to the driving preference settings to obtain the adjusted heatmap. Step S203: During the path exploration process of the vehicle based on the hybrid A* algorithm, the adjusted heatmap is used as the state transition cost correction factor of the hybrid A* algorithm to determine the low-cost path of the vehicle.

[0074] This invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: Step S201: Obtain vehicle traffic data, and generate a heat map matrix reflecting the spatial risk distribution based on the traffic data, obstacle type, and safety distance rules, wherein the safety distance rules are the rules for setting the safety distance between the vehicle and the obstacle. Step S202: Obtain the user's driving preference settings, and adjust the weight coefficients of the heatmap matrix of the vehicle according to the driving preference settings to obtain the adjusted heatmap. Step S203: During the path exploration process of the vehicle based on the hybrid A* algorithm, the adjusted heatmap is used as the state transition cost correction factor of the hybrid A* algorithm to determine the low-cost path of the vehicle.

[0075] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0076] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: Step S201: Obtain vehicle traffic data, and generate a heat map matrix reflecting the spatial risk distribution based on the traffic data, obstacle type, and safety distance rules, wherein the safety distance rules are the rules for setting the safety distance between the vehicle and the obstacle. Step S202: Obtain the user's driving preference settings, and adjust the weight coefficients of the heatmap matrix of the vehicle according to the driving preference settings to obtain the adjusted heatmap. Step S203: During the path exploration process of the vehicle based on the hybrid A* algorithm, the adjusted heatmap is used as the state transition cost correction factor of the hybrid A* algorithm to determine the low-cost path of the vehicle.

[0077] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0078] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0080] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0081] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0082] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0083] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0084] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0085] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0086] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0087] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A heat map-based vehicle path planning method, characterized in that, The method comprises the following steps: obtaining traffic data of a vehicle, generating a heat map matrix reflecting spatial risk distribution based on the traffic data, obstacle types and safety distance rules, wherein the safety distance rules represent rules for setting a safety distance between the vehicle and obstacles; obtaining driving preference settings of a user, adjusting a weight coefficient of the heat map matrix of the vehicle according to the driving preference settings to obtain an adjusted heat map; in the process of path exploration of the vehicle based on a hybrid A-star algorithm, taking the adjusted heat map as a state transition cost correction factor of the hybrid A-star algorithm to determine a low-cost path of the vehicle.

2. The method of claim 1, wherein, Generating a heat map matrix reflecting spatial risk distribution based on the traffic data, obstacle types and safety distance rules comprises: determining a diffusion distance and a danger factor of each obstacle in the heat map based on the obstacle types; generating the heat map matrix reflecting spatial risk distribution based on the traffic data, the diffusion distance and the danger factor corresponding to the obstacle types, and safety distance rules.

3. The method of claim 1, wherein, Taking the adjusted heat map as a state transition cost correction factor of the hybrid A-star algorithm to determine a low-cost path of the vehicle comprises: constructing a kinematic model of the vehicle, the kinematic model comprising a rear axle center coordinate of the vehicle, a current driving angle, a steering wheel angle, and a road length of a next time step; simulating a plurality of state transition paths of the vehicle based on the kinematic model, and determining a risk value of each state transition path based on the adjusted heat map; determining the low-cost path of the vehicle according to the risk values of the state transition paths.

4. The method of claim 3, wherein, Determining the low-cost path of the vehicle according to the risk values of the state transition paths comprises: sorting the state transition paths in order of the risk values from low to high to obtain a path sequence; selecting a front preset number of the state transition paths in the path sequence as the low-cost path of the vehicle.

5. The method of claim 3, wherein, After determining the risk values of the state transition paths based on the adjusted heat map, the method further comprises: determining whether the risk values of the state transition paths are greater than a risk threshold value; marking the state transition paths with risk values greater than the risk threshold value, so that the expansion exploration of the state transition paths by the hybrid A-star algorithm is stopped.

6. The method of claim 1, wherein, After determining the low-cost path of the vehicle, the method further comprises: in the case of search path re-planning of the vehicle, obtaining current traffic data of the vehicle, and updating the adjusted heat map based on the current traffic data to obtain an updated heat map.

7. The method of claim 1, wherein, Obtaining driving preference settings of a user comprises: determining a custom area selected by the user and a diffusion distance and a danger factor set for the custom area through a vehicle machine end of the vehicle; determining the driving preference settings of the user based on the custom area and the diffusion distance and the danger factor corresponding to the custom area.

8. A vehicle characterized by comprising: The method comprises the following steps: a controller configured to execute the heat map-based vehicle path planning method of any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium includes a stored program, wherein the program controls the device where the computer readable storage medium is located to perform the heat map based vehicle path planning method in any one of claims 1 to 7 when the program is running.

10. An electronic device, comprising: comprise: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a program for performing the heat map based vehicle path planning method in any one of claims 1 to 7.

Images