Multi-lane queuing path planning methods, devices and vehicles

Abstract

This application relates to a multi-lane queuing path planning method, apparatus, and vehicle. The method includes: acquiring the starting performance data and current position of each vehicle in multiple queuing queues ahead of the vehicle; for each vehicle in each queue, determining the required travel time from its current position to the target intersection based on the starting performance data; determining the estimated travel time for each corresponding lane based on the travel times of all vehicles in the queues; and selecting the lane with the shortest estimated travel time as the queuing lane. This method can improve traffic efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a multi-lane queuing path planning method, device and vehicle. Background Technology

[0002] With the development of intelligent driving technology, intelligent lane guidance technology based on roadside perception and on-board terminals has emerged. This method detects traffic flow at intersections or road segments and provides vehicles with a certain degree of reference for travel paths or lane selection, which improves traffic efficiency to some extent compared to the driver's visual observation and judgment.

[0003] However, related technologies recommend lanes based on indicators such as overall lane traffic flow or current queue length. For example, in traditional intelligent assisted driving systems, vehicles typically choose the lane with the fewest vehicles in the queue ahead. However, in real-world traffic conditions, the lane with the fewest vehicles in the queue ahead is often not the fastest lane to pass through. Therefore, the efficiency of vehicle passage in multi-lane queuing scenarios needs to be improved.

[0004] Therefore, a method for determining queuing lanes that can improve traffic efficiency is needed to address situations where vehicles are queuing and waiting to pass. Summary of the Invention

[0005] Therefore, it is necessary to provide a multi-lane queuing path planning method, device, vehicle, computer-readable storage medium, and computer program product that can improve traffic efficiency in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a multi-lane queuing path planning method, including:

[0007] Obtain the starting performance data and current position of each vehicle in multiple queues ahead of the vehicle;

[0008] For each vehicle in each queue of vehicles, the travel time required for the vehicle to pass through the target intersection from the current position is determined based on the starting performance data.

[0009] Based on the travel time of all the vehicles in the queue, the estimated travel time for each corresponding lane is determined.

[0010] Based on the estimated travel time of each lane, the lane with the shortest estimated travel time is designated as the queuing lane.

[0011] In one embodiment, acquiring the starting performance data of each vehicle in a queue of multiple vehicles ahead of the vehicle includes:

[0012] Acquire multimodal information of each vehicle in multiple queues ahead of the vehicle;

[0013] The multimodal information is identified to determine the vehicle type of the queuing vehicles;

[0014] The corresponding starting performance data is retrieved from a preset correspondence table based on the vehicle type; the preset correspondence table stores the correspondence between different vehicle types and their respective starting performance data.

[0015] In one embodiment, the starting performance data includes starting reaction time, acceleration time required to accelerate from a standstill to a preset speed, and acceleration. Determining the travel time required for the queued vehicles to pass the target intersection from the current position based on the starting performance data includes:

[0016] Determine the current location and the travel distance to the target intersection;

[0017] Based on the travel distance, the start-up reaction time, the acceleration time, and the acceleration, the time required for the queued vehicles to pass through the target intersection from the current position after starting under preset start-up conditions is predicted.

[0018] In one embodiment, determining the estimated travel time for each corresponding lane based on the travel time of all vehicles in the queue includes:

[0019] Determine the lane control status corresponding to each lane;

[0020] Based on the lane control status, the estimated travel time for the corresponding lane is determined according to the travel time of each vehicle in each queue.

[0021] In one embodiment, determining the estimated travel time for a corresponding lane based on the lane control state and the travel time of each vehicle in each queue of vehicles includes:

[0022] The traffic light cycle and the control status of the traffic lights at the target intersection are obtained, and the lane control status corresponding to each lane is determined based on the control status.

[0023] Based on the traffic light cycle and the lane control status, the estimated travel time for the corresponding lane is determined according to the travel time of each vehicle in each queue.

[0024] In one embodiment, the lane control state includes at least whether the current phase is a travel phase and the remaining duration of the current phase. The step of determining the estimated travel time of the corresponding lane based on the traffic light cycle and the lane control state, according to the travel time of each vehicle in each queue, includes:

[0025] Starting from the second vehicle in the queue, determine the travel time required for each vehicle in the queue to travel a safe distance.

[0026] If the current phase is a passage phase, starting from the first vehicle in the queue, the estimated passage time for the corresponding lane is determined based on the traffic light cycle, the remaining maintenance duration, the travel time of each vehicle in the queue, and the passage time.

[0027] In one embodiment, the step of designating the lane with the shortest estimated travel time as a queuing lane based on the estimated travel time of each of the lanes includes:

[0028] Obtain vehicle information for the vehicle, which includes at least the actual direction of travel, vehicle purpose, and required lane width.

[0029] Based on the vehicle information, a set of candidate lanes is determined from the lanes in the vehicle queuing area;

[0030] Based on the estimated travel time of each candidate lane in the candidate lane set, the lane with the shortest estimated travel time is designated as the queuing lane.

[0031] In one embodiment, the method further includes:

[0032] Determine the current lane where the vehicle is located;

[0033] Based on the current lane, determine the lane change cost data and safety risk indicators for changing lanes to other lanes;

[0034] For each of the other lanes, the estimated travel time, lane change cost data, and safety risk indicators are weighted to obtain a weighted value, and the lane with the largest weighted value is determined as the queuing lane.

[0035] Secondly, this application also provides a multi-lane queuing path planning device, comprising:

[0036] The data acquisition module is used to acquire the starting performance data and current position of each vehicle in multiple queues of vehicles ahead of the vehicle.

[0037] The time prediction module is used to determine the travel time required for each vehicle in each queue of vehicles to pass through the target intersection from the current position, based on the starting performance data.

[0038] The passage time determination module is used to determine the estimated passage time of each corresponding lane based on the travel time of all the vehicles in the queue.

[0039] The lane planning module is used to designate the lane with the shortest expected travel time as the queuing lane based on the expected travel time of each lane.

[0040] Thirdly, this application also provides a vehicle, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0041] Obtain the starting performance data and current position of each vehicle in multiple queues ahead of the vehicle;

[0042] For each vehicle in each queue of vehicles, the travel time required for the vehicle to pass through the target intersection from the current position is determined based on the starting performance data.

[0043] Based on the travel time of all the vehicles in the queue, the estimated travel time for each corresponding lane is determined.

[0044] Based on the estimated travel time of each lane, the lane with the shortest estimated travel time is designated as the queuing lane.

[0045] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0046] Obtain the starting performance data and current position of each vehicle in multiple queues ahead of the vehicle;

[0047] For each vehicle in each queue of vehicles, the travel time required for the vehicle to pass through the target intersection from the current position is determined based on the starting performance data.

[0048] Based on the travel time of all the vehicles in the queue, the estimated travel time for each corresponding lane is determined.

[0049] Based on the estimated travel time of each lane, the lane with the shortest estimated travel time is designated as the queuing lane.

[0050] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0051] Obtain the starting performance data and current position of each vehicle in multiple queues ahead of the vehicle;

[0052] For each vehicle in each queue of vehicles, the travel time required for the vehicle to pass through the target intersection from the current position is determined based on the starting performance data.

[0053] Based on the travel time of all the vehicles in the queue, the estimated travel time for each corresponding lane is determined.

[0054] Based on the estimated travel time of each lane, the lane with the shortest estimated travel time is designated as the queuing lane.

[0055] The aforementioned multi-lane queuing path planning method, device, vehicle, computer-readable storage medium, and computer program product, when determining the optimal driving path for vehicle queuing scenarios, acquires the starting performance data and current position of each vehicle in multiple queuing queues ahead of the vehicle. Based on the starting performance data of each queuing vehicle, it determines the travel time required for each vehicle to pass through the target intersection from its current position, and then determines the estimated travel time for each corresponding vehicle. From this, the lane with the shortest estimated travel time is selected as the queuing lane. This method considers both the number of vehicles and the starting performance of the vehicles themselves, thus determining the shortest travel path, rather than simply determining the optimal lane based on the number of lanes ahead. This avoids the situation where the lane with the fewest vehicles does not have the shortest travel time, enabling adaptive lane-changing optimization queuing strategies and improving the traffic efficiency of intelligent driving vehicles in queuing scenarios. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart illustrating a multi-lane queuing path planning method in one embodiment;

[0058] Figure 2 This is a flowchart illustrating a method for determining start-up performance data in one embodiment;

[0059] Figure 3 This is a flowchart illustrating a method for determining queuing lanes in one embodiment;

[0060] Figure 4 This is a flowchart illustrating a method for determining queuing lanes in another embodiment;

[0061] Figure 5 This is a flowchart illustrating a multi-lane queuing path planning method in another embodiment;

[0062] Figure 6 This is a structural block diagram of a multi-lane queuing path planning device in one embodiment;

[0063] Figure 7 This is a diagram of the internal structure of a vehicle in one embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] In vehicle queuing scenarios, determining the optimal travel path is crucial for improving traffic flow efficiency. Currently, this primarily relies on driver visual observation and intelligent driving assistance. However, in multi-lane situations, limitations in driver visibility and complex road conditions arise, making driver visual judgment inaccurate. Intelligent driving assistance systems recommend optimal paths based on indicators such as overall lane flow or current queue length, which often doesn't guarantee the fastest route, leading to low traffic efficiency. Therefore, a method to improve traffic flow efficiency is needed. In actual traffic, to enhance efficiency, this approach considers differences in vehicle behavior, such as starting speed, reaction time, and acceleration performance, predicts the estimated travel time for each lane, and selects the fastest possible path. This adaptive lane-changing optimization strategy improves the efficiency of intelligent driving vehicles in queuing scenarios.

[0066] In one exemplary embodiment, such as Figure 1 As shown, a multi-lane queuing path planning method is provided. This embodiment illustrates the method using a terminal as an example, with a vehicle as the terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0067] Step 102: Obtain the starting performance data and current position of each vehicle in the multiple queues of vehicles ahead of the vehicle.

[0068] The "ahead of the vehicle" refers to scenarios involving queuing traffic, which can include, but are not limited to, traffic light intersections in urban areas, multi-lane / shared lanes, areas where bus lanes can be used, parking lot entrances and exits, ETC toll stations, and temporary construction detours. Starting performance data is used to characterize the vehicle's starting response from different dimensions, such as starting speed, response time, and acceleration performance. Different vehicle types require different starting performance data. Starting performance data can include starting response time, acceleration time required to reach a preset speed from a standstill, and acceleration. The methods for obtaining starting performance data can be based on existing methods and will not be elaborated upon here.

[0069] Optionally, the starting performance data can be starting data for different types of vehicles when the red light turns green. For example, in a real intersection scenario, it can be recorded how long after the green light turns on different vehicles (such as buses, trucks, private cars, etc.) start to move, as well as the time and acceleration required to accelerate from a standstill to low speed.

[0070] Methods for obtaining starting performance data and current location include: If both the vehicle ahead and the current vehicle support vehicle-to-everything (V2X) connectivity and are connected to a unified V2X platform, the starting performance data of the vehicle ahead can be shared via vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) communication. This vehicle can then obtain the starting performance data of the vehicle ahead by receiving this shared data. Alternatively, it can analyze video images captured by the vehicle's image acquisition device to identify changes in the vehicle's position and attitude at different times, and determine the vehicle's starting performance data by combining this with known image scale and time information. Another method is to use images of vehicles queuing in each lane ahead, captured by the vehicle's image acquisition device, to identify the corresponding vehicle type and then search for it in a pre-defined correspondence table.

[0071] Step 104: For each vehicle in each queue, determine the travel time required for the vehicle to pass through the target intersection from its current position based on the starting performance data.

[0072] The methods for determining the travel time required for queuing vehicles to pass through the target intersection from their current location based on initial performance data include: calculation based on pre-determined empirical formulas, prediction based on machine learning models, and simulation. Calculation based on pre-determined empirical formulas involves first calculating the initial distance s1 and time t1 based on known initial acceleration, then calculating the remaining distance s2 based on the total road distance s and distance s1, and determining the travel time t2 for the remaining road segment. The total travel time is then the sum of these two: t1 + t2. Simulation-based methods involve simulating the vehicle's journey from its current location to the target intersection based on current traffic conditions and the vehicle's initial performance data, and then statistically analyzing the travel time.

[0073] Machine learning-based prediction can involve acquiring a pre-trained prediction model, using starting performance data, current location, and the target intersection location as inputs, and then predicting the travel time. Optionally, the model training data can be determined by reconstructing and simulating real-world queuing scenarios based on collected data. For example, acquiring data from urban intersection queuing scenarios, and analyzing traffic flow and vehicle location data, can determine information such as queue length, queue density, and queue start and end positions at different times and under different traffic light conditions, thus constructing a realistic intersection queuing scenario. The data related to this constructed urban intersection queuing scenario is then organized and stored to obtain the model training data for the prediction model. Furthermore, after training the prediction model based on the training data, V2X data can be combined to further optimize recognition accuracy and traffic prediction, improving the accuracy of traffic prediction, such as more accurately predicting the time required for vehicles to pass through intersections.

[0074] V2X (Vehicle-to-Everything) is a vehicle-to-everything (V2X) technology used to enable information exchange between vehicles and the outside world. V2X data can include data exchanged between vehicles (V2V), between vehicles and infrastructure (V2I), between vehicles and pedestrians (V2P), and between vehicles and networks (V2N).

[0075] Step 106: Determine the estimated travel time for each lane based on the travel time of all vehicles in the queue.

[0076] Specifically, for the queuing lane ahead of this vehicle, given the known travel time required for each vehicle in each queuing lane to pass through the target intersection from its current position, the estimated travel time for each corresponding lane can be determined by sorting the passage times of each vehicle in the queue to obtain the estimated travel time required for all vehicles in the queue to pass through the intersection from the current moment.

[0077] In actual driving, road conditions change in real time and need to be determined in conjunction with the current queuing scenario. For example, in the scenario of a traffic light intersection in an urban area, the estimated travel time for each corresponding lane is determined by combining the traffic light cycle and the current signal phase signal. The current signal phase signal is used to characterize the control state of the traffic light at the target intersection, which can include whether it is currently a traffic phase, the corresponding direction of travel, and the remaining time or imminent switching time of that phase. This signal can be obtained through onboard camera recognition of traffic light colors, phase and timing information acquired through vehicle-to-infrastructure communication, or online estimation based on historical signal cycles. It is used to determine whether queuing vehicles can complete the passage within the current traffic phase, thereby assessing the estimated travel time of vehicles in different lanes. For example, large trucks that start slowly are not recommended to be guided into the corresponding lane for that traffic phase when there are 5 seconds left on the green light, while cars / electric vehicles that start quickly can be guided into the corresponding lane for that traffic phase.

[0078] Step 108: Based on the estimated travel time for each lane, designate the lane with the shortest estimated travel time as the queuing lane.

[0079] For example, based on the estimated travel time of each lane, the lane with the shortest estimated travel time is designated as the queuing lane, and a lane change instruction is automatically issued when the current speed / distance allows for a safe lane change; if the system is at L2+ level, the driver is prompted to perform a manual lane change. For instance, if the system detects that the estimated travel time of the adjacent left / right lanes is significantly better than that of the current lane, and the current speed / distance allows for a safe lane change, a lane change instruction is automatically issued.

[0080] Furthermore, when a queuing lane is identified and a lane change is required, if the vehicle is an autonomous vehicle, a lane change instruction is generated. This lane change instruction is used to instruct the vehicle to safely change lanes according to the queuing lane, lane change time window, and speed curve. For manually driven vehicles, lane change prompts can be provided in the form of a human-machine interface. The prompts include the target lane and the suggested lane change distance range.

[0081] It's important to note that traditional technologies do not consider differences in starting speed, reaction time, and acceleration performance among different vehicle types, nor do they use these differences to obtain data on the impact of vehicle starting performance on traffic efficiency. This is because the conventional thinking in this field treats traffic flow as composed of "equivalent vehicles," without distinguishing between vehicle types. Furthermore, differences in vehicle type are only considered as road management rules (such as speed limits for large vehicles and dedicated lane settings), rather than as key input variables in traffic speed prediction models.

[0082] The aforementioned multi-lane queuing path planning method, when determining the optimal driving path for vehicle queuing scenarios, acquires the starting performance data and current position of each vehicle in multiple queuing queues ahead of the vehicle. Based on the starting performance data of each queuing vehicle, it determines the travel time required for each vehicle to pass through the target intersection from its current position, thereby determining the estimated travel time for each corresponding vehicle. The lane with the shortest estimated travel time is then selected as the queuing lane. This method considers both the number of vehicles and the impact of the vehicles' starting performance, thus determining the shortest travel path, rather than simply determining the optimal lane based on the number of lanes ahead. This avoids the situation where the lane with the fewest lanes does not necessarily have the shortest travel time, enabling adaptive lane-changing optimization queuing strategies and improving the traffic efficiency of intelligent driving vehicles in queuing scenarios. Furthermore, this path planning method is deployable and scalable, applicable to scenarios such as intelligent parking, highway congestion queuing, and tollbooth queuing.

[0083] The following provides a method for determining the starting performance data of queued vehicles. In an exemplary embodiment, such as... Figure 2 As shown, it includes the following steps:

[0084] Step 202: Obtain multimodal information of each vehicle in the multiple queues of vehicles in front of the vehicle.

[0085] The multimodal information can include camera data and LiDAR data. Camera data can include features such as the vehicle's overall outline, front shape, and body lines, while LiDAR data can extract spatial features such as the vehicle's dimensions and surface shape. Both camera and LiDAR data can be used to identify vehicle types. To ensure accuracy, both data are combined for vehicle type identification, with LiDAR data used to assist in vehicle type classification.

[0086] For example, image data collected by a camera and three-dimensional point cloud data collected by a lidar are acquired. The contour features of vehicles queuing in the lane (such as the shape of the vehicle front, the color of the license plate, etc.) are identified from the image data, and the spatial features of each vehicle in the queue are extracted from the three-dimensional point cloud data.

[0087] Step 204: Identify the multimodal information to determine the vehicle type of the queuing vehicles.

[0088] For example, for each queue of vehicles, multimodal feature fusion is performed on the contour features and spatial features of the vehicles in the queue within the lane to obtain fused features. The fused features are then input into a trained classification model to output the corresponding vehicle type.

[0089] Step 206: Find the corresponding starting performance data from the preset correspondence table according to the vehicle type; the preset correspondence table stores the correspondence between different vehicle types and their corresponding starting performance data.

[0090] The pre-defined mapping table is determined based on vehicle type starting behavior modeling and can be represented as a "vehicle type → starting delay & acceleration" mapping model. The table includes starting performance data for different vehicle types, including behavioral characteristics such as average starting delay and 0–20 km / h acceleration. Different vehicle types can include, but are not limited to, buses, light trucks, taxis, SUVs, and private cars. Furthermore, the pre-defined mapping table can optimize data accuracy based on actual traffic conditions, enabling dynamic updates and self-learning to ensure data accuracy and reliability.

[0091] In this embodiment, by fusing LiDAR and camera to identify the vehicle type in the queuing lane, the estimated travel time of each lane can be predicted based on the vehicle type, thereby selecting the fastest possible route. This takes into account the impact of vehicle type on travel speed and avoids the problem that traditional methods cannot ensure traffic efficiency by selecting lanes based solely on the number of vehicles in the queue.

[0092] In an exemplary embodiment, the starting performance data includes the starting reaction time, the acceleration time required to accelerate from a standstill to a preset speed, and the acceleration. Based on the starting performance data, the travel time required for the queued vehicles to pass through the target intersection from the current position is determined, including: determining the travel distance between the current position and the target intersection; and predicting the travel time based on the travel distance, starting reaction time, acceleration time, and acceleration to obtain the travel time required for the queued vehicles to pass through the target intersection from the current position after starting under preset starting conditions.

[0093] For example, the travel distance between the current location and the target intersection is determined. The travel distance, start-up reaction time, acceleration time, and acceleration are input into a trained prediction model to predict the travel time required for queued vehicles to pass through the target intersection from the current location after starting under preset start-up conditions. For instance, the start-up time of the corresponding vehicle and the travel time required to pass through the target intersection from the current location can be calculated based on start-up performance data.

[0094] Furthermore, for each lane, the type and number of vehicles queuing in each lane are identified, and based on the prediction model, the time required for the Nth vehicle to start from the green light and pass through the target intersection is calculated. Then, by combining the traffic light cycle and the current signal phase, this vehicle-by-vehicle passage time is mapped onto the actual time axis, thereby estimating the overall estimated passage time of the vehicles currently queuing in each lane.

[0095] This implementation takes into account the differences in starting speed, reaction delay, and acceleration performance of different types of vehicles to determine the estimated travel time of the lane, which can improve traffic efficiency.

[0096] It is understood that vehicle queuing scenarios can include, but are not limited to, urban traffic light intersections, multi-lane straight / shared lanes, areas where bus lanes can be used, parking lot entrances and exits, ETC toll stations, and temporary construction detour points. In an exemplary embodiment, the estimated travel time of the lane ahead of a vehicle in a queuing scenario can be determined in the following way:

[0097] Based on the travel time of all vehicles in the queue, determine the estimated travel time for each corresponding lane, including: determining the lane control status for each lane; and based on the lane control status, determining the estimated travel time for the corresponding lane according to the travel time of each vehicle in the queue.

[0098] The lane control status includes at least whether the current phase is a traffic phase and the remaining duration of the current phase. Considering actual queuing scenarios, it is necessary to consider which vehicles can pass through in the current traffic phase within a preset cycle, and which vehicles cannot pass through within the remaining duration of the current traffic phase and can only be postponed to the next traffic phase. Therefore, in order to accurately determine the expected travel time of each lane, it is necessary to consider the current signal phase and the signal cycle. The signal cycle is different in different scenarios. For example, the signal cycle can be the traffic light cycle, that is, the changing cycle of red, yellow and green lights.

[0099] For example, if the current phase is a passage phase, the travel time of each vehicle in the queue is determined sequentially based on the remaining duration of the current phase. If the remaining duration is sufficient to allow all vehicles in the corresponding lane to pass, the travel time of each vehicle is mapped onto the real timeline, and the estimated passage time for the entire lane is calculated from the final passage times of all vehicles. For example, this could be the passage time of the last vehicle. If the remaining duration is insufficient to allow all vehicles in the queue to pass, the start time of the next passage phase for that lane is determined based on the signal cycle and phase order, and the queue dissipation time within the next passage phase is added to obtain the estimated passage time for the corresponding lane.

[0100] If the current phase is not a passing phase, determine the waiting time from the current time to the start time of the next passing phase of the lane, and add the time for all queued vehicles in the lane to be released in the next passing phase to obtain the estimated travel time of the vehicle in that lane.

[0101] Taking intelligent driving vehicles at urban traffic light intersections as an example, based on the lane control status, the estimated travel time of the corresponding lane is determined according to the travel time of each vehicle in each queue. This includes: obtaining the traffic light cycle and the control status of the traffic lights at the target intersection, and determining the lane control status corresponding to each lane based on the control status; and determining the estimated travel time of the corresponding lane based on the traffic light cycle and lane control status, according to the travel time of each vehicle in each queue.

[0102] The traffic light cycle can be signal cycle information, which may include cycle length, phase order, duration of green, yellow, and red lights for each phase, and switching rules between phases. For example, a signal cycle might be 90 seconds or 120 seconds. The phase order includes, for example, phase 1, phase 2, phase 3, etc. The duration of green, yellow, and red lights for each phase is, for example, phase 1: 40 seconds green + 3 seconds yellow + 2 seconds all red, phase 2: 35 seconds green + 3 seconds yellow + 2 seconds all red, and the switching rules between phases (e.g., fixed timing or adaptive timing).

[0103] Determining the lane control status of each lane based on the control status can be achieved by decomposing the phase signal of the traffic lights at the target intersection onto each lane. For ease of explanation, this example uses one lane as an example.

[0104] For example, the system obtains the traffic light cycle and current control status of the target intersection, maps the signal control status at the intersection level to each lane, thereby determining the lane control status of each lane at this moment, and then determines the lane control status corresponding to each lane based on the control status; based on the traffic light cycle and lane control status, the system determines the estimated travel time of the corresponding lane according to the travel time of each vehicle in each queue; and then, when a vehicle approaches the traffic light queuing area, the system dynamically calculates the estimated travel time of each selectable lane, selects the fastest lane, and automatically changes lanes to queue.

[0105] Furthermore, the lane control status includes at least whether the current phase is a traveling phase and the remaining duration of the current phase. Based on the traffic light cycle and lane control status, the estimated travel time for the corresponding lane is determined according to the travel time of each vehicle in each queue. This includes: starting from the second vehicle in the queue, determining the travel time required for the safe distance between each vehicle in the queue; if the current phase is a traveling phase, starting from the first vehicle in the queue, determining the estimated travel time for the corresponding lane based on the traffic light cycle, the remaining duration of the phase, the travel time of each vehicle in the queue, and the travel time. This method considers the travel time for the safe distance between vehicles in addition to the above-mentioned determination of the estimated travel time, and can accurately determine the lane with the shortest estimated travel time.

[0106] Based on the above-mentioned determination of the optimal lane considering vehicle starting performance data, to ensure the feasibility of the optimal lane, it is necessary to consider not only the queuing time but also whether the lane is suitable for this type of vehicle. Therefore, vehicle information is further considered. In an exemplary embodiment, a method for determining a queuing lane is provided, such as... Figure 3 As shown, it includes the following steps:

[0107] Step 302: Obtain vehicle information, which includes at least one of the following: actual travel direction, vehicle purpose, and lane width requirement.

[0108] It's understandable that vehicle sizes include various dimensions, such as small / medium / large / extra-long (tractor-trailer); vehicle uses can include buses, school buses, hazardous materials transport vehicles, trucks, ride-hailing vehicles, taxis, etc. Not all lanes are suitable for all vehicles. For example, right-turn lanes are not suitable for vehicles going straight, narrow lanes are not recommended for large trucks, pedestrian crossings near schools are generally not recommended for hazardous materials vehicles, and bus lanes have priority / are only open to buses.

[0109] Step 304: Based on the vehicle information, determine the set of candidate lanes from the lanes in the vehicle queuing area.

[0110] Among them, the candidate lanes in the candidate lane set must meet at least one or more of the following conditions: consistent actual traffic direction, lane-specific nature does not conflict with vehicle use, and lane width requirements are met.

[0111] Step 306: Based on the estimated travel time of each candidate lane in the candidate lane set, the lane with the shortest estimated travel time is designated as the queuing lane.

[0112] In this embodiment, a set of candidate lanes is determined from the lanes in the vehicle queuing area based on vehicle information. Based on the estimated travel time of each candidate lane in the candidate lane set, the lane with the shortest estimated travel time is designated as the queuing lane. By adding a dimension to the determination of the queuing lane, more complex decision-making can be accommodated.

[0113] In another exemplary embodiment, a method for determining a queuing lane is provided, such as... Figure 4 As shown, it includes the following steps:

[0114] Step 402: Determine the current lane where the vehicle is located.

[0115] Step 404: Determine the lane change cost data and safety risk indicators for changing lanes to other lanes based on the current lane.

[0116] The lane change cost data may include, but is limited to, at least one or more of the following: the number of lane changes required, the lane change distance, and the lane change time. Safety risk indicators may include, but are not limited to, pedestrian density (e.g., proximity to schools, crosswalks, etc.).

[0117] Step 406: For each of the other lanes, the estimated travel time, lane change cost data and safety risk indicators are weighted to obtain a weighted value, and the lane with the largest weighted value is determined as the queuing lane.

[0118] In this embodiment, the estimated travel time, lane change cost data, and safety risk indicators are weighted to obtain a weighted value. The lane corresponding to the maximum weighted value is determined as the queuing lane. Based on vehicle type, multi-objective comprehensive decision-making is carried out, which improves the reliability of the queuing lane.

[0119] In one exemplary embodiment, such as Figure 5 As shown, a multi-lane queuing path planning method is provided. This embodiment illustrates the method by applying it to vehicles. In this embodiment, the method includes the following steps:

[0120] Step 502: Obtain multimodal information of each vehicle in the multiple queues of vehicles in front of the vehicle.

[0121] Step 504: Identify the multimodal information to determine the vehicle type of the queuing vehicles.

[0122] Step 506: Find the corresponding starting performance data from the preset correspondence table according to the vehicle type; the preset correspondence table stores the correspondence between different vehicle types and their corresponding starting performance data.

[0123] Step 508: For each vehicle in each queue, determine the travel time required for the vehicle to pass through the target intersection from its current position based on the starting performance data.

[0124] Step 510: Determine the estimated travel time for each lane based on the travel time of all vehicles in the queue.

[0125] Step 512: Based on the estimated travel time of each lane, designate the lane with the shortest estimated travel time as the queuing lane.

[0126] It should be noted that the specific implementation method in this embodiment can be implemented in the manner described above, and will not be repeated here.

[0127] In an exemplary example, considering a smart driving vehicle waiting at a city traffic light, the vehicle enters a queuing recognition zone (e.g., 30–60m from the stop line). The LiDAR and camera integrated into the vehicle simultaneously scan multiple lanes ahead, acquiring multimodal information of each vehicle in the queue. This multimodal information is then identified to determine the vehicle type. Based on the vehicle type, corresponding starting performance data is retrieved from a pre-defined mapping table. The estimated travel time for each lane is calculated based on the starting performance data. The estimated travel times of each lane are compared, and the lane with the shortest estimated travel time is designated as the queuing lane and allowed to change lanes. A lane change decision is then issued. The safety strategy for allowing lane changes can be based on whether sufficient space is available for lane changing (e.g., vehicle speed <30km / h, no obstructions in left and right blind spots); and / or, setting a travel time difference threshold (e.g., more than 2 seconds better than the current path) before triggering a lane change.

[0128] The queuing recognition zone can be understood as the stage where vehicles are about to enter the intersection but have not yet fully merged into the static queue. It assesses the type and traffic efficiency of vehicles queuing in each lane ahead. Within the range corresponding to the queuing recognition zone, the queuing pattern at the intersection is basically formed and relatively stable, while vehicles still have the space and time to safely change lanes. This facilitates lane selection and lane-changing decisions without disrupting the queue order. By predicting traffic efficiency in advance within this recognition zone, lane-changing operations can be avoided after vehicles have entered the queue, thereby improving overall traffic efficiency and reducing safety risks.

[0129] In this embodiment, under the intelligent assisted driving scenario, by fusing LiDAR and cameras to identify the types of vehicles in the queuing lanes, and predicting the estimated travel time for each lane based on vehicle behavior modeling, the fastest possible route is selected. This enables adaptive lane-changing optimization of queuing strategies, improving the efficiency of intelligent driving vehicles at urban traffic lights. In other words, by upgrading from judging the number of vehicles to predicting traffic efficiency, waiting time caused by differences in the types of vehicles ahead is reduced, thus improving the travel experience.

[0130] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0131] Based on the same inventive concept, this application also provides a multi-lane queuing path planning device for implementing the multi-lane queuing path planning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the multi-lane queuing path planning device provided below can be found in the limitations of the multi-lane queuing path planning method described above, and will not be repeated here.

[0132] In one exemplary embodiment, such as Figure 6 As shown, a multi-lane queuing route planning device is provided, including: a data acquisition module 602, a duration prediction module 604, a travel duration determination module 606, and a lane planning module 608, wherein:

[0133] The data acquisition module 602 is used to acquire the starting performance data and current position of each vehicle in the queue of multiple vehicles in front of the vehicle.

[0134] The duration prediction module 604 is used to determine the travel time required for each vehicle in each queue to pass through the target intersection from its current position, based on the starting performance data.

[0135] The passage time determination module 606 is used to determine the estimated passage time of each lane based on the travel time of all vehicles in the queue.

[0136] The lane planning module 608 is used to designate the lane with the shortest expected travel time as the queuing lane based on the expected travel time of each lane.

[0137] The aforementioned multi-lane queuing path planning device, when determining the optimal driving path for vehicle queuing scenarios, acquires the starting performance data and current position of each vehicle in multiple queuing queues ahead of the vehicle. Based on the starting performance data of each queuing vehicle, it determines the travel time required for each vehicle to pass through the target intersection from its current position, and then determines the estimated travel time for each corresponding vehicle. From this, the lane with the shortest estimated travel time is selected as the queuing lane. This method considers both the number of vehicles and the impact of the vehicle's starting performance, thus determining the shortest travel path, rather than simply determining the optimal lane based on the number of lanes ahead. This avoids the situation where the lane with the fewest vehicles does not have the shortest travel time, enabling adaptive lane-changing optimization queuing strategies and improving the traffic efficiency of intelligent driving vehicles in queuing scenarios.

[0138] In one exemplary embodiment, the multi-lane queuing path planning device includes an identification module, which is used to acquire multimodal information of each queuing vehicle in multiple queuing vehicle queues ahead of the vehicle; identify the multimodal information to determine the vehicle type of the queuing vehicles.

[0139] The data acquisition module 602 is used to look up the corresponding starting performance data from a preset correspondence table according to the vehicle type; the preset correspondence table stores the correspondence between different vehicle types and their corresponding starting performance data.

[0140] In one exemplary embodiment, the duration prediction module 604 is used to determine the travel distance between the current location and the target intersection;

[0141] Based on the travel distance, start-up reaction time, acceleration time, and acceleration, the time required for queued vehicles to pass through the target intersection from their current position after starting under preset start-up conditions is predicted.

[0142] In one exemplary embodiment, the passage duration determination module 606 is used to determine the lane control status corresponding to each lane;

[0143] Based on the lane control status, the estimated travel time for the corresponding lane is determined according to the travel time of each vehicle in each queue.

[0144] In an exemplary embodiment, the passage duration determination module 606 is used to obtain the traffic light cycle and the control status of the traffic lights at the target intersection, and determine the lane control status corresponding to each lane based on the control status.

[0145] Based on the traffic light cycle and lane control status, the estimated travel time for the corresponding lane is determined according to the travel time of each vehicle in each queue.

[0146] In an exemplary embodiment, the passage time determination module 606 is used to determine the passage time required for each vehicle in the queue to travel a safe distance, starting from the second vehicle in the queue.

[0147] If the current phase is a passage phase, starting from the first vehicle in the queue, the estimated passage time for the corresponding lane is determined based on the traffic light cycle, remaining maintenance time, travel time of each vehicle in the queue, and passage time.

[0148] In one exemplary embodiment, the lane planning module 608 is used to obtain vehicle information, which includes at least the actual travel direction, vehicle purpose, and lane width requirement.

[0149] Based on vehicle information, a set of candidate lanes is determined from the lanes in the vehicle queuing area;

[0150] Based on the estimated travel time of each candidate lane in the candidate lane set, the lane with the shortest estimated travel time is designated as the queuing lane.

[0151] In one exemplary embodiment, lane planning module 608 is used to determine the current lane in which the vehicle is located;

[0152] Based on the current lane, determine the lane change cost data and safety risk indicators for changing lanes to other lanes;

[0153] For each of the other lanes, the estimated travel time, lane change cost data, and safety risk indicators are weighted to obtain a weighted value, and the lane with the largest weighted value is determined as the queuing lane.

[0154] Each module in the aforementioned multi-lane queuing path planning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the vehicle's processor in hardware form or independent of it, or stored in the vehicle's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0155] In one exemplary embodiment, a vehicle is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown, the vehicle includes a processor, memory, input / output interfaces, a communication interface, a display unit, and input devices. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input devices are also connected to the system bus via the input / output interfaces. The vehicle's processor provides computing and control capabilities. The vehicle's memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The vehicle's input / output interfaces are used for exchanging information between the processor and external devices. The vehicle's communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a multi-lane queuing path planning method. The vehicle's display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the vehicle can be a touch layer covering the display screen, or buttons, trackballs or touchpads set on the vehicle body, or external keyboards, touchpads or mice, etc.

[0156] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the vehicle to which the present application is applied. A specific vehicle may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0157] In one exemplary embodiment, a vehicle is provided, including a memory and a processor, the memory storing a computer program that the processor executes to implement the steps in the above-described method embodiments.

[0158] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0159] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with relevant regulations.

[0160] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0161] 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 application.

[0162] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A multi-lane queuing path planning method, characterized in that, The method includes: Obtain the starting performance data and current position of each vehicle in multiple queues ahead of the vehicle; For each vehicle in each queue of vehicles, the travel time required for the vehicle to pass through the target intersection from the current position is determined based on the starting performance data. Based on the travel time of all the vehicles in the queue, the estimated travel time for each corresponding lane is determined. Based on the estimated travel time of each lane, the lane with the shortest estimated travel time is designated as the queuing lane.

2. The method according to claim 1, characterized in that, The acquisition of starting performance data for each vehicle in multiple queues ahead of the vehicle includes: Acquire multimodal information of each vehicle in multiple queues ahead of the vehicle; The multimodal information is identified to determine the vehicle type of the queuing vehicles; The corresponding starting performance data is retrieved from a preset correspondence table based on the vehicle type; the preset correspondence table stores the correspondence between different vehicle types and their respective starting performance data.

3. The method according to claim 1, characterized in that, The starting performance data includes starting reaction time, acceleration time required to accelerate from a standstill to a preset speed, and acceleration. Determining the travel time required for the queued vehicles to pass the target intersection from their current position based on the starting performance data includes: Determine the current location and the travel distance to the target intersection; Based on the travel distance, the start-up reaction time, the acceleration time, and the acceleration, the time required for the queued vehicles to pass through the target intersection from the current position after starting under preset start-up conditions is predicted.

4. The method according to claim 1, characterized in that, The step of determining the estimated travel time for each lane based on the travel time of all vehicles in the queue includes: Determine the lane control status corresponding to each lane; Based on the lane control status, the estimated travel time for the corresponding lane is determined according to the travel time of each vehicle in each queue.

5. The method according to claim 4, characterized in that, The step of determining the estimated travel time for a corresponding lane based on the lane control status and the travel time of each vehicle in each queue includes: The traffic light cycle and the control status of the traffic lights at the target intersection are obtained, and the lane control status corresponding to each lane is determined based on the control status. Based on the traffic light cycle and the lane control status, the estimated travel time for the corresponding lane is determined according to the travel time of each vehicle in each queue.

6. The method according to claim 5, characterized in that, The lane control status includes at least whether the current phase is a travel phase and the remaining duration of the current phase. The step of determining the estimated travel time of the corresponding lane based on the traffic light cycle and the lane control status, according to the travel time of each vehicle in each queue, includes: Starting from the second vehicle in the queue, determine the travel time required for each vehicle in the queue to travel a safe distance. If the current phase is a passage phase, starting from the first vehicle in the queue, the estimated passage time for the corresponding lane is determined based on the traffic light cycle, the remaining maintenance duration, the travel time of each vehicle in the queue, and the passage time.

7. The method according to any one of claims 1 to 6, characterized in that, The step of designating the lane with the shortest estimated travel time as the queuing lane based on the estimated travel time of each lane includes: Obtain vehicle information for the vehicle, which includes at least the actual direction of travel, vehicle purpose, and required lane width. Based on the vehicle information, a set of candidate lanes is determined from the lanes in the vehicle queuing area; Based on the estimated travel time of each candidate lane in the candidate lane set, the lane with the shortest estimated travel time is designated as the queuing lane.

8. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Determine the current lane where the vehicle is located; Based on the current lane, determine the lane change cost data and safety risk indicators for changing lanes to other lanes; For each of the other lanes, the estimated travel time, lane change cost data, and safety risk indicators are weighted to obtain a weighted value, and the lane with the largest weighted value is determined as the queuing lane.

9. A multi-lane queuing path planning device, characterized in that, The device includes: The data acquisition module is used to acquire the starting performance data and current position of each vehicle in multiple queues of vehicles ahead of the vehicle. The time prediction module is used to determine the travel time required for each vehicle in each queue of vehicles to pass through the target intersection from the current position, based on the starting performance data. The passage time determination module is used to determine the estimated passage time of each corresponding lane based on the travel time of all the vehicles in the queue. The lane planning module is used to designate the lane with the shortest expected travel time as the queuing lane based on the expected travel time of each lane.

10. A vehicle comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

Images