Public transportation managing system

Abstract

A public transport management system includes a plurality of roadside units. Each roadside unit includes a roadside controller, a roadside sensor, and a roadside communication module. Each roadside controller includes a roadside processor and a roadside storage medium, and each roadside storage medium is used to store the roadside management module. Based on the roadside management module, the roadside controller is used to: generate a predicted scenario for a roadside area based on roadside sensor information; generate a broadcast message at a broadcast time point based on the predicted scenario and its priority marker or timeliness marker; and transmit the broadcast message to a plurality of vehicles at the broadcast time point. This helps to further achieve second-level policy execution.

Description

Public Transportation Management System PUBLIC TRANSPORTATION MANAGING SYSTEM Technical Field

[0001] This disclosure relates to a public transport management system, and more particularly to a public transport management system that utilizes roadside units. Prior Technology

[0002] With the development of science and technology, more and more advanced technologies are being applied to the field of public transportation. However, the existing public transportation management systems and methods are still inadequate.

[0003] For example, existing technologies mostly focus on single vehicle control, local demand forecasting, or cloud-based scheduling, lacking the ability to dynamically schedule across the entire domain by combining roadside unit (RSU) edge inference, cloud-based AI (Artificial Intelligence) reinforcement learning, passenger demand analysis, and V2X (Vehicle-to-everything) real-time communication. Therefore, existing technologies typically cannot react to traffic events or fluctuations in passenger demand within seconds, and also lack event-triggered communication mechanisms, bandwidth optimization, and intra-fleet collaborative control.

[0004] Based on the above, the current market for public transport management systems and methods urgently needs public transport management systems and methods that can respond to traffic events or passenger demand fluctuations in seconds, have event-triggered communication mechanisms, bandwidth optimization, and in-fleet collaborative control. Summary of the Invention

[0005] This disclosure provides a public transport management system that includes generating a predicted scenario for a roadside area based on roadside sensing information, and generating a priority marker or a time-limit marker for the predicted scenario. The system then transmits broadcast messages to a plurality of vehicles at broadcast times based on the predicted scenario and its priority marker or time-limit marker. This enables real-time environmental perception, event detection, and scenario prediction through edge AI of the roadside unit, which helps to further achieve second-level strategy execution and closed-loop control, and can reduce communication load through event-triggered broadcasting.

[0006] According to one embodiment of this disclosure, a public transport management system is provided, comprising a plurality of roadside units. Each roadside unit includes a roadside controller, a roadside sensor, and a roadside communication module. The roadside controller, roadside sensor, and roadside communication module of each roadside unit are communicatively connected. Each roadside controller includes a roadside processor and a roadside storage medium, and each roadside storage medium is used to store a roadside management module. Based on the roadside management module, the roadside controller is used to: acquire a plurality of roadside sensing information of a roadside area at a plurality of time points through the roadside sensor; generate a predicted scenario of the roadside area based on the roadside sensing information through at least one of the roadside controllers; generate a priority mark or a time-limit mark for the predicted scenario through at least one of the roadside controllers; generate a broadcast message at a broadcast time point based on the predicted scenario and its priority mark or time-limit mark through at least one of the roadside controllers; and transmit the broadcast message to a plurality of vehicles at the broadcast time point through at least one of the roadside communication modules.

[0007] In the embodiments of the public transport management system described above, a predicted scenario can be obtained through a long short-term memory algorithm in at least one roadside management module of at least one of the roadside controllers, and the time of the predicted scenario can be between 2 seconds and 7 seconds.

[0008] In an embodiment of the public transport management system described above, a public transport fleet may include vehicles, and each vehicle may have an autonomous driving function.

[0009] In embodiments of the public transport management system described above, a cloud server may be further included, comprising a cloud processor, a cloud storage medium, and a cloud communication module. The cloud server is communicatively connected to the roadside unit, and the cloud processor, cloud storage medium, and cloud communication module are communicatively connected. The cloud storage medium is used to store a cloud management module. Based on the cloud management module, the cloud server can be used to: receive roadside sensing information, multiple vehicle sensing information, and at least one demand message from at least one user through the cloud communication module, wherein the vehicle sensing information is acquired at a given time by multiple vehicle sensors of each vehicle; generate a feature event based on the roadside sensing information, vehicle sensing information, and at least one demand message, which includes multiple features, including multiple safety features; determine whether any of the features has reached a corresponding trigger threshold; when any of the features reaches the corresponding trigger threshold, generate a processing strategy and generate at least one action list for at least one of the roadside unit and the vehicle according to the processing strategy; and transmit the at least one action list to the roadside unit and the vehicle through the cloud communication module.

[0010] In the embodiments of the public transportation management system described above, feature events can be generated through a near-end policy optimization algorithm or a deep Q-network algorithm in the cloud management module.

[0011] In the embodiments of the public transport management system described above, based on the roadside management module, the roadside controller can be used to transmit roadside sensing information to the cloud server after data anonymization processing.

[0012] In the embodiments of the public transport management system described above, based on the roadside management module, the roadside controller can be used to transmit roadside sensing information to a cloud server after preliminary data aggregation processing.

[0013] In embodiments of the public transportation management system described above, the features may further include multiple vehicle dispatch features. Based on a cloud management module, the cloud server can be used to: generate a vehicle dispatch plan based on feature events, and generate multiple driving schedules for each vehicle based on the vehicle dispatch plan; and transmit each driving schedule to the corresponding vehicle through a cloud communication module.

[0014] In the aforementioned embodiments of the public transport management system, the vehicle dispatch plan can be updated at a dispatch update time, which is between 1 minute and 10 minutes. The feature further includes a hotspot grid, which is used to determine the transport demand intensity of multiple stations or multiple road segments.

[0015] In the embodiments of the public transport management system described above, based on the cloud management module, the cloud server can be used to: perform a risk check before a vehicle dispatch plan is generated, the risk check including checking at least one of a stop safety and a minimum time slot, in order to generate a vehicle dispatch plan.

[0016] In the embodiments of the public transportation management system described above, based on the cloud management module, the cloud server can be used to: perform a contradiction and distortion check before the vehicle scheduling plan is generated. The contradiction and distortion check includes checking whether a draft vehicle scheduling plan satisfies at least one of a contradiction condition and a distortion condition. When the draft vehicle scheduling plan satisfies at least one of the contradiction condition and the distortion condition, the generated vehicle scheduling plan is a conservative vehicle scheduling plan. Simple Explanation of the Diagram

[0017] Figure 1A is a block diagram of the public transportation management system of the first embodiment of this disclosure; Figure 1B illustrates the operational status of the public transportation management system in Figure 1A; and Figure 2 illustrates a flowchart of a public transportation management method according to a second embodiment of the present disclosure. Implementation

[0018] The embodiments of this disclosure will now be described with reference to the drawings. For clarity, many practical details will be described in the following description. However, it should be understood that these practical details should not be used to limit the scope of this disclosure. That is, these practical details are not essential in the embodiments of this disclosure. Furthermore, for the sake of simplicity, some conventional structures and elements will be shown in a simple schematic manner in the drawings; and repeated elements may be represented by the same number.

[0019] Furthermore, the terms "first" and "second" are used only to describe different components and do not restrict the components themselves. Therefore, the first component can also be referred to as the second component. Moreover, the combination of components in this article is not a combination that is generally known, conventional, or familiar in this field. Whether the components themselves are familiar cannot be used to determine whether their combination relationship is easily completed by someone with ordinary knowledge in the technical field.

[0020] Figure 1A illustrates a block diagram of the public transport management system 100 according to the first embodiment of this disclosure, and Figure 1B illustrates a schematic diagram of the public transport management system 100 in use as shown in Figure 1A. Referring to Figures 1A and 1B, the public transport management system 100 includes a plurality of roadside units 130. Each roadside unit 130 includes a roadside controller 131, a roadside sensor 138, and a roadside communication module 137. The roadside controller 131, roadside sensor 138, and roadside communication module 137 of each roadside unit 130 are communicatively connected. Each roadside controller 131 includes a roadside processor 132 and a roadside storage medium 133. Each roadside storage medium 133 is used to store a roadside management module 134. Specifically, each roadside storage medium 133 is nonvolatile memory, also known as non-temporary computer-readable memory, and each roadside management module 134 is program code. Furthermore, each roadside unit 130 may include a plurality of roadside sensors 138, which may be cameras, radars, or not limited thereto.

[0021] Figure 2 illustrates a flowchart of the public transportation management method 200 according to the second embodiment of this disclosure. Please refer to Figures 1A, 1B, and 2, and use the public transportation management method 200 of the second embodiment of this disclosure to further illustrate the public transportation management system 100 of the first embodiment. It should be understood that the public transportation management system 100 of the first embodiment is not limited to implementing the public transportation management method 200 of the second embodiment, and the public transportation management method 200 of the second embodiment is not limited to being implemented using the public transportation management system 100 of the first embodiment.

[0022] Based on the roadside management module 134, the roadside controller 131 executes steps 210, 215, 220, 225, and 230 of the public transport management method 200. Step 210 includes acquiring multiple roadside sensing information of a roadside area 610 at multiple time points through the roadside sensor 138, including, but not limited to, information on pedestrian, vehicle 550, and obstacle identification. Step 215 includes generating a predicted situation (predicted state) of the roadside area 610 based on the roadside sensing information through at least one of the roadside controllers 131. Step 220 includes generating a priority marker or a time-limit marker for the predicted situation through at least one of the roadside controllers 131. Step 225 includes generating a broadcast message at a broadcast time point based on the predicted situation and its priority marker or time-limit marker through at least one of the roadside controllers 131. The broadcast message may include signal phase transition warnings, event triggers, and is not limited to these. Step 230 includes transmitting a broadcast message to a plurality of vehicles 550 at the broadcast time point via at least one of the roadside communication modules 137. Thereby, real-time environmental perception, event detection and situation prediction through the edge AI of the roadside unit 130 can help to further realize second-level policy execution and closed-loop control, and can reduce communication load through event-triggered broadcasting.

[0023] Specifically, in step 215, the public transport management system 100 can obtain a predicted scenario through a Long Short-Term Memory (LSTM) algorithm in at least one of the roadside management modules 134 of the roadside controller 131. The prediction scenario is calculated from the time the roadside sensing information is acquired, and the prediction scenario time can be between 2 seconds and 7 seconds. This allows for improved prediction accuracy and reduced communication load by utilizing edge AI. Furthermore, the prediction scenario time can be between 3 seconds and 5 seconds.

[0024] A public transport fleet 500 may include vehicles 550, and each vehicle 550 may have an autonomous driving function. Thus, the public transport management system 100 according to this disclosure can achieve second-level response to traffic events or passenger demand fluctuations, event-triggered communication mechanisms, bandwidth optimization, and intra-fleet collaborative control. Furthermore, the vehicles 550 in the public transport fleet 500 may be motorcycles, cars, buses, or trucks, and are not limited thereto. Each vehicle 550 includes an on-board unit (OBU) 551, a vehicle sensor 558, and a vehicle communication module 557. The OBU 551, vehicle sensor 558, and vehicle communication module 557 of each vehicle 550 are communicatively connected. Each OBU 551 includes an on-board processor 552 and an on-board storage medium 553, and each on-board storage medium 553 is used to store an on-board management module 554. Based on the vehicle management module 554, the vehicle unit 551 can be used to implement the public transportation management method 200. Specifically, each vehicle storage medium 553 is non-volatile memory, and each vehicle management module 554 is program code. Furthermore, each vehicle unit 551 may include a plurality of vehicle sensors 558, which may be cameras, radars, or not limited thereto.

[0025] The public transport management system 100 may further include a cloud server 110, which includes a cloud processor 112, a cloud storage medium 113, and a cloud communication module 117. The cloud server 110 is communicatively connected to the roadside unit 130 and the vehicle 550. The cloud processor 112, cloud storage medium 113, and cloud communication module 117 are also communicatively connected. The cloud storage medium 113 stores a cloud management module 114. Specifically, the cloud storage medium 113 is non-volatile memory, and the cloud management module 114 contains code and includes a cloud AI module. The cloud communication module 117, the roadside communication module 137, and the vehicle communication module 557 all support the V2X communication protocol, which includes message types such as passenger requests, fleet operation instructions, traffic incident alerts, and vehicle status feedback, thereby helping to support event-triggered message transmission and bandwidth optimization.

[0026] Based on the cloud management module 114, the cloud server 110 can be used to execute steps 240, 245, 250, 255, 260, and 265 of the public transportation management method 200. Step 240 includes acquiring multiple vehicle sensing information at a given time point through multiple vehicle sensors 558 of the vehicle 550. Step 245 includes receiving roadside sensing information, multiple vehicle sensing information, and at least one request message from at least one user 700 via at least one electronic device 770 through the cloud communication module 117. Specifically, the user 700's request message includes, but is not limited to, historical ride data, weather, activity, application query traffic, cross-data source time alignment, and feature engineering. Furthermore, step 245 may also include receiving the vehicle speed, acceleration, location, occupancy rate, driving intention, and control status of the vehicle 550 through the cloud communication module 117.

[0027] Step 250 includes generating a feature event based on roadside sensing information, vehicle sensing information, and at least one demand message, which includes multiple features, including multiple safety features. Step 255 includes determining whether any of the features has reached a corresponding trigger threshold. If any of the features reaches the corresponding trigger threshold, then step 260 is executed; if any of the features has not reached the corresponding trigger threshold, then steps 245 and 250 are returned to be executed.

[0028] Step 260 includes generating a processing strategy and, based on the processing strategy, generating at least one action list for at least one of the roadside unit 130 and vehicle 550. Step 265 includes transmitting the at least one action list to at least one of the roadside unit 130 and vehicle 550 via cloud communication module 117. Specifically, characteristic events can be categorized based on their characteristics into passenger demand, fleet operation instructions, traffic incident alerts, and vehicle status feedback. Thus, the public transport management system 100 is a smart public transport full-domain dynamic management system, particularly an integrated public transport full-domain dynamic management system based on roadside unit edge AI, cloud AI reinforcement learning, V2X communication protocols, and on-board units. The public transport management system 100 can achieve cross-level closed-loop collaborative control and second-level event response, as well as optimal allocation of public transport resources and fleet operation control, further improving transport efficiency, safety, and passenger experience through real-time situational awareness, passenger demand prediction, event triggering mechanisms, and adaptive reinforcement learning algorithms. Furthermore, the on-board unit 551 can issue longitudinal and lateral control targets (such as acceleration / deceleration, lane changing, and following distance) within 1 second after receiving the policy. The public transport fleet 500 can coordinate V2V (Vehicle-to-Vehicle) control within the fleet to stabilize spacing and energy consumption, and can also provide feedback data to form a closed-loop self-correction and policy adaptive adjustment. In addition, in step 215 of the public transport management method 200 according to the present disclosure, the cloud server 110 can generate a predicted scenario for the roadside area 610 based on roadside sensing information, vehicle sensing information, and user demand information, and then proceed to steps 220, 225, and 230.

[0029] In short, in the architecture of the public transport management system 100, the roadside units 130, vehicles 550, and the electronic devices 770 of users 700 serve as the data acquisition layer; the cloud server 110 serves as the cloud-based intelligent decision-making layer; the public transport fleet 500 and its vehicles 550 serve as the execution layer; and the V2X communication protocol layer (or extended communication layer) provides communication between the aforementioned three layers and serves as a key avoidance point. The data acquisition layer simultaneously collects road condition and demand information and sends it to the cloud-based intelligent decision-making layer. The cloud-based intelligent decision-making layer calculates and integrates this information to generate a control strategy, which is then distributed to the execution layer through the communication protocol layer.

[0030] In steps 210 and 245, based on the roadside management module 134, the roadside controller 131 can transmit roadside sensing information to the cloud server 110 after data anonymization processing. This enhances privacy protection.

[0031] In steps 210 and 245, based on the roadside management module 134, the roadside controller 131 can transmit roadside sensing information to the cloud server 110 after preliminary data aggregation processing. In this way, only necessary data is uploaded to reduce communication load.

[0032] In step 250, the public transport management system 100 can generate characteristic events through a Proximal Policy Optimization (PPO) algorithm or a Deep Q-Network (DQN) algorithm in the cloud management module 114. Thereby, the cloud management module 114 uses a reinforcement learning scheduling engine based on the PPO algorithm and / or the DQN algorithm, combined with cloud AI, to predict passenger demand, generate strategies, and schedule fleets. Instructions are then sent to the onboard unit 551 via the V2X communication protocol. This enables second-level strategy execution and closed-loop control, while generating fleet strategies based on service punctuality rate, passenger waiting time, and safety margin. Specifically, compared to existing technologies, the public transport management system 100 can reduce average passenger waiting time by more than 30%, reduce fleet spacing variation by more than 30%, increase traffic speed by more than 25%, and improve vehicle utilization by more than 20%.

[0033] The features may include multiple vehicle dispatch features. Based on the cloud management module 114, the cloud server 110 can be used to execute steps 280 and 285 of the public transport management method 200. Step 280 includes generating a vehicle dispatch plan based on feature events, and generating multiple driving schedules for each vehicle 550 based on the vehicle dispatch plan. Step 285 includes transmitting each driving schedule to the corresponding vehicle 550 via the cloud communication module 117. This helps the vehicle dispatch plan respond to traffic events or fluctuations in passenger demand within seconds. In addition, the cloud management module 114 may include a collaborative control engine to perform queue synchronization, intelligent lane changing, obstacle response strategies, and dispatch strategy consistency checks.

[0034] In step 250, the features further include a hotspot grid, which is used to determine the transport demand intensity of multiple stations or multiple road segments. In step 280, the vehicle scheduling plan can be updated at a scheduling update time, which is between 1 minute and 10 minutes. Therefore, the cloud management module 114 includes a demand prediction engine that can generate the transport demand intensity of stations or road segments through rolling predictions (e.g., 5 minutes, 1 hour, 1 day, and not limited to these) using a deep neural network (DNN) and a hierarchical long short-term memory hotspot grid.

[0035] In step 280, based on the cloud management module 114, the cloud server 110 can be used to: perform a risk check before the vehicle dispatch plan is generated. The risk check includes checking at least one of a stop safety and a minimum time slot to generate the vehicle dispatch plan. This improves public transport safety.

[0036] In step 280, based on the cloud management module 114, the cloud server 110 can be used to: perform a contradiction and distortion check before the vehicle scheduling plan is generated. The contradiction and distortion check includes checking whether a draft vehicle scheduling plan satisfies at least one of a contradiction condition and a distortion condition. When the draft vehicle scheduling plan satisfies at least one of the contradiction condition and the distortion condition, the generated vehicle scheduling plan is a conservative vehicle scheduling plan. This balances convenience and security.

[0037] Regarding the public transport management method 200 of the second embodiment of this disclosure, the public transport management method 200 includes steps 210, 215, 220, 225, and 230. Step 210 includes acquiring multiple roadside sensing information of a roadside area 610 at multiple time points through at least one roadside sensor 138 of at least one roadside unit 130. Step 215 includes generating a predicted scenario for the roadside area 610 based on the roadside sensing information through at least one roadside controller 131 of at least one roadside unit 130. Step 220 includes generating a priority flag or a time-limit flag for the predicted scenario through at least one roadside controller 131. Step 225 includes generating a broadcast message at a broadcast time point through at least one roadside controller 131 based on the predicted scenario and its priority flag or time-limit flag. Step 230 includes transmitting the broadcast message to multiple vehicles 550 at the broadcast time point through at least one roadside communication module 137 of at least one roadside unit 130. This helps to further achieve second-level policy execution and closed-loop control.

[0038] For further details regarding the public transportation management method 200 of the second embodiment, please refer to the content of the public transportation management system 100 of the first embodiment, which will not be described in detail here.

[0039] Although the present disclosure has been described above with reference to embodiments, it is not intended to limit the present disclosure. Anyone skilled in the art may make various modifications and alterations without departing from the spirit and scope of the present disclosure. Therefore, the scope of protection of the present disclosure shall be determined by the appended claims.

[0040] 100: Public Transportation Management System 110: Cloud Server 112: Cloud Processor 113: Cloud storage media 114: Cloud Management Module 117: Cloud Communication Module 130: Roadside Unit 131: Roadside Controller 132: Roadside Processor 133: Roadside storage media 134: Roadside Management Module 137: Roadside communication module 138: Roadside sensor 200: Public Transportation Management Methods 210,215,220,225,230,240,245,250,255,260,265,280,285: Steps 500: Public Transport Fleet 550: Vehicle 551: Vehicle-mounted unit 552: Vehicle Processor 553: In-vehicle storage media 554: Vehicle Management Module 557: Vehicle Communication Module 558: Vehicle Sensor 610: Roadside area 700: User 770: Electronic devices

Claims

1. A public transport management system, comprising: a plurality of roadside units, wherein each roadside unit includes a roadside controller, a roadside sensor, and a roadside communication module, the roadside controller, the roadside sensor, and the roadside communication module of each roadside unit being communicatively connected, each roadside controller including a roadside processor and a roadside storage medium, each roadside storage medium being used to store a roadside management module; wherein, Based on these roadside management modules, the roadside controllers are used to: acquire multiple roadside sensing information of a roadside area at multiple time points through the roadside sensors; generate a predicted scenario for the roadside area based on the roadside sensing information through at least one of the roadside controllers; generate a priority marker or a time-limit marker for the predicted scenario through the at least one of the roadside controllers; generate a broadcast message at a broadcast time point based on the predicted scenario and its priority marker or time-limit marker through the at least one of the roadside controllers; and transmit the broadcast message to multiple vehicles at the broadcast time point through at least one of the roadside communication modules.

2. The public transport management system as described in claim 1, wherein the predicted scenario is obtained through a long short-term memory algorithm in at least one of the roadside management modules of the roadside controllers, the predicted scenario being between 2 seconds and 7 seconds.

3. The public transport management system as described in claim 1, wherein a public transport fleet comprises the vehicles, and each vehicle has an autonomous driving function.

4. The public transportation management system as described in claim 3 further comprises: a cloud server including a cloud processor, a cloud storage medium, and a cloud communication module, wherein the cloud server is communicatively connected to the roadside units, and the cloud processor, the cloud storage medium, and the cloud communication module are communicatively connected, the cloud storage medium being used to store a cloud management module; wherein, Based on the cloud management module, the cloud server is used to: receive roadside sensing information, multiple vehicle sensing information, and at least one request message from at least one user through the cloud communication module, wherein the vehicle sensing information is acquired by multiple vehicle sensors of the vehicles at those points in time; generate a feature event based on the roadside sensing information, the vehicle sensing information, and the at least one request message, which includes multiple features, including multiple safety features; determine whether any of the features has reached a corresponding trigger threshold; when any of the features reaches the corresponding trigger threshold, generate a processing strategy, and generate at least one action list for at least one of the roadside units and at least one of the vehicles based on the processing strategy; and transmit the at least one action list to the roadside units and at least one of the vehicles through the cloud communication module.

5. The public transport management system as described in claim 4, wherein the characteristic event is generated through a near-end policy optimization algorithm or a deep Q-network algorithm in the cloud management module.

6. The public transport management system as described in claim 4, wherein, based on the roadside management modules, the roadside controllers are used to: transmit the roadside sensing information to the cloud server after data anonymization processing.

7. The public transport management system as described in claim 4, wherein, based on the roadside management modules, the roadside controllers are used to: transmit the roadside sensing information to the cloud server after preliminary data aggregation processing.

8. A public transport management system as described in claim 4, wherein these features further include a plurality of vehicle dispatching features; wherein, Based on the cloud management module, the cloud server is used to: generate a vehicle scheduling plan based on the characteristic event, and generate multiple driving schedules for the vehicles based on the vehicle scheduling plan; and transmit each driving schedule to the corresponding vehicle through the cloud communication module.

9. The public transportation management system as described in claim 8, wherein the vehicle dispatch plan is updated at a dispatch update interval between 1 minute and 10 minutes; wherein, These features also include a hotspot grid, which is used to determine the intensity of transport demand for multiple stations or multiple road segments.

10. The public transport management system as described in claim 8, wherein, based on the cloud management module, the cloud server is used to: perform a risk check before the vehicle dispatch plan is generated, the risk check including checking at least one of a stop safety and a minimum time slot, in order to generate the vehicle dispatch plan.

11. The public transport management system as described in claim 8, wherein, based on the cloud management module, the cloud server is configured to: perform a contradiction and distortion check before the vehicle dispatch plan is generated, the contradiction and distortion check comprising checking whether a draft vehicle dispatch plan satisfies at least one of a contradiction condition and a distortion condition, and when the draft vehicle dispatch plan satisfies at least one of the contradiction condition and the distortion condition, the generated vehicle dispatch plan is a conservative vehicle dispatch plan.

Images