System and method for guiding pedestrian for balancing congestion

Abstract

To provide a congestion control system configured to guide a pedestrian in order to balance a congestion over multiple areas in a controlled environment.SOLUTION: A congestion control system is operably connected to a plurality of sensors and a pedestrian guiding device. Each sensor is configured to capture measurement values corresponding to pedestrian congestion levels in various places in a controlled environment. These measurement values are provided to the congestion control system. The congestion control system uses the measurement values to calculate a pedestrian traffic flow in various places in the controlled environment. Next, the congestion control system determines a control command using the calculated traffic flow and the measured congestion level. The control command is provided to the pedestrian guiding device to configure the pedestrian guiding device so as to balance and / or reduce a congestion by providing a guiding output to the pedestrian in the controlled environment.SELECTED DRAWING: Figure 1B

Description

[Technical field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates generally to pedestrian guidance, and more specifically to systems and methods for routing pedestrians to balance congestion levels. [Background technology]

[0002] Crowd management is an important aspect of ensuring safety at large gatherings and in busy places such as transport hubs (including railway stations, bus stations, airports, etc.). Furthermore, balanced crowding levels across different walkways increase the average walking speed of pedestrians and allow traffic flow to be maintained efficiently. Equalizing crowding levels at railway stations is particularly important because uneven crowding levels at platforms reduce passenger throughput due to variations in boarding times in different parts of the train. Unbalanced passenger crowding levels can also lead to uneven passenger occupancy in individual cars.

[0003] Traditionally, pedestrians traveling in a railroad station are not aware of the congestion levels in different areas of the railroad station or different parts of the platform. For example, passengers in a railroad station concourse often cannot see the congestion level of a platform that requires the passenger to go up or down stairs. Therefore, the pedestrian cannot make an informed decision to wait in a part of the platform that is less crowded.

[0004] Therefore, there is a need to overcome the above-mentioned problems with crowd control and congestion balancing. More specifically, there is a need to develop a method and system for directing pedestrians towards less crowded parts of the platform and / or less crowded sidewalks to increase boarding efficiency and people handling capacity. Summary of the Invention

[0005] The present disclosure is generally directed to a crowd control system configured to guide pedestrians to balance crowding throughout an area of ​​a controlled environment, such as a train station. The crowd control system is operatively connected to a plurality of sensors (e.g., occupancy sensors, motion sensors, etc.) and pedestrian guidance devices (e.g., arrow displays, speaker systems, lighting systems, etc.). The sensors are configured to capture measurements corresponding to pedestrian crowding levels at various locations within the controlled environment. These measurements are provided to the crowd control system. The crowd control system uses the captured measurements to determine pedestrian traffic flows at various locations of the controlled environment. The crowd control system then uses the measured crowding levels and the determined traffic flows to determine control commands. The control commands are provided to the pedestrian guidance devices (e.g., visual displays, speaker systems, lighting systems, etc.) to configure the devices to provide guidance outputs to pedestrians in the controlled environment to balance and / or reduce crowding.

[0006] Uncontrolled traffic flow can lead to congestion in a controlled environment. Traffic flow and / or pedestrian traffic flow, as used herein, refers to the movement of people in a public space. Many aspects can affect traffic flow, such as the volume, density, and walking speed of pedestrians, as well as the timing and coordination of signals to control traffic flow. Congestion, on the other hand, refers to a state of excessive overcrowding or obstruction that prevents the smooth flow of traffic, such as pedestrian traffic. Congestion can occur on roads, highways, intersections, or public spaces with a high volume of pedestrians.

[0007] Some embodiments of the present disclosure are based on the recognition that, although many techniques can be used to control traffic flow, many practical applications require controlling congestion rather than traffic flow itself. Thus, there is a need for methods designed to control congestion at one or more locations in an environment in addition to or instead of methods designed to control traffic flow.

[0008] Some embodiments of the present disclosure are based on the realization that traffic flow and congestion can be considered as states of a system of dynamics of crowd behavior in a controlled environment. Such a dynamic system is a virtual system of crowd flow and pedestrian circulation dynamics, but treating crowd behavior as a dynamic system allows some embodiments to apply control theory to manage congestion.

[0009] Therefore, an objective of some embodiments of the present disclosure is to provide a model of the system of crowd behavior dynamics in an area under control. This model may be referred to as a crowd model. The crowd model may be configured to describe pedestrian movement into, out of, and within the environment. Additionally or alternatively, an objective of some embodiments is to provide a model of the system that captures the dynamics of pedestrian behavior influenced by the guidance output of pedestrian guidance devices arranged to affect the controlled area. Examples of pedestrian guidance devices may include display devices that display configurable signs (such as arrows) to guide pedestrians, speakers that output audio instructions, and lighting fixtures that affect traffic flow with light intensity. All these outputs of various types of devices can be treated as control inputs to the model of the dynamic system that captures the crowd dynamics.

[0010] Some embodiments of the present disclosure are based on the realization that traffic flow can be considered as a transient state of a dynamical system of crowd behavior, whereas congestion can be considered as a steady state of this dynamical system. A dynamical system, as used herein, is a system in which a function describes the time-dependence of a point in the relevant space. By treating congestion as a steady state of this system, some embodiments are based on the realization that a model of congestion must describe the time-dependence of congestion on traffic flow, rather than the inverse way (using a traffic flow model to describe the time-dependence of traffic flow on congestion). Such a model is referred to herein as a congestion model.

[0011] Therefore, in an uncontrolled situation, the congestion model links the next state of congestion to the current state of congestion, which is influenced by the current state of the traffic flow. In a controlled situation (such as an environment including a pedestrian guidance device that guides pedestrians), the congestion model links the next state of congestion to the current state of congestion, which is influenced by the current state of the traffic flow, which is influenced by the guidance output of the pedestrian guidance device. According to control theory, the congestion model can be used to efficiently control congestion by optimizing the control commands that define the guidance output of the output device. This is advantageous because it allows optimizing the operation of the pedestrian guidance device at the current time and / or within a prediction horizon.

[0012] Some further embodiments are based on the understanding that pedestrians do not follow the routing instructions of the guidance output as faithfully as they do in vehicle movement control. However, this drawback can be turned into an advantage if the relationship between the routing instructions and the percentage of pedestrians who follow these instructions is known, since in a congestion control setting, only a certain percentage of pedestrians may need to be diverted from popular routes. This percentage of pedestrians is unknown, but can also be learned as a function of traffic flow.

[0013] Some embodiments are based on the recognition that the percentage of pedestrians who will change direction based on the routing instructions depends on the presentation characteristics of the routing instructions. For example, if the routing instructions are executed by displaying an arrow pointing to a desired walking direction, the display parameters may include one or a combination of the intensity, size, color, and visual effect of displaying the arrow on the display device. Some embodiments are based on the recognition that the relationship between the display parameters and the percentage of pedestrians affected by the displayed routing instructions is not linear, but also depends on the details of the traffic flow and the controlled environment. For example, the intensity of the displayed arrow pointing to a particular direction for one value of traffic flow may affect a different percentage of pedestrians than the same arrow with the same intensity by being displayed during different traffic flow densities. However, parameterized guidance output functions for traffic flow can be learned for each location and / or for each particular controlled environment.

[0014] As a result, some embodiments are based on the recognition that the presentation characteristics of routing instructions and guidance outputs can be determined based on current traffic flow using functions learned from historical measurements observed in a particular controlled environment.

[0015] In general, in one aspect, a congestion control system for controlling congestion in a controlled environment is provided. The congestion control system is operatively connected to one or more sensors via one or a combination of wired and wireless communication channels. The one or more sensors are configured to collect measurements indicative of traffic flow in the controlled environment.

[0016] The crowd control system is also operatively connected to a pedestrian guidance device positioned to affect the controlled environment.

[0017] The congestion control system includes at least one processor, the congestion control system further including a memory having instructions stored thereon that, when executed by the processor, cause the congestion control system to (1) collect measurements indicative of a current state of traffic flow in the controlled environment, (2) generate control commands for the pedestrian guidance device by optimizing a cost function including a congestion model of a system of dynamics of crowd behavior in the controlled environment, the congestion model linking a next state of congestion to a current state of congestion affected by a current state of traffic flow affected by the pedestrian guidance device, and (3) control the pedestrian guidance device to generate a guidance output as defined by the control command.

[0018] According to one example, the cost function is optimized over different time points within the prediction horizon, such that the cost function is a model predictive control function.

[0019] According to one example, several states of the traffic flow remain constant within the prediction horizon.

[0020] According to one example, a traffic movement state varies within a prediction horizon, and values ​​corresponding to the traffic movement state at different times within the prediction horizon are determined based on historical data.

[0021] According to one example, the congestion model defines the next state of congestion as a function of the value of the control command based on a combination of the current state of congestion, the current state of the traffic flow, and a closure term that defines a change in the current state of the traffic flow.

[0022] According to one example, the closure term may be multiplied by a multiplier between 0 and 1 that indicates the effect of the control command on different people. In some examples, the multiplier is fixed for different values ​​of the control command. In other examples, the multiplier is determined based on one or more pedestrian attributes and learned routing parameters. The learned routing parameters may be based on the measured effect of the control command.

[0023] According to one example, the current state of traffic flow is predicted based on the current state of congestion. Additionally, the current state of traffic flow may be further predicted based on one or more characteristics of the controlled environment. The one or more characteristics of the controlled environment may include segment crossing times and / or schedule data.

[0024] According to one example, the current state of traffic flow is proportional to the current state of congestion.

[0025] According to one example, the current state of traffic flow is further predicted based on a predicted congestion state, which may be based on one or more characteristics of the controlled environment and the current congestion state.

[0026] According to one example, the guidance output includes routing instructions and presentation characteristics.

[0027] According to one example, the pedestrian guidance device is a display screen configured to show the guidance output.

[0028] In general, in another aspect, a method for controlling congestion in a controlled environment is provided that includes collecting measurements indicative of a current state of traffic flow in the controlled environment via one or more sensors operatively connected to a congestion control system.

[0029] The method further includes generating, via the congestion control system, control commands for the pedestrian guidance device operatively connected to the congestion control system by optimizing a cost function including a congestion model of a system of dynamics of crowd behavior in the controlled environment, the congestion model linking a next state of congestion to a current state of congestion influenced by a current state of traffic flow influenced by the pedestrian guidance device.

[0030] The method further includes controlling, via the congestion control system, the pedestrian guidance device to generate a guidance output defined by the control command.

[0031] In general, in yet another aspect, there is provided a non-transitory computer readable memory including a program executable by at least one processor to execute a method for controlling congestion in a controlled environment, the method including collecting measurements indicative of a current state of traffic flow in the controlled environment via one or more sensors operatively connected to a congestion control system.

[0032] The method further includes generating, via the congestion control system, control commands for the pedestrian guidance device operatively connected to the congestion control system by optimizing a cost function including a congestion model of a system of dynamics of crowd behavior in the controlled environment, the congestion model linking a next state of congestion to a current state of congestion influenced by a current state of traffic flow influenced by the pedestrian guidance device.

[0033] The method further includes controlling, via the congestion control system, the pedestrian guidance device to generate a guidance output defined by the control command.

[0034] In various implementations, a processor or controller can be associated with one or more storage media (generally referred to herein as "memory," e.g., volatile and non-volatile computer memory such as ROM, RAM, PROM, EPROM, and EEPROM, floppy disks, compact disks, optical disks, magnetic tape, flash, OTP-ROM, SSD, HDD, etc.). In some implementations, the storage media can be encoded with one or more programs that, when executed by one or more processors and / or controllers, perform at least some of the functions described herein. The various storage media can be fixed to the processor or controller, or can be portable, with one or more programs stored thereon that can be loaded into the processor or controller to implement various aspects described herein. In this specification, the term "program" or "computer program" is used in a comprehensive sense to refer to any type of computer code (e.g., software or microcode) that can be used to program one or more processors or controllers.

[0035] It should be understood that all combinations of the above concepts and other concepts described in more detail below (provided that such concepts are not mutually inconsistent) are intended to be part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter as set forth at the end of this disclosure are intended to be part of the inventive subject matter disclosed herein. It should also be understood that terms explicitly used herein, as may be set forth in any disclosures incorporated by reference, should be given the meaning most consistent with the specific concepts disclosed herein.

[0036] Other features and advantages will become apparent from the description and the claims.

[0037] In the drawings, like reference numbers generally refer to the same parts in the different drawings and the drawings are not necessarily to scale, emphasis instead being placed upon illustrating the principles of various embodiments. [Brief description of the drawings]

[0038] [Figure 1A] FIG. 1 illustrates a railway station scenario with arrow displays for pedestrian guidance, according to some embodiments of the present disclosure. [Figure 1B] FIG. 2 shows a block diagram of data flow between elements of the present disclosure. [Diagram 2] FIG. 1B illustrates a procedure for calculating the arrow display of FIG. 1A using the current crowding level according to some embodiments of the present disclosure. [Diagram 3] FIG. 1B illustrates a procedure for calculating the arrow display of FIG. 1A using current and predicted future crowding levels according to some embodiments of the present disclosure. [Figure 4] FIG. 1 shows a schematic diagram of a system for computing an arrow display according to some embodiments of the present disclosure. [Figure 5A] FIG. 2 illustrates an example of an intersection for pedestrian guidance according to some embodiments of the present disclosure. [Figure 5B] FIG. 1 illustrates a method for converting a congestion model into a control-oriented model according to some embodiments of the present disclosure. [Figure 6] 11A-11C illustrate various variations of an arrow display according to some embodiments of the present disclosure. [Figure 7] FIG. 1 illustrates a procedure for learning a pedestrian congestion model using data, according to some embodiments of the present disclosure. [Figure 8] FIG. 1 is a flow chart for controlling crowding in a controlled environment, according to an example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0039] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be practiced without these specific details. In other instances, the apparatus and methods are shown in block diagram form solely to avoid obscuring the present disclosure.

[0040] As used in the specification and claims, the terms "for example," "for instance," and "such as," as well as the verbs "comprising," "having," "including," and other forms of these verbs, when used in conjunction with a list of one or more components or other items, should each be construed as open-ended, meaning that the list should not be considered to exclude further components or items. The term "based on" means based at least in part on. Furthermore, it should be understood that the style and terminology used herein are for purposes of illustration and should not be considered limiting. Any headings used herein are for convenience only and should not be considered to have any legal or limiting effect.

[0041] The present disclosure is generally directed to a crowd control system configured to direct pedestrians to balance crowding across multiple areas of a controlled environment, such as a train station. The crowd control system is operatively connected to multiple sensors (such as occupancy sensors, motion sensors, etc.) and pedestrian guidance devices (e.g., arrow displays, speaker systems, lighting systems, etc.). The sensors are configured to obtain measurements corresponding to pedestrian crowding levels at various locations within the controlled environment. These measurements are provided to the crowd control system. The crowd control system uses the measurements to determine pedestrian traffic flows at the various locations of the controlled environment. The crowd control system then uses the measured crowding levels and the determined traffic flows to determine control commands. The control commands are provided to the pedestrian guidance devices to configure the devices to provide guidance outputs to pedestrians in the controlled environment to balance and / or reduce crowding.

[0042] In an example where the controlled environment is a train station platform, an objective of some embodiments of the present disclosure is to balance the crowding levels on the train platform by using an arrow display to guide pedestrians. As an example, if an area of ​​low crowding is identified near one of the escalators, the arrow display may display a signal to guide pedestrians toward one of the escalators that is closer to the low crowding area.

[0043] An objective of some embodiments is to use the current pedestrian congestion level to calculate the arrow display. If the controlled environment includes an intersection, the current pedestrian congestion level may be used to calculate the pedestrian flow across the intersection where the arrow display is located. The pedestrian flow may be combined with the current pedestrian congestion level to determine in which direction the pedestrian should be directed by the arrow display. The arrow display may be calculated using a mathematical function or optimization problem.

[0044] Alternatively, an improved procedure may be used, in which a predicted pedestrian congestion level at a future time may be used as additional information to calculate the arrow display. As an example, the future time may be 10 minutes after the current time. As an example, the current pedestrian congestion level may be used in combination with the predicted pedestrian congestion level to calculate an improved, predicted pedestrian flow. The improved, predicted pedestrian flow may be more accurate since a forecast of the predicted pedestrian congestion level may be used. The improved, predicted pedestrian flow may then be used to calculate the arrow display using a mathematical function or optimization problem.

[0045] A congestion control system for computing an arrow display may include at least one processor and a memory that stores an intersection layout, a routing objective, and a congestion model. The processor may be configured to execute instructions stored in the memory to cause the system to compute the arrow display. The congestion model may relate to how the arrow display alters congestion levels around an intersection.

[0046] The crowding model may use a crowding induced effect that indicates what percentage of pedestrians will change their route. For example, if the crowding induced effect is 40%, then 40% of pedestrians are expected to change their intended walking direction upon seeing the arrow with the highest strength.

[0047] The pedestrian flow may be predicted using a mathematical function or optimization problem that uses knowledge about the intersection characteristics. For example, the mathematical function may calculate the pedestrian flow using the current pedestrian congestion level and information about the intersection at a train station. As an example, the mathematical function may assume that the pedestrian flow across the intersection is proportional to the current pedestrian congestion level.

[0048] Alternatively, this improved procedure may be used to calculate an arrow display. In this setting, the improved predicted pedestrian flow uses the predicted pedestrian congestion level to calculate the improved predicted pedestrian flow.

[0049] The purpose of estimating pedestrian flow is to use the pedestrian flow values ​​in a congestion model. The congestion model can then be used in a predictive control framework to calculate the arrow display. The predictive control framework may use the congestion model and knowledge of the intersection characteristics to predict the best arrow display to optimize the pedestrian congestion level. The predictive control framework may use the congestion model for a prediction horizon.

[0050] Additionally, the predictive control framework may use a set of mixed integer constraints, which can be used to calculate the arrows so that they can be displayed in only one direction.

[0051] Alternatively, a relaxed predictive control framework may be used. For example, the predictive control framework may be relaxed such that a set of mixed-integer constraints are strictly enforced for only one time step. A relaxed predictive control framework may be beneficial to reduce computational requirements.

[0052] Some embodiments are based on displaying a binary intensity: displaying the arrow at full intensity or not displaying the arrow. Such a binary intensity option is easy to implement and control. For example, the arrow display is either on or off. Additionally or alternatively, some embodiments are based on displaying a variable intensity. Such a variable intensity option may provide more freedom for pedestrian routing to achieve or improve routing goals.

[0053] Some embodiments are based on a learning procedure to improve the congestion model using data. The learning procedure may use the model mismatch error between the congestion model and the data. The model mismatch error may then be used to update congestion-induced parameters that can be used to update the congestion model. In such a setting, the congestion-induced parameters may be updated each time a new data sample is collected.

[0054] As an example, the learning procedure may use a recursive least squares procedure to update the congestion induction parameters. As an example, the congestion induction effect may be calculated as a parameterized model using attributes of pedestrians approaching the intersection. The recursive least squares procedure may use a recursive implementation in which the congestion induction parameters are updated based on the model mismatch error. A first main advantage of a learning procedure implemented using a recursive least squares procedure is that all collected data points are summarized in a small number of parameters. A second main advantage of a learning procedure implemented using a recursive least squares procedure is that it is computationally inexpensive. As such, the learning procedure does not require a large memory or a powerful processor.

[0055] The learning procedure may be performed each time the arrow display is shown. Additionally or alternatively, the learning procedure may have an active search portion. For example, the arrow display may be selected to allow the learning procedure to learn routing parameters more quickly. For example, the learning procedure may display an arrow display that is obtained from a combination of an optimal arrow calculated using a mathematical function or optimization problem and a search measure.

[0056] The exploration measure decreases with the number of times a particular arrow appears and increases with time. The combination of these factors adds an element of exploration, which can be beneficial in learning the congestion model more quickly.

[0057] Turning now to the drawings, FIG. 1A illustrates a non-limiting example of a controlled environment embodied as a train station 100. In the train station 100, pedestrians must choose between a right escalator 110 and a left escalator 120 to reach a train platform 150. An objective of some embodiments of the present disclosure is to balance the congestion level on the train platform 150 by using a pedestrian guidance device 130 (shown as an arrow display in FIG. 1A ) to guide pedestrians to the right escalator 110 or the left escalator 120 using a guidance output 170. As an example, if a low-congestion area 140 is identified near the right escalator 110, the arrow display may display a guidance output 170 in the form of a signal to guide pedestrians toward the right escalator 110. The arrow display may be a digital display screen, such as a liquid crystal display (LCD) screen or a light-emitting diode (LED) screen.

[0058] Although the example pedestrian guidance device 130 of FIG. 1A is embodied as an arrow display, numerous other types of pedestrian guidance device 130 can be realized. In some examples, the pedestrian guidance device 130 may be a speaker system configured to generate voice commands to guide pedestrians toward the right escalator 110 or the left escalator 120 depending on the observed congestion level. In other examples, the pedestrian guidance device 130 may be a lighting system including one or more connected lighting fixtures configured to generate lighting outputs to guide pedestrians. In yet other examples, the pedestrian guidance device 130 may generate and wirelessly transmit alerts to guide pedestrians to all wireless-enabled devices (e.g., smartphones, tablet computers, laptop computers, etc.) within a transmission range.

[0059] The guidance output 170 may be defined by two aspects: (1) routing instructions and (2) one or more presentation characteristics. The routing instructions indicate the direction in which a pedestrian in a controlled environment should proceed. In the example of FIG. 1A, the routing instructions can be considered as the direction of an arrow on an arrow display instructing the pedestrian to use the first escalator 110 or the second escalator 120. If the pedestrian guidance device 130 is instead a speaker, the routing instructions may be voice command information informing the pedestrian of the recommended direction of travel. In another example, if the pedestrian guidance device 130 is a lighting system, the routing instructions are directional information conveyed by the settings of the lighting output.

[0060] The presentation characteristics of the guidance output 170 define the format of the guidance output 170. For example, if the guidance output 170 is visual (e.g., an arrow on an arrow signal, or a lighting output generated by a lighting system), the presentation characteristics may refer to size, color, intensity, visual effects, etc. If the guidance output 170 is audio (e.g., a voice command generated by a speaker), the presentation characteristics may refer to volume or audio effects.

[0061] The crowding level in each segment of the home is determined based on measurements captured by one or more sensors 160a, 160b, 160c. The sensors 160a, 160b, 160c shown in FIG. 1A may be any sensor or combination of sensors capable of capturing measurements relevant to crowding analysis. For example, the sensors 160a, 160b, 160c may include occupancy sensors, motion sensors, proximity sensors, audio sensors (such as microphones), video and / or still image sensors (such as cameras), infrared sensors, etc.

[0062] FIG. 1B shows a block diagram generally illustrating the flow of data in the controlled environment of FIG. 1A (embodied as a train station 100). In general, the controlled environment of FIG. 1A includes a plurality of sensors 160, a crowd control system 410, and a pedestrian guidance device 130. The sensors 160 are operatively connected to the crowd control system 410 via any combination of wired and / or wireless connections. Similarly, the crowd control system 410 is operatively connected to the pedestrian guidance device 130 via any combination of wired and / or wireless connections. In some examples, the crowd control system 410 is located in the controlled environment proximate to the sensors 160 and / or the pedestrian control device 130. In other examples, the crowd control system 410 may be located remotely from the controlled environment. In these examples, the crowd control system 410 may communicate with the sensors 160 and / or the pedestrian control device 130 via cloud computing or other remote networking methods.

[0063] 1B, during operation, the sensors 160 communicate measurement data 162 to the crowding control system 410. Generally, the measurement data 162 is indicative of crowding levels in various segments of the railway station 100. The crowding control system 410 processes the measurement data 162 to generate control commands 412. The control commands are configured to instruct the pedestrian guidance device 130 to generate guidance outputs 170 having routing instructions and presentation characteristics for guiding pedestrians within the railway station 100 to reduce crowding.

[0064] FIG. 2 illustrates a procedure 200 for controlling the pedestrian guidance device 130 of FIG. 1A using a current pedestrian congestion level 210. As previously described, the current pedestrian congestion level 210 may be determined based on measurements captured by one or more sensors 160a, 160b, 160c shown in FIG. 1A. The current pedestrian congestion level 210 may be used to calculate a pedestrian flow 220 across an intersection where the pedestrian guidance device 130 is located. The pedestrian flow 220 may be combined with the current pedestrian congestion level 210 to determine in which direction the pedestrian should be guided by the pedestrian guidance device 130. In the example of FIG. 2, the output is embodied as an arrow displayed by the arrow display of FIG. 1A. The output of the pedestrian guidance device 130 may be calculated using a mathematical function or optimization problem 230.

[0065] Alternatively, an improved procedure 300 may be used, as shown in FIG. 3. In FIG. 3, a predicted pedestrian congestion level 310 at a future time may be used as additional information to calculate the output of the pedestrian guidance device 130. In some examples, the future time may be 10 minutes after the current time. As an example, the current pedestrian congestion level 210 may be used in combination with the predicted pedestrian congestion level 310 to calculate an improved predicted pedestrian flow 320. The improved predicted pedestrian flow 320 may be more accurate since it may use a forecast value of the predicted pedestrian congestion level 310. The improved predicted pedestrian flow 320 may then be used to calculate the output of the pedestrian guidance device 130 using a mathematical function or optimization problem 230.

[0066] 4 illustrates a block diagram 400 of a congestion control system 410 for calculating an output of the pedestrian guidance device 130 according to some embodiments of the present disclosure. The system 410 includes a processor 420 and a memory 430 that stores an intersection layout 440, a routing goal 450, and a congestion model 460. The processor 420 is configured to execute instructions stored in the memory 430 to cause the system 410 to calculate the arrow display 130. The congestion model 460 may relate to how the pedestrian guidance device 130 changes the congestion level around the intersection.

[0067] FIG. 5A shows, as an example, a scenario 500 of an intersection 510 for pedestrian routing using a pedestrian guidance device 130 (embodied as an arrow display). A representation of this intersection 510 may be stored in the memory 430 of the congestion control system 410 as an intersection layout 440 shown in FIG. 4. The intersection 510 may be composed of a pre-segment 550 that defines a route to the intersection 510. The pre-segment 550 may have a specific length. A pedestrian travels this length to reach the intersection 510. This length may further determine how long the pedestrian stays in the pre-segment 550. For example, if a pedestrian walks with an average speed of 1 meter / s and the length of the pre-segment 550 is 50 m, the pedestrian stays in the pre-segment 550 for 50 seconds on average. At the intersection 510, the pedestrian can see the pedestrian guidance device 130. The pedestrian can select a post-segment after crossing the pre-segment 550 and passing the intersection 510. The pedestrian can select the first post segment 520, the second post segment 530, or the third post segment 540.

[0068]

number

[0069]

number

[0070]

number

[0071] 5B illustrates the conceptual idea of ​​converting an example scenario 500 into a control-oriented model 570 in the form of a system dynamics model. The control-oriented model 570 consists of a state-space model 560 whose states are congestion values. Such a reformulation therefore allows the control-oriented model 570 to be used with any type of classical control software, such as predictive control.

[0072]

number

[0073]

number

[0074]

number

[0075]

number

[0076]

number

[0077]

number

[0078]

number

[0079]

number

[0080]

number

[0081]

number

[0082]

number

[0083]

number

[0084]

number

[0085]

number

[0086]

number

[0087]

number

[0088] The direction of the arrows can also be applied to convey directional information for other types of guidance outputs 170 of the pedestrian control device 130, such as audio or lighting.

[0089]

number

[0090]

number

[0091]

number

[0092] A relaxed predictive control framework can be beneficial in reducing computational requirements.

[0093] FIG. 6 shows a variation of the pedestrian guidance device 130 embodied as an arrow display. As can be seen from FIG. 6, the pedestrian guidance device 130 is configured to generate a guidance output 170 in the form of an arrow. Some embodiments are based on displaying a binary intensity 610, that is, displaying the arrow at full intensity or not displaying the arrow. Such a binary intensity 610 option is easy to implement and control. As an example, the pedestrian guidance device 130 can be switched either on or off. Additionally or alternatively, some embodiments are based on displaying a variable intensity 620. Such a variable intensity 620 option can provide more freedom for pedestrian routing to achieve or improve the routing goal 450.

[0094] 7 illustrates a training procedure 700 for a congestion model 460 using data 710. The data 710 represents actual congestion levels in one or more aspects of a controlled environment, and the congestion model 460 generates predicted congestion levels based on previously measured congestion levels, traffic flows, and congestion induction effects of the induction output 170. The training procedure 700 may use a model mismatch error 720 between the congestion model 460 and the data 710. The model mismatch error 720 may then be used to update the value of a congestion induction parameter (r), also referred to as a multiplier, which may be used to update the congestion model 460. In such a setting, the congestion induction parameter 730 may be updated each time a new data sample is collected.

[0095]

number

[0096]

number

[0097]

number

[0098]

number

[0099]

number

[0100]

number

[0101]

number

[0102]

number

[0103]

number

[0104]

number

[0105]

number

[0106]

number

[0107]

number

[0108]

number

[0109] The exploration measure decreases with the number of times a particular arrow is displayed and increases with time. The combination of these factors adds an element of exploration, which can be beneficial in training the crowding model 460 more quickly.

[0110] 9 is a flow chart of a method 800 for controlling congestion in a controlled environment, according to various embodiments of the present invention. With reference to FIGS. 1-9, the method 800 includes, at step 810, collecting measurements indicative of a current state of traffic flow in the controlled environment via one or more sensors operatively connected to a congestion control system.

[0111] The method 800 further includes optimizing, via the congestion control system, a cost function including a congestion model of the system of dynamics of crowd behavior in the controlled environment to generate control commands for the pedestrian guidance devices operatively connected to the congestion control system, at step 820. The congestion model links a next state of congestion to a current state of congestion that is influenced by a current state of traffic flow influenced by the pedestrian guidance devices.

[0112] The method 800 further includes, at step 830, controlling the pedestrian guidance device via the crowd control system to generate a guidance output defined by the control command.

[0113] All definitions set forth and used herein should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms.

[0114] The indefinite articles "a" and "an," as used in the specification and claims, should be understood to mean "at least one," unless otherwise specified.

[0115] The term "and / or" as used in the specification and claims should be understood to mean "either or both" of the conjoined elements, i.e., elements that are conjoined in some cases and separated in other cases. Multiple elements listed with "and / or" should be interpreted in the same manner, i.e., "one or more" of the elements so conjoined. Other elements other than the elements specifically identified by the "and / or" clause may optionally be present, whether or not related to those elements specifically identified.

[0116] "Or" as used in the present specification and claims should be understood to have the same meaning as "and / or" above. For example, when separating items in a list, "or" or "and / or" should be interpreted as being inclusive, i.e., including at least one of, but also including more than one of, some elements or lists of elements. Only terms such as "only one of" or "exactly one of," or "consisting of" as used in the claims, that clearly indicate the opposite, will mean including exactly one of, some elements or lists of elements. In general, the term "or" as used herein should be interpreted as indicating exclusively exclusive alternatives (i.e., "one or the other, but not both") when preceded by terms indicating exclusivity, such as "any of," "one of," "only one of," or "exactly one of."

[0117] As used in the specification and claims, the phrase "at least one" in reference to a list of one or more elements should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed in the list of elements, and not excluding any combination of elements in the list of elements. This definition also allows for the optional presence of elements other than those specifically identified in the list of elements in which the phrase "at least one" is used, whether or not related to those elements specifically identified.

[0118] It is also to be understood that, unless otherwise specified, in any method claimed herein that includes two or more steps or actions, the order of the method steps or actions is not necessarily limited to the order of the method steps or actions described.

[0119] In the claims and the above specification, all transitional phrases, such as "comprising," "including," "carrying," "having," "containing," "involving," "holding," "composed of," and the like, are to be understood to be open-ended, i.e., to mean including, but not limited to. Only the transitional phrases "consisting of" and "consisting essentially of," respectively, are intended to be closed or semi-closed transitional phrases.

[0120] The above examples of the described subject matter can be implemented in any of numerous ways. For example, some aspects can be implemented using hardware, software, or a combination thereof. If any aspect is implemented at least in part in software, the software code can run on any suitable processor or collection of processors, whether provided in a single device or computer, or distributed among multiple devices / computers.

[0121] The present disclosure may be implemented as a system, method, and / or computer program product at any possible level of technical detail of integration. The computer program product may include a computer-readable storage medium(s) having computer-readable program instructions for causing a processor to execute aspects of the present disclosure.

[0122] A computer-readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of these devices. A non-exhaustive list of more specific examples of computer-readable storage media includes portable computer diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), static random access memories (SRAMs), portable compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), memory sticks, floppy disks, mechanically encoded devices such as punch cards or ridge structures with grooves in which instructions are recorded, and any suitable combination of these. Computer-readable storage media, as used herein, should not be interpreted as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or electrical signals transmitted through wires.

[0123] The computer-readable program instructions described herein can be downloaded from the computer-readable storage medium to each computing / processing device or to an external computer or storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical transmission fiber, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and transfers the computer-readable program instructions for storage in the computer-readable storage medium in the respective computing / processing device.

[0124] The computer readable program instructions for carrying out the operations of the present disclosure may be source or object code written in any combination of one or more programming languages, including assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, configuration data for an integrated circuit, or object oriented programming languages ​​such as Smalltalk, C++, etc., and procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider). In some examples, electronic circuitry including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may execute computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry to perform aspects of the present disclosure.

[0125] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to examples of the present disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0126] The computer-readable program instructions may be provided to a processor of a special purpose computer or other programmable data processing apparatus to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing apparatus implement the functions / acts specified in the block or blocks of the flowcharts and / or block diagrams. These computer-readable program instructions may also be stored on a computer-readable storage medium to direct a computer, programmable data processing apparatus, and / or other apparatus to function in a particular manner such that the computer-readable storage medium on which the instructions are stored implements the aspects of the functions / acts specified in the flowcharts and / or block diagrams or blocks.

[0127] The computer readable program instructions may also be loaded into a computer, other programmable data processing apparatus, or other device, and a series of operational steps may be executed on the computer, other programmable apparatus, or other device to generate a computer-implemented process, and the instructions may be executed on the computer, other programmable apparatus, or other device to implement the function / operation identified in a block or blocks of the flowcharts and / or block diagrams.

[0128] The flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various examples of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or part of an instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions shown in the blocks may occur in a different order than that shown in the drawings. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may be executed in reverse order, depending on the functionality involved. It should be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or executes a combination of dedicated hardware and computer instructions.

[0129] Other implementations are within the scope of the following claims and other claims to which the applicant may be entitled.

[0130] While various examples have been described and shown herein, those skilled in the art will readily conceive of a variety of other means and / or structures for performing the functions described herein and / or obtaining one or more of the results and / or advantages described herein, and each such variation and / or modification is deemed to be within the scope of the examples described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are intended to be exemplary, and that the actual parameters, dimensions, materials, and / or configurations will depend on the particular application or applications for which the teachings are used. Those skilled in the art will recognize or be able to ascertain, using no more than routine experimentation, numerous equivalents to the specific examples described herein. Thus, it should be understood that the above examples are presented by way of example only, and that, within the scope of the following claims and their equivalents, the examples may be practiced otherwise than as specifically described and claimed. The embodiments of the present disclosure are directed to each individual feature, system, article, material, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, and / or methods is within the scope of the present disclosure, unless such features, systems, articles, materials, and / or methods are mutually inconsistent.

Claims

1. 1. A congestion control system for controlling congestion in a controlled environment, the congestion control system operatively connected via one or a combination of wired and wireless communication channels to one or more sensors configured to collect measurements indicative of traffic flow in the controlled environment and to pedestrian guidance devices positioned to affect the controlled environment, the congestion control system comprising at least one processor and a memory having instructions stored thereon, the instructions, when executed by the processor, causing the congestion control system to: collecting measurements indicative of current conditions of traffic flow in said controlled environment; generating control commands for the pedestrian guidance device by optimizing a cost function including a congestion model of a system of dynamics of crowd behavior in the controlled environment, the congestion model linking a next state of congestion to a current state of congestion influenced by a current state of the traffic flow influenced by the pedestrian guidance device; and and a congestion control system for controlling the pedestrian guidance device to generate a guidance output determined by the control command.

2. The congestion control system of claim 1 , wherein the cost function is optimized over different points in time within a prediction horizon such that the cost function is a model predictive control function.

3. The congestion control system of claim 2 , wherein a plurality of states of the traffic movement remain constant within the prediction horizon.

4. The congestion control system of claim 2 , wherein a plurality of states of the traffic movement vary within the prediction horizon.

5. The congestion control system of claim 4 , wherein values ​​corresponding to a plurality of states of the traffic movement at different times within the prediction horizon are determined based on historical data.

6. 2. The congestion control system of claim 1, wherein the congestion model determines a next state of the congestion as a function of a value of the control command based on a combination of a current state of the congestion, a current state of the traffic movement, and a closure term that determines a change in the current state of the traffic movement.

7. 7. The crowd control system of claim 6, wherein the closure term is multiplied by a multiplier between 0 and 1 that indicates the effect of the control command on different people.

8. The congestion control system of claim 7 , wherein the multiplier is fixed for different values ​​of the control command.

9. The congestion control system of claim 7 , wherein the multiplier is determined based on one or more pedestrian attributes and learned routing parameters.

10. The congestion control system of claim 9 , wherein the learned routing parameters are based on measured effects of the control commands.

11. The congestion control system of claim 6 , wherein the current state of traffic flow is predicted based on the current state of congestion.

12. The congestion control system of claim 11 , wherein the current state of traffic flow is further predicted based on one or more characteristics of the controlled environment.

13. The congestion control system of claim 12 , wherein the one or more characteristics of the controlled environment include segment crossing times and / or schedule data.

14. 12. The congestion control system of claim 11, wherein the current state of traffic flow is proportional to the current state of congestion.

15. The congestion control system of claim 11 , wherein the current state of traffic movement is further predicted based on a predicted congestion state.

16. 16. The crowd control system of claim 15, wherein the predicted crowd state is based on one or more characteristics of the controlled environment and a current state of the crowd.

17. The crowd control system of claim 1 , wherein the guidance output includes routing instructions and presentation characteristics.

18. The congestion control system of claim 1 , wherein the pedestrian guidance device is a display screen configured to show the guidance output.

19. 1. A method for controlling crowding in a controlled environment, the method comprising: collecting measurements indicative of a current state of traffic flow in said controlled environment via one or more sensors operatively connected to a congestion control system; and generating, via the congestion control system, control commands for pedestrian guidance devices operatively connected to the congestion control system by optimizing a cost function including a congestion model of a system of dynamics of crowd behavior in the controlled environment, the congestion model linking a next state of congestion to a current state of congestion influenced by a current state of the traffic flow influenced by the pedestrian guidance devices, the method further comprising: controlling, via the congestion control system, the pedestrian guidance device to generate guidance outputs defined by the control commands.

20. 1. A non-transitory computer readable memory containing a program executable by at least one processor to perform a method for controlling crowding in a controlled environment, the method comprising: collecting measurements indicative of a current state of traffic flow in said controlled environment via one or more sensors operatively connected to a congestion control system; and generating, via the congestion control system, control commands for pedestrian guidance devices operatively connected to the congestion control system by optimizing a cost function including a congestion model of a system of dynamics of crowd behavior in the controlled environment, the congestion model linking a next state of congestion to a current state of congestion influenced by a current state of the traffic flow influenced by the pedestrian guidance devices, the method further comprising: and controlling, via the congestion control system, the pedestrian guidance device to generate guidance outputs defined by the control commands.

Images