Methods for reducing traffic congestion on a road network

By predicting future congestion and targeting high-impact drivers with personalized offers, the method reduces traffic congestion by altering driver behavior, optimizing incentives to minimize costs and congestion.

DE102023128756B3Active Publication Date: 2024-12-05GM GLOBAL TECHNOLOGY OPERATIONS LLC
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
DE102023128756
Authority / Receiving Office
DE · DE
Patent Type
Patents
Current Assignee / Owner
Priority Date
2023-07-13
Filing Date
2023-10-19
Publication Date
2024-12-05
Estimated Expiration
2043-10-19

AI Technical Summary

Technical Problem

Existing traffic congestion management systems primarily focus on predicting arrival times based on current congestion levels, failing to effectively reduce congestion by altering driver behavior.

Method used

A method that predicts future traffic congestion levels and identifies individual drivers contributing most to congestion, offering incentives or alternatives to avoid specific routes, thereby reducing overall network congestion.

Benefits of technology

Effectively minimizes traffic congestion by discouraging high-impact drivers, optimizing offers to achieve the greatest reduction at the lowest cost, using historical data and machine learning to personalize interventions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

A method for reducing traffic congestion in a road network. The method comprises predicting future traffic congestion levels for the road network based on historical traffic congestion levels. An individual contribution to the future traffic congestion levels for each of a multitude of drivers is predicted based on future routes corresponding to each of the multitude of drivers, where the future routes include at least one road segment through the road network. Based on the future traffic congestion levels of the road network, at least one congested road segment is identified, and the multitude of drivers with the highest individual contribution to this at least one congested road segment is identified.The majority of drivers with the highest individual contributions to at least one congested road section will be offered an initial option to avoid operating a vehicle on the road network.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] The present description relates to a system and method for reducing traffic congestion in a road network.

[0002] At certain times and on certain days, there may be increased traffic congestion that the vehicle driver wishes to avoid. Currently, the vehicle driver can obtain a route from various services that predicts the arrival time for a specific destination based on current traffic congestion. However, there is a need to reduce congestion levels and not just plan the route based on traffic congestion.

[0003] US 9 672 734 B1 describes a system, method, and computer program product for determining lane information in a road segment to control a first vehicle to minimize travel time. Navigation data of the first vehicle and at least one other vehicle in a road segment are sent via their respective clique leaders to a computer server system via a communications network. The lane information may include whether a lane change is necessary, a lane to avoid, an optimal lane, and a ranking of the navigable lanes in ascending order of travel time for the first vehicle to minimize travel time. The determined lane information is sent via the clique leader to the corresponding user device. The user device makes the lane information available to a human driver and / or the autonomous driving system of the first vehicle in a suitable manner.

[0004] US 2011 / 0 224 893 A1 describes techniques for generating and using road traffic information in various ways, including by acquiring and analyzing road traffic information on the actual behavior of vehicle drivers on a road network. The obtained information on actual driver behavior can, in some situations, be analyzed to determine actual delays for vehicles encountering various special road features in the road network, such as identified decision points where drivers must make decisions corresponding to possible alternative routes through the road network (e.g., intersections, motorway exits and / or entrances, and so on) and / or other traffic flow impediments.The information identified and obtained from the analysis can then be used in a variety of ways, including, in some situations, to assist in determining certain recommended or preferred routes for vehicles through the road network, based at least in part on information on actual driver behavior.

[0005] US 2017 / 0 057 411 A1 describes the creation of a database of high-risk locations and the identification of causal high-risk factors for the high-risk locations. Driver behavior is monitored at the locations in the database using data collection devices such as electronic tachographs or mobile phones to determine whether drivers exhibit the same specific behaviors considered contributing factors to certain types of accidents that can occur at these locations. Drivers are warned when approaching the specific locations to encourage behavioral changes that can be further monitored by the data collection devices.

[0006] WO 2008 / 078 088 A1 describes a method for operating a vehicle driven by a driver on a road, comprising the following steps: while the vehicle is being driven, collecting data indicative of the manner in which the vehicle is being operated using a driver information device mounted on the vehicle, processing the data collected by the device while the vehicle is being driven, or thereafter, or a combination of both, to generate a signal representative of the manner in which the vehicle is being operated, the signal comprising at least one indicator indicative of the behavior of the driver and / or the traffic congestion on the road at that time, and providing the driver with feedback about the mode of operation in order to change the manner in which the driver operates the vehicle in accordance with the at least one indicator fed back to the driver.An in-vehicle processing unit that provides feedback to the driver is also described.

[0007] DE 10 2007 008 880 A1 describes a method for increasing road traffic flow, wherein control means are present in the vehicles involved, which are addressed via vehicle safety systems and / or driver assistance systems, to influence the vehicle's trajectory, and wherein information about vehicles in the immediate vicinity is recorded by driver assistance systems and an environment detection is carried out, with the following steps: Determination of the number of lanes in the direction of travel by driver assistance systems and / or vehicle safety systems, Determination of a speed and a position of the vehicles traveling in the direction of travel by means of an environment detection, Permanent determination of the own vehicle data via control means located in the vehicle, Determination, recording and evaluation of information about possible vehicles in the surrounding area that impede the traffic flow,Establishing at least one mobile data transmission connection by means of at least one routing method between at least a first vehicle and a second vehicle, wherein at least one vehicle is identified as a vehicle impeding the traffic flow, transmitting information to the vehicle impeding the traffic flow, outputting the information in the vehicle impeding the traffic flow via a human-machine interface,

[0008] DE 10 2022 107 774 A1 describes systems and techniques for the collaborative detection and avoidance of phantom traffic jams. Sensor data for a segment of a roadway and vehicle communication data for vehicles traveling on the segment can be obtained. A vehicle density can be calculated using the sensor data and vehicle communication data for the segment. The sensor data and vehicle communication data can be monitored for a traffic incident based on the calculated vehicle density. A mitigation instruction can be selected for the traffic incident upon detection of the traffic incident. The mitigation instruction can be transmitted to a vehicle or a group of vehicles traveling on the roadway.In one example where infrastructure support is available, it may be determined that a roadside communication device is unavailable, and a first vehicle may transmit a decentralized ambient notification message to a second vehicle.

[0009] According to the invention, a method for reducing traffic congestion of a road network is described. The method comprises predicting future traffic congestion levels for the road network based on historical traffic congestion levels for the road network. The method comprises predicting an individual contribution to the future traffic congestion levels for each of a plurality of drivers based on future routes corresponding to each of the plurality of drivers, the future routes comprising at least one road section through the road network. The method comprises identifying at least one congested road section based on the future traffic congestion of the road network, and identifying the plurality of drivers with the highest individual contribution to the at least one congested road section.The method includes providing the plurality of drivers with the highest individual contributions to the at least one congested road section with a first offer to avoid operating a vehicle on the road network.

[0010] According to one embodiment, the individual contribution to future traffic congestion levels is determined based on historical driver route information.

[0011] According to another embodiment, the historical driver route information includes at least one of the following: a travel route, a travel route time, vehicle dynamics, or parking information recorded for each of the plurality of drivers associated with a route segment corresponding to the future routes.

[0012] According to another embodiment, the route section corresponds to a new route section that was not found in the driver's historical route information.

[0013] According to a further embodiment, predicting driver route information for the new route section based on the historical driver route information for other route sections in the road network is included.

[0014] According to a further embodiment, the first offer comprises at least one financial compensation or an alternative mode of transport.

[0015] According to a further embodiment, identifying the plurality of drivers with the highest individual contribution to the at least one congested road section comprises ranking the plurality of drivers according to their individual contribution and providing the first offer to at least one driver with the highest ranking.

[0016] According to another embodiment, the first offer is provided to the plurality of highest-ranked drivers having corresponding future routes through the most congested road network determined by the future traffic congestion levels.

[0017] According to a further embodiment, determining a first group of the plurality of drivers who have accepted the first offer and updating the future traffic congestion levels by removing the individual contribution to the future traffic congestion levels for the first group of the plurality of drivers to determine updated future traffic congestion levels is included.

[0018] According to another embodiment, identifying a remaining group of the plurality of drivers who did not accept the first offer includes having the highest individual contribution to the updated future traffic congestion levels.

[0019] According to a further embodiment, providing a second offer to the remaining group of the plurality of drivers is included if the corresponding future travel routes correspond to at least one congested road section in the updated future traffic congestion levels.

[0020] According to a further embodiment, the future traffic congestion is defined by the number of vehicles traveling per unit of time on a specific road section of the road network.

[0021] According to a further embodiment, the individual contribution to future traffic congestion levels for each of a plurality of drivers is defined in terms of a number of vehicles traveling per unit time over a predetermined driver road section in the road network.

[0022] According to a further embodiment, the first offer is determined based on a driver utility for each of the plurality of drivers traveling on the at least one congested road section.

[0023] According to another embodiment, the first offer exceeds the driver benefit for each of the plurality of drivers traveling on the at least one congested road segment.

[0024] According to one example, a non-transitory computer-readable medium is included that contains programmed instructions that, when executed by a processor, are suitable for performing a method. The method includes predicting future traffic congestion levels for the road network based on historical traffic congestion levels for the road network. An individual contribution to the future traffic congestion levels for each of a plurality of drivers is predicted based on future routes corresponding to each of the plurality of drivers, the future routes including at least one road segment through the road network. Based on the future traffic congestion of the road network, at least one congested road segment is identified, and the plurality of drivers with the highest individual contribution to the at least one congested road segment is identified.The majority of drivers with the highest individual contributions to the at least one congested road section are provided with a first offer to avoid operating a vehicle on the road network.

[0025] According to one example, a system for reducing traffic congestion levels on a road network is described, the system comprising a vehicle having a plurality of sensors and a controller that communicates with the plurality of sensors. The controller includes a processor and tangible, non-transferable memory in which instructions are recorded. The controller is configured to predict future traffic congestion levels for the road network based on historical traffic congestion levels for the road network. An individual contribution to the future traffic congestion levels for each of a plurality of drivers is predicted based on future routes corresponding to each of the plurality of drivers, the future routes comprising at least one road segment through the road network.Based on the future traffic congestion of the road network, at least one congested road section is identified, and the plurality of drivers with the highest individual contribution to the at least one congested road section is identified. The plurality of drivers with the highest individual contributions to the at least one congested road section are provided with an initial offer to avoid operating a vehicle on the road network. Fig. 1 is a schematic representation of an example vehicle. Fig. 2 shows a method for managing vehicle congestion. Fig. Figure 3 shows an example of a graph showing driver benefit versus congestion. Fig. Figure 4 shows an example of a diagram showing the benefit to the driver compared to the offer.

[0026] Those of ordinary skill in the art will recognize that terms such as "top," "bottom," "upward," "downward," "upper," "downward," "left," "right," etc., are used descriptively for the figures and do not represent limitations on the scope of the description as defined by the appended claims. Furthermore, the teachings herein may be described in terms of functional and / or logical block components and / or various processing steps. It should be understood that such block components may include a number of hardware, software, and / or firmware components configured to perform the specified functions.

[0027] With reference to the figures, in which like numerals indicate like parts which relate to the drawings, with like reference numbers referring to like components, Fig. 1 is a schematic view of a motor vehicle 10 positioned relative to a road surface, such as a carriageway 12. As in Fig. 1, the vehicle 10 includes a vehicle body 14, a first axle having a first set of wheels 16-1, 16-2, and a second axle having a second set of wheels 16-3, 16-4 (e.g., individual left and right wheels on each axle). Each of the road wheels 16-1, 16-2, 16-3, 16-4 has tires configured to provide notional contact with the vehicle track 12. Although two axles with respective road wheels 16-1, 16-2, 16-3, 16-4 are expressly shown, nothing precludes the motor vehicle 10 from having additional axles.

[0028] As in Fig. 1, a vehicle suspension system connects the vehicle body 14 to the respective sets of wheels 16-1, 16-2, 16-3, 16-4 to maintain contact between the wheels and the road surface 12 and to maintain the handling of the motor vehicle 10. The motor vehicle 10 additionally includes a drivetrain 20 having one or more power sources 20A, which may be an internal combustion engine (ICE), an electric motor, or a combination of such devices, configured to transmit drive torque to the road wheels 16-1, 16-2 and / or the road wheels 16-3, 16-4.The motor vehicle 10 also employs vehicle operating or control systems, including devices such as one or more steering actuators 22 (e.g., an electric power steering system) configured to steer the road wheels 16-1, 16-2, a steering angle (θ), an accelerator device 23 for controlling the power output of the energy source(s) 20A, a brake switch or braking device 24 for retarding the rotation of the road wheels 16-1 and 16-2 (e.g., via individual friction brakes located on the respective road wheels), etc.

[0029] As in Fig. 1, the motor vehicle 10 includes at least one sensor 25A and an electronic control unit 26 that cooperate to control, guide, and maneuver the vehicle 10 at least partially in an autonomous mode in certain situations. As such, the vehicle 10 may be referred to as an autonomous vehicle. To enable efficient and reliable autonomous vehicle control, the electronic control unit 26 may be in operative communication with the steering actuator(s) 22 embodied as an electric power steering system, the accelerator device 23, and the braking device 24. The sensors 25A of the motor vehicle 10 are capable of scanning the lane 12 and monitoring a surrounding geographical area and traffic conditions in the vicinity of the motor vehicle 10.

[0030] The sensors 25A of the vehicle 10 may include, among other things, at least one LIDAR (Light Detection and Ranging) sensor, a radar, and a camera arranged around the vehicle 10 to detect boundary indicators, such as boundary conditions, of the vehicle lane 12. The nature of the sensors 25A, their arrangement on the vehicle 10, and their operation for detecting and / or sensing the boundary indicators of the vehicle lane 12 and for monitoring the surrounding geographical area and traffic conditions are known to those skilled in the art, are not relevant to the teachings of this specification, and therefore will not be described in detail here. The vehicle 10 may additionally include sensors 25B mounted on the vehicle body and / or the powertrain 20.

[0031] The electronic control unit 26 communicates with the sensors 25A of the vehicle 10 to receive their respective measurement data relating to the detection or sensing of the vehicle lane 12 and the monitoring of the surrounding geographical area and traffic conditions. The electronic control unit 26 may alternatively be referred to as a control module, control unit, control device, control unit of the vehicle 10, computer, etc. The electronic control unit 26 may include a computer and / or processor 28 as well as software, hardware, memory, algorithms, connections (for example, to sensors 25A and 25B), etc. for managing and controlling the operation of the vehicle 10. Thus, a method described below and generally in Fig. 3, may be embodied as a program or algorithm that may be partially executed on the electronic control unit 26. It should be appreciated that the electronic control unit 26 may include a device capable of analyzing data from the sensors 25A and 25B, comparing data, making the decisions necessary to control the operation of the vehicle 10, and performing the tasks necessary to control the operation of the vehicle 10.

[0032] The electronic control unit 26 may be embodied as one or more digital computers or host machines, each including one or more processors 28, read-only memory (ROM), random access memory (RAM), electrically programmable read-only memory (EPROM), optical drives, magnetic drives, etc., a high-speed clock, analog-to-digital (A / D) circuitry, digital-to-analog (D / A) circuitry, and input / output (I / O) circuitry, I / O devices and communication interfaces, as well as signal conditioning and buffer electronics. The computer-readable memory may comprise a non-volatile / tangible medium involved in providing data or computer-readable instructions. The memory may be non-volatile or volatile. Examples of non-volatile media include optical or magnetic hard drives and other persistent storage.An example of volatile memory is dynamic random-access memory (DRAM), which can be used as main memory. Other examples of memory include flexible disks, hard disks, magnetic tape or other magnetic media, CD-ROMs, DVDs, and / or other optical media, as well as other possible storage devices such as flash memory.

[0033] The electronic control unit 26 includes a tangible, non-transferable memory 30 in which computer-executable instructions, including one or more algorithms, for controlling the operation of the motor vehicle 10 are recorded. The algorithm(s) in question may, in particular, include an algorithm configured to monitor the location of the motor vehicle 10 and determine the course of the vehicle relative to a mapped vehicle trajectory on a particular road course, which is described in detail below.

[0034] The motor vehicle 10 also includes a vehicle navigation system 34, which may be part of the integrated vehicle control system or an add-on device used to determine the vehicle's direction of travel. The vehicle navigation system 34 is also operatively connected to a global positioning system (GPS) 36 utilizing a satellite in Earth orbit. The vehicle navigation system 34, in conjunction with the GPS 36 and the aforementioned sensors 25A, may be used to automate the vehicle 10. The electronic control unit 26 communicates with the GPS 36 via the vehicle navigation system 34. The vehicle navigation system 34 uses a satellite navigation device (not shown) to receive its position data from the GPS 36, which is then correlated with the vehicle's position relative to the surrounding geographic area.Based on this information, if directions to a specific waypoint are needed, a route plan to that destination can be created and calculated. Current terrain and / or traffic information can be used to adjust the route. The current position of a vehicle 10 can be calculated using dead reckoning by using a previously determined position and extrapolating that position based on given or estimated speeds over elapsed time and course using discrete checkpoints.

[0035] The electronic control unit 26 is generally configured, that is to say programmed, to determine the localization 38 (current position in the XY plane, as in Fig. 1), determines or identifies the speed, acceleration, yaw rate, and intended path 40 and heading 42 of the motor vehicle 10 within the lane 12. The location 38, intended path 40, and heading 42 of the motor vehicle 10 may be determined via the navigation system 34 receiving data from the GPS 36, while the speed, acceleration (including longitudinal and lateral acceleration), and yaw rate may be determined from the vehicle sensors 25B. Alternatively, the electronic control unit 26 may utilize other systems or sensing sources remote from the vehicle 10, such as a camera, to determine the location 38 of the vehicle relative to the lane 12.

[0036] As previously mentioned, the motor vehicle 10 may be configured to operate in an autonomous mode controlled by the electronic control unit 26 to transport an occupant or driver 62. In such a mode, the electronic control unit 26 may also receive data from the vehicle sensors 25B to guide the vehicle along the desired path, for example, by regulating the steering actuator 22. The electronic control unit 26 may additionally be programmed to detect and monitor the steering angle (θ) of the steering actuator(s) 22 along the desired path 40, for example, during a negotiated turn. In particular, the electronic control unit 26 may be programmed to detect and monitor the steering angle (θ) by receiving and processing data signals from a steering position sensor 44 (in Fig. 1) which is connected to the steering actuator(s) 22, the accelerator device 23 and the brake device 24.

[0037] Fig. 2 illustrates a method 100 for reducing traffic congestion levels on a road network. The method 100 predicts a driver's individual contribution to traffic congestion (block 102) and determines at least one offer (block 104) that will discourage the driver from operating a motor vehicle, such as motor vehicle 10, on the roadway. With the driver's individual contribution to future traffic congestion of a road network determined and the at least one offer determined, the method 100 performs an optimization (block 106) that minimizes the costs associated with the provided offers to achieve the greatest reduction in road network congestion at the lowest cost. In one example, the method 100 will iteratively provide drivers with an offer not to operate a motor vehicle on the road network.The iteration continues until every driver accepts an offer, future congestion falls below a predetermined congestion level, or a limit on the total number of offers is reached. The limit on offers may be reached, for example, when an available pool of financial compensation has been fully distributed to the drivers.

[0038] Predicting the individual contribution of drivers to future traffic congestion levels in block 102 involves obtaining historical congestion information from a historical congestion database (block 108). The historical congestion information includes information about traffic congestion levels on a variety of different road segments that make up the road network. The historical congestion information may include traffic congestion levels, which are defined as the number of vehicles traveling per unit of time on a predetermined road segment in the road network. The historical traffic information may also include fluctuations in traffic volume relative to a specific day of the week, time of day, or holiday.The road segments forming the road network may include a predetermined length of road from the historical congestion database (block 108) that has similar characteristics, such as the intended speed, road type, or length. The method 100 uses the historical congestion information (block 108) to predict future traffic congestion levels (block 110), which are defined as the number of vehicles traveling per unit of time on a predetermined road segment in the road network.

[0039] The individual contribution of drivers to the future traffic congestion levels predicted in block 102 also includes obtaining information from a historical driver route database (block 110) containing historical driver route information about the trips taken by drivers on various road segments of the road network. The historical driver route information may include at least one of the following information: routine trip route, trip route time, vehicle dynamics, or parking information. In one example, the route timing may include a departure time, a trip duration, or a day of the week. In one example, the aforementioned driver route information is obtained through collected GPS coordinate data and sensor data from sensors 25A, 25B on a vehicle corresponding to each of the drivers.

[0040] The parking information could include the time it took the driver to search for a parking space, if the driver double-parked the vehicle 10, or if the driver blocked multiple parking spaces while parking. This information can be obtained from the sensors 25A, 25B by analyzing images of the surroundings of the parked vehicle 10 to determine if a portion of the road section is blocked or if the vehicle 10 is blocking multiple parking spaces. The sensors 25A, 25B and the GPS coordinates can also be used to determine how long it took the driver to park within a predetermined distance of a final destination.

[0041] Vehicle dynamics may include at least one of the following features: speed, speed profile, acceleration / deceleration profiles, response times to preceding vehicles, distance to the vehicle in front, left lane usage, and cooperation with other vehicles, for example, allowing other vehicles to move between traffic lanes. One feature of this description is improved historical route information for the driver through the use of information obtained from sensors 25A, 25B directly on the vehicle 10 as opposed to a mobile device in the vehicle 10. This can better determine whether a driver is exhibiting certain behaviors that may contribute to increased traffic congestion, such as the vehicle dynamics identified above.

[0042] The method 100 performs congestion predictions in block 112 based on the information obtained in blocks 108 and 110. The congestion predictions may include future traffic congestion levels for the road network. In one example, the prediction of future traffic congestion levels may be determined by analyzing the historical congestion database in block 108 and predicting future traffic congestion levels based on historical traffic congestion levels on a corresponding road segment at a particular time of day during a week.

[0043] The congestion prediction determined in block 112 may also include a future individual driver congestion prediction at the predetermined future time. The future individual driver congestion prediction may be determined for a road segment per unit of time for each of the individual drivers from the historical driver route database in block 110. The prediction of future individual traffic congestion levels may be determined by analyzing the vehicle dynamics identified above, obtained from the historical driver route database in block 110, and predicting how each of the individual drivers will contribute to traffic congestion along the given road segment at the predetermined future time. In one example, the future individual congestion prediction includes units corresponding to the future congestion prediction to enable comparison of the two numbers.

[0044] In block 114, each driver's individual contribution to the future congestion prediction is calculated for a specific route that will be traveled by one of the drivers in the future. The individual contribution to future congestion defines an impact for each driver on the future congestion prediction. In one example, the impact is defined based on the scores calculated for the driver on the given route at the future time.

[0045] Different approaches can be used to calculate each driver's contribution to traffic congestion, depending on the available information. In one example, if the historical driver route database (block 108) contains information for the driver on the given route, block 112 can calculate the driver's contribution to traffic congestion on the given route by comparing the future individual driver congestion prediction with the future traffic congestion prediction. Block 112 can then output the driver's contribution to congestion on the given route. Block 112 analyzes the vehicle dynamics described above and determines whether a driver with these vehicle dynamics operating a vehicle on this route would increase the level of congestion.In addition, block 112 may determine how congestion on a particular road segment would improve if that driver were removed from the congestion forecast to reduce the number of vehicles traveling on that route segment.

[0046] In another example, block 114 calculates the contribution to congestion for a driver traveling on a new route segment not included in the historical driver route database (block 110). To calculate the contribution to congestion under these circumstances, block 114 performs a sampling procedure to determine the individual contribution to predicting future traffic congestion levels.

[0047] In the sampling technique, a representative sample of driver scenarios along routes available in the historical driver route database (block 114) and the driver composition, including at least one routine route, route time, vehicle dynamics, demographic data, or parking information, from the historical congestion database (block 108) is provided to a simulator in block 112. The simulator simulates how the driver traveling on the new route would behave with respect to the predicted vehicle dynamics, based on the sample of driver scenarios and the composition of other drivers who previously traveled this route. The sampling technique can then output a driver's individual contribution to traffic congestion on the new route.

[0048] In another example, a driver's contribution to traffic congestion is determined by a supervised machine learning (ML) model at block 112 for a driver traveling on a route not included in the historical driver route database (block 110). The ML model receives driver compositions available for a given driver along multiple routes from the historical driver route database (block 110), as well as driver compositions for other drivers from the historical congestion database (block 108). The driver compositions for the other drivers may be for the same route as the future route or for a different route similar to the future route based on the traffic congestion level. The ML model may then model the relationship between the driver composition for the given driver and the congestion level.

[0049] The ML model can then use the historical congestion data (block 108) to determine a congestion-dependent driving behavior model. The congestion-dependent driving behavior model describes a model driver who does not contribute to congestion. In one example, the model driver can provide a baseline for comparison with other drivers. In block 112, a "gap" between each driver and the model driver can then be quantified by determining a difference between the model driver and the other drivers. This quantification represents how the driver will contribute to traffic congestion. The greater the "gap" determined for an individual driver, the greater the individual driver's contribution to congestion.

[0050] Once the driver contribution calculations have been performed for the plurality of drivers, the drivers are ranked based on their individual contribution to congestion along future travel routes (block 112) to determine which drivers make the highest individual contribution to at least one congested road segment within the road network. In this way, the method 100 can determine where individual drivers will contribute to congestion and the individual contribution of each driver to congestion on a particular route.

[0051] The inventive predictor 104 of the method 100 predicts an incentive that persuades drivers not to use the motor vehicle on a particular day or for a particular period of time within the day. A driver usage model 120 receives the drivers' preferences (block 118) and the drivers' response history (block 116). The drivers' preferences may include at least one of the following: driver demographics, a routine driving route, or a preference between a cash offer, an alternative mode of transportation, or the option to stay home to avoid contributing to traffic congestion.

[0052] The driver response history (block 116) may include a history of offers provided to drivers, as well as a record of offers accepted by drivers. The driver response history may also include the context for the offers made. In particular, the context may include at least the time of day of the future trip route, the day of the week of the future trip, the location of the future trip, and the frequency with which the driver travels the future trip route.

[0053] Using this information, the method 100 estimates the driver utility for each of the drivers in block 120. The utility estimate for each of the drivers quantifies the degree of utility each driver attributes to operating the vehicle along the future travel route. Specifically, the estimate determines the utility of a minimum monetary offer, which can be learned from demographic information and the context of the future travel route (e.g., day of the week or destination of the future travel route, such as a school).

[0054] The method 100 then implements a supply utility solver at block 122. The supply utility solver uses the estimate of the driver utility to determine a minimum supply that exceeds the driver utility such that the driver will not drive the vehicle on the at least one congested road segment in the road network.

[0055] The method 100 then performs an optimization (block 106) based on the minimum bid determined for the driver to avoid operating the vehicle and the individual drivers' contribution to future congestion levels. The optimization determines the minimum bid required to achieve a desired reduction in future congestion. EQ. ​​1 illustrates an example equation for a minimum-cost congestion optimization. ΔSLA(t,c) provides the required relief to meet a particular Service Level Agreement (SLA) at time t (#vehicles / time). MarginalCongestion(d,c) also predicts the individual congestion contribution for a driver d and context c (#vehicles / time). MinimumIncentive(d,c) provides the minimum incentive above which driver d is likely to avoid driving in context c (price*time / #vehicles).The optimization goal is to minimize EQ. 1 such that Σ. d MinimumIncentive (d, c) > ΔSLA (t, c) for each context and each time. min∑c,tΔSLA∑dMinimalIncentive(d,c)

[0056] Fig. Figure 3 shows an example of a diagram 200 that shows the benefit to the driver compared to the traffic load. As in Fig. As shown in Figure 3, the utility of a trip 202, for example, during rush hour, decreases as a function of traffic congestion (number of vehicles per unit time traveling on a road section). In one example, the utility µ is the utility the driver receives from the trip or the utility the driver receives from accepting an offer 206 not to travel. At a certain point 204 along the utility of the trip 202, the utility the driver receives from traveling on the future route becomes less than the utility the driver would receive from accepting the offer 206 to avoid traveling on the future route.

[0057] Fig. 4 shows an example of a diagram 300 that represents the utility µ versus the supply. As in Fig. As shown in Figure 4, the utility of the offer 302 increases with increasing offer amount up to an upper limit 304 for the offer. There is also a point 306 at which the offer 308 is high enough to ensure the probability that the driver will accept it to avoid a trip. While the offer amount in Fig. 4 could be monetary, the offer could also include an alternative form of transport, such as ride-sharing, which reduces the number of vehicles on a given route.

[0058] The optimization performed in block 106 outputs which drivers accepted the offer not to take the future route and which drivers rejected the offer. This information is transmitted via communication path 124 and stored in the driver response history in block 118.

[0059] Additionally, a list of drivers who accepted the offer to avoid traveling by vehicle is sent to the congestion predictor in block 110 via communication path 126. The congestion predictor in block 110 can then update the future traffic congestion levels by removing the individual contribution of each driver who accepted the offer to determine the updated future congestion levels. The driver contribution calculation in block 114 can then establish a ranking of the remaining drivers based on their contribution to the future traffic congestion levels. This ranking is also linked to the future travel routes the driver will travel to determine each driver's individual contribution to future traffic congestion along the future travel routes.

[0060] This information is then forwarded to block 106 for further optimization. Specifically, the optimization performed in block 106 determines whether the routes the drivers are traveling require further reductions in congestion levels. During the optimization, higher-ranking drivers are also offered higher incentives based on their individual contribution to congestion. The method 100 iteratively continues the above approach for reducing congestion levels with additional offers until each driver accepts the offers, a sufficient number of drivers accept the offer not to take the future route, or no further incentives are available for the drivers.

Claims

[1] A method (100) for reducing traffic congestion on a road network, the method (100) comprising: Predicting future traffic congestion levels on the road network based on historical traffic congestion levels on the road network; predicting an individual contribution to future traffic congestion levels for each of a plurality of drivers based on future routes corresponding to each of the plurality of drivers, the future routes comprising at least one road segment through the road network; Identifying at least one congested road section based on future traffic congestion levels for the road network; Identifying the plurality of drivers with a highest individual contribution to the at least one congested road segment; and Providing the majority of drivers with the highest individual contributions to the at least one congested road section a first offer to avoid operating a vehicle on the road network. [2] The method (100) of claim 1, wherein the individual contribution to future traffic congestion levels is determined based on historical driver route information. [3] The method (100) of claim 2, wherein the historical driver route information comprises at least one of the following: a routine trip route, a trip time, vehicle dynamics, or parking information recorded for each of the plurality of drivers associated with a route segment corresponding to the future routes. [4] The method (100) of claim 3, wherein the route section corresponds to a new route section not found in the historical driver route information. [5] The method (100) of claim 4, comprising predicting driver route information for the new route section based on the historical driver route information for other route sections in the road network. [6] The method (100) of claim 1, wherein the first offer comprises financial compensation or an alternative mode of transportation. [7] The method (100) of claim 1, wherein identifying the plurality of drivers with the highest individual contribution to the at least one congested road segment comprises ranking the plurality of drivers according to their individual contribution and providing the first offer to at least one driver with the highest ranking. [8] The method (100) of claim 7, wherein the first offer is provided to the plurality of highest-ranked drivers having corresponding future routes through the most congested road network determined by the future traffic congestion levels. [9] The method (100) of claim 1, comprising determining a first group of the plurality of drivers who have accepted the first offer, and updating the future traffic congestion levels by removing the individual contribution to the future traffic congestion levels for the first group of the plurality of drivers to determine updated future traffic congestion levels. [10] The method (100) of claim 9, comprising identifying a remaining group of the plurality of drivers who did not accept the first offer that have the highest individual contribution to the updated future traffic congestion levels.

Citation Information

Patent Citations

  • Road traffic flow increasing method involves determining number of lanes in direction of travel by driver assistance systems and vehicle security systems

    DE102007008880A1

  • COLLABORATIVE DETECTION AND PREVENTION OF PHANTOM BLOCKAGES

    DE102022107774A1

  • Learning road feature delay times based on aggregate driver behavior

    US20110224893A1

  • Contextual driver behavior monitoring

    US20170057411A1

  • Traffic aware lane determination for human driver and autonomous vehicle driving system

    US9672734B1