Methods and systems for estimating traffic jam lane using lane connectivity data

Abstract

To provide a system for estimating a lane-level traffic jam.SOLUTION: A system includes one or more processors. The one or more processors are programmed to: acquire a first road link, a second road link connected to the first road link, and a third road link connected to the first road link, on the basis of a map; identify a traffic jam section in the first road link on the basis of driving data of vehicles; generate initial lane-level traffic jam distribution in the first road link; update the initial lane-level traffic jam distribution in the first road link on the basis of traffic jam information on the second road link and the third road link; and transmit the lane-level traffic jam distribution to vehicles approaching the traffic jam section.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] FIELD OF THE INVENTION The present disclosure relates to systems and methods for estimating lane-level traffic congestion, and more particularly to systems and methods for estimating lane-level traffic congestion using lane connectivity data. [Background technology]

[0002] Lane-level traffic, where the average speeds of vehicles in different lanes vary, can increase collision risk, especially rear-end collisions. In addition, when different traffic levels exist, drivers may miss the rear of the traffic queue and attempt to cut in. Existing navigation systems do not provide lane-level traffic. For example, when a right exit is congested, existing navigation systems do not show the congested right lane, but instead show the entire road section with no traffic due to driving data from vehicles driving at normal speeds in other lanes.

[0003] Therefore, a need exists for a system and method that accurately estimates lane-level traffic information. Summary of the Invention

[0004] The present disclosure provides systems and methods for estimating lane-level traffic congestion using lane change signals in connected vehicles.

[0005] In one embodiment, a system for estimating lane-level traffic congestion is provided, including one or more processors that are programmed to: obtain, based on a map, a first road link, a second road link connected to the first road link, and a third road link connected to the first road link; identify a traffic congestion section on the first road link based on driving data of a vehicle; generate an initial lane-level traffic congestion distribution on the first road link; update the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link; and transmit the lane-level traffic congestion distribution to a vehicle approaching the traffic congestion section.

[0006] In another embodiment, a method for determining lane-level traffic includes: obtaining a first road link, a second road link connected to the first road link, and a third road link connected to the first road link based on a map; identifying a traffic congestion section on the first road link based on driving data of a vehicle; generating an initial lane-level traffic congestion distribution on the first road link; updating the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link; and transmitting the lane-level traffic congestion distribution to a vehicle approaching the traffic congestion section.

[0007] These and further features provided by the embodiments of the present disclosure will be more fully understood when the following detailed description is considered in conjunction with the drawings. [Brief explanation of the drawings]

[0008] The embodiments set forth in the drawings are illustrative and exemplary in nature and are not intended to limit the present disclosure. The following detailed description of illustrative embodiments can be understood when read in conjunction with the following drawings, in which like structure is designated with like reference numerals and in which:

[0009] [Figure 1A] FIG. 1A schematically depicts a system for estimating lane-level traffic congestion using lane connectivity data according to one or more embodiments shown and described herein. [Figure 1B] FIG. 1B depicts using lane connectivity data to estimate the probability of traffic congestion in each of the lanes, according to one or more embodiments shown and described herein. [Figure 1C] FIG. 1C illustrates an exemplary lane-level traffic distribution image for a road according to one or more embodiments shown and described herein. [Figure 1D] FIG. 1D depicts using lane connectivity data to estimate the probability of traffic congestion in each of the lanes, according to one or more embodiments shown and described herein. [Figure 2] FIG. 2 schematically depicts a system for estimating lane-level traffic congestion using lane connectivity data according to one or more embodiments shown and described herein. [Figure 3] FIG. 3 depicts a flowchart for estimating lane-level traffic congestion according to one or more embodiments shown and described herein. [Figure 4A] FIG. 4A depicts estimating the probability of traffic congestion in each of the lanes using the route of a connected vehicle, according to one or more embodiments shown and described herein. [Figure 4B] FIG. 4B depicts estimating the probability of traffic congestion in each of the lanes using the route of a connected vehicle according to one or more embodiments shown and described herein. [Figure 5] FIG. 5 depicts estimating the probability of traffic congestion in each of the lanes using lane connectivity information and lane change signals of a connected vehicle, according to one or more embodiments shown and described herein. [Figure 6] FIG. 6 depicts estimating the probability of traffic congestion in each of the lanes using lane connection information and lane change signals of a connected vehicle, according to one or more embodiments shown and described herein. [Figure 7] FIG. 7 depicts estimating the probability of traffic congestion in each of the lanes using lane connection information and lane change signals of a connected vehicle, according to one or more embodiments shown and described herein. DETAILED DESCRIPTION OF THE INVENTION

[0010] Embodiments disclosed herein include systems and methods for estimating lane-level traffic congestion, according to one or more embodiments shown and described herein. In particular, as used herein, lane-level traffic congestion refers to a situation in which the average speed of vehicles in one lane of a road substantially differs from the average speed of vehicles in another lane of the road. More specifically, lane-level traffic congestion may refer to a situation in which the average speed of vehicles in one lane of a road within a particular region differs from the average speed of vehicles in another lane of the road within the particular region by more than a threshold amount.

[0011] 1A , the server obtains a first road link 110, a second road link 120 connected to the first road link 110, and a third road link 130 connected to the first road link 110 based on a map. The server identifies a traffic congestion section 140 on the first road link 110 based on driving data of a vehicle on the first road link 110. The server 240 generates an initial lane-level traffic congestion distribution on the first road link 110, for example, each lane on the first road link 110 has a 33% probability of having traffic congestion thereon. The server 240 updates the initial lane-level traffic congestion distribution on the first road link 110 based on traffic congestion information on the second road link 120 and the third road link 130. For example, if the third road link 130 has a traffic congestion section thereon and the second road link 120 does not have a traffic congestion section thereon, the server 240 estimates that the lane 115 of the first road link 110 connected to the lane 131 of the third road link 130 has a relatively high probability of having a traffic congestion thereon, and estimates that the lanes 111 and 113 of the first road link 110 connected to the lanes 121 and 123 of the second road link 120 have a relatively low probability of having a traffic congestion thereon. Based on the estimation, the server 240 updates the initial lane-level traffic congestion distribution. The server 240 then transmits the updated lane-level traffic congestion distribution to vehicles approaching the traffic congestion section 140.

[0012] According to the present disclosure, the system identifies the lane ID of a traffic jam by analyzing lane connection data and / or vehicle route information. The system identifies the lane ID of a traffic jam without requesting the lane ID from the vehicle.

[0013] 1A schematically depicts a system for estimating lane-level traffic congestion using lane connectivity data, according to one or more embodiments shown and described herein. In an embodiment, the system includes first and second connected vehicles 100 and 102 and a server 240. Server 240 may be a local server, including, but not limited to, a roadside unit, an edge server, and the like. In some embodiments, server 240 may be a remote server, such as a cloud server.

[0014] Each of the first and second connected vehicles 100 and 102 may be a vehicle, including an automobile or any other passenger or non-passenger vehicle, such as a land vehicle, an underwater vehicle, and / or an air vehicle, etc. In some embodiments, one or more of the first and second connected vehicles 100 and 102 may be an unmanned aerial vehicle (UAV), commonly known as a drone.

[0015] The first and second connected vehicles 100 and 102 may be autonomous connected vehicles, each navigating its environment with limited or no human input. The first and second connected vehicles 100 and 102 are equipped with internet access and share data with other devices both inside and outside the first and second connected vehicles 100 and 102. Each of the first and second connected vehicles 100 and 102 may include actuators, such as engines, motors, and the like, that drive the vehicle. The first and second connected vehicles 100 and 102 may communicate with a server 240. The server 240 may communicate with vehicles in an area covered by the server 240. The server 240 may communicate with other servers covering different areas. The server 240 may communicate with a remote server and transmit information collected by the server 240 to the remote server.

[0016] 1A , connected vehicles 100 and 102 are traveling on a first road link 110 that includes multiple lanes, e.g., lanes 111, 113, and 115. The first road link 110 is connected to a second road link 120 and a third road link 130. The second road link 120 includes lanes 121 and 123, and the third road link 130 includes a single lane 131. The connected vehicles 100 and 102 transmit driving data of the connected vehicles 100 and 102 to a server 240, including, but not limited to, location, speed, radial acceleration, heading, wheel angle, turn signal status, and the like. While FIG. 1A depicts two connected vehicles 100 and 102, the server 240 may receive driving data from more than two connected vehicles 100 and 102. Based on the driving data from the connected vehicle, particularly the speed of the connected vehicle, the server 240 may identify a congested traffic section 140 on the first road link 110.

[0017] The connected vehicles 100 and 102 may not be equipped with high-precision GPS sensors, and as a result, the connected vehicles 100 and 102 may not know which lane the connected vehicles 100 and 102 are driving in. For example, the connected vehicle 100 has information that the connected vehicle 100 is driving on the first road link 110, but the connected vehicle 100 is not certain which of the lanes 111, 113, and 115 the connected vehicle 100 is traveling in. Similarly, the connected vehicle 102 is not certain about the lane-level trajectory information. Therefore, when the connected vehicles 100 and 102 transmit their driving data to the server 240, the driving data does not include lane ID information, i.e., identification information about the lane in which the corresponding vehicle is driving. In this regard, server 240 may identify traffic congestion section 140, but server 240 cannot identify which lanes among lanes 111, 113, and 115 include traffic congestion and which lanes do not include traffic congestion.

[0018] In an embodiment, the system may estimate lane-level traffic congestion conditions using lane connection data and traffic congestion information on different road links. Figure 1B depicts estimating the probability of traffic congestion in each of the lanes using lane connection data according to one or more embodiments shown and described herein.

[0019] 1B, the server 240 may generate a lane connection graph used to identify the next and previous lanes connected to a particular lane. For example, in FIG. 1B, the lane connection graph indicates that lane 115 of the first road link 110 is connected to lane 131 of the third road link 130, and the lane connection graph indicates that lanes 111 and 113 are connected to lanes 121 and 123 of the second road link 120. The server may use data received from the connected vehicles and the vehicles' matched positions in the map to estimate congestion dynamics, such as the positions of the front and rear of the congestion section and the average speed of vehicles in the congestion. The estimated congestion dynamics may indicate that the first road link 110 has a traffic congestion near the end of the first road link 110.

[0020] The server 240 may then generate an initial lane-level congestion distribution for the first road link 110. Because there are three lanes 111, 113, and 115, the initial lane-level congestion distribution has a uniform distribution as [0.33, 0.33, 0.33], meaning that there is a 33% chance of a traffic congestion in each lane. The server 240 determines that a traffic congestion exists near the beginning of the third road link 130 based on driving data received from vehicles on the third road link 130. Because the third road link 130 has only one lane, the lane-level congestion distribution is [1.0].

[0021] The server may determine, based on driving data received from vehicles on the second road link 120, that the second road link 120 does not have a traffic congestion near the beginning of the second road link 120. The lane-level congestion distribution for the second road link 120 is [0.05, 0.05], which means that each of the lanes 121 and 123 has a 5% probability of having a traffic congestion there.

[0022] Using the lane connectivity information obtained from the map, the server 240 calculates the probability that a traffic jam is in the ith lane using Equation 1 below:

[0023] Probability of the ith lane = γ * initial probability * weight of the next lane Equation 1

[0024] where γ is a weighting parameter (eg, γ=0.7), and the weight of the next lane is the probability that there is a traffic jam in the next lane connected to the i-th lane.

[0025] For example, for lane 111, the initial probability that a traffic jam is in lane 111 is 0.33. The weight of the next lane is the probability that a traffic jam is in lane 121, which is 0.05. Therefore, the probability that a traffic jam is in lane 111 is 0.7*0.33*0.05=0.01. Similarly, for lane 113, the initial probability that a traffic jam is in lane 113 is 0.33. The weight of the next lane is the probability that a traffic jam is in lane 123, which is 0.05. Therefore, the probability that a traffic jam is in lane 113 is 0.7*0.33*0.05=0.01. For lane 115, the initial probability that a traffic jam is in lane 115 is 0.33. The weight of the next lane is the probability that a traffic jam is in lane 131, which is 1. Therefore, the probability that a traffic jam is in lane 115 is 0.7*0.33*1.0=0.23. Because the probabilities must sum to 1, server 240 inflates and normalizes the calculated probability of [0.01, 0.01, 0.23] to obtain an updated lane-level congestion distribution of [0.04, 0.04, 0.92].

[0026] Server 240 may transmit information regarding the updated lane-level traffic congestion distribution to connected vehicles. In an embodiment, server 240 may transmit information regarding the updated lane-level traffic congestion distribution to connected vehicles approaching traffic congestion section 140, and the connected vehicles approaching traffic congestion section 140 may autonomously drive away from the lane with the traffic congestion. For example, if a connected vehicle approaching traffic congestion section 140 is driving in lane 115, the connected vehicle may proactively change lanes to the left to avoid getting stuck in traffic congestion 142.

[0027] In some embodiments, as shown in Figure 1C, a connected vehicle receiving the updated lane-level traffic congestion distribution from server 240 may display the lane-level traffic congestion distribution on an output device, such as the vehicle's head unit or a navigation app on a user's smartphone in the vehicle. Figure 1C shows an example lane-level traffic distribution image for first road link 110. Lane 111 includes bar 151, and lane 113 includes bar 153. Bars 151 and 153 indicate lanes without traffic congestion. Lane 115 includes bars 155 and 157. Bar 155 indicates traffic congestion, and bar 157 indicates a relatively slow-speed driving section.

[0028] FIG. 1D depicts estimating the probability of a traffic jam in each of the lanes using lane connection data, according to one or more embodiments shown and described herein. In FIG. 1D , the server 240 may generate a lane connection graph used to identify the next and previous lanes connected to a particular lane. For example, in FIG. 1D , the lane connection graph indicates that lane 131 of the third road link 130 is connected to lane 115 of the first road link 110, and the lane connection graph indicates that lanes 121 and 123 of the second road link 120 are connected to lanes 111 and 113 of the first road link 110. The server 240 may use the data received from the connected vehicle and the vehicle's matched position in the map to estimate congestion dynamics, such as the locations of the front and rear of the traffic congestion section and the average speed of the vehicle in the traffic congestion. The estimated congestion dynamics may indicate that the rear of the traffic congestion section is near the beginning of the first road link 110.

[0029] The server 240 may then generate an initial lane-level congestion distribution for the first road link 110. Because there are three lanes 111, 113, and 115, the initial lane-level congestion distribution has a uniform distribution as [0.33, 0.33, 0.33], meaning that there is a 33% chance of a traffic congestion in each lane. The server 240 determines that a traffic congestion exists near the end of the third road link 130 based on driving data received from vehicles on the third road link 130. Because the third road link 130 has only one lane, the lane-level congestion distribution is [1.0].

[0030] The server may determine, based on driving data received from vehicles on the second road link 120, that the second road link 120 does not have traffic congestion near the end of the second road link 120. The lane-level congestion distribution for the second road link 120 is [0.05, 0.05].

[0031] Using the lane connectivity information obtained from the map, the server 240 calculates the probability that a traffic congestion is in a lane using Equation 1 above and obtains an updated lane-level congestion distribution of [0.04, 0.04, 0.92], which indicates that lane 115 has the highest probability of having a traffic congestion there.

[0032] 2 schematically depicts a system for estimating lane-level traffic congestion using lane connectivity data according to one or more embodiments shown and described herein. The system for estimating traffic congestion lanes includes a first connected vehicle system 200, a second connected vehicle system 220, and a server 240.

[0033] It should be noted that while first connected vehicle system 200 and second connected vehicle system 220 are depicted separately, in some embodiments, each of first connected vehicle system 200 and second connected vehicle system 220 may be included within a vehicle, e.g., within each of connected vehicles 100 and 102 of FIG. 1A , respectively. In embodiments in which first connected vehicle system 200 and second connected vehicle system 220 are included within a vehicle, the vehicle may be an automobile or any other passenger or non-passenger vehicle, such as a land vehicle, an underwater vehicle, and / or an air vehicle. In some embodiments, the vehicle is an autonomous vehicle that navigates its environment with limited or no human input.

[0034] The first connected vehicle system 200 includes one or more processors 202. Each of the one or more processors 202 may be any device capable of executing machine-readable executable instructions. Accordingly, each of the one or more processors 202 may be a controller, an integrated circuit, a microchip, a computer, or any other computing device. The one or more processors 202 are connected to a communication path 204 that provides signal interconnection between various modules of the system. Thus, the communication path 204 may communicatively connect any number of processors 202 to each other, enabling the modules connected to the communication path 204 to operate in a distributed computing environment. Specifically, each of the modules may operate as a node that can send and / or receive data. As used herein, the term "communicatively connected" means that the connected components are capable of exchanging data signals with each other, such as, for example, electrical signals over a conductive medium, electromagnetic signals over the air, optical signals over optical waveguides, and the like.

[0035] Thus, communication path 204 may be formed of any medium capable of transmitting a signal, such as, for example, a conductive wire, a conductive trace, an optical waveguide, or the like. In some embodiments, communication path 204 may facilitate the transmission of wireless signals, such as WiFi, Bluetooth, near field communication (NFC), and the like. Furthermore, communication path 204 may be formed of a combination of media capable of transmitting a signal. In one embodiment, communication path 204 comprises a combination of conductive traces, conductive wires, connectors, and buses that cooperate to enable the transmission of electrical data signals to components such as processors, memories, sensors, input devices, output devices, and communication devices. Thus, communication path 204 may comprise, for example, a vehicle bus, such as a LIN bus, a CAN bus, a VAN bus, and the like. Furthermore, it should be noted that the term “signal” refers to a waveform (e.g., an electrical waveform, an optical waveform, a magnetic waveform, a mechanical waveform, or an electromagnetic waveform), such as DC, AC, a sine wave, a triangular wave, a square wave, a vibration, and the like, that is capable of traveling through a medium.

[0036] The first connected vehicle system 200 includes one or more memory modules 206 coupled to the communication path 204. The one or more memory modules 206 may comprise RAM, ROM, flash memory, a hard drive, or any device capable of storing machine-readable executable instructions such that the machine-readable executable instructions can be accessed by the one or more processors 202. The machine-readable executable instructions may comprise logic or algorithms written in any programming language of any generation (e.g., 1GL, 2GL, 3GL, 4GL, or 5GL), such as a machine language that can be executed directly by a processor, or logic or algorithms written in assembly language, object-oriented programming (OOP), scripting language, microcode, or the like that can be compiled or assembled into machine-readable executable instructions and stored in the one or more memory modules 206. Alternatively, the machine-readable executable instructions may be written in a hardware description language (HDL), such as logic implemented via a field programmable gate array (FPGA) configuration or an application-specific integrated circuit (ASIC), or equivalent. Thus, the methods described herein may be implemented in any conventional computer programming language, as pre-programmed hardware elements, or as a combination of hardware and software components.

[0037] The one or more memory modules 206 may include machine-readable instructions that, when executed by the one or more processors 202, identify a traffic congestion section based on vehicle driving data, obtain a first road link including the traffic congestion section based on a map, as well as a second road link and a third road link connected to the first road link, generate an initial lane-level traffic congestion distribution on the first road link, update the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link, and transmit the lane-level traffic congestion distribution to a vehicle approaching the traffic congestion section.

[0038] Still referring to FIG. 2 , first connected vehicle system 200 includes one or more sensors 208. One or more sensors 208 may be any device having an array of sensing devices capable of detecting radiation in the ultraviolet, visible, or infrared wavelength bands. One or more sensors 208 may have any resolution. In some embodiments, one or more optical components, such as mirrors, fisheye lenses, or any other type of lens, may be optically coupled to one or more sensors 208. In some embodiments, one or more sensors 208 may also provide navigation support. That is, data captured by one or more sensors 208 may be used to navigate connected vehicle 100 autonomously or semi-autonomously.

[0039] In some embodiments, the one or more sensors 208 include one or more imaging sensors configured to operate in the visible and / or infrared spectrum to detect visible and / or infrared light. Furthermore, while certain embodiments described herein are described with reference to hardware that detects light in the visible and / or infrared spectrum, it should be understood that other types of sensors are contemplated. For example, the systems described herein may include one or more LIDAR, radar, sonar, or other types of sensors, the data of which may be incorporated into or supplement the data collection described herein to develop a more complete real-time traffic picture. A ranging sensor, such as radar, may be used to obtain rough depth and speed information about the field of view of the first connected vehicle system 200. The first connected vehicle system 200 may use one or more imaging sensors to capture road boundaries, static objects, moving objects, and the like.

[0040] In operation, one or more sensors 208 capture image data and communicate the image data to one or more processors 202 and / or other systems communicatively connected to the communication path 204. The image data may be received by one or more processors 202, which may process the image data using one or more image processing algorithms. Any known or undeveloped video and image processing algorithms may be applied to the image data to identify objects or situations. Exemplary video and image processing algorithms include, but are not limited to, kernel-based tracking (e.g., mean-shift tracking) and contour processing algorithms. Generally, video and image processing algorithms may detect objects and movement from sequential or individual frames of image data. One or more object recognition algorithms may be applied to the image data to extract objects and determine their relative locations to one another. Any known or undeveloped object recognition algorithms may be used to extract objects or even optically extract characters and images from the image data. Exemplary object recognition algorithms include, but are not limited to, scale invariant feature transform ("SIFT"), speedup of robust features ("SURF"), and edge detection algorithms.

[0041] First connected vehicle system 200 includes a satellite antenna 214 connected to communication path 204 such that communication path 204 communicatively connects satellite antenna 214 to other modules of first connected vehicle system 200. Satellite antenna 214 is configured to receive signals from Global Positioning System satellites. Specifically, in one embodiment, satellite antenna 214 includes one or more conductive elements that interact with electromagnetic signals transmitted by Global Positioning System satellites. The received signals are converted by one or more processors 202 into data signals indicative of the location (e.g., latitude and longitude) of satellite antenna 214 or objects located near satellite antenna 214.

[0042] The first connected vehicle system 200 includes one or more vehicle sensors 212. Each of the one or more vehicle sensors 212 is connected to the communication path 204 and communicatively coupled to the one or more processors 202. The one or more vehicle sensors 212 may include one or more motion sensors that detect and measure vehicle orientation, acceleration, motion, and changes in motion. The motion sensors may include an inertial measurement unit. Each of the one or more motion sensors may include one or more accelerometers and one or more gyroscopes. Each of the one or more motion sensors converts sensed physical vehicle movement into a signal indicative of the vehicle's orientation, rotation, speed, or acceleration. The one or more vehicle sensors 212 may include wheel sensors that detect wheel angle.

[0043] Still referring to FIG. 2 , first connected vehicle system 200 includes network interface hardware 216 that communicatively couples first connected vehicle system 200 to second connected vehicle system 220 and / or server 240. Network interface hardware 216 may be any device that can be communicatively coupled to communication path 204 and capable of transmitting and / or receiving data over a network. Thus, network interface hardware 216 may include a communications transceiver that transmits and / or receives any wired or wireless communications. For example, network interface hardware 216 may include an antenna, a modem, a LAN port, a Wi-Fi card, a WiMax card, mobile communications hardware, short-range communications hardware, satellite communications hardware, and / or any wired or wireless hardware that communicates with other networks and / or devices. In one embodiment, network interface hardware 216 includes hardware configured to operate according to the Bluetooth® wireless communications protocol. Network interface hardware 216 of first connected vehicle system 200 may transmit its data to server 240. For example, the network interface hardware 216 of the first connected vehicle system 200 may transmit captured point clouds, vehicle data, location data, and the like generated by the first connected vehicle system 200 to other connected vehicles or to the server 240.

[0044] First connected vehicle system 200 may connect with one or more external vehicles and / or external processing devices (e.g., server 240) via direct connections. The direct connections may be vehicle-to-vehicle (“V2V connection”) or vehicle-to-everything (“V2X connection”). V2V or V2X connections may be established using any suitable wireless communication protocol described above. Vehicle-to-vehicle connections may utilize sessions that are time-based and / or location-based. In embodiments, connections between vehicles or between vehicles and infrastructure elements may utilize one or more connecting networks (e.g., network 250), which may be alternatives to or in addition to direct connections (e.g., V2V or V2X) between vehicles or between vehicles and infrastructure. As a non-limiting example, vehicles may act as infrastructure nodes to form a mesh network and dynamically connect on an ad-hoc basis. In this manner, vehicles may freely enter and / or exit the network, allowing the mesh network to self-organize and self-modify over time. Other non-limiting network examples include vehicles forming peer-to-peer networks with other vehicles or utilizing centralized networks that rely on specific vehicle and / or infrastructure elements. Still other examples include networks that use centralized servers and other central computing devices to store and / or relay information between vehicles.

[0045] Still referring to FIG. 2 , first connected vehicle system 200 may be communicatively coupled to server 240 by network 250. In one embodiment, network 250 may include one or more computer networks (e.g., personal area networks, local area networks, or wide area networks), cellular networks, satellite networks, and / or global positioning systems, and combinations thereof. Thus, first connected vehicle system 200 may be communicatively coupled to network 250 via a wide area network, local area network, personal area network, cellular network, satellite network, etc. Suitable local area networks may include wired Ethernet and / or wireless technologies such as, for example, Wireless Fidelity (Wi-Fi). Suitable personal area networks may include wireless technologies such as, for example, IrDA, Bluetooth, Wireless USB, Z-Wave, ZigBee, and / or other short-range communication protocols. Suitable cellular networks include, but are not limited to, technologies such as LTE, WiMAX, UMTS, CDMA, and GSM.

[0046] 2 , server 240 includes one or more processors 242, one or more memory modules 246, network interface hardware 248, and communication path 244. One or more processors 242 may be a controller, an integrated circuit, a microchip, a computer, or any other computing device. One or more memory modules 246 may comprise RAM, ROM, flash memory, a hard drive, or any device capable of storing machine-readable executable instructions such that the machine-readable executable instructions can be accessed by one or more processors 242. In some embodiments, communication path 244 may be similar to communication path 204.

[0047] The one or more memory modules 246 may include machine-readable instructions that, when executed by the one or more processors 242, identify a traffic congestion section based on vehicle driving data, obtain a first road link including the traffic congestion section based on a map, as well as a second road link and a third road link connected to the first road link, generate an initial lane-level traffic congestion distribution on the first road link, update the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link, and transmit the lane-level traffic congestion distribution to a vehicle approaching the traffic congestion section.

[0048] Still referring to FIG. 2 , the second connected vehicle system 220 includes one or more processors 222, one or more memory modules 226, one or more sensors 228, one or more vehicle sensors 232, a satellite antenna 234, network interface hardware 236, and a communication path 224 communicatively coupled to other components of the second connected vehicle system 220. The components of second connected vehicle system 220 may be structurally similar and have similar functionality to the corresponding components of first connected vehicle system 200 (e.g., one or more processors 222 correspond to one or more processors 202, one or more memory modules 226 correspond to one or more memory modules 206, one or more sensors 228 correspond to one or more sensors 208, one or more vehicle sensors 232 correspond to one or more vehicle sensors 212, satellite antenna 234 corresponds to satellite antenna 214, network interface hardware 236 corresponds to network interface hardware 216, and communication path 224 corresponds to communication path 204).

[0049] The one or more memory modules 226 may include machine-readable instructions that, when executed by the one or more processors 222, identify a traffic congestion section based on vehicle driving data, obtain a first road link including the traffic congestion section based on a map, as well as a second road link and a third road link connected to the first road link, generate an initial lane-level traffic congestion distribution on the first road link, update the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link, and transmit the lane-level traffic congestion distribution to a vehicle approaching the traffic congestion section.

[0050] FIG. 3 depicts a flowchart for estimating lane-level traffic congestion according to one or more embodiments shown and described herein.

[0051] In step 310, the server obtains, based on the map, a first road link, a second road link connected to the first road link, and a third road link connected to the first road link. In an embodiment, the server may generate a lane connection graph that identifies the next lane and the previous lane connected to a particular lane. Referring to FIG. 1A , the server 240 may obtain a first road link 110, a second road link 120, and a third road link 130 from map data. The map data may include information that the first road link 110 includes three lanes 111, 113, and 115, the second road link 120 includes two lanes 121 and 123, and the third road link 130 includes one lane 131. The map data includes information that lanes 121 and 123 are connected to lanes 111 and 113, respectively, and that lane 131 is connected to lane 115.

[0052] 3, the server identifies a traffic congestion area on the first road link based on the vehicle driving data. Referring to FIG. 1A, the server 240 may receive driving data from connected vehicles, such as connected vehicles 100 and 102 on the first road link 110, a connected vehicle on the second road link 120, and a connected vehicle on the third road link 130.

[0053] With respect to the first road link 110, based on the driving data including the speed of the connected vehicle on the first road link 110, the server 240 may identify a traffic congestion section 140 on the first road link 110. Specifically, the server 240 may detect the front and rear of the traffic congestion section 140 based on the speed of the connected vehicle and identify a traffic congestion section 140 extending from the front to the rear. For example, the front of the traffic congestion may be the location of a connected vehicle located at the front of connected vehicles whose speed is below a threshold speed, such as 5 mph (approximately 8.047 km / h), 10 mph (approximately 16.09 km / h), 20 mph (approximately 32.19 km / h), etc. The rear of a traffic jam may be the location of a connected vehicle located at the rear of connected vehicles whose speed is below a threshold speed, such as 5 mph (approximately 8.047 km / h), 10 mph (approximately 16.09 km / h), or 20 mph (approximately 32.19 km / h).

[0054] With respect to the second road link 120, the server 240 may determine that no traffic congestion exists at the beginning of the second road link 120 based on the speed of the vehicle at the beginning of the second road link 120. With respect to the third road link 130, the server 240 may identify a traffic congestion section 144 in the third road link 130. Specifically, the server 240 may detect the front and rear of the traffic congestion section 144 based on the speed of the connected vehicle and identify the traffic congestion section 144 extending from the front to the rear.

[0055] Referring again to Figure 3, at step 330, the server may generate an initial lane-level traffic congestion distribution for the first road link. Referring to Figure 1A, the server 240 may estimate the lane-level traffic congestion distribution including the probability of traffic congestion in each of the lanes 111, 113, and 115. The server 240 may generate an initial lane-level traffic congestion distribution that may have equal probabilities of traffic congestion in each of the lanes 111, 113, and 115, i.e., [0.33, 0.33, 0.33].

[0056] Referring again to FIG. 3, in step 340, the server may update the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link.

[0057] 1B , the server may determine, based on driving data received from vehicles on the second road link 120, that the second road link 120 does not have a traffic congestion near the beginning of the second road link 120. The lane-level congestion distribution for the second road link 120 is [0.05, 0.05]. The server 240 may determine, based on driving data received from vehicles on the third road link 130, that a traffic congestion exists near the beginning of the third road link 130. Because the third road link 130 has only one lane, the lane-level congestion distribution is [1.0].

[0058] Using the lane connectivity information obtained from the map, server 240 calculates the probability that a traffic jam is in a lane using Equation 1 above. For example, for lane 111, the initial probability that a traffic jam is in lane 111 is 0.33. The weight of the next lane is the probability that a traffic jam is in lane 121, which is 0.05. Therefore, the probability that a traffic jam is in lane 111 is 0.7*0.33*0.05=0.01. Similarly, for lane 113, the initial probability that a traffic jam is in lane 113 is 0.33. The weight of the next lane is the probability that a traffic jam is in lane 123, which is 0.05. Therefore, the probability that a traffic jam is in lane 113 is 0.7*0.33*0.05=0.01. For lane 115, the initial probability that a traffic jam is in lane 115 is 0.33. The next lane weight is the probability that the traffic congestion is in lane 131, which is 1. Therefore, the probability that the traffic congestion is in lane 115 is 0.7*0.33*1.0=0.23. Because the probabilities must sum to 1, server 240 inflates and normalizes the calculated probability of [0.01, 0.01, 0.23] to obtain an updated lane-level congestion distribution of [0.04, 0.04, 0.92].

[0059] Referring again to FIG. 3, in step 350, the server may transmit the lane-level traffic congestion distribution to vehicles approaching the traffic congestion area.

[0060] 1B, server 240 may transmit information about the updated lane-level traffic congestion distribution to connected vehicles approaching traffic congestion section 140, and the connected vehicles approaching traffic congestion section 140 may autonomously drive away from the lane with the traffic congestion. In some embodiments, as shown in FIG. 1C, connected vehicles receiving the updated lane-level traffic congestion distribution from server 240 may display the lane-level traffic congestion distribution on an output device, for example, a vehicle head unit or a navigation app on a user's smartphone in the vehicle.

[0061] In some embodiments, server 240 may identify lanes having a traffic congestion based on the lane-level traffic congestion distribution and transmit information about the identified lanes to vehicles approaching the traffic congestion section. For example, based on the lane-level traffic congestion distribution, server 240 identifies lane 115 as a lane having a traffic congestion and transmits information about lane 115 to connected vehicles approaching traffic congestion section 140.

[0062] FIG. 4A depicts estimating the probability of traffic congestion in each of the lanes using the route of a connected vehicle, according to one or more embodiments shown and described herein.

[0063] 4A , server 240 may identify that first road link 110 has traffic congestion near the end of first road link 110 based on driving data of connected vehicles on first road link 110. Server 240 may estimate a lane-level traffic congestion distribution including a probability of traffic congestion in each of lanes 111, 113, and 115 of first road link 110. Server 240 may generate an initial lane-level traffic congestion distribution that may have an equal probability of traffic congestion in each of lanes 111, 103, and 105, i.e., [0.33, 0.33, 0.33]. In this example, in contrast to the example of FIG. 1B , server 240 determines that third road link 130 is not congested based on driving data of connected vehicles on third road link 130.

[0064] In an embodiment, the server 240 may calculate a percentage of vehicles that were in the traffic jam in the traffic jam section 140 that moved onto a particular next road link while in the traffic jam in the traffic jam section 140. Specifically, vehicles that were in the traffic jam in the first road link 110 may proceed onto either the second road link 120 or the third road link 130. The server 240 may calculate a percentage of vehicles that were in the traffic jam in the traffic jam section 140 that moved onto the third road link 130 while in the traffic jam in the traffic jam section 140. If the percentage is greater than a threshold, for example, if substantially all of the connected vehicles in the traffic jam proceeded onto the third road link 130, the server 240 may determine that the traffic jam in the first road link 110 is likely to be in a lane connected to the third road link 130. Because lane 115 is connected to the third road link 130, server 240 may determine that a traffic congestion on the first road link 110 is likely to be in lane 115. Server 240 may determine that lanes that are not connected to the third road link 130 have a low probability of having a traffic congestion there.

[0065] The server 240 may calculate a percentage of vehicles in the traffic jam in the traffic jam section 140 that moved onto the second road link 120, where the percentage is not greater than a threshold, e.g., most of the connected vehicles in the traffic jam did not proceed onto the second road link 120. The server 240 may determine that the traffic jam in the first road link 110 is unlikely to be in the lanes connected to the second road link 120. Thus, the server 240 may determine that the traffic jam in the first road link 110 is unlikely to be in the lanes 111 and 113 connected to the second road link 120. In this regard, the server 240 may obtain an updated lane-level congestion distribution of [0.05, 0.05, 0.95], which represents the probability that a traffic jam is in each of the lanes 111, 113, and 115. That is, lane 115 has a 95% chance of having traffic congestion, and lanes 111 and 113 have a 5% chance of having traffic congestion.

[0066] FIG. 4B depicts estimating the probability of traffic congestion in each of the lanes using the route of a connected vehicle according to one or more embodiments shown and described herein.

[0067] 4B , server 240 may identify, based on driving data of connected vehicles on first road link 110, that first road link 110 has a traffic congestion near the beginning of first road link 110. Server 240 may estimate a lane-level traffic congestion distribution including the probability that there is a traffic congestion in each of lanes 111, 113, 115 of first road link 110. Server 240 may generate an initial lane-level traffic congestion distribution that may have an equal probability of traffic congestion in each of lanes 111, 113, 115, i.e., [0.33, 0.33, 0.33]. Server 240 may determine, based on driving data of connected vehicles on third road link 130, that the third road link 130 is not congested.

[0068] In an embodiment, the server 240 may calculate a percentage of vehicles that moved forward on the third road link 130 that enter the first road link 110 and get stuck in traffic congestion in the traffic congestion section 140. Specifically, the vehicles that moved forward on the third road link 130 may enter a lane with traffic congestion or a lane without traffic congestion. If the percentage is greater than a threshold, for example, if substantially all of the connected vehicles that moved forward on the third road link 130 end up getting stuck in traffic congestion in the traffic congestion section 140, the server 240 may determine that the traffic congestion on the first road link 110 is likely to be in a lane connected to the third road link 130. Because lane 115 is connected to the third road link 130, the server 240 may determine that the traffic congestion on the first road link 110 is likely to be in lane 115. The server 240 may determine that lanes that are not connected to the third road link 130 have a low probability of having traffic congestion there.

[0069] The server 240 may calculate the proportion of vehicles that have traveled previously on the second road link 120 that enter the first road link 110 and get stuck in the traffic congestion in the traffic congestion section 140. In this case, the ratio is not greater than a threshold, e.g., most of the connected vehicles that have traveled previously on the second road link 120 did not get stuck in the traffic congestion in the traffic congestion section 140. The server 240 may then determine that the traffic congestion on the first road link 110 is unlikely to be in the lanes connected to the second road link 120. Thus, the server 240 may determine that the traffic congestion on the first road link 110 is unlikely to be in the lanes 111 and 113 connected to the second road link 120. In this regard, the server 240 may obtain an updated lane-level congestion distribution of [0.05, 0.05, 0.95], which represents the probability that a traffic congestion is in each of the lanes 111, 113, and 115. That is, lane 115 has a 95% chance of having traffic congestion, and lanes 111 and 113 have a 5% chance of having traffic congestion.

[0070] FIG. 5 depicts estimating the probability of traffic congestion in each of the lanes using lane connectivity information and lane change signals of a connected vehicle, according to one or more embodiments shown and described herein.

[0071] 5 , connected vehicle 100 is driving on a first road link 510 that includes lanes 511, 513, 515, and 517. Connected vehicle 100 is approaching a traffic congestion section 502. Lanes 511, 513, and 515 are straight-through lanes, and lane 517 is a right-turn lane. Server 240 can determine that connected vehicle 100 is approaching traffic congestion section 502 based on the location of connected vehicle 100. Although FIG. 5 depicts connected vehicle 100 in lane 513 and traffic congestion 500 located in lane 513, connected vehicle 100 and server 240 do not have information that connected vehicle 100 and traffic congestion 500 are in lane 513. Server 240 may monitor the driving behavior of connected vehicles approaching heavy traffic section 502. For example, server 240 receives driving data from connected vehicle 100 that indicates that connected vehicle 100 approaching heavy traffic section 502 changes lanes to the right and continues driving straight.

[0072] Because connected vehicle 100 changed lanes to the right after reaching the traffic jam, the traffic jam may be in lane 511 or 513. If the traffic jam were in lane 515, connected vehicle 100 would not be able to continue straight after changing lanes to the right. Thus, lane-level traffic jam distribution 540 may be [0.45, 0.45, 0.05, 0.05], where lanes 515 and 517 have the lowest probability of having a traffic jam there, and lanes 511 and 513 have the highest probability of having a traffic jam there.

[0073] FIG. 6 depicts estimating the probability of traffic congestion in each of the lanes using lane connection information and lane change signals of a connected vehicle, according to one or more embodiments shown and described herein.

[0074] 6 , connected vehicle 100 is driving on a first road link 610 that includes lanes 611, 613, 615, and 617. Connected vehicle 100 is approaching a traffic congestion section 602. Lanes 611, 613, and 615 are connected to straight lanes of a second road link 620, and lane 617 is connected to a curved lane of a third road link 630. Server 240 can determine that connected vehicle 100 is approaching traffic congestion section 602 based on the location of connected vehicle 100. Although FIG. 6 depicts connected vehicle 100 in lane 613 and traffic congestion 600 located in lane 613, connected vehicle 100 and server 240 do not have information that connected vehicle 100 and traffic congestion 600 are in lane 613. Server 240 may monitor the driving behavior of connected vehicles approaching traffic jam section 602. For example, server 240 received driving data from connected vehicle 100 that connected vehicle 100 drove straight before entering first road link 610, approached traffic jam, changed lanes to the left, and continued driving straight.

[0075] The traffic jam can be in lane 613 or 615 because connected vehicle 100 changed lanes left after reaching the traffic jam. The traffic jam cannot be in lane 611 because connected vehicle 100 changed lanes left after reaching the traffic jam. The traffic jam cannot be in lane 617 because connected vehicle 100 drove straight before entering first road link 610. Thus, lane-level traffic jam distribution 640 can be [0.05, 0.45, 0.45, 0.05], where lanes 611 and 617 have the lowest probability of having a traffic jam there, and lanes 613 and 615 have the highest probability of having a traffic jam there.

[0076] FIG. 7 depicts estimating the probability of traffic congestion in each of the lanes using lane connection information and lane change signals of a connected vehicle, according to one or more embodiments shown and described herein.

[0077] 7 , connected vehicle 100 is driving on a first road link 610 that includes lanes 611, 613, 615, and 617. Connected vehicle 100 is approaching a traffic congestion section 602. Lanes 611, 613, and 615 are connected to straight lanes of a second road link 620, and lane 617 is connected to a curved lane of a third road link 630. Server 240 can determine that connected vehicle 100 is approaching traffic congestion section 602 based on the location of connected vehicle 100. Although FIG. 7 depicts connected vehicle 100 in lane 613 and traffic congestion 600 located in lane 613, connected vehicle 100 and server 240 do not have information that connected vehicle 100 and traffic congestion 600 are in lane 613. Server 240 may monitor the driving behavior of connected vehicles approaching congested traffic section 602. For example, server 240 received driving data from connected vehicle 100 that connected vehicle 100 drove straight before entering first road link 610, slowed down due to congested traffic, and continued driving straight without changing lanes.

[0078] Because connected vehicle 100 drove straight before entering first road link 610, it is not possible for the traffic congestion to be in lane 617. Because connected vehicle 100 did not change lanes, server 240 may determine, based on the driving data of connected vehicle 100, that the traffic congestion could be in lanes 611, 613, or 615 with equal distribution. Thus, lane-level traffic congestion distribution 740 may be [0.32, 0.32, 0.32, 0.04], where lane 617 has the lowest probability of having a traffic congestion there, and lanes 611, 613, and 615 have the highest probability of having a traffic congestion there.

[0079] It should be understood that the embodiments described herein are directed to a method and system for estimating lane-level traffic congestion, according to one or more embodiments shown and described herein, which includes obtaining a first road link, a second road link connected to the first road link, and a third road link connected to the first road link based on a map, identifying a traffic congestion section on the first road link based on driving data of a vehicle, generating an initial lane-level traffic congestion distribution on the first road link, updating the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link, and transmitting the lane-level traffic congestion distribution to a vehicle approaching the traffic congestion section.

[0080] According to the present disclosure, the system identifies the lane ID of a traffic jam by analyzing lane connection data, lane route information, and / or congestion information in adjacent lanes. The system identifies the lane ID of a traffic jam without requesting the lane ID from the vehicle.

[0081] It should be noted that the terms "substantially" and "about" may be used herein to express the degree of inherent uncertainty that may result from any quantitative comparison, value, measurement, or other representation. These terms are also used herein to express the degree to which a quantitative representation may vary from the stated basis without resulting in a change in the basic functionality of the subject matter at issue.

[0082] While particular embodiments have been shown and described herein, it should be understood that various other changes and modifications can be made without departing from the spirit and scope of the claimed subject matter. Moreover, although various aspects of the claimed subject matter are described herein, such aspects need not be utilized in combination. It is therefore intended that the appended claims cover all such changes and modifications that are within the scope of the claimed subject matter.

Claims

1. 1. A system comprising one or more processors, The one or more processors: obtaining a first road link, a second road link connected to the first road link, and a third road link connected to the first road link based on a map; Identifying a congested traffic section on the first road link based on vehicle driving data; generating an initial lane-level traffic congestion distribution for the first road link; updating the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link; The system is programmed to transmit the lane-level traffic congestion distribution to a vehicle approaching the traffic congestion section.

2. the first road link includes a plurality of lanes; the initial lane-level traffic congestion distribution includes a probability of traffic congestion in each of the plurality of lanes; The system of claim 1 , wherein updating the initial lane-level traffic congestion distribution comprises updating the probability of the traffic congestion in each of the plurality of lanes.

3. The one or more processors further include: determining that the second road link does not include a traffic congestion and that the third road link includes a traffic congestion; 3. The system of claim 2, further programmed to calculate a probability of the traffic congestion in a lane of the first road link connected to the third road link based on the determination that the second road link does not include a traffic congestion and the third road link includes a traffic congestion.

4. The one or more processors further include: determining that the front of the congestion section is near the end of the first road link and that the beginning of a third road link is congested; 3. The system of claim 2, further programmed to calculate a probability of traffic congestion in a lane of the first road link connected to the third road link based on the determination that the front of the traffic congestion section is near the end of the first road link and the beginning of the third road link is congested.

5. The one or more processors further include: determining that a rear end of the congestion section is near a beginning of the first road link and that an end of a third road link connected to the beginning of the first road link is congested; 3. The system of claim 2, further programmed to calculate a probability of traffic congestion in a lane of the first road link connected to the third road link based on the determination that the rear of the traffic congestion section is near the beginning of the first road link and the end of the third road link is congested.

6. The one or more processors further include:

3. The system of claim 2, further programmed to update the initial lane-level traffic congestion distribution on the first road link based on a ratio of a number of vehicles that were in a traffic congestion on the first road link to a number of vehicles that exited the traffic congestion and entered the third road link.

7. The one or more processors further include: determining that the front of the congestion section is near the end of the first road link; determining whether the ratio is greater than a threshold; 7. The system of claim 6, further programmed to calculate a probability of traffic congestion in a lane of the first road link connected to the third road link based on the determination that the ratio is greater than the threshold.

8. The one or more processors further include:

3. The system of claim 2, further programmed to update the initial lane-level traffic congestion distribution on the first road link based on a percentage of vehicles traveling on the third road link that enter the first road link and become stuck in traffic congestion.

9. The one or more processors further include: determining that the end of the congestion section is near the beginning of the first road link; determining whether the percentage is greater than a threshold; 9. The system of claim 8, further programmed to calculate a probability of traffic congestion in a lane of the first road link connected to the third road link based on the determination that the percentage is greater than the threshold.

10. The one or more processors further include: obtaining information regarding lane changes of a vehicle on the first road link; obtaining information regarding whether the vehicle will enter the second road link or the third road link after the lane change; 2. The system of claim 1, further programmed to update the initial lane-level traffic congestion distribution on the first road link based on information regarding the lane change and the information regarding whether the vehicle is entering the second road link or the third road link.

11. The one or more processors further include: obtaining information regarding lane changes of a vehicle on the first road link; obtaining information regarding whether the vehicle has been on the second road link or the third road link before driving on the first road link; 2. The system of claim 1, further programmed to update the initial lane-level traffic congestion distribution on the first road link based on information regarding the lane change and the information regarding whether the vehicle was on the second road link or the third road link before driving on the first road link.

12. 1. A method for determining lane-level traffic, the method comprising: Obtaining a first road link, a second road link connected to the first road link, and a third road link connected to the first road link based on a map; identifying a traffic congestion section on the first road link based on vehicle driving data; generating an initial lane-level traffic congestion distribution for the first road link; updating the initial lane-level traffic congestion distribution on the first road link based on traffic congestion information on the second road link and the third road link; transmitting the lane-level traffic congestion distribution to vehicles approaching the traffic congestion section; A method comprising:

13. the first road link includes a plurality of lanes; the initial lane-level traffic congestion distribution includes a probability of traffic congestion in each of the plurality of lanes; The method of claim 12 , wherein updating the initial lane-level traffic congestion distribution comprises updating the probability of traffic congestion in each of the plurality of lanes.

14. determining that the second road link does not include a traffic congestion and that the third road link includes a traffic congestion; calculating a probability of the traffic congestion in a lane of the first road link connected to the third road link based on the determination that the second road link does not include a traffic congestion and the third road link includes a traffic congestion; The method of claim 13 further comprising:

15. determining that the front of the congestion section is near the end of the first road link and the beginning of a third road link is congested; calculating a probability of traffic congestion in a lane of the first road link connected to the third road link based on the determination that the front of the traffic congestion section is near the end of the first road link and the beginning of the third road link is congested; The method of claim 13 further comprising:

16. determining that a rear end of the congestion section is near a beginning of the first road link and that an end of a third road link connected to the beginning of the first road link is congested; calculating a probability of traffic congestion in a lane of the first road link connected to the third road link based on the determination that the rear of the traffic congestion section is close to the beginning of the first road link and the end of the third road link is congested; The method of claim 13 further comprising:

17. 14. The method of claim 13, further comprising updating the initial lane-level traffic congestion distribution on the first road link based on a ratio of a number of vehicles that were in a traffic congestion on the first road link to a number of vehicles that exited the traffic congestion and entered the third road link.

18. determining that a front of the congestion section is near an end of the first road link; determining whether the ratio is greater than a threshold; calculating a probability of traffic congestion in a lane of the first road link connected to the third road link based on the determination that the ratio is greater than the threshold; 20. The method of claim 17, further comprising:

19. obtaining information regarding lane changes of a vehicle on the first road link; obtaining information regarding whether the vehicle will enter the second road link or the third road link after the lane change; further updating the initial lane-level traffic congestion distribution on the first road link based on information about the lane change and the information about whether the vehicle is entering the second road link or the third road link; The method of claim 12 further comprising:

20. obtaining information regarding lane changes of a vehicle on the first road link; obtaining information regarding whether the vehicle has been on the second road link or the third road link before driving on the first road link; further updating the initial lane-level traffic congestion distribution on the first road link based on information about the lane change and the information about whether the vehicle was on the second road link or the third road link before driving on the first road link; The method of claim 12 further comprising:

Images