EP4270352A1

EP4270352A1 - Controlling a future traffic state on a road segment

Info

Publication number: EP4270352A1
Application number: EP22169701.4A
Authority: EP
Inventors: Carl LINDBERG
Original assignee: Zenseact AB
Current assignee: Zenseact AB
Priority date: 2022-04-25
Filing date: 2022-04-25
Publication date: 2023-11-01

Abstract

The present disclosure relates to a method, system, a computer-readable storage medium and a computer program product. There is provided a method for controlling a future traffic state on road segments based on a current traffic state in a geographical region by obtaining vehicle data from at least one subset of vehicles among a plurality of vehicles in the current traffic state, determining, based on the obtained vehicle data, the future traffic state on the one or more road segment(s), determining a plurality of alternative future traffic states based on a plurality of predetermined vehicle behavior criteria configured to influence the determined future traffic state, selecting a predetermined vehicle behavior resulting in an augmented future traffic state being representative of a most desired future traffic state, and communicating the selected predetermined vehicle behavior to one or more vehicle(s) comprised in the subset of vehicles.

Description

TECHNICAL FIELD

The present disclosure relates to controlling a future traffic state on a road segment of a geographical region. More specifically, various embodiments of the present disclosure relate to systems and methods for controlling a future traffic state on a road segment of a geographical region based on a current traffic state in the geographical region involving a plurality of vehicles in the current traffic state.

BACKGROUND

During the last few years, the research and development activities related to autonomous vehicles have exploded in number and many different approaches are being explored. An increasing portion of modern vehicles have advanced driver-assistance systems (ADAS) to increase vehicle safety and more generally road safety. ADAS - which for instance may be represented by adaptive cruise control (ACC) collision avoidance system, forward collision warning, etc. - are electronic systems that may aid a vehicle driver while driving. Today, there is ongoing research and development within a number of technical areas associated to both the ADAS and the Autonomous Driving (AD) field. ADAS and AD will herein be referred to under the common term Automated Driving System (ADS) corresponding to all of the different levels of automation as for example defined by the SAE J3016 levels (0 - 5) of driving automation, and in particular for level 4 and 5.
In a not too distant future, ADS solutions are expected to have found their way into a majority of the new vehicles being put on the market. An ADS may be construed as a complex combination of various components that can be defined as systems where perception, decision making, and operation of the vehicle are performed by electronics and machinery instead of a human driver, and as introduction of automation into road traffic. This includes handling of the vehicle, destination, as well as awareness of surroundings. While the automated system has control over the vehicle, it allows the human operator to leave all or at least some responsibilities to the system. An ADS commonly combines a variety of sensors to perceive the vehicle's surroundings, such as e.g. radar, LIDAR, sonar, camera, navigation system e.g. GPS, odometer and/or inertial measurement units (IMUs), upon which advanced control systems may interpret sensory information to identify appropriate navigation paths, as well as obstacles, free-space areas, and/or relevant signage.
Traffic congestion is a well-known phenomenon for anyone who lives in a bigger city. Besides the fact that it causes often significantly longer travel times for the road users, congestion is also an indirect cause of traffic accidents. Therefore, having an adequate understanding of the traffic conditions imposed on the vehicles travelling on roads is essentially helpful to alleviate some unnecessary road incidents as well as improving the experience of travelling between the start and destination points. In combination with ADS features and the detection and perception capabilities of today's modern vehicles an attractive opportunity presents itself to enable intelligent interaction with the traffic infrastructure, with the other vehicles on the road, with several external communication networks, or with high definition maps providing depth information of roads. This in turn provides for acquiring an extensive amount of data of the surroundings of the vehicle, as well as road conditions, weather conditions, and the like to produce accurate information on the traffic situation on road segments and even large geographical regions on which the vehicles are set to travel.
Accordingly, for comfort and safety reasons, there is a need for solutions in the art capable of providing accurate predictions and management of traffic conditions on road segments and geographical regions, particularly within the territories of large urban road networks where traffic congestions and obstructions are bound to occur frequently hampering the flow of traffic over extended periods of time.

SUMMARY

It is therefore an object of the present disclosure to provide a system, a method, a computer-readable storage medium and a computer program product, which alleviate all or at least some of the drawbacks of presently known solutions.
More specifically, it is an object of the present disclosure to alleviate problems related to traffic congestions and obstructions involving vehicles, which may comprise an ADS feature, travelling on road segments comprised in a geographical region.
These objects are achieved by means of a system, a method, a computer-readable storage medium and a computer program product, as defined in the appended independent claims. The term exemplary is in the present context to be understood as serving as an instance, example or illustration.
According to a first aspect of the present disclosure, there is provided a method for controlling a future traffic state on one or more road segment(s) of a geographical region, based on a current traffic state in the geographical region, the method comprising obtaining vehicle data from at least one subset of vehicles among a plurality of vehicles in the current traffic state, the vehicle data comprising velocity data and position data of one or more vehicle(s) comprised in the at least one subset of vehicles. The method further comprises determining, based on the obtained vehicle data, the future traffic state on the one or more road segment(s) within a predetermined time period ensuing the current traffic state. Further, the method comprises determining a plurality of alternative future traffic states based on a plurality of predetermined vehicle behavior criteria configured to influence the determined future traffic state on the one or more road segment(s). Additionally, the method comprises selecting a predetermined vehicle behavior, comprised in the plurality of the predetermined vehicle behavior criteria, resulting in an augmented future traffic state among the alternative future traffic states and being representative of a most desired future traffic state on the one or more road segment(s). The method further comprises communicating the selected predetermined vehicle behavior to one or more vehicle(s) comprised in the at least one subset of vehicles among the plurality of vehicles in the current traffic state.
The present inventor has realized that by utilizing vehicle data of the one or more vehicle(s) comprised in the at least one subset of vehicles, systems and methods can be provided which output predictions of near future traffic states such as traffic congestion on one or more road segment in real time. Further, the systems and methods of the present disclosure provide a feedback process through which active intervention instructions are transmitted to one or more of the vehicle(s) comprised in the at least one subset of vehicles, enabling influencing and controlling of the future traffic state in the geographical region.
It is thus, highly advantageous to control and influence the future traffic states on the geographical region by controlling the behavior of only a limited number of vehicles travelling in traffic. By predicting the outcome of each vehicle behavior, and providing the feedback of the suitable intervention resulting in the most desired future state to the vehicles, real-life actual outcome of the intervention on the future traffic state can be controlled and observed. In several embodiments of the present disclosure, the method may further comprise determining the future traffic state on the one or more road segment(s) within the predetermined time period ensuing the current traffic state by means of generating a Markov chain model based on the velocity and position data of one or more vehicle(s) comprised in the at least one subset of vehicles.
In some further embodiments of the present disclosure, the method may further comprise determining the plurality of alternative future traffic states based on the plurality of predetermined vehicle behavior criteria for the subset of vehicles by means of the generated Markov chain model, the predetermined vehicle behavior criteria being a function of the velocity and position data of one or more vehicle(s) comprised in the at least one subset of vehicles.
In several embodiment, the step of communicating the selected predetermined vehicle behavior may further comprise transmitting a signal to one or more vehicle(s) comprised in the at least one subset of vehicles, the signal comprising an instruction to adopt the selected predetermined vehicle behavior by the one or more vehicle(s) comprised in the at least one subset of vehicles.
In various embodiments the vehicle data may comprise real-time vehicle data in the current traffic state.
In several embodiments according to the present disclosure, the predetermined vehicle behavior criteria may comprise any one of an adjusted velocity of the vehicle, an adjusted distance of the vehicle to an external vehicle ahead, and an updated route selection for the vehicle.
In some embodiments, the predetermined time period for determining the future traffic state on the one or more road segment(s) may be determined based on the velocity and the position data of one or more vehicle(s) in the at least one subset of vehicles.
In further embodiments according to the present disclosure, the future traffic state on the one or more road segment(s) may comprise a future traffic congestion state on the one or more road segment(s) and the most desired future traffic state on the one or more road segment(s) may comprise a resolved future traffic congestion state.
In various embodiments, the one or more vehicle(s) comprised in the at least one subset of vehicles may be equipped with an automated driving system, ADS, feature.
According to yet second aspect of the present disclosure there is provided a (non-transitory) computer-readable storage medium storing one or more programs configured to be executed by one or more processors of a processing system, the one or more programs comprising instructions for performing the method according to any one of the embodiments of the method of the present disclosure.
According to a third aspect of the present invention, there is provided a computer program product comprising instructions which, when the program is executed by one or more processors of a processing system, causes the processing system to carry out the method according to any one of the embodiments of the method disclosed herein.
According to a further fourth aspect, there is provided a system for controlling a future traffic state on one or more road segment(s) of a geographical region, based on a current traffic state in the geographical region, the system comprising processing circuitry configured to obtain vehicle data from at least one subset of vehicles among a plurality of vehicles in the current traffic state, the vehicle data comprising velocity data and position data of one or more vehicle(s) comprised in the at least one subset of vehicles. The processing circuitry is further configured to determine, based on the obtained vehicle data, the future traffic state on the one or more road segment(s) within a predetermined time period ensuing the current traffic state and to determine a plurality of alternative future traffic states based on a plurality of predetermined vehicle behavior criteria configured to influence the determined future traffic state on the one or more road segment(s). Further, the processing circuitry is configured to select a predetermined vehicle behavior, comprised in the plurality of the predetermined vehicle behavior criteria, resulting in an augmented future traffic state among the alternative future traffic states and being representative of a most desired future traffic state on the one or more road segment(s). The processing circuitry is further configured to communicate the selected predetermined vehicle behavior to one or more vehicle(s) comprised in the at least one subset of vehicles among the plurality of vehicles in the current traffic state.
According to a fifth aspect, there is provided a remote server comprising the system for controlling a future traffic state on one or more road segment(s) of a geographical region, based on a current traffic state in the geographical region according to any one of the embodiments of the fourth aspect disclosed herein. With this aspect, similar advantages and preferred features are present as in the previously discussed aspects and vice versa.
According to a sixth aspect, there is provided a cloud environment comprising one or more remote servers according to any one of the embodiments of the fifth aspect disclosed herein. With this aspect, similar advantages and preferred features are present as in the previously discussed aspects and vice versa.
Further embodiments of the different aspects are defined in the dependent claims.
It is to be noted that all the embodiments, elements, features and advantages associated with the first aspect also analogously apply to the second, third, and the fourth aspects of the present disclosure.
These and other features and advantages of the present disclosure will in the following be further clarified in the following detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS

Further objects, features and advantages of embodiments of the disclosure will appear from the following detailed description, reference being made to the accompanying drawings. The drawings are not to scale.

Figs. 1a-1b are schematic perspective top view illustrations of one or more vehicle(s) travelling on one or more road segment(s) of a geographical region or sub-regions in accordance with several embodiments of the present disclosure.
Fig. 2 is a schematic block diagram illustrating a traffic management system according to several embodiments of the present disclosure.
Fig. 3 is a schematic flowchart illustrating a method in accordance with several embodiments of the present disclosure.
Fig. 4 is a schematic side view illustration of a vehicle and a control system in accordance with several embodiments of the present disclosure.

DETAILED DESCRIPTION

Those skilled in the art will appreciate that the steps, services and functions explained herein may be implemented using individual hardware circuitry, using software functioning in conjunction with a programmed microprocessor or general purpose computer, using one or more Application Specific Integrated Circuits (ASICs) and/or using one or more Digital Signal Processors (DSPs). It will also be appreciated that when the present disclosure is described in terms of a method, it may also be embodied in one or more processors and one or more memories coupled to the one or more processors, wherein the one or more memories store one or more programs that perform the steps, services and functions disclosed herein when executed by the one or more processors.
In the following description of exemplary embodiments, the same reference numerals denote the same or similar components.
Fig. 1a and Fig. 1b illustrate schematic perspective top views of a geographical region 200 and one or more geographical sub-regions 200a-f comprised in the geographical region 200. Each geographical sub-region comprises road networks having a plurality of road segments 24 on which a plurality of vehicles 100 are in traffic. The geographical sub-regions 200a-f may for instance be a part of an urban traffic infrastructure comprising large urban road networks within the territories of a large city as well as outside the boundaries of the large city such as rural and suburban areas in connection to the urban road networks. These areas and road networks are collectively referred to as the geographical region 200 in the present context.
In several examples and embodiments the roads may be any type of road e.g. highways with carriageways, motorways, freeways or expressways. The roads may also be country roads or any other carriageways with one or more lanes wherein the plurality of vehicles 100 will be travelling on. Each road in the road networks may comprise road segments 24 e.g. intersections, roundabouts, various stretches of road, etc. as shown in Fig. 1a. In Fig. 1b, several geographical sub-regions 200a-f are shown with interconnected traffic routes 241 amongst the geographical sub-regions 200a-f forming an urban road network in the geographical region 200.
Amongst the plurality of vehicles 100 being in a current traffic state in the geographical sub-region 200a in the example of Fig. 1a, there is at least one subset of vehicles 110 which may also be referred to as fleet of vehicles 110 in the rest of this description. The fleet vehicles 110 travelling in the current state of traffic in the geographical sub-region 200a are shown in hatched shaded patterns in Fig. 1a for ease of identification. It should be clear that any other vehicles than the illustrated vehicles 110 being hatched shaded, may be comprised in the fleet vehicles 110, and the selection of the example vehicles in Fig. 1a is merely for the sake of assisting the reader.
Each vehicle 110 comprised in the subset of vehicles may be provided with a driver support function, which in the present context may be understood as an Autonomous Driving (AD) feature or an Advanced Driver Assistance Feature (ADAS), both of which are herein encompassed under the term an Automated Driving System (ADS), or an ADS feature. Each vehicle 110 may also be provided with means for wireless communication compatible with various short-range or long-range wireless communication protocols as further explained with reference to Fig. 4. The vehicles 110 may be any type of vehicle such as cars, motorcycles, cargo trucks, busses, smart bicycles, autonomous driving delivery vehicles, etc. The ADS feature may e.g. control one or more functions of the vehicles 110 such as acceleration, steering, route planning and braking of the vehicle 110.
Each vehicle 110 may further comprise a vehicle control system 10 which comprises control circuitry 11 configured to obtain data comprising information about the surrounding environment of the vehicle 110. Accordingly, each vehicle 110 in the at least one subset of vehicles may also comprise sensing capabilities e.g. at least one on-board sensor device which may be a part of a vehicle perception system or module 6 comprising sensor devices 6a-6c such as the ones shown in the vehicle of Fig. 4. The vehicle 110 may also comprise a localization system 5 configured to monitor a geographical position and heading of the vehicle, and may in the form of a Global Navigation Satellite System (GNSS), such as a GPS. However, the localization system may alternatively be realized as a Real Time Kinematics (RTK) GPS in order to improve accuracy. The localization system may further comprise inertial measurement units (IMUs). The vehicle control system 10 of the vehicle 110 may thus be configured to obtain vehicle data associated with a position and/or velocity and/or acceleration of the vehicle 110. Accordingly, in several aspects and embodiments the vehicle data may comprise a position, velocity and heading of each vehicle 110 comprised in the at least one subset of vehicles traveling on one or more road segments 24 of the geographical sub-regions 200a-f.
The present inventor has realized that by utilizing vehicle data of the fleet vehicles, systems and methods can be provided which output predictions of near future traffic states such as traffic congestion on one or more road segment 24 in real time. Further, the systems and methods of the present disclosure provide a feedback process through which intervention instructions are transmitted to one or more of the fleet vehicles, enabling influencing and controlling of the future traffic state in the geographical region 200.
According to the presented solution of this disclosure, a traffic management model 31 i.e. a traffic prediction and control model is constructed based on the obtained vehicle data by means of Markov chain theory in finite state and discrete time steps. By frequently querying the vehicle fleet 110 for position and velocity the Markov chain model 31 can be parameterized in real time, thanks to the large amounts of data continuously generated by the fleet vehicles 110. The generated Markov chain model 31 is then executed "into the future" i.e. in discrete time steps for predicting future outcomes of the traffic in the geographical region 200. Moreover, the generated Markov model can be automatically parameterized in real time, which provides a great advantage in terms of its application to traffic prediction and control. Further, and more importantly, the generated Markov chain model enables dynamic calculations of a plurality of alternative traffic scenarios on a road segment 24 as a function of the vehicle data. Thus, effects of modifying variables such as vehicle velocity and position associated with each vehicle 110 on a future state of traffic in the geographical region 200 can be anticipated by the model 31. This in turn improves understanding of the traffic state and handling traffic problems in the road networks, as well as adapting the traffic management in real time, and consequently alleviating traffic issues such as instances of traffic congestion on road segments 24 effectively.
To this end, as shown in Fig. 2, a traffic management system (TMS) 30 comprising the traffic management model 31 is provided which is configured to predict and control a future state of traffic on one or more road segments by obtaining the vehicle data of vehicle(s) 110 of the fleet of vehicles from the vehicle control system 10 of each vehicle 110. The TMS 30 is configured to determine, based on the obtained vehicle data, the future traffic state on one or more road segments 24 of a geographical region 200 within a predetermined time period ensuing the current traffic state. The TMS 30 may determine the future traffic state for each of the geographical sub-regions 200a-f, or in a selected number of geographical sub-regions, wherein each of these sub-regions 200a-f can be regarded as states of the Markov chain model 31, for which a future state of traffic is calculated based on the current state of traffic by means of the Markov chain model 31. This will be more elucidate with reference to Fig. 1b in the following. The TMS 30 is further configured to determine a plurality of alternative future traffic states based on a plurality of predetermined vehicle behavior criteria configured to influence the determined future traffic state on the one or more road segments 24.
The plurality of predetermined vehicle behavior criteria in the present context is a function of the velocity and position data of one or more vehicle(s) 110 in the subset of vehicles and may comprise any one of an adjusted velocity of the vehicle 110, an adjusted distance of the vehicle 110 to an external vehicle 100, 110 ahead, and an updated route selection for the vehicle 110. In some examples the predetermined vehicle behavior criteria may further comprise instructions to optimize the number of instances of a lane change by the vehicle 110, minimize an overall use of braking and idling by the vehicle 110, adjusting the ADS driving policy for "increased willingness" to let other vehicles merge into the lane on which the vehicle 110 is traveling, etc.
In several aspects and embodiments, the TMS 30 is further configured to select a predetermined vehicle behavior, comprised in the plurality of the predetermined vehicle behavior criteria, resulting in an augmented i.e. improved future traffic state among the alternative future traffic states. The selected augmented future traffic state is thus a representative of a most desired i.e. optimal future traffic state on the one or more road segment(s) 24 on the geographical region 200 and/or on one or more of the geographical sub-regions 200a-f. According to several aspects and embodiments the future traffic state on the one or more road segment(s) may comprise a future traffic congestion state on the one or more road segment(s) and the most desired future traffic state on the one or more road segment(s) may comprise a resolved future traffic congestion state on the one or more road segments 24. By resolved future traffic congestion in the present context it is to be understood as the determined future traffic congestion not taking place due to the active intervention by the TMS 30. It is clear to the person skilled in the art that a state of traffic congestion is not necessarily a full-stop traffic jam but it may comprise any intermediate traffic state leading up to such a full-stop such as slowing flow of traffic, increased time of travel for the vehicles, increased vehicle queuing, etc.
This way, the TMS 30 enables influencing and controlling the future traffic state in the geographical region by accurately calculating the various future traffic scenarios as result of specific vehicle behavior. By providing the most suitable vehicle behavior to the fleet vehicles 110, the TMS 30 actively intervenes and controls the future traffic state, thus preventing the determined future traffic state such as a determined future congestion from occurring.
In several embodiments and aspects the TMS 30 is configured to communicate the selected predetermined vehicle behavior representative of the augmented or the most desirable future traffic state to one or more vehicle 110 comprised in the at least one subset of vehicles among the plurality of vehicles 100 present in the current traffic state. In some examples and embodiments, the TMS 30 may be configured to communicate the selected predetermined vehicle behavior representative of the most desirable future traffic state to each vehicle 110 comprised in the at least one subset of vehicles. As mentioned earlier, determining the future traffic state on the one or more road segment(s) within the predetermined time period ensuing the current traffic state is performed by means of generating a Markov chain model 31 based on the velocity and position data of one or more vehicle(s) 110 comprised in the at least one subset of the plurality of vehicles. Moreover, determining the plurality of alternative future traffic states based on the plurality of predetermined vehicle behavior criteria for the subset of vehicles 110 is also performed by means of the generated Markov chain model, wherein the predetermined vehicle behavior criteria is a function of the velocity and position data of the one or more vehicle(s) comprised in the subset of vehicles.
In several aspects and embodiments the TMS 30 is configured to, when communicating the selected predetermined vehicle behavior, transmit a signal to one or more vehicle 110 comprised in the at least one subset of vehicles, the signal comprising an instruction to adopt the selected predetermined vehicle behavior by the one or more vehicles 110. In some aspects and embodiments, the signal may be transmitted to each vehicle 110 comprised in the at least one subset of vehicles.
Referring to Fig. 1b, wherein a plurality of geographical sub-regions 200a-f are connected by traffic routes 241, each geographical sub-region may be regarded as a node in a graph model of the traffic in the urban road network 200. In more detail, the traffic among the geographical sub-regions 200a-f is modelled as the Markov chain model 31 and each of these geographical sub-regions 200a-f is labeled as a state of the Markov chain model. Each of the geographical sub-regions 200a-f may also in turn comprise several states 200a'- f' of the Markov chain model 31 representative of the movement of the fleet vehicles 110 amongst these states 200a'- f'. The systems and methods of the present disclosure model the traffic by generating a discrete-time Markov chain which is a sequence of random variables "(X_n )_n≥0", "n" being discrete time steps, known as a stochastic process. In the stochastic process, a value of the next variable i.e. a future state of the process depends only on the value of the current variable i.e. current state of the process, and not any variables in the past, thus satisfying the Markov property. Here the process being the traffic in the geographical region 200 and the geographical sub-regions 200a-f. This allows for constructing a stochastic transition matrix "P" describing the transitions between the different states 200a-f of the Markov chain. The stochastic transition or probability matrix describes probabilities of moving from any of the states to each of the other states of the Markov chain. Generally speaking, each element e.g. "p_i,j"of the transition matrix "P" denotes the probability of transitioning from the state "i" to the state "j". For the matrix "P = (p_i,j :i,j E I)" to be stochastic, every row of the matrix "P" is to be a vector with a distribution λ_i wherein: $λ_{i} = ℙ (X = i) = ℙ (\{ω : X (ω) = i\}), X : Ω \to I,$
wherein "I" is a finite set, "Ω" is the probability space and "ω" is an element of "Ω". Further, it should be noted that: $\sum λ_{i} = 1 .$
Thus, (X_n )_n≥0 is a finite discrete-time Markov chain with an initial distribution λ_i and transition matrix "P" if: $ℙ (X_{0} = i_{0}) = λ_{i_{0}}$
$ℙ (X_{n + 1} = i_{n + 1} | X_{0} = i_{0}, \dots, X_{n} = i_{n}) = p_{i_{n}, i_{n + 1}}$
Based on the transition matrix "P", the probability of being in a particular state in "n"-discrete time steps into the future can be calculated.
Hence, the methods and systems of the present disclosure are adapted to determine a future traffic state on the one or more road segment(s) of the geographical region 200, within a predetermined time period i.e. "n" discrete time steps, ensuing the current traffic state in any of the geographical sub-regions 200a-f. By iteratively applying the transition matrix "P", the Markov chain model can progress to the future state of traffic in any of the geographical sub-regions accounting for the movement of the fleet vehicles 110 among the geographical sub-regions 200a-f i.e. moving from one state to another state of the Markov model and thus affecting the future traffic in that next state. In more detail:
(X_n)_0≤n≤N being a Markov chain model with initial distribution λ_i and transition matrix "P" then ∀m, n ≥ 0: $ℙ (X_{n} = j) = {({λP}^{n})}_{j}$
and $ℙ_{i} (X_{n} = j) : = ℙ (X_{n} = j | X_{0} = i) = ℙ_{i} (X_{n + m} = j | X_{m} = i) .$
Given
(X_n = j) = (λPⁿ)_j, the model can calculate what a future traffic state would be in any of the states. In an example, a future traffic congestion in any of the geographical sub-regions 200a-f can be determined based on the obtained vehicle data and the calculated probabilities of transitions of the one or more fleet vehicles 110 to that geographical sub-region. The parameters in the transition matrix "P" can be estimated with maximum likelihood, thanks to the obtained vehicle data representative of the present velocity and position i.e. paths of the one or more vehicles in the fleet of vehicles 110. Hence, according to various advantages aspects and embodiments of the present disclosure, the transition matrix "P" can be estimated very accurately in real time.
In an example to elucidate the above process and modelling by the proposed Markov chain model, assume that the transition matrix is $ℙ = [\begin{matrix} 0.7 & 0.3 & 0 \\ 0 & 0.8 & 0.2 \\ 0.3 & 0.3 & 0.4 \end{matrix}]$
.
Matrix "P" is a model of a simple three node traffic system. Assume that the proportions of vehicles on each node is λ_i = [0.4 0.5 0.1]. In two time steps (n=2), the proportions of vehicles in each node would be
(X_n = j) = (λPⁿ⁼²)_j = [0.427 0.398 0.379].
Further, by using the Markov chain model, a plurality of alternative future traffic states based on a plurality of predetermined vehicle behavior criteria configured to influence the determined future traffic states on the one or more road segment(s) may be determined. The alternative future traffic states are in fact, predictions of future outcomes of the traffic state in the geographical sub-regions 200a-f based on a specific behavior, as a function of the velocity and position of the fleet vehicles 110, adapted by the one or more vehicles 110 in the subset of vehicles. The future outcomes of the alternative vehicle behaviors and their impact on the future traffic state of the geographical region 200 are calculated by the Markov chain model. As mentioned earlier, the TMS 30 is configured to control the future traffic state by selecting a predetermined vehicle behavior, comprised in the plurality of the predetermined vehicle behavior criteria, resulting in an improved future traffic state among the alternative future traffic states. Referring to the example of traffic congestion as the future traffic state, the Markov model is adapted to calculate which vehicle behavior adopted by the one or more fleet vehicles 110 would result in resolving the traffic congestion in the geographical region 200 and/or in a certain geographical sub-region 200a-f in question. For instance, the effect of a predetermined speed reduction by the one or more fleet vehicles 110 on a certain portion of the one or more road segment(s) on the future state of congestion in the geographical region in question is calculated. In an alternative example, the impact of reducing speed by the one or more fleet vehicles for a certain predetermined period of time in the current traffic state in one or more of the geographical regions is calculated. A particular pattern of behavior for reducing speed on a certain portion of the road and/or for a certain period of time can thus be selected as the most suitable intervention resulting in the most promising future traffic state i.e. resolution of the future traffic congestion. The selected predetermined vehicle behavior can then be communicated by the TMS 30 to one or more of the fleet vehicle(s) 110. The one or more or each vehicle 110 in the vehicle fleet 110, may also receive a signal from the TMS 30, the signal being comprised in the communication with the fleet of vehicles 110. The transmitted signal by the TMS 30 comprises instructions, instructing the one or more or each of the fleet vehicles 110 to adopt the selected predetermined vehicle behavior. The TMS 30 may be configured to transmit the instruction signal to a vehicle control system 10 of the one or more fleet vehicle(s) 110 for controlling a driver-assistance or an autonomous driving (ADS) feature of the one or more or each of the vehicles 110, thus influencing and controlling the future traffic state on the one or more road segment(s) of the geographical region 200, based on the current traffic state in the geographical region 200. Fig. 3 illustrates a flowchart of the method 300 according to various aspects and embodiments of the present disclosure for controlling a future traffic state on one or more road segment(s) 24 of a geographical region 200, based on a current traffic state in the geographical region 200. The method comprises obtaining 301 vehicle data from at least one subset of vehicles 110 among a plurality of vehicles 100 in the current traffic state, the vehicle data comprising velocity data and position data of one or more vehicle(s) comprised in the at least one subset of vehicles. The method further comprises determining 303, based on the obtained vehicle data, the future traffic state on the one or more road segment(s) within a predetermined time period ensuing the current traffic state and determining 305 a plurality of alternative future traffic states based on a plurality of predetermined vehicle behavior criteria configured to influence the determined future traffic state on the one or more road segment(s). Moreover, the method 300 comprises selecting 307 a predetermined vehicle behavior, comprised in the plurality of the predetermined vehicle behavior criteria, resulting in an augmented future traffic state among the alternative future traffic states and being representative of a most desired future traffic state on the one or more road segment(s). As mentioned earlier, the most desired future traffic state in the present context is to be construed as an optimal future traffic state on the one or more road segment(s) 24. According to several aspects and embodiments the future traffic state on the one or more road segment(s) may comprise a traffic congestion state on the one or more road segment(s) and the most desired future traffic state on the one or more road segment(s) may comprise a resolved traffic congestion state on the one or more road segments 24. The method further comprises communicating 309 the selected predetermined vehicle behavior to one or more vehicle(s) 110 comprised in the at least one subset of vehicles among the plurality of vehicles 100 in the current traffic state. According to several embodiments, the method may further comprise determining 303 the future traffic state on the one or more road segment(s) within the predetermined time period ensuing the current traffic state by means of generating a Markov chain model 31 based on the velocity and position data of one or more vehicle(s) 110 comprised in the subset of vehicles. Even further, the method 300 may comprise determining 305 the plurality of alternative future traffic states based on the plurality of predetermined vehicle behavior criteria for the subset of vehicles by means of the generated Markov chain model 31, the predetermined vehicle behavior criteria being a function of the velocity and position data of the one or more vehicle(s) comprised in the subset of vehicles. In several embodiments and aspects, the vehicle data may comprise real-time vehicle data in the current traffic state. Optionally, the TMS 30 may make use of historic vehicle data, historic traffic information in the geographical region, real-time or historic map data such as data from HD-maps, real-time and/or historic weather forecast data, specific traffic restrictions/planned interruptions in certain time points such as a particular time of day, on or during one or more particular day(s) within a month, or one or more particular month(s) during the year, etc. for controlling the traffic on the geographical region.
Since even in realistic size traffic models individual vehicles may have few alternatives to change paths in each situation, the present model can advantageously be parameterized very quickly. This means that the model framework by construction is capable of accounting for parameters like time of day, time of week, present weather conditions, etc.
Such data may be obtained from external communication networks in real time or from data bases stored on external networks such as a cloud network. However, as mentioned above, significant advantage is provided by the solution of the present disclosure to make highly accurate estimations of future traffic states based on the current traffic states and real time data obtained from the fleet of vehicles travelling in the traffic without the need of historic traffic/vehicle data. The predetermined vehicle behavior criteria in various aspects and embodiments may comprise any one of an adjusted velocity of the vehicle 110, an adjusted distance of the vehicle 110 to an external vehicle 100, 110 ahead, and an updated route selection for the vehicle 110. In several embodiments, the step of communicating 309 the selected predetermined vehicle behavior may further comprise transmitting 311 a signal to one or more vehicle(s) 110 comprised in the at least one subset of vehicles 110, the signal comprising an instruction to adopt the selected predetermined vehicle behavior by the one or more vehicle(s) comprised in the at least one subset of vehicles.
Thus, by factoring in a huge variety of scenarios with variables assigned to parameters such as velocity and position of the travelling vehicles 110 in the current state of traffic, effect of each scenario on the future traffic states can be predicted accurately by the Markov chain model 31. It is thus, highly advantageous to control and influence the future traffic states on the geographical region 200 and sub-regions 200a-f by controlling the behavior of only a limited number of vehicles 110 travelling in traffic. By predicting the outcome of each vehicle behavior, and providing the feedback of the suitable intervention resulting in the most desired future state to the vehicles in the fleet, real-life actual outcome of the intervention on the future traffic state can be controlled and observed. Further, the instructions are variable based on the actual outcome of the communicated instructions and the Markov chain model 31 can be accordingly improved by obtaining the data on how well the communicated instructions have worked in real-life in e.g. resolving traffic congestion on the geographical region.
In several embodiments, the predetermined time period for determining the future traffic state on the one or more road segment(s) may also be determined based on the velocity and the position data of one or more vehicle(s) in the subset of vehicles. In other words, the model 31 is enabled to calculate and predict the whereabouts of the one or more vehicles of the fleet on the road by taking the real-time velocity and position of the one or more vehicle into account. For instance the model could calculate where a particular vehicle 110 would be located within a 10-second, 1-minute, 5-minute, 15-minute, etc. discrete time steps from now, based on the current vehicle data of that particular vehicle. In several aspects and embodiments, the one or more vehicles 110 comprised in the fleet may be equipped with an automated driving system, ADS, feature. Thus, in several embodiments, the method 300 may also comprise controlling the one or more vehicles 110 based on the determined suitable vehicle behavior to achieve the most desired future traffic state. For example, the adjusted velocity of the one or more vehicle(s) 110, and/or the adjusted distance of the vehicles 110 to the one or more external vehicles (not shown) ahead, and/or the updated route selection for the one or more vehicle(s) 110, etc. may be used as input to the one or more ADS features of the one or more vehicle(s) 110 of the fleet configured to control one or more of acceleration, steering, braking, route planning, etc. of the vehicles 110. As mentioned earlier, the method 300 and all embodiments of the method 300 are iterative processes, thus obtaining the vehicle data and updating of the Markov chain model 31 are performed continuously.
Fig. 4 is a schematic side view of a vehicle 110 comprised in the subset of vehicles travelling in traffic on the geographical region 200. The vehicle 110 comprises velocity measurement and calculation devices to obtain the velocity of the ego vehicle on the road portion 24. The vehicle 110 also comprises a localization system 5 configured to monitor a geographical position and heading of the vehicle, and may be in the form of a Global Navigation Satellite System (GNSS), such as a GPS. However, the localization system may alternatively be realized as a Real Time Kinematics (RTK) GPS in order to improve accuracy. The localization system may further comprise inertial measurement units (IMUs). An IMU may be understood as a device configured to detect linear acceleration using one or more accelerometers and rotational rate using one or more gyroscopes. Thus, in some embodiments the localization of the vehicle's heading and orientation may be based on motion sensor data e.g. data from accelerometers and gyroscopes, from the IMU. Moreover, in the present context the vehicle 110 may also have access to a digital map (e.g. a HD-map), either in the form of a locally stored digital map or via a remote data repository accessible via an external communication network 20. The vehicle 110 may further comprise a perception system 6. A perception system 6 is in the present context to be understood as a system responsible for acquiring raw as well as processed sensor data of the on- board sensors 6a, 6b, 6c such as cameras, LIDARs and RADARs, ultrasonic sensors, and converting this data into scene understanding. The vehicle 110 also comprises a vehicle control system 10 configured to obtain vehicle data comprising velocity and position data from the localization system 5 and provide the obtained data to the TMS 30 for use in modeling the traffic on the one or more road segment(s) 24.
Accordingly, it should be understood that parts of the described solution, particularly the TMS may be implemented either in the one or more vehicle(s) 110, in a system located external the vehicles 110, or in a combination of internal and external the vehicle; for instance in an external/remote server or remote control center 400 in communication with the one or more fleet vehicle(s) 110. The solution may in some embodiments be implemented on a cloud platform. For instance, vehicle data comprising velocity and position data may be transmitted to the remote control center 400 comprising a control system 401 to perform the method steps according to several embodiments of the method 300.
Accordingly, the one or more fleet vehicles 110 may be connected to external network(s) 20 via for instance a wireless link. Thus the vehicle control system 10 of the one or more vehicle(s) 110 may be connected to the remote control system 401 and the TMS 30 of the remote control center 400 via the wireless link. In various embodiments, the remote control system 401 may fully or partially comprise the TMS 30. The same or some other wireless link may be used to communicate with other external vehicles in the vicinity of the vehicle or with local infrastructure elements. Cellular communication technologies may be used for long range communication such as to external networks and if the cellular communication technology used have low latency it may also be used for communication between vehicles, vehicle to vehicle (V2V), and/or vehicle to infrastructure, V2X, vehicle to remote control center 400, etc. Examples of cellular radio technologies are GSM, GPRS, EDGE, LTE, 5G, 5G NR, and so on, also including future cellular solutions. However, in some solutions mid to short range communication technologies are used such as Wireless Local Area (LAN), e.g. IEEE 802.11 based solutions. ETSI is working on cellular standards for vehicle communication and for instance 5G is considered as a suitable solution due to the low latency and efficient handling of high bandwidths and communication channels.
The vehicle control system 10 and the remote control system 401 may comprise one or more processors 11, one or more memory module(s) 12, sensor interfaces 13 and communication interfaces 14. The processor(s) 11 may also be referred to as a control circuit 11 or control circuitry 11. The control circuit 11 is configured to execute instructions stored in the memory 12 to perform embodiments of method 300 according to the present disclosure. The memory 12 of the vehicle control system 10 can include one or more (non-transitory) computer-readable storage mediums, for storing computer-executable instructions, which, when executed by one or more computer processors 11, for example, can cause the computer processors 11 to perform the techniques described herein. The memory 12 optionally includes high-speed random access memory, such as DRAM, SRAM, DDR RAM, or other random access solid-state memory devices; and optionally includes non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices.
The present disclosure has been presented above with reference to specific embodiments. However, other embodiments than the above described are possible and within the scope of the disclosure. The different features and steps of the embodiments may be combined in other combinations than those described. Different method steps than those described above, performing the method by hardware or software, may be provided within the scope of the disclosure. Thus, according to an exemplary embodiment, there is provided a non-transitory computer-readable storage medium storing one or more programs configured to be executed by one or more processors of a vehicle control system, the one or more programs comprising instructions for performing the method according to any one of the above-discussed embodiments. In several aspects and embodiments, there is provided a computer program product comprising instructions which, when the program is executed by one or more processors of a processing system, causes the processing system to carry out the method according to any one of the embodiments of the method of the present disclosure.
Alternatively or additionally, according to exemplary embodiments a cloud computing system can be configured to perform any of the methods presented herein. The cloud computing system may comprise distributed cloud computing resources that jointly perform the methods presented herein under control of one or more computer program products.
Generally speaking, a computer-accessible medium may include any tangible or non-transitory storage media or memory media such as electronic, magnetic, or optical media-e.g., disk or CD/DVD-ROM coupled to computer system via bus. The terms "tangible" and "non-transitory," as used herein, are intended to describe a computer-readable storage medium (or "memory") excluding propagating electromagnetic signals, but are not intended to otherwise limit the type of physical computer-readable storage device that is encompassed by the phrase computer-readable medium or memory. For instance, the terms "non-transitory computer-readable medium" or "tangible memory" are intended to encompass types of storage devices that do not necessarily store information permanently, including for example, random access memory (RAM). Program instructions and data stored on a tangible computer-accessible storage medium in non-transitory form may further be transmitted by transmission media or signals such as electrical, electromagnetic, or digital signals, which may be conveyed via a communication medium such as a network and/or a wireless link.
The processor(s) 11 (associated with the control device 10) may be or include any number of hardware components for conducting data or signal processing or for executing computer code stored in memory 12. The vehicle control system 10 or the remote control system 401 may have an associated memory 12, and the memory 12 may be one or more devices for storing data and/or computer code for completing or facilitating the various methods described in the present description. The memory may include volatile memory or non-volatile memory. The memory 12 may include database components, object code components, script components, or any other type of information structure for supporting the various activities of the present description. According to an exemplary embodiment, any distributed or local memory device may be utilized with the systems and methods of this description. According to an exemplary embodiment the memory 12 is communicably connected to the processor 11 (e.g., via a circuit or any other wired, wireless, or network connection) and includes computer code for executing one or more processes described herein.
It should be appreciated that the vehicle 110 further comprises the sensor interface 13 which may also provide the possibility to acquire sensor data directly or via dedicated perception module 6 in the vehicle. The vehicle 110 also comprises a communication/antenna interface 14 which may further provide the possibility to send output to and/or receive input from a remote location (e.g. remote operator or control center 400) by means of an antenna 8. Moreover, some sensors in the vehicle may communicate with the vehicle control device 10 using a local network setup, such as CAN bus, I2C, Ethernet, optical fibres, and so on. The communication interface 14 may be arranged to communicate with other control functions of the vehicle and may thus be seen as control interface also; however, a separate control interface (not shown) may be provided. Local communication within the vehicle may also be of a wireless type with protocols such as WiFi, LoRa, Zigbee, Bluetooth, or similar mid/short range technologies.
It should be noted that the word "comprising" does not exclude the presence of other elements or steps than those listed and the words "a" or "an" preceding an element do not exclude the presence of a plurality of such elements. It should further be noted that any reference signs do not limit the scope of the claims, that the disclosure may be at least in part implemented by means of both hardware and software, and that several "means" or "units" or "modules" may be represented by the same item of hardware.
Although the figures may show a specific order of method steps, the order of the steps may differ from what is depicted. In addition, two or more steps may be performed concurrently or with partial concurrence. Such variation will depend on the software and hardware systems chosen and on designer choice. All such variations are within the scope of the disclosure. Likewise, software implementations could be accomplished with standard programming techniques with rule-based logic and other logic to accomplish the various connection steps, processing steps, comparison steps and decision steps. The above mentioned and described embodiments are only given as examples and should not be limiting to the present disclosure. Other solutions, uses, objectives, and functions within the scope of the disclosure as claimed in the below described patent embodiments should be apparent for the person skilled in the art.

Claims

A method for controlling a future traffic state on one or more road segment(s) of a geographical region, based on a current traffic state in the geographical region, the method comprising:
obtaining vehicle data from at least one subset of vehicles among a plurality of vehicles in the current traffic state, the vehicle data comprising velocity data and position data of one or more vehicle(s) comprised in the at least one subset of vehicles;

determining, based on the obtained vehicle data, the future traffic state on the one or more road segment(s) within a predetermined time period ensuing the current traffic state;

determining a plurality of alternative future traffic states based on a plurality of predetermined vehicle behavior criteria configured to influence the determined future traffic state on the one or more road segment(s);

selecting a predetermined vehicle behavior, comprised in the plurality of the predetermined vehicle behavior criteria, resulting in an augmented future traffic state among the alternative future traffic states and being representative of a most desired future traffic state on the one or more road segment(s);

communicating the selected predetermined vehicle behavior to one or more vehicle(s) comprised in the at least one subset of vehicles among the plurality of vehicles in the current traffic state.
The method according to claim 1, wherein the method further comprises:
determining the future traffic state on the one or more road segment(s) within the predetermined time period ensuing the current traffic state by means of generating a Markov chain model based on the velocity and position data of one or more vehicle(s) comprised in the at least one subset of vehicles.
The method according to claim 1, wherein the method further comprises:
determining the plurality of alternative future traffic states based on the plurality of predetermined vehicle behavior criteria for the subset of vehicles by means of the generated Markov chain model, the predetermined vehicle behavior criteria being a function of the velocity and position data of one or more vehicle(s) comprised in the at least one subset of vehicles.
The method according to any one of claims 1 - 3, wherein the step of communicating the selected predetermined vehicle behavior further comprises:
transmitting a signal to one or more vehicle(s) comprised in the at least one subset of vehicles, the signal comprising an instruction to adopt the selected predetermined vehicle behavior by the one or more vehicle(s) comprised in the at least one subset of vehicles.
The method according to any one of claims 1-4, wherein the vehicle data comprises real-time vehicle data in the current traffic state.
The method according to any of the preceding claims, wherein the predetermined vehicle behavior criteria comprises any one of an adjusted velocity of the vehicle, an adjusted distance of the vehicle to an external vehicle ahead, and an updated route selection for the vehicle.
The method according to any of the preceding claims, wherein the predetermined time period for determining the future traffic state on the one or more road segment(s) is determined based on the velocity and the position data of one or more vehicle(s) in the at least one subset of vehicles.
The method according to any of the preceding claims, wherein the future traffic state on the one or more road segment(s) comprises a future traffic congestion state on the one or more road segment(s) and the most desired future traffic state on the one or more road segment(s) comprises a resolved future traffic congestion state.
The method according to any of the preceding claims wherein the one or more vehicle(s) comprised in the at least one subset of vehicles are equipped with an automated driving system, ADS, feature.
A computer-readable storage medium storing one or more programs configured to be executed by one or more processors of a processing system, the one or more programs comprising instructions for performing the method according to any one of the preceding claims.
A system for controlling a future traffic state on one or more road segment(s) of a geographical region, based on a current traffic state in the geographical region, the system comprising processing circuitry configured to:
obtain vehicle data from at least one subset of vehicles among a plurality of vehicles in the current traffic state, the vehicle data comprising velocity data and position data of one or more vehicle(s) comprised in the at least one subset of vehicles;

determine, based on the obtained vehicle data, the future traffic state on the one or more road segment(s) within a predetermined time period ensuing the current traffic state;

determine a plurality of alternative future traffic states based on a plurality of predetermined vehicle behavior criteria configured to influence the determined future traffic state on the one or more road segment(s);

select a predetermined vehicle behavior, comprised in the plurality of the predetermined vehicle behavior criteria, resulting in an augmented future traffic state among the alternative future traffic states and being representative of a most desired future traffic state on the one or more road segment(s);

communicate the selected predetermined vehicle behavior to one or more vehicle(s) comprised in the at least one subset of vehicles among the plurality of vehicles in the current traffic state.
The system according to claim 11, wherein the processing circuitry is further configured to:
determine the future traffic state on the one or more road segment(s) within the predetermined time period ensuing the current traffic state by means of generating a Markov chain model based on the velocity and position data of one or more vehicle(s) comprised in the at least one subset of vehicles.
The system according to any one of claims 11 or 12, wherein the processing circuitry is further configured to:
determine the plurality of alternative future traffic states based on the plurality of predetermined vehicle behavior criteria for the subset of vehicles by means of the generated Markov chain model, the predetermined vehicle behavior criteria being a function of the velocity and position data of one or more vehicle(s) comprised in the at least one subset of vehicles.
The system according to any one of claims 11 - 13, wherein the processing circuitry is further configured to:
transmit a signal to one or more vehicle(s) comprised in the at least one subset of vehicles, the signal comprising an instruction to adopt the selected predetermined vehicle behavior by the one or more vehicle(s) comprised in the at least one subset of vehicles.
The system according to any one of claims 11 - 14, wherein the predetermined vehicle behavior criteria comprises any one of an adjusted velocity of the vehicle, an adjusted distance of the vehicle to an external vehicle ahead, and an updated route selection for the vehicle.