DETERMINING AN OPTIMAL VEHICLE MANEUVERING PLAN IN A TRAFFIC TRAFFIC SITUATION

Abstract

Method for providing information to an occupant of a vehicle (12), wherein the method comprises: Identifying a traffic congestion type in an environment surrounding the vehicle (12), wherein the traffic congestion type is characterized by a traffic congestion characteristic parameter set; Determining an optimal vehicle maneuvering plan, based at least partially on the traffic congestion type and the traffic congestion characteristic parameter set; and Providing a notification to the vehicle occupant (12), wherein the notification is based at least partially on the optimal vehicle maneuvering plan; furthermore, determining the optimal vehicle maneuvering plan involves: Selecting a chosen machine learning maneuvering model from a variety of maneuvering models, where each of the multiple maneuvering models corresponds to a predefined traffic jam type, and where the selected maneuvering model corresponds to the traffic jam type; and Determining the optimal vehicle maneuvering plan using the selected machine learning maneuvering model, wherein the selected machine learning maneuvering model is configured to receive the traffic jam characteristic parameter set as an input and to provide the optimal vehicle maneuvering plan as an output.

Description

INTRODUCTION

[0001] The present description refers to systems and procedures for providing information to a vehicle occupant.

[0002] To enhance occupant alertness and comfort, vehicles can be equipped with advanced driver assistance systems (ADAS) and / or automated driving systems (ADS). ADAS systems can use various sensors, such as cameras, radar, and LiDAR (Light Detection and Ranging), to detect and identify objects in the vehicle's surroundings, including other vehicles, pedestrians, road configurations, traffic signs, and road markings. Based on environmental conditions, ADAS systems can take action, such as braking or warning the vehicle's occupants. ADS systems can use various sensors to detect objects in the vehicle's environment and steer the vehicle to navigate through the environment to a predetermined destination.However, current ADAS and ADS systems may not be able to effectively detect traffic jams and ensure optimal maneuvering of the vehicle in traffic jam situations.

[0003] DE 10 2008 035 944 A1 describes a method for optimizing the driving operation of a motor vehicle based on several parameters with the following steps: - Determining a route for the vehicle, whereby a destination is specified for determining the route, - Determining several different route parameters that are characteristic for a route profile of the determined route of the vehicle between the geometric location or a starting point of the vehicle and the destination, - Determining at least one driving condition that is characteristic for the determined route of the vehicle between the geometric location of the vehicle or the starting point and the destination.Taking into account the route parameters and the driving conditions, a target driving speed of the vehicle is determined along the calculated route, whereby the route is divided into several segments and the division of the route into segments is based on the route parameters and / or the driving conditions.

[0004] DE 10 2008 047 143 A1 describes a method and a device for determining a driving strategy as information for the driver of a motor vehicle, in which, in particular, local information from other vehicles, especially those driving ahead, is acquired by means of a receiving device and information derived from this is made available to the driver. In order to create a way to improve traffic flow and at the same time reduce energy consumption, travel times and the risk of accidents, the provision of information includes at least a recommendation for a recommended speed. This provides the driver with an individual recommendation for a recommended speed, which is not based on a general assessment of the traffic situation, but is derived from the acquired information from vehicles driving ahead.

[0005] DE 10 2015 217 793 A1 describes devices, methods, and computer programs for providing traffic jam information via a vehicle-to-vehicle interface. The device for a vehicle includes a means of receiving traffic jam indicators. The traffic jam indicators include the speed of the vehicle or vehicles in the vicinity of the vehicle and a traffic jam warning. The device further includes a means of determining traffic jam information based on the traffic jam indicators. The traffic jam information indicates whether the vehicle is in a traffic jam. The device further includes a vehicle-to-vehicle interface configured for providing the traffic jam information to one or more other vehicles via a vehicle-to-vehicle communication link.

[0006] DE 10 2008 003 039 A1 describes a method for detecting traffic conditions based on measurement data acquired in a vehicle, which includes the vehicle's speed, whereby the detection is carried out in the vehicle itself.

[0007] DE 10 2013 014 872 A1 describes a method, an evaluation system, and a cooperative vehicle for predicting at least one traffic congestion parameter. The method includes recording traffic density, recording the current position present at the time of traffic density recording, and transmitting the traffic density and current position to an evaluation unit. Furthermore, the method includes evaluating the traffic density and providing at least one traffic congestion parameter.

[0008] DE 199 44 075 C2 describes a method for monitoring the traffic condition in a road network with effective bottlenecks, in which the traffic condition is classified into one of several condition phases, taking into account recorded traffic measurement data of one or more traffic parameters, which include at least information on the traffic volume and / or the average vehicle speed.

[0009] While ADAS and ADS systems and procedures fulfill their purpose, there is therefore a need for a new and improved system and procedure for characterizing traffic jams, determining an optimal vehicle maneuvering plan, and providing information about the optimal vehicle maneuvering plan to the vehicle occupants. DESCRIPTION

[0010] According to the invention, a method for providing information to a vehicle occupant is provided. The method can include identifying a traffic jam type in the environment surrounding the vehicle. The traffic jam type is characterized by a traffic jam characteristic parameter set. The method can further include determining an optimal vehicle maneuvering plan, which is based at least partially on the traffic jam type and the traffic jam characteristic parameter set. The method can further include providing a notification to the vehicle occupant. The notification is based at least partially on the optimal vehicle maneuvering plan. Determining the optimal vehicle maneuvering plan further includes selecting a machine learning maneuvering model from a plurality of maneuvering models.Each of the multiple maneuvering models corresponds to a predefined traffic jam type, and the selected maneuvering model corresponds to that traffic jam type. Determining the optimal vehicle maneuvering plan can further involve determining the optimal vehicle maneuvering plan using the selected machine learning maneuvering model. The selected machine learning maneuvering model is configured to receive the traffic jam characteristic parameter set as input and provide the optimal vehicle maneuvering plan as output.

[0011] In another aspect of this description, identifying the traffic congestion type may further involve receiving one or more messages from one or more distant vehicles using a vehicle communication system. Identifying the traffic congestion type may also involve determining a multitude of individual speed-time curves, based at least in part on the one or more messages. Each of the multiple individual speed-time curves corresponds to one of the one or more distant vehicles. Identifying the traffic congestion type may further involve determining the traffic congestion type, at least in part, based on the multiple individual speed-time curves.

[0012] In another aspect of the present description, the determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further involve the determination of a multitude of individual curve characteristic parameter sets. One of the multiple individual curve characteristic parameter sets describes each of the multiple individual speed-time curves. The determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further involve the determination of a multitude of individual curve confidence values. Each of the multiple individual curve confidence values ​​corresponds to one of the multiple individual curve characteristic parameter sets.

[0013] In another aspect of the present description, the determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further include combining each of the multitude of individual speed-time curves into a combined speed-time curve. The determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further include determining a combined curve characteristic parameter set that describes the combined speed-time curve. The determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further include determining a combined curve confidence value of the combined curve characteristic parameter set.

[0014] In another aspect of the present description, determining the traffic congestion type, at least partially based on the multiple individual speed-time curves, may further involve combining each of the multiple individual speed-time curves with the combined speed-time curve to generate a combined speed-time curve. The combined speed-time curve is generated, at least partially, based on the multiple individual curve characteristic parameter sets, the multiple individual curve confidence values, the combined curve characteristic parameter set, and the combined curve confidence value.Determining the traffic congestion type, which is at least partially based on the multitude of individual speed-time curves, can further include determining the traffic congestion characteristic parameter set that describes the combined speed-time curve. Determining the traffic congestion type, which is at least partially based on the multitude of individual speed-time curves, can further include determining the traffic congestion type that is at least partially based on the combined speed-time curve and the traffic congestion characteristic parameter set.

[0015] In another aspect of the present description, the determination of the traffic congestion type, based at least partially on the combined velocity-time curve and the traffic congestion characteristic parameter set, may further include performing one or more perception measurements of the one or more distant vehicles using one or more vehicle perception sensors. The determination of the traffic congestion type, based at least partially on the combined velocity-time curve and the traffic congestion characteristic parameter set, may also include the verification of the traffic congestion type, based at least partially on the one or more perception measurements.

[0016] According to the invention, determining the optimal vehicle maneuver plan further comprises determining the optimal vehicle maneuver plan using the selected machine learning maneuver model. The selected machine learning maneuver model is configured to receive the traffic congestion characteristic parameter set as an input and to provide the optimal vehicle maneuver plan as an output. The optimal vehicle maneuver plan includes an optimal velocity-time curve.

[0017] In another aspect of this description, the provision of the notification may further include the determination of one or more optimal acceleration and braking levels, based at least partially on the optimal velocity-time curve. The provision of the notification may also include the provision of the notification to the vehicle occupant. The notification includes at least one of: the optimal velocity-time curve and the one or more optimal acceleration and braking levels.

[0018] In another aspect of this description, providing the notification may further include determining a recommended vehicle maneuver, based at least in part on the traffic congestion type. Providing the notification may also include delivering the notification to the vehicle occupants. The notification contains the recommended vehicle maneuver.

[0019] A system for providing information to a vehicle occupant is provided according to several aspects. The system may include a vehicle communication system, a display, and a control unit that communicates electrically with the vehicle communication system and the display. The control unit is programmed to use the vehicle communication system to detect the type of traffic congestion in the vehicle's surrounding environment. The traffic congestion type is characterized by a traffic congestion characteristic parameter set. The control unit is further programmed to determine an optimal vehicle maneuvering plan, based at least partially on the traffic congestion type and the traffic congestion characteristic parameter set. The control unit is also programmed to provide a notification to the vehicle occupant via the display. This notification is based at least partially on the optimal vehicle maneuvering plan.

[0020] In another aspect of this description, the control system for identifying the traffic jam type is further programmed to receive one or more messages from one or more distant vehicles using the vehicle communication system. To identify the traffic jam type, the control system is further programmed to determine a multitude of individual speed-time curves, based at least partially on the one or more messages. Each of the multiple individual speed-time curves corresponds to one of the one or more distant vehicles. To identify the traffic jam type, the control system is further programmed to determine the traffic jam type, at least partially, based on the multiple individual speed-time curves.

[0021] In another aspect of this description, the control system for determining the traffic congestion type is programmed, at least partially, based on multiple individual speed-time curves to determine multiple individual curve characteristic parameter sets. One of these individual curve characteristic parameter sets describes each of the multiple individual speed-time curves. Furthermore, to determine the traffic congestion type, at least partially, based on these multiple individual speed-time curves, the control system is programmed to calculate multiple individual curve confidence values. Each of these individual curve confidence values ​​corresponds to one of the multiple individual curve characteristic parameter sets.To determine the traffic congestion type, at least partially, based on the multiple individual speed-time curves, the controller is further programmed to combine each of the multiple individual speed-time curves into a combined speed-time curve. To determine the traffic congestion type, at least partially, based on the multiple individual speed-time curves, the controller is further programmed to determine a combined curve characteristic parameter set that describes the combined speed-time curve. To determine the traffic congestion type, at least partially, based on the multiple individual speed-time curves, the controller is further programmed to determine a combined curve confidence value for the combined curve characteristic parameter set.To determine the traffic congestion type, at least partially, based on the multiple individual speed-time curves, the controller is further programmed to combine each of the multiple individual speed-time curves with the combined speed-time curve to generate a combined speed-time curve. The combined speed-time curve is generated, at least partially, based on the multiple individual curve characteristic parameter sets, the multiple individual curve confidence values, the combined curve characteristic parameter set, and the combined curve confidence value. To determine the traffic congestion type, at least partially, based on the multiple individual speed-time curves, the controller is further programmed to determine the traffic congestion characteristic parameter set that describes the combined speed-time curve.In order to determine the traffic congestion type at least partially based on the multiple individual speed-time curves, the control system is further programmed to determine the traffic congestion type at least partially based on the combined speed-time curve and the traffic congestion characteristic parameter set.

[0022] In another aspect of this description, the system also includes one or more perception sensors electrically connected to the controller. To determine the traffic congestion type, at least partially, based on the combined speed-time curve and the traffic congestion characteristic parameter set, the controller is further programmed to perform one or more perception measurements of the one or more distant vehicles using the one or more perception sensors. To determine the traffic congestion type, at least partially, based on the combined speed-time curve and the traffic congestion characteristic parameter set, the controller is further programmed to verify the traffic congestion type, at least partially, based on the one or more perception measurements.

[0023] According to the invention, the control system for determining the optimal vehicle maneuver plan is further programmed to select a chosen machine learning maneuver model from a plurality of maneuver models. The selected machine learning maneuver model corresponds to the traffic jam type. To determine the optimal vehicle maneuver plan, the control system is further programmed to determine the optimal vehicle maneuver plan using the selected machine learning maneuver model. The selected machine learning maneuver model is configured to receive the traffic jam characteristic parameter set as input and to provide the optimal vehicle maneuver plan as output. The optimal vehicle maneuver plan includes an optimal velocity-time curve.

[0024] In another aspect of this description, the controller is further programmed to determine one or more optimal acceleration and braking levels, based at least partially on the optimal speed-time curve, in order to provide the notification. To provide the notification, the controller is further programmed to display the notification to the vehicle occupant via the display. The notification includes at least one of the following: the optimal speed-time curve and the one or more optimal acceleration and braking levels.

[0025] In another aspect of this description, the display may also include a head-up display (HUD) electrically connected to the control unit. To provide the notification, the control unit is further programmed to deliver the notification to the vehicle occupants via the HUD. The notification includes at least one of the following: the optimal speed-time curve and one or more optimal acceleration and braking levels.

[0026] A method for providing information to a vehicle occupant is provided according to several aspects. The method may involve receiving one or more messages from one or more remote vehicles using a vehicle communication system. The method may further involve determining a plurality of individual speed-time curves, based at least partially on the one or more messages. Each of the plurality of individual speed-time curves corresponds to one of the one or more remote vehicles. The method may further involve determining a traffic jam type, based at least partially on the plurality of individual speed-time curves. The traffic jam type is characterized by a traffic jam characteristic parameter set.The procedure may further include determining an optimal vehicle maneuvering plan based at least partially on the traffic congestion type and the traffic congestion characteristic parameter set. The optimal vehicle maneuvering plan includes at least one optimal speed-time curve. The procedure may further include determining one or more optimal acceleration and braking levels based at least partially on the optimal speed-time curve. The procedure may further include providing a notification to the vehicle occupant using a head-up display (HUD). The notification includes at least one of the optimal speed-time curve and one or more optimal acceleration and braking levels.

[0027] In another aspect of the present description, the determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further involve the determination of a multitude of individual curve characteristic parameter sets. One of the multiple individual curve characteristic parameter sets describes each of the multiple individual speed-time curves. The determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further involve the determination of a multitude of individual curve confidence values. Each of the multiple individual curve confidence values ​​corresponds to one of the multiple individual curve characteristic parameter sets.Determining the traffic congestion type, which is at least partially based on a multitude of individual speed-time curves, may further involve combining each of the multitude of individual speed-time curves into a combined speed-time curve. Determining the traffic congestion type, which is at least partially based on the multitude of individual speed-time curves, may further involve determining a combined curve characteristic parameter set that describes the combined speed-time curve. Determining the traffic congestion type, which is at least partially based on the multitude of individual speed-time curves, may further involve determining a combined curve confidence value for the combined curve characteristic parameter set.The determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further involve merging each of the multitude of individual speed-time curves with the merged speed-time curve to generate a merged speed-time curve. The merged speed-time curve is generated at least partially based on the multiple individual curve characteristic parameter sets, the multiple individual curve confidence values, the merged curve characteristic parameter set, and the merged curve confidence value. The determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further involve determining the traffic congestion characteristic parameter set that describes the merged speed-time curve.The determination of the traffic congestion type, which is based at least partially on the multitude of individual speed-time curves, may further include the determination of the traffic congestion type, which is based at least partially on the combined speed-time curve and the traffic congestion characteristic parameter set.

[0028] According to the invention, determining the optimal vehicle maneuvering plan further comprises selecting a chosen machine learning maneuvering model from a plurality of maneuvering models. The selected maneuvering model corresponds to the traffic jam type. Determining the optimal vehicle maneuvering plan can further comprise determining the optimal vehicle maneuvering plan using the selected machine learning maneuvering model. The selected machine learning maneuvering model is configured to receive the traffic jam characteristic parameter set as input and to provide the optimal vehicle maneuvering plan as output. The optimal vehicle maneuvering plan includes an optimal velocity-time curve.

[0029] Further areas of application will become apparent from the present description. It is understood that the description and the specific examples serve only for illustration and are not intended to limit the scope of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings described here are for illustrative purposes only and are not intended to limit the scope of the present description in any way. Fig. Figure 1 is a schematic diagram of a system for providing information to an occupant of a vehicle, shown with a host vehicle in an exemplary context of a roadway with one or more distant vehicles, according to an exemplary embodiment; Fig. Figure 2 is a schematic representation of the system for providing information to a vehicle occupant according to an exemplary embodiment; Fig. Figure 3 is a flowchart of a procedure for providing information to a vehicle occupant according to an exemplary embodiment; Fig. Figure 4A is a first exemplary speed-time diagram showing a first traffic jam type according to an exemplary embodiment; Fig. 4B is a second exemplary speed-time diagram showing a second type of traffic jam according to an exemplary embodiment; Fig. 4C is a third exemplary speed-time diagram showing a third type of traffic jam according to an exemplary embodiment; and Fig. Figure 5 is an exemplary view from inside the vehicle with an exemplary HUD notification and an exemplary HMI notification according to an exemplary embodiment. DETAILED DESCRIPTION

[0031] The following description is merely exemplary and is not intended to limit the present disclosure, application or use.

[0032] Traffic congestion can be unpleasant for vehicle occupants. Furthermore, occupants may be unsure which actions or maneuvers (e.g., acceleration, braking, lane changes, etc.) are optimal for increasing comfort and facilitating the vehicle's progress in traffic jams. Therefore, this description presents a new and improved system and procedure for characterizing traffic jams, determining an optimal vehicle maneuver plan, and providing information about that plan to the vehicle occupant(s).

[0033] In Fig. Figure 1 is a system 10 for providing information to a vehicle occupant with a host vehicle 12 in an exemplary context of a roadway 14 with one or more distant vehicles 16. It is understood that the roadway 14 can be any open route for the passage and transport of vehicles (e.g., roads, highways, expressways, motorways, boulevards, avenues, park paths, tree-lined avenues, bridges, tunnels, and / or the like). In the Fig. In the exemplary embodiment shown in Figure 1, the one or more remotely controlled vehicles 16 comprise a first remotely controlled vehicle 16a and a second remotely controlled vehicle 16b. It is understood that the one or more remote vehicles 16 can comprise any number of vehicles traveling on the roadway 14. The one or more remote vehicles 16 can be, for example, SUVs, sedans, compact cars, trucks, commercial vehicles, and / or the like. In some examples, the one or more remote vehicles 16 can also include additional road users, such as pedestrians, bicycles, and / or the like.

[0034] Fig. Figure 2 shows a schematic representation of the system 10 for providing information to a vehicle occupant. The system 10 is shown with the host vehicle 12. Although a passenger car is shown, the host vehicle 12 can be any type of vehicle without this deviating from the scope of this description. The system 10 generally comprises a controller 20, a variety of vehicle sensors 22, a human-machine interface (HMI) 24, and a head-up display (HUD) 26.

[0035] The controller 20 is used to implement a method 100 for providing information to a vehicle occupant, as described below. The controller 20 comprises at least one processor 28 and a non-transient, computer-readable device or medium 30. The processor 28 may be a custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor among several processors associated with the controller 20, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally, an instruction-executing device.

[0036] The computer-readable devices or media 30 can contain volatile and non-volatile memory, such as read-only memory (ROM), random-access memory (RAM), and keep-alive memory (KAM). KAM is a persistent or non-volatile memory that can be used to store various operating variables while the processor 28 is powered off. The computer-readable memory device or media 30 can be implemented using a variety of memory devices such as PROMs (programmable read-only memory), EPROMs (electrical PROMs), EEPROMs (electrically erasable PROMs), flash memory, or other electrical, magnetic, optical, or combined memory devices capable of storing data, some of which represents executable instructions used by the controller 20 to control various systems of the host vehicle 12.

[0037] The control unit 20 can also consist of several control units that communicate electrically with each other. The control unit 20 can be connected to additional systems and / or control units of the host vehicle 12, so that the control unit 20 can access data such as speed, acceleration, braking, and steering angle of the base vehicle 12.

[0038] The controller 20 communicates electrically with the multiple vehicle sensors 22, the HMI 24, and the HUD 26. In one exemplary embodiment, the electrical communication is established, for example, via a CAN network, a FLEXRAY network, a local area network (e.g., WiFi, Ethernet, and the like), a serial peripheral interface network (SPI), or the like. It is understood that various additional wired and wireless technologies and communication protocols for communicating with the controller 20 fall within the scope of this description. It is also understood that one or more of the multiple vehicle sensors 22, the HMI 24, and the HUD 26 can be integrated into the controller 20 (e.g., on the same circuit board as the controller 20 or otherwise as part of the controller 20) without this deviating from the scope of this description.It should further be understood that, within the scope of this description, electrical communication also includes the transfer of power and / or energy between electrical devices (e.g., using conductive wires and / or wireless power transmission techniques).

[0039] The plurality of vehicle sensors 22 is used to acquire information about the one or more remote vehicles 16. In an exemplary embodiment, the plurality of vehicle sensors 22 comprises one or more perception sensors 32, a global navigation satellite system (GNSS) 34, and a vehicle communication system 36.

[0040] The one or more perception sensors 32 are used to perceive objects and / or to measure distances in the vicinity of the host vehicle 12. In an exemplary embodiment, the one or more perception sensors 32 comprise at least one of: a camera 38, a radar sensor 40, and a LiDAR (Light Detection and Ranging) sensor 42.

[0041] The camera 38 is a perception sensor used to capture images and / or videos of the environment surrounding the host vehicle 12. In one exemplary embodiment, the camera 38 comprises a photo and / or video camera positioned to capture the environment surrounding the host vehicle 12. In a non-limiting example, the camera 38 comprises a camera mounted inside the host vehicle 12, for example, in the headliner of the host vehicle 12, and capable of seeing through a windshield 44 of the host vehicle 12. In another non-limiting example, the camera 38 comprises a camera mounted outside the host vehicle 12, for example, on the roof of the host vehicle 12, providing a view of the environment in front of the host vehicle 12.

[0042] In another exemplary embodiment, the camera 38 is a surround-view camera system comprising a plurality of cameras (also known as satellite cameras) arranged to provide a view of the surroundings on all sides of the base vehicle 12. In a non-limiting example, the camera 38 includes a forward-facing camera (e.g., mounted in a radiator grille of the host vehicle 12), a rear-facing camera (e.g., mounted on a tailgate of the host vehicle 12), and two side-facing cameras (e.g., mounted below each of the two side mirrors of the host vehicle 12). In a further non-limiting example, the camera 38 also includes an additional reversing camera mounted near a high-mounted center brake light of the base vehicle 12.

[0043] It is understood that camera systems with additional cameras and / or additional mounting locations fall within the scope of this description. It should further be understood that cameras with different sensor types, such as CCD (charge-coupled device) sensors, CMOS (complementary metal oxide semiconductor) sensors, and / or HDR (high dynamic range) sensors, also fall within the scope of this description. Furthermore, cameras with different lens types, such as wide-angle and / or narrow-angle lenses, also fall within the scope of this description. The camera 38 communicates electrically with the controller 20, as described above.

[0044] The radar sensor 40 is used to detect and measure the distance, speed, and direction of objects (e.g., one or more distant vehicles 16) by emitting radio waves and analyzing the reflections of those radio waves. In an exemplary embodiment, the radar sensor 40 comprises a radar transmitter (not shown), a radar antenna (not shown), a radar receiver (not shown), and a radar signal processing unit (not shown). In a non-limiting example, the radar transmitter uses the radar antenna to emit radio frequency signals (RF signals) that travel through space until they encounter an object. The RF signals bounce off the surface of the object and return to the radar sensor 40.The radar receiver detects the reflected signals using the radar antenna, and the radar signal processing unit analyzes the time delay, frequency shift, and amplitude of the returned RF signals to determine the distance, speed, and direction of the detected objects. The radar sensor 40 communicates electrically with the controller 20, as described above.

[0045] The LiDAR sensor 42 is used for remote sensing and environmental mapping by emitting laser pulses and measuring the time it takes for the laser pulses to return to the LiDAR sensor 42 after striking objects. In an exemplary embodiment, the LiDAR sensor 42 comprises a LiDAR laser source (not shown), a LiDAR scanner or mirror (not shown), a LiDAR photodetector (not shown), and a LiDAR time-of-flight measurement system (not shown). In a non-limiting example, the LiDAR laser source emits laser pulses that travel toward the target area, and the LiDAR scanner directs these pulses in various directions. The emitted laser pulses interact with objects in the environment, and their reflections are detected by the LiDAR photodetector.The LiDAR time-of-flight measurement system calculates the distance to the objects based on the time between the emission of the laser pulses by the LiDAR laser source and the reception of the reflected laser pulses by the LiDAR photodetector. The LiDAR sensor 42 is in electrical communication with the controller 20, as described above.

[0046] In one exemplary embodiment, the one or more perception sensors 32 are mounted inside the host vehicle 12, for example, in the headliner of the host vehicle 12, with a view through the windshield 44 of the host vehicle 12. In another example, the one or more perception sensors 32 are mounted outside the host vehicle 12, for example, on the roof of the host vehicle 12, allowing a view of the host vehicle 12's surroundings. It is understood that various additional types of perception sensors, such as stereoscopic cameras with distance measurement capabilities, ultrasonic distance sensors, and time-of-flight sensors, fall within the scope of this description. The one or more perception sensors 32 are in electrical communication with the controller 20, as described above.

[0047] The GNSS 34 is used to determine the geographic location of the host vehicle 12. In an exemplary embodiment, the GNSS 34 is a global positioning system (GPS). In a non-limiting example, the GPS comprises a GPS receiving antenna (not shown) and a GPS controller (not shown) electrically connected to the GPS receiving antenna. The GPS receiving antenna receives signals from a plurality of satellites, and the GPS controller calculates the geographic location of the host vehicle 12 based on the signals received by the GPS receiving antenna.

[0048] In one exemplary embodiment, the GNSS 34 additionally includes a map. The map contains information about infrastructure such as municipal boundaries, roads, railways, sidewalks, buildings, and the like. Therefore, the geographic location of the host vehicle 12 is contextualized using the map information. In a non-restrictive example, the map is retrieved from a remote source via a wireless connection. In another non-restrictive example, the map is stored in a database or memory of the GNSS 34.

[0049] It is understood that various additional types of satellite-based radio navigation systems, such as the Global Positioning System (GPS), Galileo, GLONASS, and the BeiDou Navigation Satellite System (BDS), fall within the scope of this description. The GNSS 34, as described above, communicates electrically with the controller 20.

[0050] The vehicle communication system 36 is used by the controller 20 to communicate with other systems outside the host vehicle 12. For example, the vehicle communication system 36 includes capabilities for communicating with vehicles (“V2V” communication), infrastructure (“V2I” communication), remote systems in a remote call center (e.g., GENERAL MOTORS ON-STAR), and / or personal devices. In general, the term vehicle-to-everything communication (“V2X” communication) refers to communication between the host vehicle 12 and any remote system (e.g., vehicles, infrastructure, and / or remote systems).

[0051] In certain embodiments, the vehicle communication system 36 is a wireless communication system configured to communicate via a wireless local area network (WLAN) using IEEE 802.11 standards or using cellular data communication (e.g., using GSMA standards such as SGP.02, SGP.22, SGP.32, and the like). Accordingly, the vehicle communication system 36 may further include an embedded universal integrated circuit (eUICC) configured to store at least one configuration profile for cellular connectivity, for example, an embedded subscriber identity module (eSIM) profile.

[0052] The vehicle communication system 36 is further configured to communicate via a personal area network (e.g., Bluetooth), near-field communication (NFC), and / or any other type of radio frequency communication. However, additional or alternative communication methods, such as a dedicated short-range communication channel (DSRC) and / or mobile telecommunications protocols based on the standards of the 3rd Generation Partnership Project (3GPP), are also considered within the scope of this description. DSRC channels refer to one-way or two-way short- to medium-range wireless communication channels specifically designed for use in motor vehicles, as well as a range of protocols and standards. The 3GPP is a partnership between several standards organizations that develop protocols and standards for mobile telecommunications. The 3GPP standards are structured as releases.

[0053] Therefore, communication methods based on 3GPP versions 14, 15, 16 and / or future 3GPP versions fall within the scope of this description.

[0054] Accordingly, the vehicle communication system 36 can include one or more antennas and / or communication transceivers (not shown) for receiving and / or transmitting signals, such as cooperative acquiring messages (CSMs). The vehicle communication system 36 is configured to wirelessly transmit information between the host vehicle 12 and another vehicle. Furthermore, the vehicle communication system 36 is configured to wirelessly transmit information between the host vehicle 12 and the infrastructure or other vehicles (e.g., one or more remote vehicles 16).

[0055] In another exemplary embodiment, the plurality of vehicle sensors 22 also includes sensors for determining performance data about the host vehicle 12. In a non-limiting example, the plurality of vehicle sensors 22 also includes at least one engine speed sensor, one engine torque sensor, one voltage and / or current sensor of the electric drive motor, one accelerator pedal position sensor, one brake position sensor, one coolant temperature sensor, one cooling fan speed sensor, and one transmission oil temperature sensor.

[0056] In another exemplary embodiment, the plurality of vehicle sensors 22 also includes additional sensors for determining information about an environment inside the host vehicle 12. In a non-limiting example, the plurality of vehicle sensors 22 also includes at least a seat occupancy sensor, a cabin air temperature sensor, a cabin motion detection sensor, a cabin camera, a cabin microphone, an occupant eye sensor and / or the like.

[0057] In another exemplary embodiment, the plurality of vehicle sensors 22 also includes additional sensors for determining information about the environment of the host vehicle 12. In a non-limiting example, the plurality of vehicle sensors 22 also includes at least one sensor for ambient air temperature, an air pressure sensor, and / or similar sensors. The multiple vehicle sensors 22 are in electrical communication with the controller 20, as described above.

[0058] The human-machine interface 24 serves to provide information to an occupant of the host vehicle 12. For the purposes of this description, the occupant includes a driver and / or a passenger of the host vehicle 12. In the Fig. In the exemplary embodiment shown in Figure 2, the HMI 24 is a display (e.g., part of an infotainment system of the host vehicle 12) located in the occupant's field of vision and capable of displaying text, graphics, and / or images. It is understood that HMI display systems, including LCD displays, LED displays, and the like, fall within the scope of this description. Further exemplary embodiments in which the HMI 24 is arranged in a rearview mirror also fall within the scope of this description. In one exemplary embodiment, the occupant can interact with the HMI 24 using a human-interface device (HID), including, for example, a touchscreen, an electromechanical switch, a capacitive switch, a rotary knob, a microphone for receiving voice commands, and the like.It is understood that additional systems for displaying information to the occupant of the host vehicle 12 also fall within the scope of this description. The HMI 24 communicates electrically with the controller 20, as described above.

[0059] The HUD 26 is used to provide information to the occupant of the host vehicle 12. In one exemplary embodiment, the HUD 26 is configured to provide information to the occupant by projecting text, graphics, and / or images onto the windshield 44 of the base vehicle 12. In a non-limiting example, the HUD 26 includes a projector (not shown) used by the controller 20 to project the text, graphics, and / or images onto the windshield 44 of the host vehicle 12. The text, graphics, and / or images are reflected off the windshield 44 of the host vehicle 12 and are visible to the occupant without requiring them to take their eyes off the road 14 in front of the host vehicle 12.It is understood that various types of head-up display devices, including, for example, augmented reality head-up display devices (AR-HUDs), fall within the scope of this description. In an exemplary embodiment, the occupant can interact with the HUD 26 by using a human-interface device (HID), including, for example, a touchscreen, an electromechanical switch, a capacitive switch, a rotary knob, a microphone for receiving voice commands, and the like. It is understood that additional systems for displaying information to the occupant of the host vehicle 12 also fall within the scope of this description. The HUD 26 communicates electrically with the controller 20, as described above.

[0060] In Fig. Figure 3 shows a flowchart of the procedure 100 for providing information to a vehicle occupant. The procedure 100 begins at block 102 and proceeds to blocks 104 and 106. In block 104, the controller 20 uses the vehicle communication system 36 to receive one or more messages from the one or more remote vehicles 16. The one or more messages contain at least a speed, a position, a vehicle identifier (e.g., a vehicle identification number (VIN) and / or other temporary identifier based on the Society of Automotive Engineers (SAE) message standards), and a message time for each of the one or more remote vehicles 16. In an exemplary embodiment, the one or more messages are basic safety messages (BSM) from each of the one or more remote vehicles 16, containing information such as:The messages contain position, speed, speed profile over time, acceleration, direction, vehicle type, vehicle identifier, vehicle dimensions, vehicle status, driver intent, message time, and / or similar information. In a non-restrictive example, the one or more messages are transmitted using vehicle-to-vehicle (V2V) communication techniques, such as Dedicated Short-Range Communications (DSRC). In another non-restrictive example, the messages are routed through one or more central servers (e.g., transmission over the internet or using cellular data communication). After Block 104, Procedure 100 proceeds to Block 108.

[0061] In block 108, the controller 20 determines a multitude of individual speed-time curves. For the purposes of this description, a speed-time curve is a set of data points representing the speed of a vehicle over a specific period of time (e.g., ten minutes). In a non-restrictive example, the speed-time curve contains speed measurements taken every second over the ten-minute period. The speed curve can be visually represented in a two-dimensional graph, with time on the horizontal axis (e.g., the x-axis) and speed on the vertical axis (e.g., the y-axis). Each of the multiple individual speed-time curves corresponds to one or more vehicles 16 located at a distance.Therefore, each of the multiple individual speed-time curves contains speed data for one of the one or more remote vehicles 16. In an exemplary embodiment, the controller 20 aggregates the one or more messages received in block 104 to determine the multiple individual speed-time curves and extracts the speed and time data from the one or more messages received in block 104 for each of the one or more remote vehicles 16. After block 108, the method 100 continues with blocks 110 and 112.

[0062] In block 110, the controller 20 combines each of the multiple individual velocity-time curves determined in block 108 into a single merged velocity-time curve. In an exemplary embodiment, to merge each of the multiple individual velocity-time curves into the merged velocity-time curve, the controller 20 first balances each of the multiple individual velocity-time curves. The controller 20 then averages each of the multiple individual velocity-time curves to generate the merged velocity-time curve. It is understood that additional methods for merging the multiple individual velocity-time curves, including, for example, additional mathematical or statistical methods, machine learning-based methods, and / or the like, fall within the scope of this description.After block 110, procedure 100 continues to block 114.

[0063] In block 114, the controller 20 determines a merged curve characteristic parameter set that describes the merged velocity-time curve determined in block 110. For the purposes of this description, the merged curve characteristic parameter set comprises parameter values ​​that characterize the shape of the merged velocity-time curve. In an exemplary embodiment, the merged velocity-time curve is fitted using a regression or curve-fitting algorithm (e.g., a linear, polynomial, exponential, or logarithmic curve-fitting algorithm) that generates the merged curve characteristic parameter set. In a non-restrictive example, the curve-fitting algorithm uses an iterative process to determine optimal values ​​for the merged curve characteristic parameter set.In a non-restrictive example, the merged curve characteristic parameter set includes a maximum velocity, a minimum velocity, a maximum acceleration, a minimum acceleration, one or more coefficients for a mathematical equation describing a curve fit, and / or similar parameters. The merged curve characteristic parameter set can be used to estimate or predict past or future values ​​of the merged velocity-time curve.

[0064] The controller 20 also determines a combined curve confidence value of the combined curve characteristic parameter set. Within the scope of this description, the combined curve confidence value quantifies how accurately the combined curve characteristic parameter set describes the combined velocity-time curve. In one exemplary embodiment, the combined curve confidence value is a proportion of the points predicted by the combined curve characteristic parameter set that fall on the combined velocity-time curve. In another exemplary embodiment, the combined curve confidence value is a coefficient of determination (R). 2It is understood that the merged curve confidence value can include any value that quantifies how accurately the merged curve characteristic parameter set describes the merged velocity-time curve without going beyond the scope of the present description. Following Block 114, Procedure 100 proceeds to Block 116, as explained in more detail below.

[0065] In block 112, the controller 20 determines a plurality of individual curve characteristic parameter sets. One of the several individual curve characteristic parameter sets describes each of the several individual velocity-time curves determined in block 108. For the purposes of this description, each individual curve characteristic parameter set comprises parameter values ​​that characterize the shape of one of the several individual velocity-time curves. In an exemplary embodiment, each of the several individual velocity-time curves is fitted using a regression or curve-fitting algorithm (e.g., a linear, polynomial, exponential, or logarithmic curve-fitting algorithm) that generates an individual curve characteristic parameter set.In a non-restrictive example, the curve-fitting algorithm uses an iterative process to determine optimal values ​​for each of the multiple individual curve characteristic parameter sets. In this non-restrictive example, each of the multiple individual curve characteristic parameter sets includes a maximum velocity, a minimum velocity, a maximum acceleration, a minimum acceleration, one or more coefficients for a mathematical equation describing a curve fit, and / or similar parameters. The multiple individual curve characteristic parameter sets can be used to estimate or predict past or future values ​​of each of the multiple individual velocity-time curves.

[0066] The controller 20 also determines a multitude of individual curve confidence values. Each of the multiple individual curve confidence values ​​corresponds to one of the multiple individual curve characteristic parameter sets. In the context of this description, each of the multiple individual curve confidence values ​​quantifies how accurately each of the multiple individual curve characteristic parameter sets describes each of the multiple individual velocity-time curves. In one exemplary embodiment, the individual curve confidence value is a proportion of the points predicted by the individual curve characteristic parameter set that fall on the individual velocity-time curve. In another exemplary embodiment, the individual curve confidence value is a coefficient of determination (R). 2It is understood that the individual curve confidence value can encompass any value that quantifies how accurately the individual curve characteristic parameter set describes the individual velocity-time curve without deviating from the scope of the present description. Following Block 112, Procedure 100 proceeds to Block 116.

[0067] In block 116, the controller 20 combines each of the multiple individual velocity-time curves determined in block 108 with the merged velocity-time curve determined in block 110 to generate a merged velocity-time curve. In an exemplary embodiment, each of the multiple individual velocity-time curves and the merged velocity-time curve are merged using a machine learning curve-merging algorithm configured to receive the multiple individual curve characteristic parameter sets, the multiple individual curve confidence values, the merged curve characteristic parameter set, and the merged curve confidence value as inputs and to provide the merged velocity-time curve as output.

[0068] In another exemplary embodiment, each of the multiple individual velocity-time curves and the combined velocity-time curve are merged using a weighted averaging of the multiple individual curve characteristic parameter sets and the combined curve characteristic parameter set. The weighting is based on the multiple individual curve confidence values ​​and the combined curve confidence value. It should be understood that the aforementioned embodiments are merely exemplary and that additional methods for combining, averaging, and / or merging multiple data sets based on characteristic parameters and confidence values ​​of the characteristic parameters fall within the scope of this description. After Block 116, Method 100 transitions to Block 118.

[0069] In block 118, the controller 20 determines a traffic congestion characteristic parameter set that describes the connected velocity-time curve determined in block 116. For the purposes of this description, the traffic congestion parameter set comprises parameter values ​​that characterize the shape of the connected velocity-time curve. In an exemplary embodiment, the connected velocity-time curve is fitted using a regression or curve-fitting algorithm (e.g., a linear, polynomial, exponential, or logarithmic curve-fitting algorithm) that generates the traffic congestion characteristic parameter set. In a non-restrictive example, the curve-fitting algorithm uses an iterative process to determine optimal values ​​for the traffic congestion characteristic parameter set.In a non-restrictive example, the traffic congestion characteristic parameter set includes a maximum speed, a minimum speed, a maximum acceleration, a minimum acceleration, one or more coefficients for a mathematical equation describing a curve fit, and / or similar parameters. The traffic congestion characteristic parameter set can be used to estimate or predict past or future values ​​of the associated speed-time curve.

[0070] The controller 20 also determines a connected curve confidence value of the traffic jam characteristic parameter set. Within the scope of this description, the connected curve confidence value indicates how accurately the traffic jam characteristic parameter set describes the connected velocity-time curve. In one exemplary embodiment, the connected curve confidence value is a proportion of the points predicted by the traffic jam characteristic parameter set that fall on the connected velocity-time curve. In another exemplary embodiment, the connected curve confidence value is a coefficient of determination (R). 2It is understood that the combined curve confidence value can include any value that quantifies how accurately the traffic congestion characteristic parameter set describes the merged speed-time curve without deviating from the scope of the present description. Following Block 118, Procedure 100 proceeds to Block 120, as explained in more detail below.

[0071] In Block 106, the controller 20 uses the one or more perception sensors 32 to perform one or more perception measurements of each of the one or more remote vehicles 16. In an exemplary embodiment, the one or more perception measurements include a speed and position measurement of each of the one or more remote vehicles 16. In a non-restrictive example, the controller 20 uses the camera 38 to perform the one or more perception measurements. In a non-restrictive example, the controller 20 uses the radar sensor 40 to perform the one or more perception measurements. In a non-restrictive example, the controller 20 uses the LiDAR sensor 42 to perform the one or more perception measurements. Following Block 106, the method 100 transitions to Block 122.

[0072] In block 122, the controller 20 determines a plurality of observed individual velocity-time curves. Each of the multiple observed individual velocity-time curves corresponds to one of the one or more distant vehicles 16. Therefore, each of the multiple observed individual velocity-time curves contains velocity data for one of the one or more distant vehicles 16. In some embodiments, outlier velocity data and / or outliers of the velocity-time curves are detected and removed from the plurality of velocity-time curves. In an exemplary embodiment, to determine the multiple observed individual velocity-time curves, the controller 20 aggregates the velocity-time data from the one or more perception measurements performed in block 106 for each of the one or more distant vehicles 16.After block 122, procedure 100 continues to block 124.

[0073] In Block 124, the controller 20 determines a plurality of observed individual curve characteristic parameter sets. One of the multiple observed individual curve characteristic parameter sets describes each of the multiple observed individual velocity-time curves determined in Block 122. For the purposes of this description, each individual curve characteristic parameter set contains parameter values ​​that characterize the shape of one of the plurality of observed individual velocity-time curves. In an exemplary embodiment, each of the multiple observed individual velocity-time curves is fitted using a regression or curve-fitting algorithm (e.g., a linear, polynomial, exponential, or logarithmic curve-fitting algorithm) that generates an observed individual curve characteristic parameter set.In a non-restrictive example, the curve-fitting algorithm uses an iterative process to determine optimal values ​​for each of the multiple observed individual curve characteristic parameter sets. In this non-restrictive example, each of the multiple observed individual curve characteristic parameter sets includes a maximum velocity, a minimum velocity, a maximum acceleration, a minimum acceleration, one or more coefficients for a mathematical equation describing a curve fit, and / or similar parameters. The multiple observed individual curve characteristic parameter sets can be used to estimate or predict past or future values ​​of each of the multiple observed individual velocity-time curves.

[0074] The controller 20 also determines a multitude of observed individual curve confidence values. Each of the multiple observed individual curve confidence values ​​corresponds to one of the multiple observed individual curve characteristic parameter sets. In the context of this description, each of the multiple observed individual curve confidence values ​​quantifies how accurately each of the multiple observed individual curve characteristic parameter sets describes each of the multiple observed individual velocity-time curves. In one exemplary embodiment, the observed individual curve confidence value is a proportion of the points predicted by the observed individual curve characteristic parameter set that fall on the observed individual velocity-time curves. In another exemplary embodiment, the observed individual curve confidence value is a coefficient of determination (R). 2It is understood that the observed individual curve confidence value can include any value that quantifies how accurately the observed individual curve characteristic parameter set describes the observed individual velocity-time curve without deviating from the scope of the present description. Following Block 124, Procedure 100 proceeds to Block 120.

[0075] In block 120, the controller 20 determines a traffic congestion type. Within the scope of this description, the traffic congestion type classifies the traffic congestions occurring on lane 14 into one or more predefined categories. In an exemplary embodiment, the traffic congestion type comprises one of three predefined traffic congestion types that can typically occur.

[0076] In Fig. Figure 4A shows a first exemplary velocity-time diagram 50, illustrating a first type of traffic congestion. The first exemplary velocity-time diagram 50 includes a horizontal axis 52a representing time (e.g., in minutes), a vertical axis 52b representing velocity (e.g., in kilometers per hour), and a first exemplary velocity-time curve 54. The first type of traffic congestion with the first exemplary velocity-time curve 54 is characteristic of a long queue at a congested intersection, resulting in relatively long periods of idling separated by relatively long periods of rapid acceleration and deceleration.

[0077] In Fig. Figure 4B shows a second exemplary speed-time diagram 60, illustrating a second type of traffic congestion. This second exemplary speed-time diagram 60 comprises a horizontal axis 62a, representing time (e.g., in minutes), a vertical axis 62b, representing speed (e.g., in kilometers per hour), and a second exemplary speed-time curve 64. The second type of traffic congestion with the second exemplary speed-time curve 64 is characteristic of a road closure (e.g., due to roadworks, a motor vehicle accident, and / or similar events) that results in quasi-continuous movement with a minimum non-zero speed and relatively short periods of speed fluctuations (e.g., to allow other vehicles to merge into the free lane(s)).

[0078] In Fig. Figure 4C shows a third exemplary velocity-time diagram 70, illustrating a third type of traffic congestion. This diagram contains a horizontal axis 72a representing time (e.g., in minutes), a vertical axis 72b representing velocity (e.g., in kilometers per hour), and a third exemplary velocity-time curve 74. The third type of traffic congestion, represented by the third exemplary velocity-time curve 74, is characteristic of a slow, intermittently moving queue (e.g., caused by a toll plaza or other checkpoint), resulting in relatively short periods of no movement separated by relatively short periods of acceleration and deceleration at a relatively low maximum speed.

[0079] The in the Fig. The first, second, and third traffic congestion types shown in Figures 4A-4C are merely examples. Any number of additional traffic congestion types can be considered in Procedure 100 without exceeding the scope of this description.

[0080] Referring again to Fig. 3 In an exemplary embodiment, the controller 20 analyzes the connected velocity-time curve generated in block 116 and the traffic congestion characteristic parameter set determined in block 118 to determine the traffic congestion type in block 120. In a non-restrictive example, the controller 20 uses mathematical and / or statistical methods (e.g., root mean error, coefficient of determination, and / or similar) to compare the connected velocity-time curve with the exemplary velocity-time curves (e.g., the first exemplary velocity-time curve 54, the second exemplary velocity-time curve 64, and the third exemplary velocity-time curve 74) of each of the predefined traffic congestion types (e.g., the first, second, and third traffic congestion types), taking the traffic congestion characteristic parameter set into account.The traffic jam type is determined as the one from the predefined traffic jam types that most closely matches the associated speed-time curve. In another, non-restrictive example, controller 20 uses a machine learning algorithm to determine the traffic jam type.

[0081] In a non-restrictive example, the machine learning algorithm for traffic jam types comprises several layers, including an input layer, an output layer, and one or more hidden layers. The input layer receives the exemplary speed-time curves of each of the predefined traffic jam types (e.g., the first exemplary speed-time curve 54, the second exemplary speed-time curve 64, and the third exemplary speed-time curve 74), the associated speed-time curve, and the traffic jam characteristic parameter set as inputs. The inputs are then passed to the hidden layers. Each hidden layer applies a transformation (e.g., a nonlinear transformation) to the data and passes the result to the next hidden layer, and so on, until the last hidden layer. The output layer provides the traffic jam type.

[0082] To train the machine learning algorithm, a dataset containing inputs and their corresponding jamming types is used. The algorithm is trained by adjusting the internal weights between nodes in each hidden layer to minimize the prediction error. During training, an optimization procedure (e.g., gradient descent) is used to further refine the internal weights and reduce the prediction error. The training process is repeated with the entire dataset until the prediction error is minimized, and the resulting trained model is then used to classify new input data.

[0083] After sufficient training of the machine learning algorithm for traffic congestion type, the algorithm is able to accurately and precisely determine the traffic congestion type based on the example speed-time curves of each of the predefined traffic congestion types, the associated speed-time curve, and the traffic congestion characteristic parameter set. By adjusting the weights between the nodes in each hidden layer during training, the algorithm "learns" to recognize patterns in the data that indicate the traffic congestion type.

[0084] It is understood that any mathematical, statistical, rule-based, and / or machine learning-based algorithm or any procedure can be used to determine which of the predefined traffic jam types most closely resembles the associated speed-time curve. It is understood that the speed data collected during the journeys of the host vehicle 12 can be used for incremental and / or continuous training of the machine learning algorithm for traffic jam types.

[0085] In one exemplary embodiment, the controller 20 additionally verifies the traffic congestion type, at least partially, based on one or more perception measurements performed in Block 106. In another exemplary embodiment, the controller 20 determines an observed traffic congestion type based on the multiple observed velocity-time curves generated in Block 122 and the multiple observed individual curve characteristic parameter sets determined in Block 124. In a non-restrictive example, the controller 20 combines the majority of the observed velocity-time curves and the majority of the observed individual curve characteristic parameter sets, as discussed above with reference to Block 116, to generate a combined observed velocity-time curve and an observed traffic congestion characteristic parameter set.

[0086] The controller 20 then uses mathematical, statistical, or machine learning methods, as described above, to determine an observed traffic jam type. The controller 20 then compares the observed traffic jam type with the traffic jam type determined as described above. In one exemplary embodiment, the procedure 100 terminates or restarts if the observed traffic jam type differs from the traffic jam type. In another exemplary embodiment, if the observed traffic jam type differs from the traffic jam type, the observed traffic jam type is assumed to be the exact traffic jam type. After block 120, the procedure 100 proceeds to blocks 126 and 128.

[0087] In block 126, the controller 20 selects a chosen machine learning maneuvering model from a variety of maneuvering models. For the purposes of this description, the multiple maneuvering models are used to determine an optimal vehicle maneuvering plan for the host vehicle 12. In this context, the optimal vehicle maneuvering plan is a plan for maneuvering the host vehicle 12 that maximizes occupant comfort and the progress of the host vehicle 12 while minimizing traffic congestion. The optimal vehicle maneuvering plan includes an optimal velocity-time curve that the host vehicle 12 should follow to achieve the objectives of the optimal vehicle maneuvering plan.The optimal vehicle maneuvering plan further includes one or more optimal acceleration and braking levels, which are determined on the basis of the optimal velocity-time curve and which should be used by the host vehicle 12 to follow the optimal velocity-time curve.

[0088] According to the invention, each of the multiple maneuvering models corresponds to one of the predefined traffic jam types (e.g., the first, second, and third traffic jam types). Each of the multiple maneuvering models is a machine learning model that has been trained to determine the optimal vehicle maneuvering plan when the host vehicle 12 experiences one of the predefined traffic jam types (e.g., the first, second, and third traffic jam types).

[0089] In a non-restrictive example, each of the multiple maneuvering models is trained using experimental data obtained from real-world road tests and / or simulated data from computer-simulated driving situations. It should further be understood that speed data collected during the driving sessions of the host vehicle 12 can be used for incremental and / or continuous training of each of the multiple maneuvering models. In block 126, the controller 20 selects the maneuvering model from the multitude that corresponds to the traffic jam type determined in block 120 and is referred to as the selected machine learning maneuvering model. After block 126, the procedure 100 proceeds to block 130.

[0090] In Block 130, the controller 20 determines the optimal vehicle maneuver plan using the machine learning maneuver model selected in Block 126. In a non-restrictive example, the selected machine learning maneuver model comprises multiple layers, including an input layer and an output layer, as well as one or more hidden layers. The input layer receives the traffic jam characteristic parameter set (determined in Block 118) as input. The inputs are then passed to the hidden layers. Each hidden layer applies a transformation (e.g., a nonlinear transformation) to the data and passes the result to the next hidden layer, up to the last hidden layer. The output layer generates the optimal vehicle maneuver plan, including the optimal velocity-time curve and the one or more optimal acceleration and deceleration steps.

[0091] To train the selected maneuvering model using machine learning, a dataset containing inputs and the corresponding optimal maneuvering plan of the vehicle, including the optimal velocity-time curve and one or more optimal acceleration and braking steps, is used. The algorithm is trained by adjusting the internal weights between nodes in each hidden layer to minimize the prediction error. During training, an optimization procedure (e.g., gradient descent) is used to adjust the internal weights to further reduce the prediction error. The training process is repeated with the entire dataset until the prediction error is minimized, and the resulting trained model is then used to classify new input data.

[0092] After sufficient training of the selected machine learning model, the algorithm is able to accurately and precisely determine the optimal vehicle maneuver plan, including the optimal speed-time curve and one or more optimal acceleration and braking levels, based on the traffic jam characteristic parameter set. By adjusting the weights between the nodes in each hidden layer during training, the algorithm "learns" to recognize patterns in the data that indicate the optimal vehicle maneuver plan, including the optimal speed-time curve and one or more optimal acceleration and braking levels. After Block 130, Procedure 100 proceeds to Block 132, as explained in more detail below.

[0093] In block 128, the controller 20 determines a recommended vehicle maneuver, which is based at least partially on the traffic congestion type determined in block 120. For the purposes of this description, the recommended vehicle maneuver is a rule-based, predefined action intended to increase occupant comfort or promote efficient progress of the host vehicle 12. In a non-restrictive example, the recommended vehicle maneuver for the first traffic congestion type involves maneuvering the host vehicle 12 into a lane with the shortest or fastest queue. For the second traffic congestion type, the recommended vehicle maneuver involves maneuvering the host vehicle 12 into a lane with a higher minimum speed or a higher maximum speed.

[0094] For the third type of traffic jam, the recommended vehicle maneuver involves the host vehicle 12 maneuvering to prevent the one or more distant vehicles 16 from "jumping" the queue (i.e., overcoming their original position in the queue by passing vehicles). In a non-restrictive example, preventing queue skipping might involve reducing the distance between the host vehicle 12 and one or more distant vehicles 16 directly in front of the host vehicle 12. In another non-restrictive example, preventing queue skipping might involve maneuvering the host vehicle 12 close to the left or right edge of the lane to prevent the one or more distant vehicles 16 from overtaking the host vehicle 12.

[0095] It should be clear that the recommended vehicle maneuvers mentioned above are only examples and that various additional maneuvers, such as non-deterministic maneuvers and / or maneuvers provided by a machine learning algorithm, may be selected depending on the type of traffic jam. It should also be understood that in some cases no recommended vehicle maneuver will be selected. After Block 128, the procedure continues with Block 132.

[0096] In block 132, the controller 20 transmits a notification to the occupant of the host vehicle 12, based at least in part on the optimal vehicle maneuver plan determined in block 130 and the recommended vehicle maneuver determined in block 128. In an exemplary embodiment, the controller 20 uses either the HMI 24 and / or the HUD 26, or both, to transmit the notification. In a non-restrictive example, the notification contains text and / or graphics displaying one or more of the following: the optimal velocity-time curve determined in block 130, the one or more optimal acceleration and braking levels determined in block 130, and the recommended vehicle maneuver determined in block 128.

[0097] Fig. Figure 5 shows an example view 80 from inside the host vehicle 12. The example view 80 contains an example HUD notification 82, which is displayed using the HUD 26 ( Fig. 1) displayed on the windshield 44, and an example HMI notification 84 displayed on the HMI 24. The example HUD notification 82 includes a graphical representation 82a of the optimal speed-time curve, informational text 82b, and a current time display 82c.

[0098] The graphical representation 82a of the optimal velocity-time curve includes descending lines 86a, flat lines 86b, and ascending lines 86c. The descending lines 86a indicate a decrease in vehicle speed, and the optimal acceleration and braking level is a slight braking level to achieve gradual deceleration. The flat lines 86b indicate a constant vehicle speed (greater than or equal to zero), and that the optimal acceleration and braking level is neither acceleration nor braking. The ascending lines 86c indicate an increase in vehicle speed, and the optimal acceleration and braking level is a slight acceleration level to achieve gradual acceleration. In some embodiments, the descending lines 86a, the flat lines 86b, and the ascending lines 86c are highlighted in different colors or graphic styles.In some embodiments, the descending lines 86a, the flat lines 86b and the ascending lines 86c also contain text with additional explanations.

[0099] Information text 82b provides the vehicle occupant with additional information about the optimal speed-time curve, one or more optimal acceleration and braking levels, and / or the recommended vehicle maneuver. In one exemplary embodiment, information text 82b contains information about the current optimal acceleration and braking level (e.g., "light braking" or "light acceleration"). In another exemplary embodiment, information text 82b contains information about the traffic congestion type. In yet another exemplary embodiment, information text 82b contains information about the recommended vehicle maneuver (e.g., "Move to the left lane when it is safe").

[0100] The current time display 82c indicates the current position of the host vehicle 12 along the graphical representation 82a of the optimal speed-time curve. In an exemplary embodiment, the current time display 82c moves along the graphical representation 82a of the optimal speed-time curve (e.g., from left to right) as time progresses, thus indicating the optimal vehicle speed and the current optimal acceleration and braking levels at a given time.

[0101] Exemplary HMI notification 84 contains graphics and / or text providing information about the optimal speed-time curve, the one or more optimal acceleration and braking levels, and / or the recommended vehicle maneuver. In one exemplary embodiment, exemplary HMI notification 84 is substantially similar to or identical with exemplary HUD notification 82. In another exemplary embodiment, exemplary HMI notification 84 contains additional information about the optimal speed-time curve, the one or more optimal acceleration and braking levels, and / or the recommended vehicle maneuver that is not displayed in exemplary HUD notification 82.If, for example, the information text 82b of the example HUD notification 82 contains the current optimal acceleration and braking levels, the example HMI notification 84 can contain information about the recommended vehicle maneuver. If the HUD 26 is not functioning or is unavailable, the example HMI notification 84 can be used to provide the occupant of the host vehicle 12 with information about the optimal speed-time curve, the one or more optimal acceleration and braking levels, and / or the recommended vehicle maneuver.

[0102] It should be understood that the preceding discussion regarding the exemplary view 80, the exemplary HUD notification 82, and the exemplary HMI notification 84 is merely illustrative. The exemplary HUD notification 82 and the exemplary HMI notification 84, which are described in Fig. The images shown in section 5 are merely examples, and variations in size, shape, color, opacity, display position, graphic style and / or similar aspects are within the scope of this description.

[0103] Referring again to Fig. 3. The controller 20 in block 132 delivers the notification to the occupant of the host vehicle 12 (e.g., the exemplary HUD notification 82 and / or the exemplary HMI notification 84, as above with reference to Fig. 5 explained). In an exemplary embodiment where the host vehicle 12 is a semi- or fully autonomous vehicle, the host vehicle 12 uses an automated driving system (not shown) to follow one or more optimal acceleration and braking levels and / or to perform the recommended vehicle maneuver. According to Block 132, the method 100 in Block 134 enters a standby state.

[0104] In one exemplary embodiment, the controller 20 repeatedly exits the standby state 134 and restarts the procedure 100 in block 102. In a non-restrictive example, the controller 20 exits the standby state 134 and restarts the procedure 100 according to a timer, e.g., every three hundred milliseconds.

[0105] System 10 and method 100 of this description offer several advantages. By combining the merged speed-time curve and the multiple individual speed-time curves to generate the merged speed-time curve, the effects of outliers and fluctuations in driver behavior can be minimized, leading to an accurate characterization of the overall movement trends of the remote vehicles 16 and thus the traffic congestion type. By determining the traffic congestion type, more efficient and accurate machine learning maneuvering models can be used to determine the optimal vehicle maneuvering plan. By displaying the optimal vehicle maneuvering plan via the HMI 24 and / or the HUD 26, the occupants of the host vehicle 12 are informed about automated host vehicle actions and / or about optimal actions to increase comfort and progress in congestion situations.

[0106] The description in this disclosure is merely exemplary, and variations that do not deviate from the core of this disclosure are to be considered within its scope. Such variations are not to be regarded as a deviation from the core ideas and scope of this description.

Claims

[1] Method for providing information to an occupant of a vehicle (12) wherein the method comprises: Identifying a traffic congestion type in an environment surrounding the vehicle (12), wherein the traffic congestion type is characterized by a traffic congestion characteristic parameter set; Determining an optimal vehicle maneuvering plan, based at least partially on the traffic congestion type and the traffic congestion characteristic parameter set; and Providing a notification to the vehicle occupant (12), wherein the notification is based at least partially on the optimal vehicle maneuvering plan; furthermore, determining the optimal vehicle maneuvering plan involves: Selecting a chosen machine learning maneuvering model from a variety of maneuvering models, where each of the multiple maneuvering models corresponds to a predefined traffic jam type, and where the selected maneuvering model corresponds to the traffic jam type; and Determining the optimal vehicle maneuvering plan using the selected machine learning maneuvering model, wherein the selected machine learning maneuvering model is configured to receive the traffic jam characteristic parameter set as an input and to provide the optimal vehicle maneuvering plan as an output. [2] Method according to claim 1, wherein the identification of the traffic jam type further comprises: Receiving one or more messages from one or more remote vehicles (16) using a vehicle communication system; Determining a plurality of individual velocity-time curves (54, 64, 74) based at least partially on the one or more messages, wherein each of the plurality of individual velocity-time curves (54, 64, 74) corresponds to one of the one or more remote vehicles (16); and Determining the traffic congestion type based at least partially on the multitude of individual speed-time curves (54, 64, 74). [3] Method according to claim 2, wherein the determination of the traffic congestion type based at least partially on the plurality of individual speed-time curves (54, 64, 74) further comprises: Determining a plurality of individual curve characteristic parameter sets, wherein one of the plurality of individual curve characteristic parameter sets describes each of the plurality of individual velocity-time curves (54, 64, 74); and Determining a multitude of individual curve confidence values, where each of the multitude of individual curve confidence values ​​corresponds to one of the multitude of individual curve characteristic parameter sets. [4] Method according to claim 3, wherein the determination of the traffic jam type based at least partially on the plurality of individual speed-time curves (54, 64, 74) further comprises: Combining each of the several individual velocity-time curves (54, 64, 74) into a combined velocity-time curve; Determining a merged curve characteristic parameter set that describes the merged velocity-time curve; and Determining a combined curve confidence value of the combined curve characteristic parameter set. [5] Method according to claim 4, wherein the determination of the traffic jam type based at least partially on the plurality of individual speed-time curves (54, 64, 74) further comprises: Combine each of the plurality of individual velocity-time curves (54, 64, 74) with the merged velocity-time curve to generate a combined velocity-time curve, wherein the combined velocity-time curve is generated at least partially on the basis of the plurality of individual curve characteristic parameter sets, the plurality of individual curve confidence values, the merged curve characteristic parameter set and the merged curve confidence value; Determining the traffic congestion characteristic parameter set that describes the merged velocity-time curve; and Determining the traffic congestion type, at least partially, based on the combined velocity-time curve and the traffic congestion characteristic parameter set. [6] Method according to claim 5, wherein the determination of the traffic congestion type further comprises, at least partially, the following based on the combined velocity-time curve and the traffic congestion characteristic parameter set: Performing one or more perception measurements of the one or more remote vehicles (16) using one or more perception sensors of the vehicle (12); and Verifying the traffic congestion type, at least partially, based on one or more perception measurements. [7] Method according to claim 1, wherein determining the optimal vehicle maneuvering plan further comprises: Determining the optimal vehicle maneuvering plan using the selected machine learning maneuvering model, wherein the selected machine learning maneuvering model is configured to receive the traffic jam characteristic parameter set as an input and to provide the optimal vehicle maneuvering plan as an output, and wherein the optimal vehicle maneuvering plan includes an optimal velocity-time curve. [8] Method according to claim 7, wherein the provision of the notification further comprises: Determining one or more optimal acceleration and deceleration levels, based at least partially on the optimal velocity-time curve; and Providing the notification to the vehicle occupant (12), wherein the notification includes at least one of: the optimal speed-time curve and the optimal acceleration and braking levels. [9] The method of claim 1, wherein the provision of the notification further comprises: Determining a recommended vehicle maneuver based at least partially on the traffic congestion type; and Providing the notification to the occupants of the vehicle (12), the notification containing the recommended vehicle maneuver.

Images