Determining optimal vehicle maneuver plan in traffic jam situations

Abstract

According to several aspects, a method for providing information to an occupant of a vehicle is provided. The method may include identifying a traffic jam type in an environment surrounding the vehicle. The traffic jam type is characterized by a set of traffic jam characteristic parameters. The method may also include determining an optimal vehicle maneuver plan based at least in part on the traffic jam type and the set of traffic jam characteristic parameters. The method may also include providing a notification to the vehicle occupant. The notification is based at least in part on the optimal vehicle maneuver plan.

Description

Technical Field

[0001] This invention relates to systems and methods for providing information to vehicle occupants. Background Technology

[0002] To enhance occupant awareness and convenience, vehicles can be equipped with Advanced Driver Assistance Systems (ADAS) and / or Automated Driving Systems (ADS). ADAS systems use various sensors, such as cameras, radar, and LiDAR (Light Detection and Ranging), to detect and identify objects around the vehicle, including other vehicles, pedestrians, road configurations, traffic signs, and road markings. ADAS systems can then take actions based on environmental conditions around the vehicle, such as applying braking or warning vehicle occupants. ADS systems use various sensors to detect objects in the environment around the vehicle and control the vehicle to navigate through the environment to a predefined destination. However, current ADAS and ADS systems may not effectively characterize traffic congestion and provide optimal vehicle handling in congested conditions.

[0003] Therefore, while ADAS and ADS systems and methods have achieved their intended purposes, a new and improved system and method is needed to characterize traffic congestion, determine optimal vehicle handling plans, and provide vehicle occupants with information about optimal vehicle handling plans. Summary of the Invention

[0004] According to several aspects, a method for providing information to vehicle occupants is provided. The method may include identifying traffic congestion types in the environment surrounding the vehicle. The traffic congestion type is characterized by a set of traffic congestion characteristic parameters. The method may further include determining an optimal vehicle handling plan based at least in part on the traffic congestion type and the set of traffic congestion characteristic parameters. The method may also include providing a notification to the vehicle occupants. This notification is based at least in part on the optimal vehicle handling plan.

[0005] In another aspect of the invention, identifying traffic congestion types may further include receiving one or more messages from one or more remote vehicles using a vehicle communication system. Identifying traffic congestion types may also include determining multiple individual speed-to-time curves, at least in part based on the one or more messages. Each of the multiple individual speed-to-time curves corresponds to one of the one or more remote vehicles. Identifying traffic congestion types may also include determining the traffic congestion type, at least in part based on the multiple individual speed-to-time curves.

[0006] In another aspect of the invention, determining the type of traffic congestion based at least in part on multiple individual speed-to-time curves may further include determining multiple individual sets of curve feature parameters. One of the multiple individual sets of curve feature parameters describes each of the multiple individual speed-to-time curves. Determining the type of traffic congestion based at least in part on multiple individual speed-to-time curves may further include determining multiple individual curve confidence values. Each of the multiple individual curve confidence values ​​corresponds to one of the multiple individual sets of curve feature parameters.

[0007] In another aspect of the invention, determining traffic congestion type based at least in part on multiple individual speed-to-time curves may further include fusing each of the multiple individual speed-to-time curves into a fused speed-to-time curve. Determining traffic congestion type based at least in part on multiple individual speed-to-time curves may further include determining a set of fused curve feature parameters describing the fused speed-to-time curve. Determining traffic congestion type based at least in part on multiple individual speed-to-time curves may further include determining a fused curve confidence value for the fused curve feature parameter set.

[0008] In another aspect of the invention, determining traffic congestion type based at least in part on multiple individual speed-to-time curves may further include merging each of the multiple individual speed-to-time curves with a merged speed-to-time curve to generate a merged speed-to-time curve. The merged speed-to-time curve is generated at least in part based on the multiple individual curve feature parameter sets, the multiple individual curve confidence values, the merged curve feature parameter set, and the merged curve confidence values. Determining traffic congestion type based at least in part on multiple individual speed-to-time curves may further include determining a set of traffic congestion feature parameters describing the merged speed-to-time curve. Determining traffic congestion type based at least in part on multiple individual speed-to-time curves may further include determining the traffic congestion type based at least in part on the merged speed-to-time curve and the set of traffic congestion feature parameters.

[0009] In another aspect of the invention, determining the traffic congestion type based at least in part on the merged speed-to-time curve and a set of traffic congestion characteristic parameters may further include using one or more sensing sensors of the vehicle to perform one or more sensing measurements of one or more remote vehicles. Determining the traffic congestion type based at least in part on the merged speed-to-time curve and a set of traffic congestion characteristic parameters may further include verifying the traffic congestion type based at least in part on one or more sensing measurements.

[0010] In another aspect of the invention, determining the optimal vehicle handling plan may further include selecting a chosen machine learning handling model from a plurality of handling models. The selected handling model corresponds to a traffic congestion type. Determining the optimal vehicle handling plan may further include using the selected machine learning handling model to determine the optimal vehicle handling plan. The selected machine learning handling model is configured to receive a set of traffic congestion feature parameters as input and provide the optimal vehicle handling plan as output.

[0011] In another aspect of the invention, determining the optimal vehicle handling plan may further include using a selected machine learning handling model to determine the optimal vehicle handling plan. The selected machine learning handling model is configured to receive a set of traffic congestion feature parameters as input and provide the optimal vehicle handling plan as output. The optimal vehicle handling plan includes an optimal speed-to-time curve.

[0012] In another aspect of the invention, providing the notification may further include determining one or more optimal acceleration and braking levels based at least in part on the optimal speed-to-time curve. Providing the notification may also include providing a notification to vehicle occupants. The notification includes at least one of the following: the optimal speed-to-time curve and one or more optimal acceleration and braking levels.

[0013] In another aspect of the invention, providing the notification may further include determining recommended vehicle maneuvers based at least in part on the type of traffic congestion. Providing the notification may also include providing a notification to vehicle occupants. This notification includes the recommended vehicle maneuvers.

[0014] According to several aspects, a system for providing information to vehicle occupants is provided. The system may include a vehicle communication system, a display, and a controller electrically communicating with the vehicle communication system and the display. The controller is programmed to use the vehicle communication system to identify traffic congestion types in the environment surrounding the vehicle. The traffic congestion types are characterized by a set of traffic congestion characteristic parameters. The controller is also programmed to determine an optimal vehicle handling plan based at least in part on the traffic congestion type and the set of traffic congestion characteristic parameters. The controller is further programmed to provide a notification to the vehicle occupants using the display. This notification is based at least in part on the optimal vehicle handling plan.

[0015] In another aspect of the invention, to identify traffic congestion types, the controller is also programmed to receive one or more messages from one or more remote vehicles using a vehicle communication system. To identify traffic congestion types, the controller is also programmed to determine multiple individual speed-to-time curves based at least in part on the one or more messages. Each of the multiple individual speed-to-time curves corresponds to one of the one or more remote vehicles. To identify traffic congestion types, the controller is also programmed to determine the traffic congestion type based at least in part on the multiple individual speed-to-time curves.

[0016] In another aspect of the invention, to determine the traffic congestion type at least in part based on multiple individual speed-to-time curves, the controller is also programmed to determine multiple individual sets of curve feature parameters. One of the multiple individual sets of curve feature parameters describes each of the multiple individual speed-to-time curves. To determine the traffic congestion type at least in part based on multiple individual speed-to-time curves, the controller is also programmed to determine multiple individual curve confidence values. Each of the multiple individual curve confidence values ​​corresponds to one of the multiple individual sets of curve feature parameters. To determine the traffic congestion type at least in part based on multiple individual speed-to-time curves, the controller is also programmed to merge each of the multiple individual speed-to-time curves into a merged speed-to-time curve. To determine the traffic congestion type at least in part based on multiple individual speed-to-time curves, the controller is also programmed to determine a merged curve feature parameter set describing the merged speed-to-time curve. To determine the traffic congestion type at least in part based on multiple individual speed-to-time curves, the controller is also programmed to determine the merged curve confidence value of the merged curve feature parameter set. To determine traffic congestion type at least in part based on multiple individual speed-to-time curves, the controller is also programmed to merge each of the multiple individual speed-to-time curves with a merged speed-to-time curve to generate a merged speed-to-time curve. This merged speed-to-time curve is generated at least in part based on the multiple individual curve feature parameter sets, the multiple individual curve confidence values, the merged curve feature parameter set, and the merged curve confidence value. To determine traffic congestion type at least in part based on multiple individual speed-to-time curves, the controller is also programmed to determine a set of traffic congestion feature parameters describing the merged speed-to-time curve. To determine traffic congestion type at least in part based on multiple individual speed-to-time curves, the controller is also programmed to determine traffic congestion type at least in part based on the merged speed-to-time curve and the set of traffic congestion feature parameters.

[0017] In another aspect of the invention, the system further includes one or more sensing sensors in electrical communication with the controller. To determine the traffic congestion type at least in part based on the merged speed-to-time curve and a set of traffic congestion characteristic parameters, the controller is also programmed to use the one or more sensing sensors to perform one or more sensing measurements of one or more remote vehicles. To further determine the traffic congestion type at least in part based on the merged speed-to-time curve and the set of traffic congestion characteristic parameters, the controller is also programmed to verify the traffic congestion type at least in part based on one or more sensing measurements.

[0018] In another aspect of the invention, to determine the optimal vehicle handling plan, the controller is also programmed to select a chosen machine learning handling model from a plurality of handling models. The selected machine learning handling model corresponds to a traffic congestion type. To determine the optimal vehicle handling plan, the controller is further programmed to use the selected machine learning handling model to determine the optimal vehicle handling plan. The selected machine learning handling model is configured to receive a set of traffic congestion feature parameters as input and provide the optimal vehicle handling plan as output. The optimal vehicle handling plan includes an optimal speed-to-time curve.

[0019] In another aspect of the invention, to provide notification, the controller is also programmed to determine one or more optimal acceleration and braking levels based at least in part on the optimal speed-to-time curve. To provide notification, the controller is also programmed to provide a notification to vehicle occupants using a display. This notification includes at least one of the following: the optimal speed-to-time curve and one or more optimal acceleration and braking levels.

[0020] In another aspect of the invention, the display may further include a head-up display (HUD) that is in electrical communication with the controller. For providing notifications, the controller is also programmed to use the HUD to provide notifications to vehicle occupants. The notification includes at least one of the following: an optimal speed-to-time curve and one or more optimal acceleration and braking levels.

[0021] According to several aspects, a method for providing information to vehicle occupants is provided. The method may include receiving one or more messages from one or more remote vehicles using a vehicle communication system. The method may also include determining multiple individual speed-to-time curves based at least in part on the one or more messages. Each of the multiple individual speed-to-time curves corresponds to one of the one or more remote vehicles. The method may also include determining a traffic congestion type based at least in part on the multiple individual speed-to-time curves. The traffic congestion type is characterized by a set of traffic congestion characteristic parameters. The method may also include determining an optimal vehicle handling plan based at least in part on the traffic congestion type and the set of traffic congestion characteristic parameters. The optimal vehicle handling plan includes at least an optimal speed-to-time curve. The method may also include determining one or more optimal acceleration and braking levels based at least in part on the optimal speed-to-time curve. The method may also include providing a notification to vehicle occupants using a head-up display (HUD). The notification includes at least one of the following: the optimal speed-to-time curve and one or more optimal acceleration and braking levels.

[0022] In another aspect of the invention, determining the traffic congestion type based at least in part on multiple individual speed-to-time curves may further include determining multiple individual sets of curve feature parameters. One of the multiple individual sets of curve feature parameters describes each of the multiple individual speed-to-time curves. Determining the traffic congestion type based at least in part on multiple individual speed-to-time curves may further include determining multiple individual curve confidence values. Each of the multiple individual curve confidence values ​​corresponds to one of the multiple individual sets of curve feature parameters. Determining the traffic congestion type based at least in part on the multiple individual speed-to-time curves may further include fusing each of the multiple individual speed-to-time curves into a fused speed-to-time curve. Determining the traffic congestion type based at least in part on multiple individual speed-to-time curves may further include determining a fused curve feature parameter set describing the fused speed-to-time curve. Determining the traffic congestion type based at least in part on multiple individual speed-to-time curves may further include determining a fused curve confidence value for the fused curve feature parameter set. Determining the traffic congestion type based at least in part on the plurality of individual speed-to-time curves may also include merging each of the plurality of individual speed-to-time curves with the merged speed-to-time curve to generate a merged speed-to-time curve. The merged speed-to-time curve may be generated based at least in part on the plurality of individual curve feature parameter sets, the plurality of individual curve confidence values, the merged curve feature parameter set, and the merged curve confidence value. Determining the traffic congestion type based at least in part on the plurality of individual speed-to-time curves may also include determining a set of traffic congestion feature parameters describing the merged speed-to-time curve. Determining the traffic congestion type based at least in part on the plurality of individual speed-to-time curves may also include determining the traffic congestion type based at least in part on the merged speed-to-time curve and the set of traffic congestion feature parameters.

[0023] In another aspect of the invention, determining the optimal vehicle handling plan may further include selecting a chosen machine learning handling model from a plurality of handling models. The selected handling model corresponds to a traffic congestion type. Determining the optimal vehicle handling plan may further include using the selected machine learning handling model to determine the optimal vehicle handling plan. The selected machine learning handling model is configured to receive a set of traffic congestion feature parameters as input and provide the optimal vehicle handling plan as output. The optimal vehicle handling plan includes an optimal speed-to-time curve.

[0024] Further applications will become clear from the description provided herein. It should be understood that the specification and specific embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Attached Figure Description

[0025] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of the invention in any way.

[0026] Figure 1 This is a schematic diagram of a system for providing information to vehicle occupants according to an exemplary embodiment, shown together with a main vehicle in an exemplary context of a road including one or more remote vehicles;

[0027] Figure 2 This is a schematic diagram of a system for providing information to vehicle occupants according to an exemplary embodiment;

[0028] Figure 3 This is a flowchart of a method for providing information to vehicle occupants according to an exemplary embodiment;

[0029] Figure 4A This is a first exemplary speed versus time graph illustrating a first type of traffic congestion according to an exemplary embodiment;

[0030] Figure 4B This is a second exemplary speed-to-time graph illustrating a second type of traffic congestion according to an exemplary embodiment;

[0031] Figure 4C This is a third exemplary speed-to-time graph illustrating a third type of traffic congestion according to an exemplary embodiment; and

[0032] Figure 5 This is an exemplary view of the vehicle interior, including exemplary HUD notifications and exemplary HMI notifications, according to an exemplary embodiment. Detailed Implementation

[0033] The following description is merely exemplary in nature and is not intended to limit the invention, application, or use.

[0034] Traffic congestion can cause discomfort for vehicle occupants. Furthermore, during congested traffic, occupants may be unable to determine the optimal actions or vehicle maneuvers (e.g., acceleration, braking, lane changing, etc.) to increase comfort and facilitate vehicle movement. Therefore, this invention provides a novel and improved system and method for characterizing traffic congestion, determining optimal vehicle maneuvering plans, and providing vehicle occupants with information about these optimal maneuvering plans.

[0035] refer to Figure 1 In an exemplary context of a road 14 comprising one or more remote vehicles 16, a system 10 is shown that utilizes a master vehicle 12 to provide information to vehicle occupants. It should be understood that the road 14 may include any open road (e.g., road, street, highway, expressway, boulevard, avenue, park road, alleyway, bridge, tunnel, etc.) for vehicle passage and transport. Figure 1In the exemplary embodiment shown, one or more remote vehicles 16 include a first remote vehicle 16a and a second remote vehicle 16b. It should be understood that the one or more remote vehicles 16 may include any number of vehicles occupying the road 14. The one or more remote vehicles 16 may include, for example, sport utility vehicles (SUVs), sedans, cars, trucks, multi-purpose vehicles, etc. In some examples, the one or more remote vehicles 16 may also include other road users, such as pedestrians, bicycles, etc.

[0036] refer to Figure 2 A schematic diagram of a system 10 for providing information to vehicle occupants is provided. System 10 is shown together with a main vehicle 12. Although a bus is illustrated, it should be understood that the main vehicle 12 can be any type of vehicle without departing from the scope of the invention. System 10 typically includes a controller 20, multiple vehicle sensors 22, a human-machine interface (HMI) 24, and a head-up display (HUD) 26.

[0037] The controller 20 is used to implement a method 100 for providing information to vehicle occupants, as described below. The controller 20 includes at least one processor 28 and a non-transitory computer-readable storage 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 a device typically used for executing instructions.

[0038] Computer-readable storage device or medium 30 may include volatile and non-volatile storage devices 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 operational variables when the processor 28 is powered off. Computer-readable storage device or medium 30 may be implemented using multiple storage devices such as PROM (programmable read-only memory), EPROM (electrical PROM), EEPROM (electrically erasable PROM), flash memory, or other electrical, magnetic, optical, or combined storage devices capable of storing data, some of which represents executable instructions that can be used by controller 20 to control various systems of vehicle 12.

[0039] Controller 20 may also include multiple controllers that are electrically communicating with each other. Controller 20 may interconnect with additional systems and / or controllers of the main vehicle 12, thereby allowing controller 20 to access data of the main vehicle 12, such as speed, acceleration, braking, and steering angle.

[0040] The controller 20 communicates electrically with multiple vehicle sensors 22, HMI 24, and HUD 26. In an exemplary embodiment, electrical communication is established using, for example, a CAN network, FLEXRAY network, local area network (e.g., WiFi, Ethernet, etc.), Serial Peripheral Interface (SPI) network, etc. It should be understood that various additional wired and wireless technologies and communication protocols used for communicating with the controller 20 are within the scope of this invention. It should be understood that one or more of the multiple vehicle sensors 22, HMI 24, and HUD 26 may be integrated with the controller 20 (e.g., integrated on the same circuit board as the controller 20 or on other parts of the controller 20) without departing from the scope of this invention. It should also be understood that, within the scope of this invention, electrical communication also includes power and / or energy transfer between electrical devices (e.g., using wired and / or wireless power transfer technologies).

[0041] Multiple vehicle sensors 22 are used to acquire information about one or more remote vehicles 16. In an exemplary embodiment, the multiple vehicle sensors 22 include one or more sensing sensors 32, a Global Navigation Satellite System (GNSS) 34, and a vehicle communication system 36.

[0042] One or more sensing sensors 32 are used to sense objects and / or measure distances in the environment surrounding the main vehicle 12. In one exemplary embodiment, the one or more sensing sensors 32 include at least one of the following: a camera 38, a radar sensor 40, and a light detection and ranging (LiDAR) sensor 42.

[0043] Camera 38 is a sensing sensor for capturing images and / or video of the environment surrounding the main vehicle 12. In an exemplary embodiment, camera 38 includes a photographic and / or video camera positioned to observe the environment surrounding the main vehicle 12. In a non-limiting example, camera 38 includes a camera fixed inside the main vehicle 12, for example, in the roof of the main vehicle 12, having a field of view through the windshield 44 of the main vehicle 12. In another non-limiting example, camera 38 includes a camera fixed outside the main vehicle 12, for example, on the roof of the main vehicle 12, having a field of view of the environment in front of the main vehicle 12.

[0044] In another exemplary embodiment, camera 38 is a surround-view camera system comprising multiple cameras (also referred to as satellite cameras) arranged to provide a view of the environment adjacent to all sides of the host vehicle 12. In a non-limiting example, camera 38 includes a forward-facing camera (e.g., mounted in the front grille of the host vehicle 12), a rearward-facing camera (e.g., mounted on the rear tailgate of the host vehicle 12), and two lateral cameras (e.g., mounted below each of the two side mirrors of the host vehicle 12). In another non-limiting example, camera 38 also includes an additional rear-view camera mounted near the center high-mounted brake light of the host vehicle 12.

[0045] It should be understood that camera systems with additional cameras and / or additional mounting locations are within the scope of this invention. It should also be understood that cameras with various sensor types, including, for example, charge-coupled device (CCD) sensors, complementary metal-oxide-semiconductor (CMOS) sensors, and / or high dynamic range (HDR) sensors, are within the scope of this invention. Furthermore, cameras with various lens types, including, for example, wide-angle lenses and / or narrow-angle lenses, are also within the scope of this invention. As described above, camera 38 communicates electrically with controller 20.

[0046] Radar sensor 40 is used to detect and measure the distance, speed, and orientation of an object (e.g., one or more remote vehicles 16) by emitting radio waves and analyzing the reflection of the radio waves. In an exemplary embodiment, radar sensor 40 includes 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 (RF) signals that travel through space until they encounter an object. The RF signals bounce off the object's surface and return to radar sensor 40. The radar receiver uses the radar antenna to capture the reflected signals, 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 orientation of the detected object. Radar sensor 40 communicates electrically with controller 20 as described above.

[0047] 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 hitting an object. In an exemplary embodiment, the LiDAR sensor 42 includes a LiDAR laser source (not shown), a LiDAR scanner or reflector (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 propagate to a target area, and the LiDAR scanner guides these pulses in different directions. The emitted laser pulses interact with objects in the environment, and their reflections are captured by the LiDAR photodetector. The LiDAR time-of-flight measurement system calculates the distance to the object based on the time between the LiDAR laser source emitting the laser pulses and the LiDAR photodetector receiving the reflected laser pulses. As described above, the LiDAR sensor 42 communicates electrically with the controller 20.

[0048] In an exemplary embodiment, one or more sensing sensors 32 are fixed inside the main vehicle 12, for example, in the roof of the main vehicle 12, having a field of view through the windshield 44 of the main vehicle 12. In another example, one or more sensing sensors 32 are fixed outside the main vehicle 12, for example, on the roof of the main vehicle 12, having a field of view of the environment surrounding the main vehicle 12. It should be understood that various additional types of sensing sensors, such as, for example, stereo cameras with distance measurement capabilities, ultrasonic ranging sensors, and time-of-flight sensors, are within the scope of the invention. As described above, one or more sensing sensors 32 are in electrical communication with the controller 20.

[0049] GNSS 34 is used to determine the geographic location of the main vehicle 12. In an exemplary embodiment, GNSS 34 is a Global Positioning System (GPS). In a non-limiting example, GPS includes a GPS receiver antenna (not shown) and a GPS controller (not shown) in electrical communication with the GPS receiver antenna. The GPS receiver antenna receives signals from multiple satellites, and the GPS controller calculates the geographic location of the main vehicle 12 based on the signals received by the GPS receiver antenna.

[0050] In an exemplary embodiment, GNSS 34 also includes a map. This map includes information about infrastructure such as municipal boundaries, roads, railways, sidewalks, buildings, etc. Therefore, the geographic location of the main vehicle 12 is contextualized using the map information. In a non-limiting example, the map is retrieved from a remote source using a wireless connection. In another non-limiting example, the map is stored in a database or memory of GNSS 34.

[0051] It should be understood that various additional types of satellite-based radio navigation systems, such as the Global Positioning System (GPS), Galileo, GLONASS, and BeiDou Navigation Satellite System (BDS), are within the scope of this invention. GNSS 34 communicates electrically with controller 20 as described above.

[0052] The controller 20 uses the vehicle communication system 36 to communicate with other systems outside the main vehicle 12. For example, the vehicle communication system 36 includes the ability to communicate with vehicles (“V2V” communication), infrastructure (“V2I” communication), remote systems at remote call centers (e.g., General Motors’ ON-STAR), and / or personal devices. Generally, the term vehicle-to-everything communication (“V2X” communication) refers to communication between the main vehicle 12 and any remote system (e.g., vehicles, infrastructure, and / or remote systems).

[0053] In some embodiments, the vehicle communication system 36 is a wireless communication system configured to communicate via a wireless local area network (WLAN) using the IEEE 802.11 standard or by using cellular data communication (e.g., using GSMA standards such as, for example, SGP.02, SGP.22, SGP.32, etc.). Therefore, the vehicle communication system 36 may also include an embedded universal integrated circuit card (eUICC) configured to store at least one cellular connectivity configuration profile, such as an embedded subscriber identity module (eSIM) profile.

[0054] The vehicle communication system 36 is also configured to communicate via a personal area network (e.g., BLUETOOTH), near-field communication (NFC), and / or any additional types of radio frequency communication. However, additional or alternative communication methods, such as Dedicated Short-Range Communication (DSRC) channels and / or mobile telecommunications protocols based on 3GPP standards, are also considered to be within the scope of this invention. A DSRC channel refers to a unidirectional or bidirectional short- to medium-range wireless communication channel specific to automotive applications, along with the corresponding set of protocols and standards. 3GPP refers to a partnership between several standards organizations that develop protocols and standards for mobile telecommunications. 3GPP standards are constructed as “versions.” Therefore, communication methods based on 3GPP versions 14, 15, 16, and / or future 3GPP versions are considered to be within the scope of this invention.

[0055] Therefore, the vehicle communication system 36 may include one or more antennas and / or communication transceivers (not shown) for receiving and / or transmitting signals, such as cooperative sensing messages (CSM). The vehicle communication system 36 is configured to transmit wireless information between the host vehicle 12 and another vehicle. Furthermore, the vehicle communication system 36 is configured to transmit wireless information communication between the host vehicle 12 and infrastructure or other vehicles (e.g., one or more remote vehicles 16).

[0056] In another exemplary embodiment, the plurality of vehicle sensors 22 further include sensors for determining performance data regarding the main vehicle 12. In a non-limiting example, the plurality of vehicle sensors 22 also include at least one of an electric motor speed sensor, an electric motor torque sensor, an electric drive motor voltage and / or current sensor, an accelerator pedal position sensor, a brake position sensor, a coolant temperature sensor, a cooling fan speed sensor, and a transmission oil temperature sensor.

[0057] In another exemplary embodiment, the plurality of vehicle sensors 22 further include additional sensors to determine information about the environment within the main vehicle 12. In a non-limiting example, the plurality of vehicle sensors 22 also include at least one of a seat occupancy sensor, a cabin air temperature sensor, a cabin motion detection sensor, a cabin camera, a cabin microphone, an occupant eye tracker, etc.

[0058] In another exemplary embodiment, the plurality of vehicle sensors 22 further include additional sensors to determine information about the environment surrounding the main vehicle 12. In a non-limiting example, the plurality of vehicle sensors 22 may also include at least one of an ambient air temperature sensor, an atmospheric pressure sensor, etc. As described above, the plurality of vehicle sensors 22 are in electrical communication with the controller 20.

[0059] HMI 24 is used to provide information to the occupants of the main vehicle 12. Within the scope of this invention, occupants include the driver and / or passengers of the main vehicle 12. Figure 2 In the exemplary embodiment shown, HMI 24 is a display (e.g., part of the infotainment system of the main vehicle 12) located within the occupant's field of vision and capable of displaying text, graphics, and / or images. It should be understood that HMI display systems including LCD displays, LED displays, etc., are within the scope of this invention. Other exemplary embodiments in which HMI 24 is disposed in a rearview mirror are also within the scope of this invention. In the exemplary embodiment, the occupant can interact with HMI 24 using a human-machine interface device (HID), which includes, for example, a touchscreen, electromechanical switches, capacitive switches, knobs, microphones for receiving voice commands, etc. It should be understood that additional systems for displaying information to the occupants of the main vehicle 12 are also within the scope of this invention. As described above, HMI 24 communicates electrically with controller 20.

[0060] HUD 26 is used to provide information to the occupants of the host vehicle 12. In an exemplary embodiment, HUD 26 is configured to provide information to the occupants by projecting text, graphics, and / or images onto the windshield 44 of the host vehicle 12. In a non-limiting example, HUD 26 includes a projector (not shown) used by controller 20 to project text, graphics, and / or images onto the windshield 44 of the host vehicle 12. The text, graphics, and / or images are reflected by the windshield 44 of the host vehicle 12 and are visible to the occupants without deviating from the road 14 in front of the host vehicle 12. It should be understood that various types of head-up displays (including, for example, augmented reality head-up display (AR-HUD) devices) are within the scope of this invention. In an exemplary embodiment, the occupants can interact with HUD 26 using a human-machine interface device (HID), which includes, for example, a touchscreen, electromechanical switches, capacitive switches, knobs, microphones for receiving voice commands, etc. It should be understood that additional systems for displaying information to the occupants of the main vehicle 12 are also within the scope of this invention. As described above, the HUD 26 communicates electrically with the controller 20.

[0061] refer to Figure 3 A flowchart of a method 100 for providing information to vehicle occupants is shown. Method 100 begins at block 102 and proceeds to blocks 104 and 106. At block 104, controller 20 receives one or more messages from one or more remote vehicles 16 using vehicle communication system 36. The one or more messages include at least the speed, location, vehicle identifier (e.g., vehicle identification number (VIN) and / or other temporary identifiers based on the Society of Automotive Engineers (SAE) messaging standard) and 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 (BSMs) from each of the one or more remote vehicles 16, including information such as, for example, location, speed, speed history over time, acceleration, heading, vehicle type, vehicle identifier, vehicle size, vehicle status, driver intent, message time, etc. In a non-limiting example, one or more messages are sent using vehicle-to-vehicle (V2V) communication technologies, such as, for example, Dedicated Short Range Communication (DSRC). In another non-limiting example, messages are relayed via one or more central servers (e.g., via the Internet or using cellular data communication). After box 104, method 100 proceeds to box 108.

[0062] At block 108, controller 20 determines multiple individual speed-to-time profiles. Within the scope of the invention, a speed-to-time profile is a set of data points representing the speed of a vehicle over a period of time (e.g., ten minutes). In a non-limiting example, the speed-to-time profile includes speed measurements acquired per second over a ten-minute time interval. The speed-to-time profile can be visually represented on a two-dimensional graph, where time is on a horizontal axis (e.g., the x-axis) and speed is on a vertical axis (e.g., the y-axis). Each of the multiple individual speed-to-time profiles corresponds to one of one or more remote vehicles 16. Therefore, each of the multiple individual speed-to-time profiles includes speed data for one of one or more remote vehicles 16. In an exemplary embodiment, to determine the multiple individual speed-to-time profiles, controller 20 aggregates one or more messages received at block 104 and extracts speed and time data for each of the one or more remote vehicles 16 from the one or more messages received at block 104. Following block 108, method 100 proceeds to blocks 110 and 112.

[0063] At block 110, controller 20 merges each of the multiple individual velocity-time curves determined at block 108 into a single merged velocity-time curve. In an exemplary embodiment, to merge each of the multiple individual velocity-time curves into a merged velocity-time curve, controller 20 first aligns each of the multiple individual velocity-time curves. Then, controller 20 averages each of the multiple individual velocity-time curves to generate the merged velocity-time curve. It should be understood that additional methods for merging multiple individual velocity-time curves, including, for example, additional mathematical or statistical methods, machine learning-based methods, and / or similar methods, are within the scope of this invention. Following block 110, method 100 proceeds to block 114.

[0064] At block 114, controller 20 determines a set of fusion curve feature parameters describing the fusion velocity versus time curve determined at block 110. Within the scope of the invention, the set of fusion curve feature parameters includes parameter values ​​characterizing the shape of the fusion velocity versus time curve. In an exemplary embodiment, a regression or curve fitting algorithm (e.g., a linear curve fitting algorithm, a polynomial curve fitting algorithm, an exponential curve fitting algorithm, or a logarithmic curve fitting algorithm) is used to fit the fusion velocity versus time curve, generating the set of fusion curve feature parameters. In a non-limiting example, the curve fitting algorithm uses an iterative process to determine the optimal values ​​of the set of fusion curve feature parameters. In a non-limiting example, the set of fusion curve feature parameters includes maximum velocity, minimum velocity, maximum acceleration, minimum acceleration, one or more coefficients of a mathematical equation describing the curve fitting, etc. The set of fusion curve feature parameters can be used to estimate or predict past or future values ​​of the fusion velocity versus time curve.

[0065] The controller 20 also determines a fusion curve confidence value for the fusion curve feature parameter set. Within the scope of this invention, the fusion curve confidence value quantifies how accurately the fusion curve feature parameter set describes the fusion velocity-time curve. In an exemplary embodiment, the fusion curve confidence value is the proportion of points predicted by the fusion curve feature parameter set that fall on the fusion velocity-time curve. In another exemplary embodiment, the fusion curve confidence value is a coefficient of determination (R²). 2 The confidence value of the fusion curve may include any value that quantifies how accurately the set of characteristic parameters of the fusion curve describes the fusion rate versus time curve. Following box 114, method 100 proceeds to box 116, which will be discussed in more detail below.

[0066] At block 112, controller 20 determines multiple individual sets of curve feature parameters. One of the multiple individual sets of curve feature parameters describes each of the multiple individual velocity-to-time curves determined at block 108. Within the scope of the invention, each individual set of curve feature parameters includes parameter values ​​characterizing the shape of one of the multiple individual velocity-to-time curves. In an exemplary embodiment, a regression or curve fitting algorithm (e.g., a linear curve fitting algorithm, a polynomial curve fitting algorithm, an exponential curve fitting algorithm, or a logarithmic curve fitting algorithm) is used to fit each of the multiple individual velocity-to-time curves, which produces a separate set of curve feature parameters. In a non-limiting example, the curve fitting algorithm uses an iterative process to determine the optimal value for each of the multiple individual sets of curve feature parameters. In a non-limiting example, each of the multiple individual sets of curve feature parameters includes a maximum velocity, a minimum velocity, a maximum acceleration, a minimum acceleration, one or more coefficients for a mathematical equation describing the curve fitting, etc. The multiple individual sets of curve feature parameters can be used to estimate or predict past or future values ​​for each of the multiple individual velocity-to-time curves.

[0067] The controller 20 also determines a plurality of individual curve confidence values. Each of the plurality of individual curve confidence values ​​corresponds to one of a plurality of individual sets of curve feature parameters. Within the scope of the invention, each of the plurality of individual curve confidence values ​​quantifies how accurately each of the plurality of individual sets of curve feature parameters describes each of the plurality of individual velocity-to-time curves. In an exemplary embodiment, the individual curve confidence value is the proportion of points predicted by the individual sets of curve feature parameters that fall on the individual velocity-to-time curve. In another exemplary embodiment, the individual curve confidence value is a coefficient of determination (R²). 2The confidence value of a single curve can include any value that quantifies how accurately a single set of curve feature parameters describes a single velocity versus time curve without departing from the scope of the invention. Following block 112, method 100 proceeds to block 116.

[0068] At block 116, controller 20 merges each of the multiple individual velocity-time curves determined at block 108 with the fused velocity-time curve determined at block 110 to generate a merged velocity-time curve. In an exemplary embodiment, a curve merging machine learning algorithm is used to merge each of the multiple individual velocity-time curves and the fused velocity-time curve. This curve merging machine learning algorithm is configured to receive multiple individual sets of curve feature parameters, multiple individual curve confidence values, a fused curve feature parameter set, and a fused curve confidence value as input, and to provide the merged velocity-time curve as output.

[0069] In another exemplary embodiment, a weighted average of multiple individual curve feature parameter sets and a fused curve feature parameter set is used to merge each of multiple individual velocity-time curves and the fused velocity-time curve. This weighting is based on the confidence values ​​of the multiple individual curves and the confidence value of the fused curve. It should be understood that the above embodiments are merely exemplary in nature, and additional methods for combining, averaging, and / or merging multiple datasets based on feature parameters and their confidence values ​​are within the scope of this invention. Following block 116, method 100 proceeds to block 118.

[0070] At block 118, controller 20 determines a set of traffic congestion feature parameters describing the merging speed versus time curve determined at block 116. Within the scope of the invention, the traffic congestion feature parameter set includes parameter values ​​characterizing the shape of the merging speed versus time curve. In an exemplary embodiment, a regression or curve fitting algorithm (e.g., a linear curve fitting algorithm, a polynomial curve fitting algorithm, an exponential curve fitting algorithm, or a logarithmic curve fitting algorithm) that generates the traffic congestion feature parameter set is used to fit the merging speed versus time curve. In a non-limiting example, the curve fitting algorithm uses an iterative process to determine the optimal values ​​of the traffic congestion feature parameter set. In a non-limiting example, the traffic congestion feature parameter set includes maximum speed, minimum speed, maximum acceleration, minimum acceleration, one or more coefficients of a mathematical equation describing the curve fitting, etc. The traffic congestion feature parameter set can be used to estimate or predict past or future values ​​of the merging speed versus time curve.

[0071] Controller 20 also determines a merge curve confidence value for the traffic congestion feature parameter set. Within the scope of this invention, the merge curve confidence value quantifies how accurately the traffic congestion feature parameter set describes the merging speed versus time curve. In an exemplary embodiment, the merge curve confidence value is the proportion of points predicted by the traffic congestion feature parameter set that fall on the merging speed versus time curve. In another exemplary embodiment, the merge curve confidence value is a coefficient of determination (R²). 2 The confidence value of the merged curve can include any value that quantifies how accurately the set of traffic congestion feature parameters describes the merged speed versus time curve without departing from the scope of the invention. Following box 118, method 100 proceeds to box 120, which will be discussed in more detail below.

[0072] At block 106, controller 20 uses one or more perception sensors 32 to perform one or more perception measurements for each of the one or more remote vehicles 16. In an exemplary embodiment, the one or more perception measurements include speed and position measurements for each of the one or more remote vehicles 16. In a non-limiting example, controller 20 uses camera 38 to perform one or more perception measurements. In a non-limiting example, controller 20 uses radar sensor 40 to perform one or more perception measurements. In a non-limiting example, controller 20 uses LiDAR sensor 42 to perform one or more perception measurements. Following block 106, method 100 proceeds to block 122.

[0073] At block 122, controller 20 determines multiple observed individual speed-to-time profiles. Each of the multiple observed individual speed-to-time profiles corresponds to one of one or more remote vehicles 16. Therefore, each of the multiple observed individual speed-to-time profiles includes speed data from one of the one or more remote vehicles 16. In some embodiments, abnormal speed data and / or abnormal observed individual speed-to-time profiles are detected and removed from the multiple observed individual speed-to-time profiles. In an exemplary embodiment, to determine the multiple observed individual speed-to-time profiles, controller 20 aggregates speed-to-time data from one or more sensing measurements performed at block 106 for each of the one or more remote vehicles 16. Following block 122, method 100 proceeds to block 124.

[0074] At block 124, controller 20 determines a plurality of individual sets of observed curve feature parameters. One of the plurality of individual sets of observed curve feature parameters describes each of the plurality of individual observed velocity-to-time curves determined at block 122. Within the scope of the invention, each individual set of curve feature parameters includes parameter values ​​characterizing the shape of one of the plurality of individual velocity-to-time curves. In an exemplary embodiment, a regression or curve fitting algorithm (e.g., a linear curve fitting algorithm, a polynomial curve fitting algorithm, an exponential curve fitting algorithm, or a logarithmic curve fitting algorithm) is used to fit each of the plurality of individual velocity-to-time curves, the regression or curve fitting algorithm generating the individual set of observed curve feature parameters. In a non-limiting example, the curve fitting algorithm uses an iterative process to determine the optimal value for each of the plurality of individual sets of observed curve feature parameters. In a non-limiting example, each of the plurality of individual sets of observed curve feature parameters includes a maximum velocity, a minimum velocity, a maximum acceleration, a minimum acceleration, one or more coefficients for a mathematical equation describing the curve fitting, etc. The plurality of individual sets of observed curve feature parameters can be used to estimate or predict past or future values ​​for each of the plurality of individual velocity-to-time curves.

[0075] The controller 20 also determines a plurality of individual curve confidence values. Each of the plurality of individual curve confidence values ​​corresponds to one of a plurality of individual curve feature parameter sets. Within the scope of the invention, each of the plurality of individual curve confidence values ​​quantifies how accurately each of the plurality of individual curve feature parameter sets describes each of the plurality of individual velocity-to-time curves. In an exemplary embodiment, the individual curve confidence value is the proportion of points predicted by the individual curve feature parameter set to fall on the individual velocity-to-time curve. In another exemplary embodiment, the individual curve confidence value is a coefficient of determination (R²). 2 The confidence value of an observed individual curve may include any value that quantifies how accurately the observed individual set of curve characteristic parameters describes the observed individual velocity-time curve, without departing from the scope of this disclosure. Following box 124, method 100 proceeds to box 120.

[0076] At box 120, controller 20 determines the traffic congestion type. Within the scope of this invention, the traffic congestion type categorizes traffic congestion occurring on road 14 into one or more predefined categories. In an exemplary embodiment, the traffic congestion type includes one of three predefined traffic congestion types that typically occur.

[0077] refer to Figure 4AA first exemplary speed-to-time graph 50 depicting a first type of traffic congestion is shown. The first exemplary speed-to-time graph 50 includes a horizontal axis 52a depicting time (e.g., in minutes), a vertical axis 52b depicting speed (e.g., in kilometers per hour), and a first exemplary speed-to-time curve 54. The first type of traffic congestion with the first exemplary speed-to-time curve 54 is characterized by long queues at congested intersections, resulting in relatively long periods of inactivity, separated by relatively long periods of rapid acceleration and deceleration.

[0078] refer to Figure 4B A second exemplary speed-to-time graph 60 depicting a second type of traffic congestion is shown. The second exemplary speed-to-time graph 60 includes a horizontal axis 62a depicting time (e.g., in minutes), a vertical axis 62b depicting speed (e.g., in kilometers per hour), and a second exemplary speed-to-time curve 64. The second type of traffic congestion with the second exemplary speed-to-time curve 64 is characterized by lane closures (e.g., due to roadworks, motor vehicle accidents, etc.), resulting in quasi-continuous motion with non-zero minimum speeds and relatively short speed fluctuation periods (e.g., allowing other vehicles to merge into open lanes).

[0079] refer to Figure 4C A third exemplary speed-to-time graph 70 depicting a third type of traffic congestion is shown. The third exemplary speed-to-time graph 70 includes a horizontal axis 72a depicting time (e.g., in minutes), a vertical axis 72b depicting speed (e.g., in kilometers per hour), and a third exemplary speed-to-time curve 74. The third type of traffic congestion with the third exemplary speed-to-time curve 74 is characterized by slow, intermittently moving queues (e.g., caused by toll booths or other checkpoints), resulting in relatively short periods of waiting without movement, separated by relatively short periods of acceleration and deceleration with relatively low maximum speeds.

[0080] It should be understood that, Figures 4A-4C The traffic congestion types described herein, as well as the first, second, and third types described above, are merely exemplary in nature. Any number of additional traffic congestion types may be considered in method 100 without departing from the scope of the invention.

[0081] Refer again Figure 3In an exemplary embodiment, to determine the traffic congestion type at block 120, controller 20 analyzes the merged speed-to-time curve generated at block 116 and the set of traffic congestion feature parameters determined at block 118. In a non-limiting example, controller 20 uses mathematical and / or statistical methods (e.g., root mean square error, coefficient of determination, and / or similar methods) to compare the merged speed-to-time curve with exemplary speed-to-time curves (e.g., first exemplary speed-to-time curve 54, second exemplary speed-to-time curve 64, and third exemplary speed-to-time curve 74) for each predefined traffic congestion type (e.g., a first traffic congestion type, a second traffic congestion type, and a third traffic congestion type) that take into account the set of congestion feature parameters. The traffic congestion type is determined as one of the predefined traffic congestion types that best matches the merged speed-to-time curve. In another non-limiting example, controller 20 uses a traffic congestion type machine learning algorithm to determine the traffic congestion type.

[0082] In a non-limiting example, the traffic congestion type machine learning algorithm includes multiple layers, including an input layer and an output layer, as well as one or more hidden layers. The input layer receives exemplary speed-to-time curves for each predefined traffic congestion type (e.g., first exemplary speed-to-time curve 54, second exemplary speed-to-time curve 64, and third exemplary speed-to-time curve 74), combines the speed-to-time curves with a set of congestion feature parameters as input. The input is then passed to the hidden layers. Each hidden layer applies a transformation (e.g., a non-linear transformation) to the data and passes the result to the next hidden layer, until the final hidden layer. The output layer generates the traffic congestion type.

[0083] To train a machine learning algorithm for traffic congestion types, an input dataset and its corresponding traffic congestion types are used. The algorithm is trained to minimize prediction error by adjusting the internal weights between nodes in each hidden layer. During training, optimization techniques (e.g., gradient descent) are used to adjust the internal weights to reduce prediction error. The training process is repeated on the entire dataset until the prediction error is minimized, and then the resulting trained model is used to classify new input data.

[0084] After being thoroughly trained, the machine learning algorithm for traffic congestion types is able to accurately and precisely determine the type of traffic congestion based on exemplary speed-to-time curves, merged speed-to-time curves, and a set of congestion feature parameters for each predefined traffic congestion type. By adjusting the weights between nodes in each hidden layer during training, the algorithm "learns" to identify patterns in the data that indicate the type of traffic congestion.

[0085] It should be understood that any mathematical, statistical, rule-based, and / or machine learning-based algorithms or methods can be used to identify which predefined traffic congestion type most closely resembles the merged speed-to-time curve. It should also be understood that speed-to-time data collected during the driving session of the primary vehicle 12 can be used for incremental and / or continuous training of traffic congestion-based machine learning algorithms.

[0086] In an exemplary embodiment, controller 20 also verifies the traffic congestion type based at least in part on one or more perception measurements performed at block 106. In an exemplary embodiment, controller 20 determines the observed traffic congestion type based on multiple observed speed-to-time curves generated at block 122 and multiple observed individual curve feature parameter sets determined at block 124. In a non-limiting example, controller 20 merges the multiple observed speed-to-time curves and multiple observed individual curve feature parameter sets, as discussed above with reference to block 116, to generate a merged observed speed-to-time curve and observed congestion feature parameter set.

[0087] Controller 20 then uses the mathematical, statistical, or machine learning methods described above to determine the observed traffic congestion type. Controller 20 then compares the observed traffic congestion type with the traffic congestion type determined as described above. In an exemplary embodiment, if the observed traffic congestion type differs from the traffic congestion type, method 100 terminates or restarts. In another exemplary embodiment, if the observed traffic congestion type differs from the traffic congestion type, the observed traffic congestion type is considered the accurate traffic congestion type. After block 120, method 100 proceeds to blocks 126 and 128.

[0088] At box 126, controller 20 selects a chosen machine learning manipulation model from a plurality of manipulation models. Within the scope of this invention, the plurality of manipulation models are used to determine an optimal vehicle manipulation plan for the master vehicle 12. Within the scope of this invention, the optimal vehicle manipulation plan is a plan for maneuvering the master vehicle 12 that maximizes occupant comfort and forward movement of the master vehicle 12 while minimizing traffic congestion. The optimal vehicle manipulation plan includes an optimal speed-to-time curve, which the master vehicle 12 should follow to achieve the objectives of the optimal vehicle manipulation plan. The optimal vehicle manipulation plan also includes one or more optimal acceleration and braking levels determined based on the optimal speed-to-time curve, which the master vehicle 12 should use to follow the optimal speed-to-time curve.

[0089] In an exemplary embodiment, each of the plurality of maneuvering models corresponds to one of the predefined traffic congestion types (e.g., first, second, and third traffic congestion types). Each of the plurality of maneuvering models is a machine learning model that has been trained to determine the optimal vehicle maneuvering plan when the master vehicle 12 is experiencing one of the predefined traffic congestion types (e.g., first, second, and third traffic congestion types).

[0090] In a non-limiting example, each of the multiple handling models is trained using experimental data collected from real-world, road experiments and / or simulated data collected from computer-simulated driving situations. It should also be understood that speed-to-time data collected during a driving session of the master vehicle 12 can be used for incremental and / or sequential training of each of the multiple handling models. At box 126, the controller 20 selects one of the multiple handling models corresponding to the traffic congestion type determined at box 120, referred to as the selected machine learning handling model. Following box 126, method 100 proceeds to box 130.

[0091] At box 130, controller 20 uses the machine learning maneuvering model selected at box 126 to determine the optimal vehicle maneuvering plan. In a non-limiting example, the selected machine learning maneuvering model comprises multiple layers, including an input layer and an output layer, as well as one or more hidden layers. The input layer receives a set of traffic congestion feature parameters (determined at box 118) as input. The input is 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, until the final hidden layer. The output layer produces the optimal vehicle maneuvering plan, which includes the optimal speed-to-time curve and one or more optimal acceleration and braking levels.

[0092] To train the selected machine learning manipulation model, an input dataset and its corresponding optimal vehicle handling plan are used, including optimal speed-to-time curves and one or more optimal acceleration and braking levels. The algorithm is trained to minimize prediction error by adjusting the internal weights between nodes in each hidden layer. During training, optimization techniques (e.g., gradient descent) are used to adjust the internal weights to reduce prediction error. The training process is repeated on the entire dataset until the prediction error is minimized, and then the resulting trained model is used to classify new input data.

[0093] After sufficient training on the selected machine learning maneuvering model, the algorithm is able to accurately and precisely determine the optimal vehicle maneuvering plan based on a set of traffic congestion feature parameters, including the optimal speed-to-time curve and one or more optimal acceleration and braking levels. By adjusting the weights between nodes in each hidden layer during training, the algorithm "learns" to identify patterns in the data indicating the optimal vehicle maneuvering plan, which includes the optimal speed-to-time curve and one or more optimal acceleration and braking levels. Following box 130, method 100 proceeds to box 132, which will be discussed in more detail below.

[0094] At block 128, controller 20 determines recommended vehicle maneuvers based at least in part on the traffic congestion type determined at block 120. Within the scope of the invention, the recommended vehicle maneuvers are rule-based, predefined behaviors designed to increase occupant comfort or facilitate efficient movement of the master vehicle 12. In a non-limiting example, for a first traffic congestion type, recommended vehicle maneuvers include maneuvering the master vehicle 12 into the lane with the shortest or fastest queue. For a second traffic congestion type, recommended vehicle maneuvers include maneuvering the master vehicle 12 into the lane with a higher minimum speed or a higher maximum speed.

[0095] For the third type of traffic congestion, recommended vehicle maneuvering includes maneuvering the primary vehicle 12 to prevent one or more remote vehicles 16 from overtaking (i.e., skipping their original position in the queue by passing other vehicles). In a non-limiting example, preventing overtaking may include reducing the following distance between the primary vehicle 12 and one or more remote vehicles 16 directly in front of the primary vehicle 12. In another non-limiting example, preventing overtaking may include maneuvering the primary vehicle 12 closer to the left or right lane edge to prevent one or more remote vehicles 16 from passing the primary vehicle 12.

[0096] It should be understood that the vehicle maneuvers recommended above are merely exemplary in nature, and various additional maneuvers can be selected based on the type of traffic congestion, including, for example, nondeterministic maneuvers and / or maneuvers provided by machine learning algorithms. It should also be understood that in some cases, the recommended vehicle maneuvers are not selected. Following box 128, the method proceeds to box 132.

[0097] At block 132, controller 20 provides notification to the occupants of the main vehicle 12 based at least in part on the optimal vehicle handling plan determined at block 130 and the recommended vehicle handling determined at block 128. In an exemplary embodiment, controller 20 uses one or both of HMI 24 and / or HUD 26 to provide the notification. In a non-limiting example, the notification includes text and / or graphics indicating one or more of the following: the optimal speed-to-time curve determined at block 130, one or more optimal acceleration and braking levels determined at block 130, and the recommended vehicle handling determined at block 128.

[0098] refer to Figure 5 An exemplary view 80 is shown, viewed from inside the main vehicle 12. Exemplary view 80 includes a HUD 26 (…). Figure 1 The exemplary HUD notification 82 displayed on the windshield 44 and the exemplary HMI notification 84 displayed on the HMI 24 are shown. The exemplary HUD notification 82 includes a graphical depiction 82a of the optimal speed versus time curve, informational text 82b, and a current time indicator 82c.

[0099] The graphical representation of the optimal speed versus time curve 82a includes a downward sloping line 86a, a flat line 86b, and an upward sloping line 86c. The downward sloping line 86a represents a decrease in vehicle speed, and the optimal acceleration and braking level is a slight braking level providing gradual deceleration. The flat line 86b represents a constant vehicle speed (greater than or equal to zero), and the optimal acceleration and braking level is no acceleration or braking. The upward sloping line 86c represents an increase in vehicle speed, and the optimal acceleration and braking level is a slight acceleration level providing gradual acceleration. In some embodiments, the downward sloping line 86a, the flat line 86b, and the upward sloping line 86c are highlighted with different colors or graphical styles. In some embodiments, the downward sloping line 86a, the flat line 86b, and the upward sloping line 86c also include text providing additional explanations.

[0100] Information text 82b provides occupants with additional information regarding the optimal speed versus time curve, one or more optimal acceleration and braking levels, and / or recommended vehicle handling. In an exemplary embodiment, information text 82b includes information about the current optimal acceleration and braking level (e.g., “light braking” or “light acceleration”). In another exemplary embodiment, information text 82b includes information about the type of traffic congestion. In yet another exemplary embodiment, information text 82b includes information about recommended vehicle handling (e.g., “merge into the left lane when safe”).

[0101] The current time indicator 82c indicates the current position of the master vehicle 12 along the graphical depiction 82a of the optimal speed versus time curve. In an exemplary embodiment, as time progresses, the current time indicator 82c moves along the graphical depiction 82a of the optimal speed versus time curve (e.g., from left to right), thereby indicating the optimal vehicle speed and the current optimal acceleration and braking level at any given time.

[0102] The exemplary HMI notification 84 includes graphics and / or text that provides information about optimal speed-to-time curves, one or more optimal acceleration and braking levels, and / or recommended vehicle handling. In an exemplary embodiment, the exemplary HMI notification 84 is substantially similar to or equivalent to the exemplary HUD notification 82. In another exemplary embodiment, the exemplary HMI notification 84 includes additional information about optimal speed-to-time curves, one or more optimal acceleration and braking levels, and / or recommended vehicle handling not shown in the exemplary HUD notification 82. For example, if the information text 82b of the exemplary HUD notification 82 includes the current optimal acceleration and braking level, the exemplary HMI notification 84 may include information about recommended vehicle handling. If the HUD 26 is inoperable or unavailable, the exemplary HMI notification 84 may be used to provide information to the occupants of the master vehicle 12 about optimal speed-to-time curves, one or more optimal acceleration and braking levels, and / or recommended vehicle handling.

[0103] It should be understood that the foregoing discussion of exemplary view 80, exemplary HUD notification 82 and exemplary HMI notification 84 is merely exemplary in nature. Figure 5 The exemplary HUD notification 82 and exemplary HMI notification 84 shown are merely exemplary in nature, and variations in size, shape, color, opacity, display position, graphic style, etc., are within the scope of this invention.

[0104] Refer again Figure 3 At box 132, controller 20 provides notification to the occupants of main vehicle 12 (e.g., as referenced above). Figure 5 The exemplary HUD notification 82 and / or exemplary HMI notification 84 discussed herein. In an exemplary embodiment where the master vehicle 12 is a partially or fully automated driving vehicle, the master vehicle 12 uses an automated driving system (not shown) to follow one or more optimal acceleration and braking levels, and / or perform recommended vehicle maneuvers. After block 132, method 100 enters a standby state at block 134.

[0105] In an exemplary embodiment, controller 20 repeatedly exits standby state 134 and restarts method 100 at block 102. In a non-limiting example, controller 20 exits standby state 134 and restarts method 100 according to a timer (e.g., every 300 milliseconds).

[0106] The system 10 and method 100 of the present invention have several advantages. By generating a merged speed-to-time curve by combining the fused speed-to-time curve with multiple individual speed-to-time curves, the impact of anomalies and variations in driver behavior can be minimized, thereby achieving an accurate representation of the overall motion trend of the remote vehicle 16, and thus an accurate representation of the traffic congestion type. By determining the traffic congestion type, an optimal vehicle handling plan can be determined using a more efficient and accurate machine learning handling model. By displaying the optimal vehicle handling plan using the HMI 24 and / or HUD 26, the occupants of the primary vehicle 12 are informed of the automatic primary vehicle actions and / or the optimal actions, increasing comfort and progress in congested traffic situations.

[0107] The description of this invention is merely exemplary in nature, and variations that do not depart from the spirit of the invention are intended to be within its scope. Such variations should not be considered as a departure from the spirit and scope of the invention.

Claims

1. A method for providing information to vehicle occupants, comprising: Identify the type of traffic congestion in the environment surrounding the vehicle, wherein the type of traffic congestion is characterized by a set of traffic congestion feature parameters; The optimal vehicle handling plan is determined at least in part based on the traffic congestion type and the set of traffic congestion characteristic parameters; and The occupants of the vehicle are provided with a notification, wherein the notification is based at least in part on the optimal vehicle handling plan.

2. The method according to claim 1, wherein, Identifying the traffic congestion type also includes: Use a vehicle communication system to receive one or more messages from one or more remote vehicles; Determine multiple individual speed-to-time curves, at least in part, based on the one or more messages, wherein each of the multiple individual speed-to-time curves corresponds to one of the one or more remote vehicles; and The type of traffic congestion is determined at least in part based on the multiple individual speed-to-time curves.

3. The method according to claim 2, wherein, Determining the traffic congestion type, at least in part, based on the multiple individual speed-to-time curves, also includes: Determine multiple individual sets of curve feature parameters, wherein one of the multiple individual sets of curve feature parameters describes each of the multiple individual velocity-to-time curves; and Determine multiple individual curve confidence values, wherein each of the multiple individual curve confidence values ​​corresponds to one of the multiple individual curve feature parameter sets.

4. The method according to claim 3, wherein, Determining the traffic congestion type, at least in part, based on the multiple individual speed-to-time curves, also includes: Each of the multiple individual velocity-time curves is merged into a fused velocity-time curve; Determine the set of characteristic parameters of the fusion curve describing the fusion rate versus time curve; and Determine the confidence value of the fusion curve based on the set of characteristic parameters of the fusion curve.

5. The method according to claim 4, wherein, Determining the traffic congestion type, at least in part, based on the multiple individual speed-to-time curves, also includes: Each of the multiple individual velocity-time curves is merged with the fused velocity-time curve to generate a merged velocity-time curve, wherein the merged velocity-time curve is generated at least in part based on the multiple individual curve feature parameter sets, the multiple individual curve confidence values, the fused curve feature parameter set, and the fused curve confidence values; Determine the set of traffic congestion characteristic parameters describing the merged speed versus time curve; and The traffic congestion type is determined at least in part based on the merged speed-to-time curve and the set of traffic congestion characteristic parameters.

6. The method according to claim 5, wherein, Determining the traffic congestion type, at least in part, based on the merged speed-to-time curve and the set of traffic congestion characteristic parameters, also includes: Perform one or more perception measurements of the one or more remote vehicles using one or more perception sensors of the vehicle; and The traffic congestion type is verified at least in part based on one or more of the perception measurements.

7. The method according to claim 1, wherein, Determining the optimal vehicle handling plan also includes: Selecting a machine learning manipulation model from multiple manipulation models, wherein the selected machine learning manipulation model corresponds to the traffic congestion type; and The selected machine learning manipulation model is used to determine the optimal vehicle manipulation plan, wherein the selected machine learning manipulation model is configured to receive the set of traffic congestion feature parameters as input and provide the optimal vehicle manipulation plan as output.

8. The method according to claim 7, wherein, Determining the optimal vehicle handling plan also includes: The selected machine learning manipulation model is used to determine the optimal vehicle manipulation plan, wherein the selected machine learning manipulation model is configured to receive the set of traffic congestion feature parameters as input and provide the optimal vehicle manipulation plan as output, and wherein the optimal vehicle manipulation plan includes an optimal speed-to-time curve.

9. The method according to claim 8, wherein, Providing the notification also includes: One or more optimal acceleration and braking levels are determined, at least in part, based on the optimal speed versus time curve; and The notification is provided to the occupants of the vehicle, wherein the notification includes at least one of the following: the optimal speed versus time curve and the one or more optimal acceleration and braking levels.

10. The method according to claim 1, wherein, Providing the notification also includes: Recommended vehicle maneuvers are determined at least in part based on the type of traffic congestion; and The notification is provided to the vehicle occupants, wherein the notification includes the recommended vehicle handling.

Images