Weather-dependent vehicle path planning

Abstract

According to aspects, a method for vehicle path planning includes determining a predicted trajectory for a remote vehicle. The predicted trajectory of the remote vehicle includes a plurality of predicted trajectory nodes. The method also includes determining a plurality of possible trajectories of the vehicle. The plurality of possible trajectories includes a plurality of possible trajectory nodes. The method further includes determining one or more evaluation metrics for each of the plurality of possible trajectory nodes based at least in part on a weather condition in the vehicle surroundings. The method further includes selecting an optimal trajectory for the vehicle from the plurality of possible trajectories based at least in part on the one or more evaluation metrics for each of the plurality of possible trajectory nodes. The method further includes performing a first action based at least in part on the optimal trajectory.

Description

Technical Field

[0001] The present disclosure relates to advanced driver assistance and automated driving systems and methods for vehicles, and more particularly, to systems and methods for vehicle path planning. Background Art

[0002] To improve occupant awareness and convenience, vehicles may be equipped with advanced driver assistance systems (ADAS) and / or automated driving systems (ADS). ADAS systems may use various sensors such as cameras, radars, 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 may take actions based on environmental conditions around the vehicle, such as applying brakes or warning vehicle occupants. ADS systems may use various sensors to detect objects in the vehicle's surroundings and control the vehicle to navigate the vehicle through the environment to a predetermined destination. However, current ADAS and ADS systems may not take into account severe weather conditions, which may result in suboptimal path planning and / or remote vehicle trajectory prediction. In addition, current ADAS and ADS systems may not take into account unconventional maneuvers, which may be necessary to avoid collisions in severe weather conditions.

[0003] Therefore, while ADAS and ADS systems and methods achieve their intended purposes, a new and improved system and method for vehicle path planning is needed. Summary of the invention

[0004] According to several aspects, a method for vehicle path planning is provided. The method may include determining a predicted trajectory of a remote vehicle. The predicted trajectory of the remote vehicle includes a plurality of predicted trajectory nodes. The method may also include determining a plurality of possible trajectories for the vehicle. The plurality of possible trajectories include a plurality of possible trajectory nodes. The method may also include determining one or more evaluation indicators for each of the plurality of possible trajectory nodes based at least in part on weather conditions in an environment surrounding the vehicle. The method may also include selecting an optimal trajectory for the vehicle from the plurality of possible trajectories based at least in part on the one or more evaluation indicators for each of the plurality of possible trajectory nodes. The method may also include performing a first action based at least in part on the optimal trajectory.

[0005] In another aspect of the present disclosure, one or more evaluation indicators also include a collision potential score. Determining the collision potential score of each of the multiple possible trajectory nodes may also include determining multiple uncertainties. The multiple uncertainties include multiple predicted trajectory uncertainties and multiple possible trajectory uncertainties. Each of the multiple predicted trajectory uncertainties corresponds to one of the multiple predicted trajectory nodes. Each of the multiple possible trajectory uncertainties corresponds to one of the multiple possible trajectory nodes. Determining the collision potential score of each of the multiple possible trajectory nodes may also include determining multiple biased predicted trajectory uncertainties and multiple biased possible trajectory uncertainties by applying a bias to each of the multiple predicted trajectory uncertainties and each of the multiple possible trajectory uncertainties. The bias is based at least in part on weather conditions in the vehicle's surroundings. Determining the collision potential score of each of the multiple possible trajectory nodes may also include determining the collision potential score of each of the multiple possible trajectory nodes based at least in part on multiple biased predicted trajectory uncertainties and multiple biased possible trajectory uncertainties.

[0006] In another aspect of the present disclosure, determining the plurality of uncertainties may further include determining the plurality of uncertainties based on at least one of: weather conditions in the vehicle surroundings and positioning errors of one or more of the plurality of vehicle sensors.

[0007] In another aspect of the present disclosure, determining multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations may also include determining a longitudinal deviation for each of a plurality of possible trajectory nodes and each of a plurality of predicted trajectory nodes. Determining multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations may also include determining a lateral deviation for each of a plurality of possible trajectory nodes and each of a plurality of predicted trajectory nodes. The lateral deviation is determined at least in part based on a dynamics-based model and weather conditions in the vehicle's surroundings. Determining multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations may also include applying a longitudinal deviation and a lateral deviation to each of a plurality of predicted trajectory uncertainties. Determining multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations may also include applying a longitudinal deviation and a lateral deviation to each of a plurality of possible trajectory uncertainties.

[0008] In another aspect of the present disclosure, determining the collision potential score for each of the plurality of possible trajectory nodes may further include determining the collision potential score using the following formula:

[0009]

[0010] Among them, p iis the collision potential score of the ith node among multiple possible trajectory nodes, r i is one of the multiple biased prediction trajectory uncertainties corresponding to the i-th node among the multiple prediction trajectory nodes, e i is one of a plurality of biased possible trajectory uncertainties corresponding to the i-th node among a plurality of possible trajectory nodes, ∩ is an intersection operator, and ∪ is a union operator.

[0011] In another aspect of the present disclosure, the one or more evaluation indicators further include a maneuverability score. Determining the maneuverability score for each of the plurality of possible trajectory nodes may also include determining an estimated propulsion system torque required to reach each of the plurality of possible trajectory nodes. Determining the maneuverability score for each of the plurality of possible trajectory nodes may also include determining the maneuverability score for each of the plurality of possible trajectory nodes based at least in part on the estimated propulsion system torque using the following formula:

[0012]

[0013] Among them, m i is the maneuverability score of the i-th node among multiple possible trajectory nodes, T i is the estimated propulsion system torque required to reach the i-th node among multiple possible trajectory nodes, and T MAX is the maximum torque available from the vehicle's propulsion system.

[0014] In another aspect of the present disclosure, the one or more evaluation metrics further include a traffic violation score. The traffic violation score quantifies the legality of maneuvering the vehicle to each of the plurality of possible trajectory nodes.

[0015] In another aspect of the present disclosure, selecting the best trajectory may further include selecting a subset of the plurality of possible trajectory nodes as the best trajectory. The subset of the plurality of possible trajectory nodes is selected to minimize the sum of each of the one or more evaluation indicators of each subset of the plurality of possible trajectory nodes.

[0016] In another aspect of the present disclosure, selecting the best trajectory may further include selecting a subset of the plurality of possible trajectory nodes as the best trajectory. Selecting the subset of the plurality of possible trajectory nodes to minimize an objective function;

[0017]

[0018] Where c is the objective function, N is the number of nodes in a subset of multiple possible trajectory nodes, and p i is the collision potential score of the ith node in a subset of multiple possible trajectory nodes, v i is the traffic violation score of the i-th node in a subset of multiple possible trajectory nodes, and m iis the operability score of the ith node in the subset of the plurality of possible trajectory nodes. Each subset of the plurality of possible trajectory nodes is from the same one of the plurality of possible trajectories. A first node in the subset of the plurality of possible trajectory nodes and a second node in the subset of the plurality of possible trajectory nodes have a collision potential score less than 1.

[0019] In another aspect of the present disclosure, performing the first action may also include adjusting operation of an autonomous driving system of the vehicle based at least in part on the optimal trajectory.

[0020] According to several aspects, a system for vehicle path planning is provided. The system may include multiple vehicle sensors, an autonomous driving system, and a controller in electrical communication with the multiple vehicle sensors and the autonomous driving system. The controller is programmed to use multiple vehicle sensors to determine a predicted trajectory of a remote vehicle. The predicted trajectory of the remote vehicle includes multiple predicted trajectory nodes. The controller is also programmed to use multiple vehicle sensors to determine multiple possible trajectories of the vehicle. The multiple possible trajectories include multiple possible trajectory nodes. The controller is also programmed to determine one or more evaluation indicators for each of the multiple possible trajectory nodes based at least in part on weather conditions in the vehicle's surroundings. The weather conditions are determined using multiple vehicle sensors. The controller is also programmed to select an optimal trajectory for the vehicle from multiple possible trajectories based at least in part on one or more evaluation indicators for each of the multiple possible trajectory nodes. The controller is also programmed to adjust the operation of the autonomous driving system based at least in part on the optimal trajectory.

[0021] In another aspect of the present disclosure, one or more evaluation indicators also include a collision potential score. In order to determine the collision potential score of each of the multiple possible trajectory nodes, the controller is also programmed to determine multiple uncertainties. The multiple uncertainties include multiple predicted trajectory uncertainties and multiple possible trajectory uncertainties. Each of the multiple predicted trajectory uncertainties corresponds to one of the multiple predicted trajectory nodes. Each of the multiple possible trajectory uncertainties corresponds to one of the multiple possible trajectory nodes. In order to determine the collision potential score of each of the multiple possible trajectory nodes, the controller is also programmed to determine multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations by applying deviations to each of the multiple predicted trajectory uncertainties and each of the multiple possible trajectory uncertainties. The deviation is based at least in part on the weather conditions of the vehicle's surroundings. In order to determine the collision potential score of each of the multiple possible trajectory nodes, the controller is also programmed to determine the collision potential score of each of the multiple possible trajectory nodes based at least in part on multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations.

[0022] In another aspect of the present disclosure, in order to determine multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations, the controller is also programmed to determine the longitudinal deviation of each of the multiple predicted trajectory nodes and each of the multiple possible trajectory nodes. In order to determine multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations, the controller is also programmed to determine the lateral deviation of each of the multiple possible trajectory nodes and each of the multiple predicted trajectory nodes. The lateral deviation is determined at least in part based on weather conditions and a dynamics-based model in the vehicle's surrounding environment. In order to determine multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations, the controller is also programmed to apply the longitudinal deviation and the lateral deviation to each of the multiple predicted trajectory uncertainties. In order to determine multiple predicted trajectory uncertainties with deviations and multiple possible trajectory uncertainties with deviations, the controller is also programmed to apply the longitudinal deviation and the lateral deviation to each of the multiple possible trajectory uncertainties.

[0023] In another aspect of the present disclosure, to determine the collision potential score for each of the plurality of possible trajectory nodes, the controller is further programmed to determine the collision potential score using the following formula:

[0024]

[0025] Among them, p i is the collision potential score of the ith node among multiple possible trajectory nodes, r i is one of the multiple biased prediction trajectory uncertainties corresponding to the i-th node among the multiple prediction trajectory nodes, e i is one of a plurality of biased possible trajectory uncertainties corresponding to the i-th node among a plurality of possible trajectory nodes, ∩ is an intersection operator, and ∪ is a union operator.

[0026] In another aspect of the present disclosure, the one or more evaluation indicators further include a maneuverability score. To determine the maneuverability score for each of the plurality of possible trajectory nodes, the controller is further programmed to determine an estimated propulsion system torque required to reach each of the plurality of possible trajectory nodes. To determine the maneuverability score for each of the plurality of possible trajectory nodes, the controller is further programmed to determine the maneuverability score for each of the plurality of possible trajectory nodes based at least in part on the estimated propulsion system torque using the following formula:

[0027]

[0028] Among them, m i is the maneuverability score of the i-th node among multiple possible trajectory nodes, T iis the estimated propulsion system torque required to reach the i-th node among multiple possible trajectory nodes, and T MAX is the maximum torque available from the vehicle's propulsion system.

[0029] In another aspect of the present disclosure, the one or more evaluation metrics further include a traffic violation score. The traffic violation score quantifies the legality of maneuvering the vehicle to each of the plurality of possible trajectory nodes.

[0030] In another aspect of the present disclosure, in order to select the best trajectory, the controller is further programmed to select a subset of the plurality of possible trajectory nodes as the best trajectory. The subset of the plurality of possible trajectory nodes is selected to minimize the objective function:

[0031]

[0032] Where c is the objective function, N is the number of nodes in a subset of multiple possible trajectory nodes, and p i is the collision potential score of the ith node in a subset of multiple possible trajectory nodes, v i is the traffic violation score of the i-th node in a subset of multiple possible trajectory nodes, and m i is the operability score of the ith node in the subset of the plurality of possible trajectory nodes. Each subset of the plurality of possible trajectory nodes is from the same one of the plurality of possible trajectories. A first node in the subset of the plurality of possible trajectory nodes and a second node in the subset of the plurality of possible trajectory nodes have a collision potential score less than 1.

[0033] According to several aspects, a system for vehicle path planning is provided. The system may include a plurality of vehicle sensors, an autonomous driving system, and a controller in electrical communication with the plurality of vehicle sensors and the autonomous driving system. The controller is programmed to determine a predicted trajectory of a remote vehicle using a plurality of vehicle sensors. The predicted trajectory of the remote vehicle includes a plurality of predicted trajectory nodes. The controller is also programmed to determine a plurality of possible trajectories of the vehicle using a plurality of vehicle sensors. The plurality of possible trajectories include a plurality of possible trajectory nodes. The controller is also programmed to perform a proximity check of the plurality of possible trajectories. The proximity check includes removing the first trajectory from the plurality of possible trajectories in response to determining that the first trajectory includes one or more possible trajectory nodes in the plurality of possible trajectory nodes, wherein the one or more possible trajectory nodes are located within a predetermined minimum stopping distance of one or more predicted trajectory nodes in the plurality of predicted trajectory nodes. The controller is also programmed to determine one or more evaluation indicators for each of the plurality of possible trajectory nodes based at least in part on weather conditions in the vehicle's surroundings. The one or more evaluation indicators include a collision potential score, a maneuverability score, and a traffic violation score. The controller is also programmed to select an optimal trajectory of the vehicle from the plurality of possible trajectories based at least in part on the one or more evaluation indicators for each of the plurality of possible trajectory nodes. The controller is also programmed to adjust operation of the automated driving system. The operation of the automated driving system is adjusted so that the vehicle leaves the lane boundary based at least in part on the optimal trajectory.

[0034] In another aspect of the present disclosure, in order to determine the collision potential score of each of a plurality of possible trajectory nodes, the controller is also programmed to determine a plurality of uncertainties. The plurality of uncertainties include a plurality of predicted trajectory uncertainties and a plurality of possible trajectory uncertainties. Each of the plurality of predicted trajectory uncertainties corresponds to one of a plurality of predicted trajectory nodes. Each of the plurality of possible trajectory uncertainties corresponds to one of a plurality of possible trajectory nodes. In order to determine the collision potential score of each of a plurality of possible trajectory nodes, the controller is also programmed to determine a plurality of predicted trajectory uncertainties with deviations and a plurality of possible trajectory uncertainties with deviations by applying a deviation to each of the plurality of predicted trajectory uncertainties and each of the plurality of possible trajectory uncertainties. The deviation is based at least in part on the weather conditions of the vehicle's surroundings. In order to determine the collision potential score of each of a plurality of possible trajectory nodes, the controller is also programmed to determine the collision potential score of each of a plurality of possible trajectory nodes based at least in part on a plurality of predicted trajectory uncertainties with deviations and a plurality of possible trajectory uncertainties with deviations.

[0035] In another aspect of the present disclosure, in order to select the best trajectory, the controller is further programmed to select a subset of the plurality of possible trajectory nodes as the best trajectory. The subset of the plurality of possible trajectory nodes is selected to minimize the objective function:

[0036]

[0037] Where c is the objective function, N is the number of nodes in a subset of multiple possible trajectory nodes, and p i is the collision potential score of the ith node in a subset of multiple possible trajectory nodes, v i is the traffic violation score of the i-th node in a subset of multiple possible trajectory nodes, and m i is the operability score of the ith node in the subset of the plurality of possible trajectory nodes. Each subset of the plurality of possible trajectory nodes is from the same one of the plurality of possible trajectories. A first node in the subset of the plurality of possible trajectory nodes and a second node in the subset of the plurality of possible trajectory nodes have a collision potential score less than 1.

[0038] Further areas of applicability will become apparent from the description provided herein.It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way.

[0040] Figure 1 is a schematic diagram of a system for vehicle path planning according to an exemplary embodiment;

[0041] Figure 2 is a schematic diagram of a first exemplary road scene according to an exemplary embodiment;

[0042] Figure 3 is a flow chart of a method for vehicle path planning according to an exemplary embodiment;

[0043] Figure 4 is a schematic diagram of a second exemplary road scenario including uncertainty according to an exemplary embodiment;

[0044] Figure 5 is a flow chart of a method for determining a collision potential score according to an exemplary embodiment;

[0045] Figure 6 is a schematic diagram of a third exemplary road scenario including uncertainty with bias according to an exemplary embodiment; and

[0046] Figure 7 is a flow chart of a method for determining a maneuverability score according to an exemplary embodiment. DETAILED DESCRIPTION

[0047] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses.

[0048] Adverse weather conditions, such as extremely high or low temperatures, precipitation, and / or the like, may result in adverse road conditions, such as wet, icy, and / or snowy road conditions. Vehicle dynamics may be affected by the aforementioned weather and / or road conditions, resulting in changes in handling characteristics, driving characteristics, vehicle performance, etc. In addition, adverse weather and / or road conditions may present situations where evasive or other unconventional actions are required to avoid collisions. Therefore, the present disclosure provides a new and improved system and method for vehicle path planning that takes into account the effects of weather and road conditions on vehicle dynamics, and takes into account the use of unconventional actions to avoid collisions in extreme weather conditions.

[0049] refer to Figure 1 , a system for vehicle path planning is shown and generally designated by reference numeral 10. The system 10 is shown with an exemplary vehicle 12. Although a passenger vehicle is shown, it should be understood that the vehicle 12 may be any type of vehicle without departing from the scope of the present disclosure. The system 10 generally includes a controller 14, a plurality of vehicle sensors 16, and an autonomous driving system 18.

[0050] The controller 14 is used to implement the method 100 for vehicle path planning, as will be described below. The controller 14 includes at least one processor 20 and a non-transitory computer-readable storage device or medium 22. The processor 20 can be a customized or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor of several processors associated with the controller 14, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination of the above, or a device generally used to execute instructions. The computer-readable storage device or medium 22 may include, for example, volatile and non-volatile storage devices in a read-only memory (ROM), a random access memory (RAM), and a keep-alive memory (KAM). KAM is a persistent or non-volatile memory that can be used to store various operating variables when the processor 20 is powered off. The computer readable storage device or medium 22 may be implemented using a plurality of storage devices, such as a PROM (programmable read-only memory), an EPROM (electrical PROM), an EEPROM (electrically erasable PROM), flash memory, or other electrical, magnetic, optical, or combination thereof memory capable of storing data (some of which represents executable instructions) that is used by the controller 14 to control the various systems of the vehicle 12. The controller 14 may also be comprised of a plurality of controllers that are in electrical communication with one another. The controller 14 may be interconnected with additional systems and / or controllers of the vehicle 12, thereby allowing the controller 14 to access data, such as the speed, acceleration, braking, and steering angle of the vehicle 12.

[0051] The controller 14 is in electrical communication with a plurality of vehicle sensors 16 and an autonomous driving system 18. In an exemplary embodiment, the electrical communication is established using, for example, a CAN network, a FLEXRAY network, a local area network (e.g., WiFi, Ethernet, etc.), a serial peripheral interface (SPI) network, etc. It should be understood that various additional wired and wireless technologies and communication protocols for communicating with the controller 14 are within the scope of the present disclosure.

[0052] A plurality of vehicle sensors 16 are used to acquire information related to the vehicle 12 . In the exemplary embodiment, the plurality of vehicle sensors 16 include a camera system 24 , a vehicle communication system 26 , and a global navigation satellite system (GNSS) 28 .

[0053] In another exemplary embodiment, the plurality of vehicle sensors 16 further include sensors for determining performance data regarding the vehicle 12. In a non-limiting example, the plurality of vehicle sensors 16 further include at least one of a motor speed sensor, a 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.

[0054] In another exemplary embodiment, the plurality of vehicle sensors 16 also include sensors for determining information about the environment within the vehicle 12. In a non-limiting example, the plurality of vehicle sensors 16 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, etc.

[0055] In another exemplary embodiment, the plurality of vehicle sensors 16 also include sensors for determining information about the environment surrounding the vehicle 12. In a non-limiting example, the plurality of vehicle sensors 16 also include at least one of an ambient air temperature sensor, an atmospheric pressure sensor, and / or a camera and / or video camera positioned to observe the environment in front of the vehicle 12.

[0056] In another exemplary embodiment, at least one of the plurality of vehicle sensors 16 is a perception sensor capable of perceiving objects in the environment surrounding the vehicle 12 and / or measuring distances. In a non-limiting example, the plurality of vehicle sensors 16 include a stereo camera with distance measurement capabilities. In one example, at least one of the plurality of vehicle sensors 16 is fixed inside the vehicle 12, such as in the roof of the vehicle 12, with a view through the windshield of the vehicle 12. In another example, at least one of the plurality of vehicle sensors 16 is fixed outside the vehicle 12, such as on the roof of the vehicle 12, with a view of the environment surrounding the vehicle 12. It should be understood that various additional types of perception sensors, such as LiDAR sensors, ultrasonic ranging sensors, radar sensors, and / or time-of-flight sensors are within the scope of the present disclosure. The plurality of vehicle sensors 16 are in electrical communication with the controller 14 as described above.

[0057] The camera system 24 is a perception sensor for capturing images and / or video of the environment surrounding the vehicle 12. In an exemplary embodiment, the camera system 24 includes a still camera and / or video camera positioned to view the environment surrounding the vehicle 12. In a non-limiting example, the camera system 24 includes a camera fixed to the interior of the vehicle 12, such as fixed to the roof of the vehicle 12, with a field of view through the windshield. In another non-limiting example, the camera system 24 includes a camera fixed to the exterior of the vehicle 12, such as fixed to the roof of the vehicle 12, with a field of view of the environment in front of the vehicle 12.

[0058] In another exemplary embodiment, the camera system 24 is a surround view camera system that includes multiple cameras (also referred to as satellite cameras) arranged to provide a view of the environment adjacent to all sides of the vehicle 12. In a non-limiting example, the camera system 24 includes a forward-facing camera (e.g., mounted in the front grille of the vehicle 12), a rear-facing camera (e.g., mounted on the tailgate of the vehicle 12), and two side-facing cameras (e.g., mounted below each of the two side-view mirrors of the vehicle 12). In another non-limiting example, the camera system 24 also includes an additional rear-view camera mounted near the center high-mounted brake light of the vehicle 12.

[0059] It should be understood that camera systems with additional cameras and / or additional mounting locations are within the scope of the present disclosure. 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 the present disclosure. In addition, cameras with various lens types, including, for example, wide angle lenses and / or narrow angle lenses, are also within the scope of the present disclosure.

[0060] The controller 14 uses the vehicle communication system 26 to communicate with other systems outside the vehicle 12. For example, the vehicle communication system 26 includes the ability to communicate with vehicles ("V2V" communication), with infrastructure ("V2I" communication), with remote systems at a remote call center (e.g., ON-STAR of GENERAL MOTORS), and / or with personal devices. In general, the term vehicle-to-everything communication ("V2X" communication) refers to communication between the vehicle 12 and any remote system (e.g., vehicle, infrastructure, and / or remote system). In some embodiments, the vehicle communication system 26 is a wireless communication system that is 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 SGP.02, SGP.22, SGP.32, etc.). Therefore, the vehicle communication system 26 may also include an embedded universal integrated circuit card (eUICC) that is configured to store at least one cellular connection profile, such as an embedded subscriber identity module (eSIM) file. The vehicle communication system 26 is also configured to communicate via a personal area network (e.g., Bluetooth) and / or near field communication (NFC). However, additional or alternative communication methods such as dedicated short-range communication (DSRC) channels and / or mobile telecommunication protocols based on the third generation partnership project (3GPP) standard are also considered to be within the scope of the present disclosure. A DSRC channel refers to a one-way or two-way short-range to medium-range wireless communication channel designed specifically for automotive use and a set of corresponding protocols and standards. 3GPP refers to a partnership between several standard organizations that develop protocols and standards for mobile telecommunications. The structure of the 3GPP standard is "release". Therefore, communication methods based on 3GPP releases 14, 15, 16 and / or future 3GPP releases are considered to be within the scope of the present disclosure. Therefore, the vehicle communication system 26 may include one or more antennas and / or communication transceivers for receiving and / or transmitting signals, such as collaborative sensing messages (CSM). The vehicle communication system 26 is configured to wirelessly transmit information between the vehicle 12 and another vehicle. In addition, the vehicle communication system 26 is configured to wirelessly transmit information between the vehicle 12 and infrastructure or other vehicles. It should be understood that the vehicle communication system 26 can be integrated with the controller 14 (e.g., integrated on the same circuit board as the controller 14 or otherwise integrated as part of the controller 14) without departing from the scope of the present disclosure.

[0061] GNSS28 is used to determine the geographic location of vehicle 12. In an exemplary embodiment, GNSS28 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 a plurality of satellites, and the GPS controller calculates the geographic location of vehicle 12 based on the signals received by the GPS receiver antenna. In an exemplary embodiment, GNSS28 also includes a map. The map includes information about infrastructure, such as municipal boundaries, roads, railways, sidewalks, buildings, etc. Therefore, the map information is used to consider the geographic location of vehicle 12 in context. In a non-limiting example, a wireless connection is used to retrieve a map from a remote source. In another non-limiting example, the map is stored in a database of GNSS28. It should be understood that various additional types of satellite-based radio navigation systems are within the scope of the present disclosure, such as the Global Positioning System (GPS), the Galileo system (Galileo), GLONASS, and the Beidou Navigation Satellite System (BDS). It should be appreciated that the GNSS 28 may be integrated with the controller 14 (eg, on the same circuit board as the controller 14 or otherwise integrated as part of the controller 14) without departing from the scope of the present disclosure.

[0062] The automated driving system 18 is used to provide assistance to the occupants to increase the occupant's awareness and / or control the behavior of the vehicle 12. Within the scope of the present disclosure, the automated driving system 18 encompasses systems that provide any level of assistance to the occupants (e.g., blind spot warning, lane departure warning, etc.) as well as systems that are capable of automatically driving the vehicle 12 under some or all conditions (e.g., automatic lane keeping, adaptive cruise control, fully automated driving, etc.). It should be understood that all levels of driving automation, such as defined by SAE J3016 (i.e., SAE Level 0, SAE Level 1, SAE Level 2, SAE Level 3, SAE Level 4, and SAE Level 5) are within the scope of the present disclosure.

[0063] In an exemplary embodiment, the autonomous driving system 18 is configured to detect and / or receive information about the environment surrounding the vehicle 12 and process the information to provide assistance to the occupants. In some embodiments, the autonomous driving system 18 is a software module executed on the controller 14. In other embodiments, the autonomous driving system 18 includes a separate autonomous driving system controller similar to the controller 14, which is capable of processing information about the environment surrounding the vehicle 12. In an exemplary embodiment, the autonomous driving system 18 can operate in a manual operating mode, a partially automated operating mode, and a fully automated operating mode.

[0064] Within the scope of this disclosure, manual operation mode refers to the autonomous driving system 18 providing warnings or notifications to the occupants, but not directly intervening or controlling the vehicle 12. In a non-limiting example, the autonomous driving system 18 receives information from a plurality of vehicle sensors 16. Using techniques such as computer vision, the autonomous driving system 18 understands the environment around the vehicle 12 and provides assistance to the occupants. For example, if the autonomous driving system 18 identifies that the vehicle 12 may collide with a remote vehicle based on data from the plurality of vehicle sensors 16, the autonomous driving system 18 may use a display to provide a warning to the occupants.

[0065] Within the scope of the present disclosure, a partially automated mode of operation means that the autonomous driving system 18 provides warnings or notifications to the occupants and may directly intervene or control the vehicle 12 in certain circumstances. In a non-limiting example, the autonomous driving system 18 is in additional electrical communication with components of the vehicle 12, such as the braking system, propulsion system, and / or steering system of the vehicle 12, so that the autonomous driving system 18 can control the behavior of the vehicle 12. In a non-limiting example, the autonomous driving system 18 can control the behavior of the vehicle 12 by applying the brakes of the vehicle 12 to avoid an imminent collision. In another non-limiting example, the autonomous driving system 18 can control the steering system of the vehicle 12 to provide an automatic lane keeping feature. In another non-limiting example, the autonomous driving system 18 can control the braking system, propulsion system, and steering system of the vehicle 12 to temporarily drive the vehicle 12 toward a predetermined destination. However, occupant intervention may be required at any time. In an exemplary embodiment, the autonomous driving system 18 may include additional components, such as an eye tracking device configured to monitor the occupant's attention level and ensure that the occupant is ready to take over control of the vehicle 12.

[0066] Within the scope of the present disclosure, a fully automated mode of operation refers to the automated driving system 18 using data from the plurality of vehicle sensors 16 to understand the environment and control the vehicle 12 to drive the vehicle 12 to a predetermined destination without requiring control or intervention by an occupant.

[0067] The automated driving system 18 operates using a path planning algorithm that is configured to generate a safe and efficient trajectory for the vehicle 12 to navigate the environment around the vehicle 12. In an exemplary embodiment, the path planning algorithm is a machine learning algorithm that is trained to output control signals for the vehicle 12 based on input data collected from the plurality of vehicle sensors 16. In another exemplary embodiment, the path planning algorithm is a deterministic algorithm that has been programmed to output control signals for the vehicle 12 based on data collected from the plurality of vehicle sensors 16.

[0068] In a non-limiting example, the path planning algorithm generates a series of waypoints or a continuous path that the vehicle 12 should follow to reach the destination while complying with rules, regulations, and safety constraints. A series of waypoints or a continuous path is generated based at least in part on a detailed map and the current state of the vehicle 12 (i.e., the position, speed, and direction of the vehicle 12). The detailed map includes, for example, information about lane boundaries, road geometry, speed limits, traffic signs, and / or other relevant features. In an exemplary embodiment, the detailed map is stored in the medium 22 of the controller 14 and / or on a remote database or server. In another exemplary embodiment, the path planning algorithm performs perception and mapping tasks to interpret data collected from multiple vehicle sensors 16 and create, update, and / or augment the detailed map. In some examples, the path planning algorithm can be configured to generate multiple possible trajectories. The best trajectory is then selected for use by the autonomous driving system 18, as will be discussed in more detail below.

[0069] It should be understood that the autonomous driving system 18 may include any software and / or hardware modules configured to operate in a manual operation mode, a partially automated operation mode, or a fully automated operation mode as described above.

[0070] refer to Figure 2 , a schematic diagram of a first exemplary road scene 30a is shown. The first exemplary road scene 30a includes the vehicle 12 and the remote vehicle 32. The first exemplary road scene 30a also includes a predicted trajectory 34 of the remote vehicle 32. Within the scope of the present disclosure, the predicted trajectory 34 describes the predicted path of the remote vehicle 32, as will be discussed in more detail below. The predicted trajectory 34 includes a plurality of predicted trajectory nodes 36. In an exemplary embodiment, the plurality of predicted trajectory nodes 36 describe points along the predicted trajectory 34 and are positioned based on the predicted speed of the remote vehicle 32. In a non-limiting example, the plurality of predicted trajectory nodes 36 are positioned so that the time required to travel between any two adjacent predicted trajectory nodes 36 is equal to a predetermined node interval time (e.g., one second) based on the predicted speed of the remote vehicle 32. Although the first exemplary road scene 30a includes a single remote vehicle 32, it should be understood that the system 10 and method 100 of the present disclosure are also applicable to situations involving multiple remote vehicles.

[0071] The first exemplary road scene 30a also includes a plurality of possible trajectories 38 of the vehicle 12. Within the scope of the present disclosure, the plurality of possible trajectories 38 include at least two possible paths that the vehicle 12 can take, as will be discussed in more detail below. The plurality of possible trajectories 38 include a plurality of possible trajectory nodes 40. In an exemplary embodiment, the plurality of possible trajectory nodes 40 describe points along the plurality of possible trajectories 38 and are positioned based on the speed of the vehicle 12. In a non-limiting example, the plurality of possible trajectory nodes 40 are positioned so that the time required to travel between any two adjacent possible trajectory nodes 40 is equal to a predetermined node interval time (e.g., one second) based on the speed of the vehicle 12. The first subset 40a of the plurality of possible trajectory nodes 40 is from the first possible trajectory 38a of the plurality of possible trajectories 38. The second subset 40b of the plurality of possible trajectory nodes 40 is from the second possible trajectory 38b of the plurality of possible trajectories 38. In the first exemplary road scene 30a, the plurality of possible trajectories 38 include two possible trajectories 38 (i.e., the first possible trajectory 38a and the second possible trajectory 38b). However, it should be understood that the plurality of possible trajectories 38 may include more than two possible trajectories without departing from the scope of the present disclosure.

[0072] refer to Figure 3 , a flow chart of a method 100 for vehicle path planning is shown. Figure 3 And continue to refer to Figure 2 , the method 100 begins at block 102 and proceeds to block 104. At block 104, the controller 14 determines a predicted trajectory 34 of the remote vehicle 32. In an exemplary embodiment, to determine the predicted trajectory 34, the controller 14 uses a plurality of vehicle sensors 16 to receive information about the remote vehicle 32. In a non-limiting example, the information includes one or more measurements of the remote vehicle 32, such as a position of the remote vehicle 32, a speed of the remote vehicle 32, a heading of the remote vehicle 32, and the like.

[0073] In another exemplary embodiment, the controller 14 uses the vehicle communication system 26 to receive information about the remote vehicle 32. In a non-limiting example, the controller 14 uses the vehicle communication system 26 to receive V2V (vehicle-to-vehicle) communications from the remote vehicle 32. The V2V communications may include information such as the location of the remote vehicle 32, the speed of the remote vehicle 32, the heading of the remote vehicle 32, the expected path of the remote vehicle 32, etc. In another non-limiting example, the controller 14 uses the vehicle communication system 26 to receive V2I (vehicle-to-infrastructure) communications including information about the remote vehicle 32 from infrastructure (e.g., traffic control devices, traffic cameras, etc.).

[0074] The controller 14 then uses a path prediction algorithm to determine a predicted trajectory 34 based at least in part on the information about the remote vehicle 32. In a non-limiting example, the path prediction algorithm is a deterministic algorithm that uses a set of rules to determine the predicted trajectory 34 based on the information about the remote vehicle 32. In another non-limiting example, the path prediction algorithm is a machine learning algorithm, such as a convolutional neural network (CNN), a reinforcement learning algorithm, etc. After block 104, the method 100 proceeds to block 106.

[0075] At box 106, the controller 14 determines a plurality of possible trajectories 38 for the vehicle 12. In an exemplary embodiment, to determine the plurality of possible trajectories 38, the controller 14 uses a plurality of vehicle sensors 16 to receive information about the environment surrounding the vehicle 12. The controller 14 then uses a path planning algorithm of the autonomous driving system 18 to generate the plurality of possible trajectories 38 based on the information about the environment surrounding the vehicle 12.

[0076] In an exemplary embodiment, a proximity check of the plurality of possible trajectories 38 is performed. The proximity check includes removing trajectories that are too close to the predicted trajectory 34 from the plurality of possible trajectories 38. In a non-limiting example, if a given node (e.g., a first node) in the plurality of possible trajectory nodes 40 is within a predetermined distance from any node (e.g., the first node) in the plurality of predicted trajectory nodes 36, then a possible trajectory in the plurality of possible trajectories 38 that includes the given node is determined to be too close and removed from the plurality of possible trajectories 38. In a non-limiting example, the predetermined distance is a predetermined minimum stopping distance required to bring the vehicle 12 to a complete stop based at least in part on weather and / or road conditions.

[0077] In an exemplary embodiment, the predetermined minimum stopping distance required for vehicle 12 to come to a complete stop is calculated using the following formula:

[0078]

[0079] Among them, D P is the predetermined minimum stopping distance, d BR is the braking reaction distance (ie, the distance traveled by the vehicle 12 before the brakes are applied), d B is the braking distance (ie, the distance traveled by the vehicle 12 when the brakes are applied), V is the longitudinal speed of the vehicle 12, t is the braking reaction time, and μ is the road surface friction coefficient. The road surface friction coefficient is based at least in part on weather and / or road surface conditions.

[0080] It is contemplated that in some examples, when alternative trajectories involve a high risk of collision, trajectories that include traffic violations (e.g., trajectories that require vehicle 12 to leave lane boundaries) may be optimal. Therefore, trajectories that involve traffic violations but are not too close to predicted trajectory 34 are not eliminated from multiple possible trajectories 38 during the proximity check.

[0081] After frame 106, method 100 proceeds to frames 108, 110, and 112 to determine one or more evaluation indicators for each of the plurality of possible trajectory nodes 40. In an exemplary embodiment, the one or more evaluation indicators include a collision potential score, a maneuverability score, and a traffic violation score. Within the scope of the present disclosure, the one or more evaluation indicators are indicators for quantifying the optimality of each of the plurality of possible trajectories 38.

[0082] At block 108 , the controller 14 determines a collision potential score for each of the plurality of possible trajectory nodes 40 , as will be discussed in greater detail below. Following block 108 , the method 100 proceeds to block 114 , as will be discussed in greater detail below.

[0083] At block 110 , the controller 14 determines a maneuverability score for each of the plurality of possible trajectory nodes 40 , as will be discussed in greater detail below. Following block 110 , the method 100 proceeds to block 114 , as will be discussed in greater detail below.

[0084] At box 112, the controller 14 determines a traffic violation score for each of the plurality of possible trajectory nodes 40. Within the scope of the present disclosure, the traffic violation score quantifies the legality of maneuvering the vehicle 12 to each of the plurality of possible trajectory nodes 40. In a non-limiting example, a higher traffic violation score indicates that maneuvering the vehicle 12 to a given one of the plurality of possible trajectory nodes is more illegal. In an exemplary embodiment, to determine the traffic violation score, the controller 14 evaluates the position of each of the plurality of possible trajectory nodes 40 against known road geometry (e.g., from a detailed map used by a path planning algorithm of the autonomous driving system 18 and / or a map included in the GNSS 28).

[0085] In a non-limiting example, if a first given node in the plurality of possible trajectory nodes 40 is located in an oncoming travel lane (i.e., requiring the vehicle 12 to travel in the wrong direction on a one-way travel lane), the traffic violation score of the first given node is determined to be one (1). If a second given node in the plurality of possible trajectory nodes 40 is located in a non-road area (i.e., requiring the vehicle 12 to leave the road and travel on a shoulder, median, sidewalk, etc.), the traffic violation score of the second given node is determined to be one-half (0.5). If a third given node in the plurality of possible trajectory nodes 40 is not located in a non-road area and is not located in an oncoming travel lane, the traffic violation score of the third given node is determined to be zero (0).

[0086] It should be understood that the above-described scenarios and traffic violation scores are merely exemplary in nature. Without departing from the scope of the present disclosure, the traffic violation score may be a continuous value. Without departing from the scope of the present disclosure, other methods may be used to determine the traffic violation score, including, for example, a machine learning algorithm trained to determine the traffic violation score, a rule-based algorithm configured to determine the traffic violation score based on a set of known traffic rules, etc. In addition, it is conceivable that in some examples, when alternative trajectories involve a high risk of collision, a trajectory that includes a traffic violation (e.g., a trajectory that requires the vehicle 12 to leave the lane boundary) may be optimal. After frame 112, the method 100 proceeds to frame 114.

[0087] At box 114, the controller 14 selects an optimal trajectory based at least in part on one or more evaluation metrics (i.e., collision potential score, maneuverability score, and traffic violation score). In an exemplary embodiment, the optimal trajectory is a subset of the plurality of possible trajectory nodes 40 that minimizes the sum of the collision potential score, maneuverability score, and traffic violation score for each subset of the plurality of possible trajectory nodes 40. In a non-limiting example, the subset of the plurality of possible trajectory nodes 40 is selected to minimize the objective function:

[0088]

[0089] Where c is the objective function, N is the number of nodes in the subset of multiple possible trajectory nodes 40, and p i is the collision potential score of the ith node in the subset of the plurality of possible trajectory nodes 40, v i is the traffic violation score of the ith node in the subset of the plurality of possible trajectory nodes 40, and m i is the operability score of the ith node in the subset of the plurality of possible trajectory nodes 40 .

[0090] The objective function includes two constraints. The first constraint is that each of the subset of the plurality of possible trajectory nodes 40 is from the same one of the plurality of possible trajectories 38. This means that the best trajectory can only contain nodes from one of the plurality of possible trajectories 38. The second constraint is that the first node of the subset of the plurality of possible trajectory nodes 40 and the second node of the subset of the plurality of possible trajectory nodes 40 must have a collision potential score less than 1. This means that the best trajectory can only be one of the plurality of possible trajectories 38 that does not cause the remote vehicle 32 to collide with the first two nodes of the subset of the plurality of possible trajectory nodes 40.

[0091] factor The evaluation metrics of nodes in the subset of the plurality of possible trajectory nodes 40 that are farther from the vehicle 12 are reduced. Thus, the objective function is biased toward the evaluation metrics of nodes that are closer to the vehicle 12, because the evaluation metrics of nodes that are farther from the vehicle 12 may change as the vehicle 12 gets closer and receives more and / or new information.

[0092] It should be understood that any mathematical optimization technique for finding one of the plurality of possible trajectories 38 that minimizes the objective function (Equation 1), including, for example, iterative methods (e.g., Newton's method, gradient descent, etc.), heuristic methods (e.g., differential evolution, genetic algorithms, hill climbing algorithms, etc.), etc., are within the scope of the present disclosure. After block 114, the method 100 proceeds to block 116.

[0093] At box 116, the controller 14 performs a first action. In an exemplary embodiment, the first action includes adjusting the operation of the autonomous driving system 18. In a non-limiting example, the path planning algorithm is adjusted so that the optimal trajectory selected at box 114 is used for further control and navigation of the vehicle 12. It is contemplated that in some examples, a trajectory that includes a traffic violation (e.g., a trajectory that requires the vehicle 12 to leave the lane boundary) may be optimal when alternative trajectories involve a high risk of collision. Therefore, in some examples, at box 116, the vehicle 12 takes an action that includes a traffic violation based on the optimal trajectory selected at box 114.

[0094] In another exemplary embodiment, the first action includes the controller 14 transmitting the optimal trajectory to an external system, such as a remote vehicle (e.g., remote vehicle 32), a traffic control infrastructure, a remote server system, etc., using the vehicle communication system 26. The remote systems that receive the optimal trajectory from the vehicle 12 may be configured to adjust their operations based on the optimal trajectory of the vehicle 12. For example, the remote systems that receive the optimal trajectory from the vehicle 12 may be configured to take actions to reduce collision risk, optimize traffic flow, provide information to road users, etc. After frame 116, the method 100 continues at frame 118 to enter a standby state.

[0095] In an exemplary embodiment, the controller 14 repeatedly exits the standby state 118 and restarts the method 100 at block 102. In a non-limiting example, the controller 14 exits the standby state 118 and restarts the method 100 based on a timer, such as every three hundred milliseconds.

[0096] refer to Figure 4 , a schematic diagram of a second exemplary road scene 30b including uncertainties is shown. The second exemplary road scene 30b includes all elements of the first exemplary road scene 30a (i.e., vehicle 12, remote vehicle 32, predicted trajectory 34, and multiple possible trajectories 38). However, the second exemplary road scene 30b also includes multiple uncertainties 50. Within the scope of the present disclosure, each of the multiple uncertainties 50 is a two-dimensional area around each of the multiple predicted trajectory nodes 36 and each of the multiple possible trajectory nodes 40, which defines the uncertainty of the position of each of the multiple predicted trajectory nodes 36 and the position of each of the multiple possible trajectory nodes 40. The multiple uncertainties 50 include multiple predicted trajectory uncertainties 50a and multiple possible trajectory uncertainties 50b.

[0097] refer to Figure 5 , a flow chart of an exemplary embodiment 108a of block 108 is shown. The exemplary embodiment 108a begins at block 502. Figure 4 and Figure 5 , at box 502, the controller 14 determines a plurality of uncertainties 50. In an exemplary embodiment, each of the plurality of uncertainties 50 is a two-dimensional Gaussian probability distribution. In a non-limiting example, one or more parameters (e.g., a covariance matrix) of the two-dimensional Gaussian probability distribution of each of the plurality of uncertainties 50 are determined based at least in part on weather conditions and / or road conditions in the environment surrounding the vehicle 12. In another non-limiting example, one or more parameters of the two-dimensional Gaussian probability distribution of each of the plurality of uncertainties 50 are determined based on known errors of one or more vehicle sensors in the plurality of vehicle sensors 16 (e.g., known positioning errors of the GNSS 28).

[0098] In an exemplary embodiment, multiple vehicle sensors 16 are used to determine weather conditions. In a non-limiting example, camera system 24 is used to capture one or more images of the environment surrounding vehicle 12, and weather conditions are inferred from the one or more images. In another non-limiting example, vehicle communication system 26 is used to receive weather information from a remote vehicle (e.g., remote vehicle 32) and / or a remote server system. For example, in inclement weather and / or poor road conditions, the position uncertainty of vehicle 12 and / or remote vehicle 32 may be higher due to potential extended stopping distances, larger turning radius, loss of traction, etc.

[0099] It should be understood that additional methods for determining parameters of the plurality of uncertainties 50 may be used without departing from the scope of the present disclosure, including, for example, the systems and methods disclosed in U.S. Application No. 18 / 335,758, filed on June 15, 2023, entitled “END-TO-END PERCEPTION PERTURBATION MODELING SYSTEM FOR A VEHICLE”, the entire contents of which are incorporated herein by reference. After box 502, the exemplary embodiment 108a proceeds to box 504 and box 506.

[0100] At box 504, the controller 14 determines the longitudinal deviation of each of the multiple possible trajectory nodes 40 and each of the multiple predicted trajectory nodes 36. In an exemplary embodiment, the longitudinal deviation is determined at least in part based on longitudinal following driving behavior modeling. In a non-limiting example, the Gipps following model is used to determine the longitudinal deviation. In another non-limiting example, the longitudinal deviation is determined at least in part based on weather conditions in the environment surrounding the vehicle 12, for example, as disclosed in U.S. application No. 18 / 340,249, entitled "PROBABILISTIC DRIVING BEHAVIOR MODELING SYSTEM FOR AVEHICLE" filed on June 23, 2023, the entire contents of which are incorporated herein by reference. After box 504, the exemplary embodiment 108a proceeds to box 508, as will be discussed in more detail below.

[0101] At block 506, the controller 14 determines a lateral deviation for each of the plurality of possible trajectory nodes 40 and each of the plurality of predicted trajectory nodes 36. In an exemplary embodiment, the lateral deviation is determined at least in part based on a dynamics-based model that takes into account weather conditions in the environment surrounding the vehicle 12. In a non-limiting example, the dynamics-based model is a mathematical model of the vehicle that is capable of determining the lateral motion of the vehicle 12 based on a plurality of parameters. Thus, the dynamics-based model outputs a lateral deviation for each of the plurality of possible trajectory nodes 40 and each of the plurality of predicted trajectory nodes 36 based on the plurality of parameters.

[0102] The plurality of parameters include vehicle parameters, such as vehicle speed, vehicle acceleration, vehicle steering angle, vehicle braking force, tire tread wear, tire temperature, etc. The plurality of parameters also include weather and / or road condition parameters, such as road surface temperature, road surface moisture level, amount of water, snow, sleet, or hail on the road surface, precipitation rate on the road surface, wind speed, etc. In an exemplary embodiment, the plurality of parameters are received using a plurality of vehicle sensors 16 .

[0103] In an exemplary embodiment, the dynamics-based model uses the Burckhardt method to determine the lateral acceleration of the vehicle based on weather and / or road conditions, as discussed in "An Observer of Tire-Road Forces and Friction for Active Security Vehicle Systems" by Baffet et al., IEEE / ASME TRANSACTIONS ON MECHATRONICS Journal, Vol. 12, No. 6, December 2007, pp. 651-661, the entire contents of which are incorporated herein by reference. After frame 506, the exemplary embodiment 108a proceeds to frame 508.

[0104] refer to Figure 6 , a schematic diagram of a third exemplary road scene 30c including uncertainty with deviations is shown. The third exemplary road scene 30c includes all elements of the first exemplary road scene 30a (i.e., the vehicle 12, the remote vehicle 32, the predicted trajectory 34, and the plurality of possible trajectories 38). However, the third exemplary road scene 30c also includes a plurality of uncertainties with deviations 60. Within the scope of the present disclosure, each of the plurality of uncertainties with deviations 60 is a two-dimensional area around each of the plurality of predicted trajectory nodes 36 and each of the plurality of possible trajectory nodes 40, which defines the uncertainty with deviations of the position of each of the plurality of predicted trajectory nodes 36 and the position of each of the plurality of possible trajectory nodes 40 based on the longitudinal deviation determined at box 504 and the lateral deviation determined at box 506. The plurality of uncertainties with deviations 60 include a plurality of predicted trajectory uncertainties 60a with deviations and a plurality of possible trajectory uncertainties 60b with deviations.

[0105] refer to Figure 5 and Figure 6 At box 508, the controller 14 generates a plurality of biased predicted trajectory uncertainties 60a by applying the longitudinal bias determined at box 504 and the lateral bias determined at box 506 to each of the plurality of predicted trajectory uncertainties 50a. The controller 14 also generates a plurality of biased possible trajectory uncertainties 60b by applying the longitudinal bias determined at box 504 and the lateral bias determined at box 506 to each of the plurality of possible trajectory uncertainties 50b.

[0106] In an exemplary embodiment, the longitudinal deviation and the lateral deviation are applied to each of the plurality of uncertainties 50 using the following formula:

[0107]

[0108] in, is one of a plurality of biased uncertainties 60, I is the identity matrix, is one of the uncertainties 50, H k is the measurement model, and R k is one of the longitudinal bias determined at block 504 or the lateral bias determined at block 506. Equation 3 is used twice for each of the plurality of uncertainties 50, once to apply the longitudinal bias and once to apply the lateral bias. After block 508, the exemplary embodiment 108a proceeds to block 510.

[0109] At block 510, the controller 14 determines a collision potential score for each of the plurality of possible trajectory nodes 40 based at least in part on the plurality of biased predicted trajectory uncertainties 60a and the plurality of predicted trajectory uncertainties 50a. In an exemplary embodiment, the collision potential score for each of the plurality of possible trajectory nodes 40 is defined by:

[0110]

[0111] Among them, p i is the collision potential score of the ith node among the plurality of possible trajectory nodes 40, r i is one of the plurality of biased predicted trajectory uncertainties 60a corresponding to the i-th node in the plurality of predicted trajectory nodes 36, e i is one of the plurality of biased possible trajectory uncertainties 60b corresponding to the i-th node in the plurality of possible trajectory nodes 40, ∩ is an intersection operator, and ∪ is a union operator. In other words, the collision potential score is related to the overlap between the plurality of biased predicted trajectory uncertainties 60a and the plurality of biased possible trajectory uncertainties 60b. After block 510, the exemplary embodiment 108a ends, and the method 100 continues as described above.

[0112] refer to Figure 7 , a flow chart of an exemplary embodiment 110a of the block 110 is shown. The exemplary embodiment 110a begins at block 702 and block 704. At block 702, the controller 14 determines the maximum torque available from the propulsion system (e.g., internal combustion engine, hybrid electric drive, all-electric drive, etc.) of the vehicle 12. In the exemplary embodiment, the maximum torque available is predetermined and stored in the medium 22 of the controller 14. After block 702, the exemplary embodiment 110a proceeds to block 706, as will be discussed in more detail below.

[0113] At box 704, the controller 14 determines the estimated propulsion system torque required to reach each of the multiple possible trajectory nodes 40. In an exemplary embodiment, the estimated propulsion system torque required to reach a given node is determined at least in part based on a dynamics-based model that takes into account weather conditions in the environment surrounding the vehicle 12. In a non-limiting example, the dynamics-based model is a mathematical model of the vehicle that is capable of determining the estimated propulsion system torque required to reach a given node based on multiple parameters. Therefore, the dynamics-based model outputs an estimated propulsion system torque for each of the multiple possible trajectory nodes 40. It should be understood that in some examples, one or more of the multiple possible trajectory nodes 40 may be located in an area that is impossible to reach with the available torque anyway. Therefore, in the case where one or more of the multiple possible trajectory nodes 40 are, for example, located in a body of water, blocked by a wall or other obstacle, etc., the maneuverability score is determined to be a very large value (e.g., infinity).

[0114] The plurality of parameters include terrain parameters, such as road surface type (e.g., paved, dirt, sand, etc.), road surface condition (e.g., damaged road surface, recently resurfaced road surface, etc.), road elevation changes, etc. The plurality of parameters also include weather parameters, such as road surface temperature, road surface moisture level, amount of water, snow, sleet, or hail on the road surface, precipitation rate on the road surface, wind speed, etc. In an exemplary embodiment, the plurality of parameters are received using a plurality of vehicle sensors 16. After block 704, the exemplary embodiment 110a proceeds to block 706.

[0115] At block 706, the controller 14 determines a maneuverability score for each of the plurality of possible trajectory nodes 40 using the following formula:

[0116]

[0117] Among them, m i is the maneuverability score of the ith node among the multiple possible trajectory nodes 40, T i is the estimated propulsion system torque required to reach the i-th node of the plurality of possible trajectory nodes 40 determined at block 704, and T MAX is the maximum torque available from the propulsion system of the vehicle as determined at block 702. Following block 706, the exemplary embodiment 110a ends and the method 100 continues as described above.

[0118] The system 10 and method 100 of the present disclosure provide several advantages. By considering weather and / or road conditions to determine the optimal trajectory, the system 10 and method 100 of the present disclosure provide improved performance of the autonomous driving system 18, thereby improving the awareness and convenience of the vehicle 12 occupants. In addition, it is conceivable that in some examples, when alternative trajectories involve a high risk of collision, a trajectory that includes unconventional maneuvers (e.g., traffic violations) may be optimal. Therefore, the system 10 and method 100 of the present disclosure allow for consideration of evasion or other unconventional maneuvers, which may be necessary to avoid collisions in conditions involving severe weather. The description of the present disclosure is merely exemplary in nature, and changes that do not deviate from the subject matter of the present disclosure are intended to fall within the scope of the present disclosure. These changes should not be regarded as departing from the spirit and scope of the present disclosure.

Claims

1. A method for vehicle path planning, the method comprising: determining a predicted trajectory of a remote vehicle, wherein the predicted trajectory of the remote vehicle comprises a plurality of predicted trajectory nodes; determining a plurality of possible trajectories of the vehicle, wherein the plurality of possible trajectories comprises a plurality of possible trajectory nodes; determining one or more evaluation metrics for each of the plurality of possible trajectory nodes based at least in part on weather conditions in a surrounding environment of the vehicle; selecting an optimal trajectory for the vehicle from the plurality of possible trajectories based at least in part on the one or more evaluation metrics for each of the plurality of possible trajectory nodes; and A first action is performed based at least in part on the optimal trajectory.

2. The method of claim 1 , wherein the one or more evaluation metrics further include a collision potential score, and wherein determining the collision potential score for each of the plurality of possible trajectory nodes further includes: determining a plurality of uncertainties, wherein the plurality of uncertainties includes a plurality of predicted trajectory uncertainties and a plurality of possible trajectory uncertainties, wherein each of the plurality of predicted trajectory uncertainties corresponds to one of the plurality of predicted trajectory nodes, and wherein each of the plurality of possible trajectory uncertainties corresponds to one of the plurality of possible trajectory nodes; determining a plurality of biased predicted trajectory uncertainties and a plurality of biased possible trajectory uncertainties by applying a bias to each of the plurality of predicted trajectory uncertainties and to each of the plurality of possible trajectory uncertainties, wherein the bias is based at least in part on weather conditions in a surrounding environment of the vehicle; and The collision potential score for each possible trajectory node in the plurality of possible trajectory nodes is determined based at least in part on the plurality of biased predicted trajectory uncertainties and the plurality of biased possible trajectory uncertainties.

3. The method of claim 2, wherein determining the plurality of uncertainties further comprises: The plurality of uncertainties is determined based on at least one of: weather conditions in a surrounding environment of the vehicle and positioning errors of one or more of a plurality of vehicle sensors.

4. The method of claim 2, wherein determining the plurality of predicted trajectory uncertainties with deviations and the plurality of possible trajectory uncertainties with deviations further comprises: determining a longitudinal deviation of each of the plurality of possible trajectory nodes and each of the plurality of predicted trajectory nodes; determining a lateral deviation of each of the plurality of possible trajectory nodes and each of the plurality of predicted trajectory nodes, wherein the lateral deviation is determined based at least in part on a dynamically based model and weather conditions in a surrounding environment of the vehicle; applying the longitudinal bias and the lateral bias to each of the plurality of predicted trajectory uncertainties; as well as The longitudinal deviation and the lateral deviation are applied to each of the plurality of possible trajectory uncertainties.

5. The method of claim 2, wherein determining the collision potential score of each of the plurality of possible trajectory nodes further comprises: The collision potential score is determined using the following formula: Among them, p i is the collision potential score of the ith node among the multiple possible trajectory nodes, r i is one of the plurality of biased predicted trajectory uncertainties corresponding to the i-th node among the plurality of predicted trajectory nodes, e i is one of the plurality of biased possible trajectory uncertainties corresponding to the i-th node of the plurality of possible trajectory nodes, ∩ is an intersection operator, and ∪ is a union operator.

6. The method of claim 2, wherein the one or more evaluation metrics further include a maneuverability score, and wherein determining the maneuverability score for each of the plurality of possible trajectory nodes further includes: determining an estimated propulsion system torque required to reach each of the plurality of possible trajectory nodes; as well as The maneuverability score for each of the plurality of possible trajectory nodes is determined based at least in part on the estimated propulsion system torque using the following formula: Among them, m i is the maneuverability score of the i-th node among the multiple possible trajectory nodes, T i is the estimated propulsion system torque required to reach the i-th node among the plurality of possible trajectory nodes, and T MAX is the maximum torque available from the vehicle's propulsion system.

7. The method of claim 6, wherein the one or more evaluation metrics further include a traffic violation score, and wherein the traffic violation score quantifies the legality of maneuvering the vehicle to each of the plurality of possible trajectory nodes.

8. The method of claim 7, wherein selecting the optimal trajectory further comprises: A subset of the plurality of possible trajectory nodes is selected as the best trajectory, wherein the subset of the plurality of possible trajectory nodes is selected to minimize a sum of each of one or more evaluation metrics for each subset of the plurality of possible trajectory nodes.

9. The method of claim 7, wherein selecting the optimal trajectory further comprises: A subset of the plurality of possible trajectory nodes is selected as the optimal trajectory, wherein the subset of the plurality of possible trajectory nodes is selected to minimize an objective function: Wherein, c is the objective function, N is the number of nodes in the subset of the multiple possible trajectory nodes, and p i is the collision potential score of the ith node in the subset of the plurality of possible trajectory nodes, v i is the traffic violation score of the ith node in the subset of the plurality of possible trajectory nodes, and m i The operability score of the i-th node in the subset of the plurality of possible trajectory nodes, wherein each subset of the plurality of possible trajectory nodes is from the same one of the plurality of possible trajectories, and wherein a first node in the subset of the plurality of possible trajectory nodes and a second node in the subset of the plurality of possible trajectory nodes have a collision potential score less than 1.

10. The method of claim 1, wherein performing the first action further comprises: Operation of an autonomous driving system for the vehicle is adjusted based at least in part on the optimal trajectory.

Images