Vehicle trajectory planning system and method

Abstract

A vehicle trajectory planning system and method are disclosed. Specifically, a computer-implemented method and related aspects for providing a trajectory executed by a vehicle are disclosed. The method includes: obtaining a free space region in the vehicle's surrounding environment, the free space region being formed based on sensor data output from one or more onboard sensors. The obtained free space region is defined by edges having one or more edge characteristic classes, the one or more edge characteristic classes being defined by corresponding object classes of segments of the edges defining the obtained free space region. The method further includes: updating the obtained free space region by modifying the size of the obtained free space region based on the one or more edge characteristic classes, and determining or approving a vehicle speed for candidate paths to be executed by the vehicle within the updated free space region. The vehicle speed is determined based on the determined modification of the size of the obtained free space region.

Description

Technical Field

[0001] The disclosed technology relates to methods and systems for planning trajectories to be performed by vehicles. In particular, but not exclusively, the disclosed technology relates to autonomous driving systems and trajectory planning solutions using free space region estimation. Background Technology

[0002] Over the past decade, research and development activities involving autonomous vehicles have surged, exploring numerous different approaches. An increasing number of modern vehicles incorporate Advanced Driver Assistance Systems (ADAS) to enhance vehicle safety and, more generally, road safety. Autonomous driving systems (also known as driving automation systems) represent a suite of technologies designed to assist the driver or operate a vehicle autonomously without direct human intervention. These systems utilize a range of sensors, such as cameras, radar, lidar, ultrasonic sensors, and GNSS, to collect real-time data about the environment. This sensor data is then processed to enable various core functions of the autonomous driving system, such as perception, localization, and planning, which together ensure safe and efficient vehicle operation. The terms Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD) will be referred to herein as the common term Driving Automation System (DAS), corresponding to all the different levels of driving automation (e.g., levels 1-5 as defined by SAE J3016, and particularly levels 3, 4, and 5).

[0003] A crucial component of safe and reliable navigation in autonomous driving systems is free space estimation, which refers to the estimation of the area in the vehicle's surrounding environment where there are no obstacles and therefore the vehicle can drive on or enter. Accurate free space estimation allows the vehicle to understand its surroundings, detect obstacles, and determine a path that the vehicle can take with low collision risk. Another important component for autonomous driving systems is trajectory planning, which involves generating safe, efficient, and smooth trajectories using the identified free space. Summary of the Invention

[0004] The techniques disclosed herein are intended to mitigate, alleviate, or eliminate one or more of the aforementioned defects and disadvantages in the prior art in order to address various problems related to the safe driving of vehicles using driving automation systems in an environment.

[0005] The various aspects and embodiments of the disclosed technology are defined below and in the appended independent and dependent claims.

[0006] A first aspect of the disclosed technology includes a computer-implemented method for providing a trajectory executed by a vehicle. The computer-implemented method includes: obtaining a free space region in the vehicle's surrounding environment, the free space region being formed based on sensor data output from one or more onboard sensors. The obtained free space region is defined by edges having one or more edge characteristic classes, the one or more edge characteristic classes being defined by corresponding object classes of segments of the edges defining the obtained free space region. The computer-implemented method further includes: updating the obtained free space region by modifying its size based on the one or more edge characteristic classes, and determining or approving a vehicle speed for candidate paths to be executed by the vehicle within the updated free space region. The vehicle speed is determined based on the determined modification of the size of the obtained free space region.

[0007] The second aspect of the disclosed technology includes a computer program product containing instructions that, when executed by a computer, cause the computer to perform a method according to any of the embodiments disclosed herein. Utilizing this aspect of the disclosed technology offers advantages and preferred features similar to those of the other aspects.

[0008] A third aspect of the disclosed technology includes a (non-transitory) computer-readable storage medium containing instructions that, when executed by a computer, cause the computer to perform a method according to any of the embodiments disclosed herein. Utilizing this aspect of the disclosed technology offers advantages and preferred features similar to those of the other aspects.

[0009] As used herein, the term "non-transitory" is intended to describe a computer-readable storage medium (or "memory") that does not include propagating electromagnetic signals, but is not intended to otherwise limit the type of physical computer-readable storage device included in the term computer-readable medium or memory. For example, the terms "non-transitory computer-readable medium" or "tangible memory" are intended to cover types of storage devices that do not necessarily store information permanently, including, for example, random access memory (RAM). Program instructions and data stored in a non-transitory form on a tangible computer-accessible storage medium can be further transmitted via a transmission medium or a signal such as an electrical, electromagnetic, or digital signal, which can be transmitted via a communication medium such as a network and / or a wireless link. Therefore, the term "non-transitory" as used herein is a limitation on the medium itself (i.e., tangible, not a signal), rather than a limitation on the persistence of data storage (e.g., RAM and ROM).

[0010] A fourth aspect of the disclosed technology includes a system for providing a trajectory executed by a vehicle. The system includes control circuitry configured to acquire a free space region in the vehicle's surrounding environment, formed based on sensor data output from one or more onboard sensors. The acquired free space region is defined by edges having one or more edge characteristic classes, which are defined by corresponding object classes of segments of the edges defining the acquired free space region. Further, the control circuitry is configured to update the acquired free space region by modifying its size based on the one or more edge characteristic classes, and to determine or approve a vehicle speed for candidate paths to be executed by the vehicle within the updated free space region. The vehicle speed is determined based on the determined modification of the size of the acquired free space region. Utilizing this aspect of the disclosed technology offers advantages and preferred features similar to those of the other aspects.

[0011] The fifth aspect of the disclosed technology includes a vehicle comprising a system according to any of the embodiments of the fourth aspect disclosed herein. This aspect of the disclosed technology offers advantages and preferred features similar to the other aspects.

[0012] The disclosed aspects and preferred embodiments may be appropriately combined with each other in any manner obvious to those skilled in the art, such that one or more features or embodiments disclosed with respect to one aspect may also be considered as disclosed with respect to embodiments of another aspect or another aspect.

[0013] One advantage of some embodiments is that free space area estimation becomes more dynamic and can mitigate the risks associated with unexpected hazardous situations, thereby improving overall road safety.

[0014] One advantage of some embodiments is that free space region estimation can take into account unseen or undetected but still relevant potential objects and proactively mitigate collision risks, thereby improving overall road safety.

[0015] Further embodiments are defined in the dependent claims. It should be emphasized that when the term "comprising" and variations thereof are used in this specification, they are used to specify the presence of a described feature, integer, step, or component. They do not exclude the presence or addition of one or more other features, integers, steps, components, or groups thereof.

[0016] These and other features and advantages of the disclosed technology will be further illustrated below with reference to the embodiments described herein. Attached Figure Description

[0017] The foregoing aspects, features, and advantages of the disclosed technology will be more fully understood by referring to the following illustrative and non-limiting detailed description of exemplary embodiments of the present disclosure, in conjunction with the accompanying drawings, in which:

[0018] Figure 1 This is a schematic flowchart representation of a method for providing a trajectory executed by a vehicle, according to some embodiments.

[0019] Figure 2 This is a schematic top view illustration of the free space area of ​​a vehicle according to some embodiments.

[0020] Figure 3a According to some embodiments Figure 2 The diagram above illustrates a schematic top-view explanation of the modifications to the free space region.

[0021] Figure 3b According to some embodiments Figure 3a The diagram above illustrates a schematic top view showing the adjustment of the modified free space region.

[0022] Figure 4a According to some embodiments Figure 2 The diagram above illustrates a schematic top-view explanation of the modifications to the free space region.

[0023] Figure 4b According to some embodiments Figure 4a The diagram above illustrates a schematic top view showing the adjustment of the modified free space region.

[0024] Figure 5 Based on some embodiments from Figure 3b and Figure 4b A schematic top-view illustration of the combined free space region.

[0025] Figure 6 This is an illustrative illustration of a vehicle, including a system for providing a trajectory executed by the vehicle, according to some embodiments. Specific Implementation

[0026] This disclosure will now be described in detail with reference to the accompanying drawings, in which some exemplary embodiments of the disclosed technology are illustrated. However, the disclosed technology may be embodied in other forms and should not be construed as limited to the exemplary embodiments disclosed. The exemplary embodiments disclosed are provided to fully convey the scope of the disclosed technology to those skilled in the art. Those skilled in the art will appreciate that the steps, services, and functions explained herein can be implemented using separate hardware circuitry, software that works in conjunction with a programmable microprocessor or general-purpose computer, one or more application-specific integrated circuits (ASICs), one or more field-programmable gate arrays (FPGAs), and / or one or more digital signal processors (DSPs).

[0027] It will also be appreciated that, while this disclosure is described in terms of method, it is also embodied in an apparatus that includes one or more processors and one or more memories coupled to the one or more processors that load computer code to implement the method. For example, in some embodiments, the one or more memories may store one or more computer programs that, when executed by the one or more processors, cause the apparatus to perform the steps, services, and functions disclosed herein.

[0028] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be restrictive. It should be noted that the words “a,” “the,” and “described,” as used in the specification and appended claims, are intended to mean the presence of one or more elements unless the context explicitly specifies otherwise. Thus, for example, in some contexts, references to “unit” or “the unit” may refer to more than one unit, etc. Furthermore, the words “comprising,” “including,” and “containing” do not exclude other elements or steps. It should be emphasized that when the term “comprising” and its variations are used in this specification, they are used to specify the presence of the described features, integers, steps, or components. It does not exclude the presence or addition of one or more other features, integers, steps, components, or groups thereof. The term “and / or” should be interpreted as also meaning “both” and each is an alternative.

[0029] It should also be understood that although the terms first, second, etc., may be used herein to describe various elements or features, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first signal may be referred to as a second signal, and similarly, a second signal may be referred to as a first signal, without departing from the scope of the embodiments. Both the first signal and the second signal are signals, but they are not the same signal.

[0030] Overview

[0031] As mentioned, accurate free space estimation allows a vehicle (or more specifically, DAS) to understand its surroundings and determine a path that the vehicle can take with low collision risk. In other words, free space estimation is used to tell the vehicle where it cannot go. Another important component of driving automation systems is trajectory planning, which involves generating safe, efficient, and smooth trajectories using the identified free space.

[0032] However, estimating free space solely based on objects detected in the vehicle's surroundings may be insufficient to demonstrate that DAS is safe to operate not only relative to the space occupied by the vehicle but also relative to other road users.

[0033] To address this, the inventors propose a free space estimation solution that takes into account the dynamic characteristics of the environment. This dynamic characteristic is incorporated into the free space estimation by allowing the defined free space to contract and expand based on sensing data and assumptions about the modeling behavior of various objects or obstacles. Furthermore, the proposed solution allows the DAS to consider objects that were not detected but may still appear with a certain probability.

[0034] More specifically, the free space region is defined by edges having one or more edge characteristic classes. These edge characteristic classes are in turn defined by the corresponding object classes that define or define the free space region. For example, if the free space region is restricted in one direction by a parked vehicle, then that segment of the edge of the free space region is assigned the edge characteristic class "parked vehicle" based on the corresponding object class. Therefore, the edges of the free space region will be assigned various characteristic classes based on the object restricting the free space region. For example, the edge characteristic class can be an obstacle, parked vehicle, moving vehicle, pedestrian, curb, and ditch, etc. Moreover, segments of the edge of the free space region can be further assigned edge characteristic classes based on the state of the corresponding object class. For example, a "parked vehicle" parked parallel to the road can be assigned a different edge characteristic class than a "parked vehicle" parked with its rear facing the road (i.e., parked at a perpendicular angle to the direction of travel of the road). In some embodiments, if the object class restricting the free space region is unknown or if the restriction is due to a limitation of the sensing range, the segment of the edge of the free space region can be assigned an "unclassified" edge characteristic class.

[0035] Once the edges of a free space region are assigned one or more edge characteristic classes, these classes are used to update the free space region by shrinking and / or expanding its size. This can be done, for example, by having some predefined assumptions or models associated with a predefined set of object classes, which are evaluated in consideration of various edge characteristic classes with respect to potential risks associated with them. For instance, if the object class "pedestrian" is considered and the edge characteristic class for a segment of the free space region's edge is "curb" (i.e., the divider between the road and the sidewalk / pedestrian walkway), then the behavioral model for the object class "pedestrian" could indicate a risk that a pedestrian might unexpectedly enter the free space region at any point along that segment of the edge with a certain probability or likelihood. Therefore, the free space region is correspondingly shrunk along that segment of the edge in consideration of this risk. Similarly, if the edge characteristic class is "obstacle," then the behavioral model for the object class "pedestrian" could indicate a risk that a pedestrian might unexpectedly enter the free space region at any point along that segment of the edge with a certain probability or likelihood. However, it can be assumed here that the probability of a pedestrian entering the free space at an edge feature class defined as an "obstacle" is significantly lower than the probability at an edge feature class defined as a "curb." This is then reflected in the amount of "contraction" applied at each segment, with higher risk resulting in greater contraction.

[0036] These modeling behaviors for various object classes can be derived from statistical models, such as likelihood functions and distributions describing the probability of a specific object class entering a free space region conditioned on the presence or absence of specific edge characteristic classes within that region. Furthermore, the modeling behaviors can also incorporate the expected velocity of a specific object class entering the free space region, or the statistical distribution of that velocity.

[0037] Statistical models can be defined, for example, based on sensor data collected from a fleet of vehicles equipped with appropriate sensing systems and / or on studies of the behavior of different object classes in traffic conducted in available literature (which can then be confirmed by fleet data). For example, for a specific edge characteristic class, the modeling behavior for the object class "pedestrian" could be that the pedestrian will cross the segment of the edge with a 2% probability, and if so, enter the free space region at a speed of 1 m / s. Then, taking this modeling behavior into account, the free space region shrinks by a predetermined amount at the segment of the edge associated with that edge characteristic class. More specifically, the free space region can be shrunk by moving the segment of the edge inward by 0.5 meters, as this will give the vehicle's safety system (e.g., a collision avoidance system) sufficient time to mitigate a potential collision based on the specifications of the vehicle's safety system. Accordingly, the solution proposed in this paper for free space region estimation and trajectory planning can be understood as one of many systems of DAS that together reduce the risk of collisions.

[0038] It should be noted that the values ​​(2% and 1 m / s) in the examples above are merely examples of possible values ​​to facilitate understanding of the embodiments disclosed herein by those skilled in the art. In a simple implementation, it may also be considered (depending on the associated edge property class) to assign a probability of 100% or 0% to any object entering the free space region via a segment of the edge.

[0039] In other words, this paper proposes to view the free space region as a region with a sufficiently high probability or likelihood that there are no objects of one or more object classes both at the current moment (“now”) and a few seconds later (“future”). The conclusion that this region is free of obstacles in the “future” is based on the process of updating the size of the free space region presented in this paper.

[0040] Examples of the process for updating a free space region by contraction and / or expansion will be further illustrated with reference to the accompanying figures.

[0041] Furthermore, once the free space region is updated by shrinking and / or expanding, the vehicle speed for candidate paths within the updated free space region is determined. In other words, the candidate trajectory of the vehicle is determined taking into account the updated free space region. Thus, the candidate trajectory generated by the process proposed in this paper is limited to the vehicle speed when traversing a free space region considered safe or below a certain predefined risk level.

[0042] definition

[0043] In the current context, a Driver Automation System (DAS) refers to a complex combination of hardware and software components designed to control and operate a vehicle without direct human intervention. DAS technology aims to automate various aspects of driving, such as steering, acceleration, deceleration, and monitoring of the surrounding environment. The primary goal of DAS is to improve safety, efficiency, and convenience in transportation. The range of DAS can vary from basic driver assistance systems to highly advanced autonomous driving systems, depending on its level of automation, as categorized by standards such as SAE J3016. These systems utilize various sensors, cameras, radar, lidar, and powerful computer algorithms to perceive the environment and make driving decisions. The specific capabilities and characteristics / functions of DAS can vary considerably, from systems providing limited assistance to systems capable of independently handling complex driving tasks under specific conditions.

[0044] Advanced Driver Assistance Systems (ADAS) are technologies that assist drivers during driving, although they do not provide complete autonomy relative to the driving task. ADAS features are often used as building blocks for DAS. Examples include adaptive cruise control, lane keeping assist, automatic emergency braking, and parking assist. They improve safety and convenience, but typically require a certain level of human supervision and intervention. Autonomous Driving (AD), on the other hand, is a technology designed to control and navigate a vehicle without human supervision. Accordingly, the difference between ADAS and AD can be said to lie in the level of autonomy and control. ADAS systems are designed to assist and support the driver, while AD solutions aim for complete control of the vehicle without the need for continuous human supervision. Accordingly, AD aims for a higher level of autonomy (e.g., Levels 4 and 5 according to SAE International Standards), where the vehicle can operate independently in most or all driving scenarios without human intervention. As mentioned earlier, the term "DAS" used in this article is a collective term encompassing both ADAS and AD. In the current context, DAS functions or DAS features can be understood as specific functions or features of the entire DAS stack, such as high-speed navigation features, traffic congestion navigation features, and route planning features.

[0045] Free space region estimation typically refers to the process of detecting and determining the navigable, unobstructed area around a vehicle in real time. This estimation is crucial for safe navigation and path or trajectory planning, allowing the vehicle to identify locations where it can navigate without colliding with obstacles or other vehicles. It involves collecting data from sensors such as cameras, LiDAR, radar, or ultrasonic sensors, and processing that data using perception algorithms to detect objects and distinguish between obstacles and drivable areas. A representation of the environment can typically be created in the form of a grid map, polygons, or point clouds, marking free and occupied areas. The free space region is continuously updated as the vehicle moves and the environment changes (such as the appearance of dynamic obstacles like pedestrians). This information can then be provided as input to path planning or trajectory planning algorithms, enabling the vehicle to make real-time decisions for safe and efficient navigation.

[0046] Furthermore, the estimated free space region can be a combination of multiple free space regions, one for each object class. For example, a free space region can be estimated considering pedestrians, a free space region considering vehicles, and a free space region considering cyclists, and so on. Each of these individual class-specific free space regions can then be combined to form a general free space region estimate.

[0047] The "surrounding environment" of a vehicle can be understood as the general area around the vehicle, in which objects (such as other vehicles, landmarks, obstacles, etc.) can be detected and identified by the vehicle's sensors (radar, LIDAR, cameras, etc.) (i.e., within the sensor range of the vehicle).

[0048] In the current context, "sensor" or "sensor device" refers to a specialized component or system designed to capture and collect information from the vehicle's surrounding environment. These sensors play a crucial role in enabling Autonomous Vehicles (ADSs) to perceive and understand their environment, make informed decisions, and navigate safely. Sensor devices are typically integrated into the hardware and software systems of autonomous vehicles to provide real-time data for various tasks such as obstacle detection, localization, road model estimation, and object recognition. Common types of sensor devices used in autonomous driving include LiDAR (LiDAR detection and ranging), radar, cameras, and ultrasonic sensors. LiDAR sensors use laser beams to measure distances and create high-resolution 3D maps of the vehicle's surroundings. Radar sensors use radio waves to determine the distance and relative speed of objects around the vehicle. Camera sensors capture visual data, enabling the vehicle's computer system to identify traffic signs, lane markings, pedestrians, and other vehicles. Ultrasonic sensors use sound waves to measure proximity to objects. Various machine learning algorithms (such as artificial neural networks) can be used to process the output from the sensors to understand the environment.

[0049] The term "object class" refers to a predefined category or type of object that a perception function is designed to identify and classify in its environment. These classes are used to group detected objects based on their physical characteristics, behavior, or relevance to the driving task. Common object classes include vehicles, pedestrians, cyclists, traffic signs, animals, and road infrastructure elements (e.g., obstacles or lanes). By assigning detected objects to specific classes, the perception function enables the DAS to understand its environment and make situational decisions such as adjusting speed for pedestrians, maintaining distance from other vehicles, or responding to traffic signals.

[0050] The term "edge characteristic class" refers to a predefined category or type that, according to some embodiments, a system is configured to assign to a segment of the edge of a free space region. The edge characteristic class is further defined by the object class corresponding to the outer edge of the free space region. For example, if the free space region is restricted in a specific direction by an object already classified as "vehicle," then the segment of the edge of that free space region (restricted by a vehicle) is assigned the edge characteristic class "vehicle."

[0051] The term "candidate path" refers to a potential route or path that a vehicle can follow within its environment. It is typically a geometric representation of a curve or straight line within a free-space area that satisfies certain constraints such as staying within the lane, avoiding obstacles, and obeying road rules. Multiple candidate paths are usually generated and evaluated to find the path that best suits the vehicle's expected motion.

[0052] The term "candidate trajectory" refers to a time-parameterized version of a candidate path, defining not only the spatial route but also the time-varying speed of vehicles along that path. Accordingly, a candidate trajectory can be understood as the candidate path including the time-varying, defined speeds of vehicles along it. The candidate trajectory incorporates dynamic constraints such as vehicle kinematics, dynamics, and environmental changes (e.g., moving obstacles) to ensure safe and feasible movement. The candidate path may also define the acceleration and direction of the vehicle along it.

[0053] The term "actuation capability" refers to the ability of a system to control the physical mechanisms of a vehicle to perform desired driving actions. This depends on the vehicle's design and includes controlling the throttle (to regulate speed), braking (to decelerate or stop), and steering (to change direction), as well as other components such as gear shifting or signaling. Actuation capability ensures that the planned path or trajectory generated by the DAS can be followed accurately and safely by translating high-level decisions into precise, realistic vehicle motion. It must take into account the vehicle's dynamics, mechanical limitations, and responsiveness to commands. In some embodiments, actuation capability defines the vehicle's acceleration capability, steering capability, and / or braking capability.

[0054] The term "acquire" is to be interpreted broadly herein and encompasses the receiving, retrieving, collecting, and acquiring of information directly and / or indirectly between two entities configured to communicate with each other or further with other external entities. However, in some embodiments, the term "acquire" is to be interpreted as determining, deriving, forming, calculating, etc. In other words, acquiring the attitude of a vehicle can encompass determining or calculating the attitude of a vehicle based on, for example, GNSS data and / or perception data, together with map data. Thus, as used herein, "acquire" can indicate receiving parameters at a first entity / first unit from a second entity / second unit, or indicating determining parameters at a first entity / first unit based on data received from another entity / another unit.

[0055] Example

[0056] Figure 1 This is a schematic flowchart representation of a method for providing / determining a trajectory executed by a vehicle. Method S100 is preferably a computer-implemented method S100 executed by a processing system of a vehicle equipped with DAS. The processing system may, for example, include one or more processors and one or more memories coupled to the one or more processors, wherein the one or more memories store one or more programs that, when executed by the one or more processors, perform the steps, services, and functions of method S100 disclosed herein.

[0057] Method S100 includes: obtaining a free space region in the vehicle's surrounding environment, formed based on sensor data output from one or more onboard sensors. Furthermore, the obtained free space region is defined by edges having one or more edge characteristic classes, each edge characteristic class being defined by an object class corresponding to a segment of the edge defining the obtained free space region. In some embodiments, the free space region may be received from the vehicle's perception system, and method S100 may include: assigning edge characteristic classes to the received free space region based on detected and classified objects in the vehicle's surrounding environment. Alternatively, the free space region received from the perception system may include the assigned edge characteristic classes.

[0058] Further, method S100 includes updating the free space region obtained in S102 (S101) by modifying the size of the obtained free space region based on one or more edge characteristic classes. Modifying the size of the obtained free space region in S101 can involve shrinking and / or expanding / increasing the free space region. In the current context, shrinking refers to, for example, reducing the size of the free space region by moving the edges of the free space region inward toward the center of the free space region, while expanding / increasing refers to, for example, increasing the size of the free space region by moving the edges of the free space region outward away from the center of the free space region.

[0059] Now refer to Figure 2 , Figure 3a , Figure 3b , Figure 4a , Figure 4b and Figure 5 The free space region obtained by S102 is further explained by modifying its size.

[0060] Figure 2 This is a schematic illustration of the free space region 20 in the environment surrounding vehicle 1. In the depicted scene, vehicle 1 (also referred to as vehicle 1) is traveling on a two-lane road, where both lanes are associated with the same direction of travel as indicated by the bold arrows. Ahead of vehicle 1 is another vehicle 2, approaching a set of parking spaces on the right side of the vehicle, where two of the closest parking spaces have two parked vehicles 3. The road is restricted to the right side of the vehicle by a curb 32 that serves as a separator between the road and the pedestrian walkway / sidewalk 33. Three pedestrians 41 are present in the surrounding environment. One pedestrian is on the sidewalk 33, and the other two are in the set of parking spaces. The road is restricted to the left side by a barrier or wall 31. The free space region 20 has an edge 21 that defines the outer boundary of the free space region.

[0061] Modifications to the free space region 20 obtained in S101 can be performed on a per-object-class basis. More specifically, a first modification to obtain S101 can be performed on the first object class in the predefined object-class set, followed by a second modification to obtain S101 on the second object class in the predefined object-class set, and so on, until all object classes in the predefined object-class set have been processed. Then, the various modified free space regions for each object class in the predefined object-class set can be combined into a final free space region that forms the free space region for updating S102. Combinations of multiple modified free space regions can be performed such that the combined free space region is the intersection (∩) of the multiple modified free space regions.

[0062] The term "intersection" refers to a mathematical operation in set theory, where the intersection of two sets A and B (denoted as A∩B) is the set containing all elements of A that also belong to B. For example, if set A = {1, 2, 3} and set B = {2, 3, 4}, then the intersection of A and B is {2, 3}. In the current context, this can be understood as the intersection of the first modified free space region and the second modified free space region including all segments of the first modified free space region that also belong to the second free space region.

[0063] In some embodiments, the update S102 of the obtained free space region 20 is performed as a three-step process, which is in Figure 3a , Figure 3b , Figure 4a , Figure 4b and Figure 5 The diagram is schematically shown. More specifically, updating the free space region obtained in S101, S102, may include: for each object class in the predefined object class set, modifying the size of the free space region obtained in S105 based on the motion model used for that object class, and adjusting the modified free space region of S105 in S106 based on one or more edge characteristic classes. Then, the modified free space regions of the predefined object class set can be combined in S107 to form an updated free space region.

[0064] exist Figure 3a , Figure 3b , Figure 4a , Figure 4b and Figure 5 In the example depicted, the predefined collection of object classes are "pedestrians" and "vehicles". Specifically, Figure 3a and Figure 3b This involves modifying S105 and adjusting S106 to take pedestrians into account, and Figure 4a and Figure 4b This involves modifications S105 and adjustments S106, taking into account the vehicle.

[0065] In some embodiments, the predefined set of object classes is independent of any classified objects in the surrounding environment of vehicle 1. Therefore, the predefined set of object classes can be static and defined at "design time," such that the free space estimation process performed by the vehicle is configured to always consider the predetermined set of object classes, regardless of any currently detected and classified objects in the vehicle's surrounding environment. Thus, free space region estimation can depend less on the reliability of any object detection system in the DAS. Furthermore, the use of a predefined set of object classes independent of any classified objects in the surrounding environment of vehicle 1 allows the resulting free space estimation to consider undetected but still present objects (e.g., occluded objects).

[0066] In some embodiments, the predefined set of object classes includes one or more of vulnerable road users (VRUs), vehicles, or wildlife. The VRU object class may include subclasses such as pedestrians, cyclists, and motorcyclists that can be independently included in the predefined set of object classes. Similar reasoning can be considered for the object class "wildlife" (which may include elk, bears, deer, badgers, foxes, etc.). Furthermore, the predefined set of object classes may include statically unknown objects, despite having trivial motion / behavioral models. In other words, the predefined set of object classes may include pedestrians, cyclists, motorcyclists, vehicles, elk, bears, deer, badgers, foxes, and / or statically unknown objects.

[0067] Turn now Figure 3a The size of the free space region 20 has been modified by shrinking the size of the free space region 20 based on a motion model for an object class that takes the form of a pedestrian. The free space region 20 obtained in S101 is indicated by the dashed line 21 showing the original extension of the free space region 20, while the free space region of the modified S105 is indicated by line 22a. As indicated by the arrows extending from the original free space edge 21 to the modified free space edge 22a, the modification S105 may include shrinking the obtained free space region based on a motion model for a specific object class. More specifically, the motion model may be defined at design time and is correspondingly a predefined motion model for pedestrians, indicating the potential behavior of a pedestrian if they linger at the edge 21 of the obtained free space region. In this modification S105 of the free space region obtained in S101, edge characteristic classes are (temporarily) ignored. In other words, the "motion model" for an object class, as used herein, does not take edge characteristic classes into account.

[0068] Therefore, given a motion model for an object class, in the case of a pedestrian, a uniform contraction of the free space region 20 of the obtained S101 is applied to account for the potential risk of a pedestrian entering the obtained free space 20 from any point along the edge 21 of the obtained free space 20. The motion model can be a predefined model based on collected fleet data (i.e., real-world sensor measurements performed by vehicles in traffic) and / or information from literature such as Forde and Daniel's "Pedestrian walking speeds at unsignaled middle block crosswalks and their impact on urban street segment performance," or Levine and Norenzayan's "Life rhythms in 31 countries" study.

[0069] Then, given the edge characteristic class of the free space region obtained in S101, an adjustment S106 is performed on the modified free space region (defined by edge 22a). In some embodiments, the adjustment S106 of the free space region of the modified S105 is performed at the "per-segment level". In other words, the adjustment S106 includes: for each segment of the edge of the free space region of the modified S105, adjusting the free space region of the modified S105 based on the behavior model of the object for that segment's edge characteristic class. Similar to the motion model, the behavior model can be a predefined model based on collected fleet data (i.e., real-world sensor measurements performed by vehicles in traffic) and / or information from literature.

[0070] Adjust S106 in Figure 3b The free space region is schematically shown and defined by edge 23a. For example, the left edge 22a of the modified free space region (relative to the direction of travel of vehicle 1) is limited by an obstacle or wall 31. Therefore, the edge characteristic class of this segment of the edge is "obstacle" or "wall". It can be assumed here that a pedestrian is unlikely to appear and cross the obstacle or wall, or at least not at any high speed. This can be given, for example, by a behavior model of a "pedestrian" for the edge characteristic class "obstacle" or "wall". Therefore, the contraction S105 previously applied to this segment of the edge (near obstacle 31) is considered unnecessary and is restored to the original edge of the obtained free space region. Similarly, the segment of the edge of the free space region 20 defined by the preceding vehicle 2 is assigned the edge characteristic class "preceding vehicle" or "moving vehicle". As before, it can be assumed that a pedestrian will appear at this segment of the edge, as this would require the pedestrian to leave the moving vehicle, which is considered highly unlikely. Therefore, the contraction S105 previously applied at the edge (near the vehicle in front) of this section is considered unnecessary and is restored to the original edge of the gained free space area. Similar reasoning applies to parked vehicle 3 and the risk of pedestrians leaving through the trunk or tailgate of parked vehicle 3.

[0071] However, the contraction S105 applied to other parts of the free space region 20 is maintained. For example, the section near the edge of the curb 32 is assigned the edge characteristic class of "curb". Here, it is not extremely unlikely that a pedestrian will step onto the road from the curb 32, and therefore the modification (contraction) S105 previously applied to the section near the edge of the curb 32 is maintained.

[0072] Turn now Figure 4a The size of the free space region in S105 has been modified by shrinking the size of the free space region 20 obtained in S101 based on the motion model of the object class that adopts the form of a vehicle. The free space region 20 obtained in S101 is indicated by the dashed line 21 showing the original extension of the free space region 20, while the modified free space region in S105 is indicated by the line 22b.

[0073] In the illustrated example, vehicles that might appear "from the side" are not considered; however, in this example, the object class "vehicle" is limited to vehicles that can travel on the same road in the same direction of travel as vehicle 1. This is primarily done to improve readability and facilitate understanding by reducing complexity. Therefore, in the illustrated example, the modification S105 for the object class "vehicle" only covers the contraction of the free space region obtained in S101 for potential vehicles that may appear on the road and travel in the same direction as vehicle 1, as indicated by the arrow extending from the original free space edge 21 to the modified free space edge 22b.

[0074] Therefore, given the motion model of the object class, in the case of a vehicle (in this example, a vehicle traveling on a road in the same direction as vehicle 1), a longitudinal contraction of the free space region of the obtained S101 is applied to account for the potential risk of the vehicle entering the obtained free space 20 from any point along the longitudinal edge of the obtained free space 20. As mentioned earlier, the motion model can be a predefined model based on collected fleet data (i.e., real-world sensor measurements performed by vehicles in traffic) and / or information from literature (such as Natural Driving Studies (NDS) performed by the Strategic Highway Research Project).

[0075] Then, given the edge characteristic class of the free space region obtained in S101, adjustment S106 is performed on the modified free space region (defined by edge 22b). As before, the adjustment S106 of the free space region of the modified S105 is performed at the "per segment level". In other words, adjustment S106 includes: for each segment of the edge of the free space region of the modified S105, adjusting the free space region of the modified S105 based on the behavior model of the edge characteristic class of the object for that segment.

[0076] This adjustment is in Figure 4b The area is schematically shown and defined by edge 23b. For example, the segment of edge 22b of the modified free space region is restricted by the preceding vehicle 2. Therefore, the edge characteristic class for this segment of the edge is "preceding vehicle". It can be assumed here that the vehicle is unlikely to appear and start moving towards vehicle 1, or that the preceding vehicle 2 is unlikely to start reversing. Therefore, the contraction S105 previously applied at the segment of the edge (close to the preceding vehicle 2) is considered unnecessary and is restored (adjusted) to the original edge of the free space region. Moreover, for the segment of edge 22b that is close to the parked vehicle 3, which has been marked with the edge characteristic class "parked vehicle", adjustment S106 is performed to contract the modified free space region, because the edge characteristic class restricts the parked vehicle 3 to begin moving (albeit slowly - due to the... Figure 4a The contraction along the middle of the road is indicated by a relatively smaller contraction.

[0077] However, the contraction S105 applied to other parts of the free space region 20 is maintained. For example, the segment along the longitudinal edge of the lane adjacent to the vehicle lane can be assigned the object class of "unknown" or "unclassified" because the edge of the free space region is not as restricted by any classified objects as those specific segments. Here, it may not be possible to exclude the possibility of vehicles (traveling in the same direction as vehicle 1 on the road) (or at least not to a sufficient extent), and therefore the modification (contraction) S105 previously applied to those segments of the edge is maintained.

[0078] Next, in order to form the updated free space region, the adjusted free space region of the predefined object class set in S106 is combined in S107 to form the updated free space region. In other words, as from... Figure 5 The edge 24 in the middle indicates that it is by Figure 3b Edge 23a and by Figure 4b The free space regions defined by edge 23b in S106 are combined to form an updated free space region. More specifically, the combination S107 of the free space regions of the adjusted S106 may include: forming the updated free space region as the intersection of the free space regions of the adjusted S106 of the predefined object class set.

[0079] In the foregoing, the update S102 of the obtained free space region 20 is described as a three-step process (modifying and adjusting the free space region of each object class, and then combining the adjusted free space regions of all object classes). However, in some embodiments, the previously described modifications and adjustments can be performed in a modification S103 process at each object class level. More specifically, given one or more edge characteristic classes, the size of the free space region obtained in S101 by S103 can be modified based on the behavior model for the object class. In other words, edge characteristic classes have been considered in the modification S103 of the obtained free space region of S101. Similar to before, once the obtained free space region of S101 has been modified S103 for each object class, the modified free space regions of S103 of the predefined object class set are combined S104 to form an updated free space region. Here, the combination S104 of the modified free space regions of S103 may include: forming the updated free space region as the intersection of the modified free space regions of S103 of the predefined object class set.

[0080] It should also be understood that the terms "motion model" and "behavior model" are used only to distinguish one model from another. For example, a motion model can be called a behavior model, and similarly, a behavior model can be called a motion model, without departing from the scope of the embodiment. These two different terms are primarily used to improve readability and separate the two models, but both models serve a similar purpose: to parameterize or model the behavior of object classes in a traffic scenario. However, in the current context, the motion model for object classes does not consider edge characteristic classes when determining the contraction or expansion of the free space region, while the behavior model does. In other words, the motion model for object classes is independent of any edge characteristic classes, while the behavior model for object classes depends on the edge characteristic classes.

[0081] Continuing, method S100 further includes: determining or approving, in S109, the vehicle speed for a candidate path to be executed by the vehicle within the updated free space region. Here, the vehicle speed depends on the modification of the dimensions of the free space region obtained in S101. Accordingly, method S100 may include: determining the vehicle speed for a given candidate path within the free space region for updating S102, or approving a suggested vehicle speed for a candidate path within the free space region for updating S102. In other words, one or more candidate paths to be executed by vehicle 1 may be received, and the vehicle speed may then be determined based on the modification of the dimensions of the free space region obtained in S101 to output a candidate trajectory for the vehicle. Alternatively, a set of candidate trajectories that may be defined by the same candidate path may be received, thereby allowing one of the candidate trajectories (i.e., candidate paths that also include vehicle speeds) to be approved based on the modification of the dimensions of the free space region obtained in S101. In some embodiments, the vehicle speed in S109 is determined or approved to meet a predefined risk level for vehicle 1, taking into account the updated free space region.

[0082] Furthermore, in some embodiments, method S100 includes transmitting the determined or approved vehicle speed for the candidate path (S109) to one or more downstream functions of the vehicle's Driver Automation System (DAS) via S110. Here, the one or more downstream functions are configured to cause the vehicle to execute the candidate path at the determined or approved vehicle speed. The downstream function of the DAS may, for example, be a decision and control module configured to output control signals to one or more actuators of the vehicle to control the movement of the vehicle at least in part based on the determined or approved vehicle speed for the candidate path (S109). Moreover, method S100 may include controlling the vehicle to execute the candidate path at the determined or approved vehicle speed (S109).

[0083] Furthermore, in some embodiments, method S100 further includes: obtaining the actuation capability of the vehicle, wherein the actuation capability defines the vehicle's acceleration capability, steering capability, and / or braking capability. Moreover, based on the obtained actuation capability, method S109 further determines or approves the vehicle speed for the candidate path. In other words, method S100 also considers the vehicle's ability to set its speed for the candidate path to ensure that the vehicle can execute the obtained candidate trajectory.

[0084] Executable instructions for performing these functions may optionally be included in a non-transitory computer-readable storage medium or other computer program product configured for execution by one or more processors.

[0085] Figure 6This is an illustrative illustration of a vehicle 1 equipped with a DAS, including a system 10 for providing a trajectory executed by the vehicle, according to some embodiments. System 10 includes control circuitry (e.g., one or more processors) 11 configured to perform the functions of the method S100 disclosed herein, wherein the functions may be included in a non-transitory computer-readable storage medium 12 or in other computer program products configured for execution by the control circuitry 11. In other words, system 10 includes one or more memory storage areas 12 containing program code configured, together with one or more processors 11, to cause system 10 to perform method S100 according to any of the embodiments disclosed herein. As used herein, “vehicle” means any form of motorized transport. For example, vehicle 1 can be any road vehicle such as (as illustrated herein) a car, motorcycle, (freight) truck, bus, etc.

[0086] Control circuitry 11 may physically comprise a single circuit device. Alternatively, control circuitry 11 may be distributed across several circuit devices. As an example, system 10 may share its control circuitry 11 with other parts of vehicle 1, such as DAS 310. Moreover, system 10 may form part of DAS 310, i.e., system 10 may be implemented as a module or feature of DAS. Control circuitry 11 may include one or more processors such as a central processing unit (CPU), graphics processing unit (GPU), microcontroller, or microprocessor. One or more processors may be configured to execute program code stored in memory 12 to perform various functions and operations of vehicle 1 in addition to the methods disclosed herein. Processors may be or include any number of hardware components for performing data or signal processing or for executing computer code stored in memory 12. Memory 12 may optionally include high-speed random access memory such as DRAM, SRAM, DDR RAM, or other random access solid-state memory devices; and may optionally include non-volatile memory such as one or more disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. The memory 12 may include a database component, an object code component, a script component, or any other type of information structure used to support the various activities of this specification.

[0087] More specifically, the control circuit 11 is configured to obtain a free space region in the surrounding environment of the vehicle 1 based on sensor data output from one or more on-board sensors 324. The obtained free space region is defined by edges having one or more edge characteristic classes, which are defined by the corresponding object class of the segment of the edge defining the obtained free space region. Further, the control circuit 11 is configured to update the obtained free space region by modifying its size based on one or more edge characteristic classes, and to determine or approve a vehicle speed for candidate paths to be executed by the vehicle within the updated free space region. Here, the vehicle speed is determined based on the determined modification of the size of the obtained free space region.

[0088] Furthermore, the control circuit 11 can be configured to transmit the determined or approved vehicle speed for the candidate path to one or more downstream functions of the vehicle's driving automation system. The one or more downstream functions are configured to cause the vehicle to execute the candidate path at the determined or approved vehicle speed.

[0089] The control circuit 11 can be configured to update the obtained free space region by: for each of the predefined object class set, given one or more edge characteristic classes, modifying the size of the obtained free space region based on the behavior model for that object class; and combining the modified free space regions of the predefined object class set to form an updated free space region.

[0090] Furthermore, the control circuit 11 can be configured to update the obtained free space region for each of the predefined object class set by modifying the size of the obtained free space region based on the motion model for that object class and adjusting the modified free space region depending on one or more edge characteristic classes. Further, the control circuit 11 can be configured to update the obtained free space region by combining the adjusted free space regions of the predefined object class set to form an updated free space region.

[0091] Furthermore, the control circuit 11 can be configured to adjust the modified free space region for each segment of the edge of the modified free space region by adjusting the modified free space region based on the behavior model of the edge characteristic class of the object for that segment.

[0092] In the illustrated example, memory 12 further stores map data 308. Map data 308 can be used, for example, by the DAS 310 of vehicle 1 to perform autonomous functions of vehicle 1. Map data 308 may include high-definition (HD) map data. It is contemplated that memory 12, even though illustrated as a separate element from DAS 310, may be provided as an integrated element of DAS 310. In other words, according to exemplary embodiments, any distributed or local memory device can be utilized in the implementation of the inventive concept. Similarly, control circuitry 11 may be distributed, for example, such that one or more processors of control circuitry 11 are provided as integrated elements of DAS 310 of vehicle 1 or any other system. In other words, according to exemplary embodiments, any distributed or local control circuitry device can be utilized in the implementation of the inventive concept. DAS 310 is configured to implement the functions and operations of autonomous or semi-autonomous functions of vehicle 1. DAS 310 may include multiple modules, each responsible for a different function of DAS 310.

[0093] Vehicle 1 includes several components typically found in autonomous or semi-autonomous vehicles. It should be understood that vehicle 1 is capable of having… Figure 6 Any combination of the various elements shown. Furthermore, vehicle 1 may include, in addition to... Figure 6 Other elements besides those shown herein. Although various elements are shown herein as being located inside vehicle 1, one or more of these elements can be located outside vehicle 1. For example, map data can be stored in a remote server and accessed by various components of vehicle 1 via communication system 326. Furthermore, as will be readily understood by those skilled in the art, even though various elements are depicted in a certain arrangement herein, they can be implemented in different arrangements. It should also be noted that various elements can be communicatively connected to each other in any suitable manner. Figure 6 Vehicle 1 should be considered merely as an illustrative example, as the components of vehicle 1 can be implemented in several different ways.

[0094] Vehicle 1 further includes a sensor system 320. Sensor system 320 is configured to acquire sensing data about the vehicle itself or its surrounding environment. Sensor system 320 may, for example, include a Global Navigation Satellite System (GNSS) module 322 (e.g., GPS) configured to collect geographic location data of vehicle 1. Sensor system 320 may further include one or more sensors 324. Sensors 324 may be any type of onboard sensor such as a camera, lidar and radar, ultrasonic sensors, gyroscope, accelerometer, odometer, etc. It should be understood that sensor system 320 may also provide the possibility of acquiring sensing data directly or via dedicated sensor control circuitry in vehicle 1.

[0095] Vehicle 1 further includes a communication system 326. Communication system 326 is configured to communicate with external units such as other vehicles (i.e., via vehicle-to-vehicle (V2V) communication protocols), remote servers (e.g., cloud servers), databases, or other external devices (i.e., vehicle-to-infrastructure (V2I) communication protocols or vehicle-to-everything (V2X) communication protocols). Communication system 326 can communicate using one or more communication technologies. Communication system 326 may include one or more antennas (not shown). Cellular communication technologies can be used for remote communication, such as with remote servers or cloud computing systems. Additionally, if the cellular communication technology used has low latency, it can also be used for V2V, V2I, or V2X communication. Examples of cellular radio technologies are GSM, GPRS, EDGE, LTE, 5G, 5G NR, etc., and future cellular solutions are also included. However, in some solutions, short-to-medium range communication technologies such as wireless local area networks (LANs) based on, for example, IEEE 802.11 can be used to communicate with other vehicles near vehicle 1 or with local infrastructure components. ETSI is developing cellular standards for vehicle communications, and 5G is considered a suitable solution, for example, due to its low latency and efficient handling of high bandwidth and communication channels.

[0096] The communication system 326 can accordingly provide the possibility of sending outputs to and / or receiving inputs from remote locations (e.g., remote operators or control centers) via one or more antennas. Furthermore, the communication system 326 can be further configured to allow various components of vehicle 1 to communicate with each other. As an example, the communication system can provide a local network setup such as CAN bus, I2C, Ethernet, fiber optics, etc. Local communication within the vehicle can also be a wireless type with protocols such as WiFi, LoRa, Zigbee, Bluetooth, or similar medium / short-range technologies.

[0097] Vehicle 1 further includes a control system 328. The control system 328 is configured to control the handling of vehicle 1. The control system 328 includes a steering module 330 configured to control the heading of vehicle 1. The control system 328 further includes a throttle module 332 configured to control the actuation of the throttle valve of vehicle 1. The control system 328 further includes a braking module 334 configured to control the actuation of the brakes of vehicle 1. The various modules of the control system 328 can also receive manual input from the driver of vehicle 1 (i.e., from the steering wheel, throttle pedal, and brake pedal, respectively). However, the control system 328 can be communicatively connected to the vehicle's DAS 310 to receive instructions on how the various modules of the control system 328 should operate. Therefore, the DAS 310 can control the handling of vehicle 1, for example, via a decision and control module 318.

[0098] DAS 310 may include a positioning module 312 or a positioning block / system. Positioning module 312 is configured to determine and / or monitor the geographic location and heading of vehicle 1, and may utilize data from sensor system 320, such as data from GNSS module 322. Alternatively or in combination, positioning module 312 may utilize data from one or more sensors 324. Alternatively, the positioning system may be implemented as real-time dynamic (RTK) GPS to improve accuracy.

[0099] DAS 310 may further include a perception module 314 or a perception block / system 314. The perception module 314 may refer to any known module and / or function, for example, included in one or more electronic control modules and / or nodes of vehicle 1, adapted and / or configured to interpret driving-related sensing data of vehicle 1 to identify, for example, obstacles, lanes, relevant signs, appropriate navigation paths, etc. Therefore, the perception module 314 may be adapted to combine, for example, sensing data from sensor system 320, relying on and obtaining input from multiple data sources such as automotive imaging, image processing, computer vision, and / or in-vehicle networks.

[0100] The DAS may further include a path planning module 316, which is configured to output one or more candidate paths to be executed by the vehicle. The path planning module 316 may receive input from the perception module 314 to generate candidate paths, and it may output the generated candidate paths to the decision and control module 318 for execution. Depending on the specific implementation and method, the path planning module 316 may alternatively take the form of a trajectory planning module.

[0101] The positioning module 312 and / or the sensing module 314 can be communicatively connected to the sensor system 320 to receive sensing data from the sensor system 320. The positioning module 312 and / or the sensing module 314 can further transmit control commands to the sensor system 320.

[0102] The present invention has been presented above with reference to specific embodiments. However, other embodiments besides those described above are also possible and are within the scope of the invention. Within the scope of the invention, method steps different from those described above, performed by hardware or software, can be provided. Therefore, according to exemplary embodiments, a (non-transitory) computer-readable storage medium is provided storing one or more programs configured to be executed by one or more processors of a vehicle control system, the programs including instructions for performing the methods according to any of the above embodiments. Alternatively, according to another exemplary embodiment, a cloud computing system can be configured to perform any of the methods presented herein. The cloud computing system may include distributed cloud computing resources that collectively perform the methods presented herein under the control of one or more computer program products.

[0103] Generally, computer-accessible media can include any tangible or non-transitory storage medium or memory medium, such as electronic, magnetic, or optical media, for example, a disk or CD / DVD-ROM coupled to a computer system via a bus. As used herein, the terms “tangible” and “non-transitory” are intended to describe computer-readable storage media (or “memory”) that do not include propagating electromagnetic signals, but are not intended to otherwise limit the types of physical computer-readable storage devices included in the term computer-readable media or memory. For example, the terms “non-transitory computer-readable medium” or “tangible memory” are intended to cover types of storage devices that do not necessarily store information permanently, including, for example, random access memory (RAM). Program instructions and data stored in a non-transitory form on a tangible computer-accessible storage medium can be further transmitted via a transmission medium or a signal such as an electrical, electromagnetic, or digital signal, which can be transmitted via a communication medium such as a network and / or a wireless link.

[0104] It should be noted that no reference numerals in the accompanying drawings limit the scope of the claims. The invention can be implemented, at least in part, by both hardware and software, and the same hardware can represent multiple “devices” or “units”.

[0105] Although the accompanying drawings may illustrate a specific order of method steps, the order of steps may differ from that depicted. Furthermore, two or more steps may be performed simultaneously or partially simultaneously. This variation will depend on the chosen software and hardware system and the designer's choices. All such variations are within the scope of this invention. Similarly, software implementation can be accomplished using standard programming techniques based on rule-based logic and other logics to perform various acquisition, update, determination, approval, modification, adjustment, and transmission steps. The embodiments mentioned and described above are given by way of example only and should not be considered as limiting the invention. Other solutions, uses, purposes, and functions within the scope of the invention claimed in the patent claims described below will be apparent to those skilled in the art.

Claims

1. A computer-implemented method (S100) for providing a trajectory executed by a vehicle, the computer-implemented method comprising: (S101) Obtain a free space region in the surrounding environment of the vehicle, the free space region being formed based on sensor data output from one or more on-board sensors, wherein the obtained free space region is defined by an edge having one or more edge characteristic classes, the one or more edge characteristic classes being defined by an object class corresponding to a segment of the edge of the obtained free space region. The obtained free space region is updated (S102) by modifying the size of the obtained free space region based on the one or more edge characteristic classes; and Determine or approve (S109) the vehicle speed for the candidate path to be executed by the vehicle within the updated free space region, wherein the vehicle speed depends on the determined modification of the size of the obtained free space region.

2. The computer-implemented method (S100) according to claim 1, further comprising: The determined or approved vehicle speed for the candidate path is transmitted (S110) to one or more downstream functions of the vehicle's driving automation system, the one or more downstream functions being configured to cause the vehicle to execute the candidate path at the determined or approved vehicle speed.

3. The computer-implemented method (S100) according to claim 1 or 2, wherein, The free space region obtained by the update (S102) includes: For each of the predefined set of object classes, given the one or more edge characteristic classes, the size of the free space region obtained based on the behavioral model modification (S103) for that object class; and The modified free space regions of the predefined object class set are combined (S104) to form the updated free space regions.

4. The computer-implemented method (S100) according to claim 1 or 2, wherein, The free space region obtained by the update (S102) includes: For each of the predefined object classes: The size of the free space region is obtained based on the motion model modification (S105) for this object class, and depends on the free space region modified by the one or more edge characteristic class adjustments (S106); and The adjusted free space regions of the predefined object class set are combined (S107) to form the updated free space regions.

5. The computer-implemented method (S100) according to claim 4, wherein, The modified free space region, as adjusted (S105), includes: For each segment of the edge of the modified free space region: The free space region is adjusted and modified based on the behavior model of the edge characteristic class of the object for that segment.

6. The computer-implemented method (S100) according to claim 3, wherein, The predefined set of object classes is independent of any categorized objects in the vehicle's surrounding environment.

7. The computer-implemented method (S100) according to claim 3, wherein, The predefined set of object classes includes one or more of vulnerable road users, vehicles, and wildlife.

8. The computer-implemented method (S100) according to claim 1, wherein, The free space region refers to the area in the vehicle's surrounding environment where there are no objects.

9. The computer-implemented method (S100) according to claim 1, further comprising: (S108) Obtain the actuation capability of the vehicle, wherein the actuation capability defines the acceleration capability, steering capability and / or braking capability of the vehicle. The vehicle speed is further determined or approved based on the obtained actuation capability (S109).

10. The computer-implemented method according to claim 1, wherein, Further determine or approve (S109) the vehicle speed to meet a predefined risk level for the vehicle, taking into account the updated free space region.

11. A computer program product comprising instructions, wherein when the program is executed by a computing device, the instructions cause the computing device to perform the method (S100) according to claim 1.

12. A non-transitory computer-readable storage medium storing instructions that, when executed by a computing device, cause the computing device to perform the method (S100) according to claim 1.

13. A system (10) for providing a trajectory executed by a vehicle (1), the system comprising a control circuit (11) configured to: A free space region (20) in the surrounding environment of the vehicle is obtained, the free space region (20) being formed based on sensor data output from one or more onboard sensors (324), wherein, The obtained free space region (20) is defined by an edge (21) having one or more edge characteristic classes, the one or more edge characteristic classes being defined by the object class corresponding to the segment of the edge of the obtained free space region defined by the object; The obtained free space region is updated by modifying the size of the obtained free space region based on one or more edge characteristic classes; as well as Determine or approve vehicle speeds for candidate paths to be executed by the vehicle (1) within the updated free space region, wherein the vehicle speeds are determined based on the determined modifications to the dimensions of the obtained free space region.

14. The system (10) according to claim 13, wherein, The control circuit (11) is further configured to: The determined or approved vehicle speed for the candidate path is transmitted to one or more downstream functions of the vehicle's driving automation system (310), the one or more downstream functions being configured to cause the vehicle to execute the candidate path at the determined or approved vehicle speed.

15. A vehicle (1) comprising the system (10) according to claim 13 or 14.

Images