Estimation of accident risk level of road traffic participants

Abstract

A method for estimating an accident risk level of a first traffic participant based on an interaction or negotiation between the first traffic participant and one or more other traffic participants. The method includes generating a plurality of virtual trajectories of the first traffic participant based on a recorded initial position of the first traffic participant, a recorded final position, and a recorded initial position of each of the one or more other traffic participants. The plurality of virtual trajectories of the first traffic participant are associated with the plurality of virtual behaviors of the first traffic participant. The method also includes identifying a virtual trajectory that is most similar to the recorded trajectory of the first traffic participant. The method is capable of automatically interpreting the actual actions of the first traffic participant based on the virtual behaviors of the first traffic participant associated with the identified virtual trajectories.

Description

Technical Field

[0001] The present invention relates generally to the field of traffic monitoring systems and, more particularly, to a method of estimating the accident risk level of road traffic participants. Background Art

[0002] As traffic density increases, road congestion and accidents are also increasing. Therefore, traffic monitoring is a huge challenge in this context. Traffic monitoring has many technologies and applications, and understanding the user's past driving behavior is also considered to be helpful in assessing accident risks. For example, one of the goals of car insurance providers is to set policy prices (premiums) that are related to the identifiable risk of loss for the policyholder (also known as the user or driver). From this perspective, it should be understood that the user's past driving behavior can help predict the possibility of a car accident resulting in a loss to the insurance provider.

[0003] Currently, some attempts have been made to determine the user's past driving behavior by installing conventional sensor devices (or sensor boxes) on conventional motor vehicles. Conventional sensor devices include global navigation satellite system (GNSS) receivers, accelerometers, inertial measurement units (IMUs) or external sensing sensors (such as cameras, radars) for estimating the user's accident risk level (also known as collision risk level). The user's accident risk level (or collision risk level) is estimated by using conventional sensor devices according to two conventional methods. The first conventional method is used to detect safety-critical events based on direct processing of conventional sensor devices (such as accelerometers). The first conventional method relies on identifying any hard acceleration or braking during the user's natural driving. However, the disadvantage of the first conventional method is that the correlation between hard acceleration or braking and the user's aggressiveness and the accident risk level (or collision risk level) is poorly interpretable. For example, in some cases, a user (e.g., a policyholder) may not care about a possible collision with another motor vehicle and will not slow down to negotiate with other motor vehicles through an intersection, so even if the situation does not involve any hard acceleration or braking, it will still be labeled as high risk. This means that a critical event can occur without any hard acceleration or braking. The second conventional method is based on identifying risk scores using conventional sensor devices (e.g., global navigation satellite system (GNSS) receivers and cameras). A risk score is assigned to each identified action of the user based on a statistical correlation with the accident risk level. For example, a user who frequently changes lanes is more likely to encounter a car accident or collision, so such actions of the user are assigned a high risk score. The different actions of the user are identified based on changing lanes, turning around, or overtaking, so the user is not focused on interacting and negotiating with other motor vehicles, resulting in a car accident or collision. However, the risk score assigned in this way may not be sufficient to accurately estimate the accident risk level of the user's motor vehicle. Therefore, there is a technical problem of inefficient and inaccurate estimation of the accident risk level of the user's motor vehicle (i.e., road traffic participant).

[0004] Therefore, in light of the foregoing discussion, there exists a need to overcome the aforementioned shortcomings associated with conventional methods of estimating a user's motor vehicle accident risk level. Summary of the invention

[0005] The present invention aims to provide a method for estimating the accident risk level of road traffic participants. The present invention aims to provide a solution to the existing problem of inefficient and inaccurate estimation of the accident risk level of road traffic participants. The purpose of the present invention is to provide a solution that at least partially solves the problems encountered in the prior art and provides an improved method and system for accurately estimating the accident risk level of road traffic participants.

[0006] The objects of the invention are achieved by what is presented in the attached independent claim. Advantageous implementations of the invention are further defined in the dependent claims.

[0007] In one aspect, the present invention provides a method for estimating an accident risk level of a road traffic participant. The road traffic participant is a first participant among a plurality of road traffic participants. The plurality of road traffic participants include the first participant and one or more other participants. The method includes generating a plurality of virtual trajectories of the first participant according to the following items: a recorded initial position of the first participant, a recorded final position of the first participant, and a recorded initial position of each of the one or more other participants, wherein each of the virtual trajectories of the first participant extends from the recorded initial position of the first participant to the recorded final position of the first participant, and the plurality of virtual trajectories of the first participant are associated one-to-one with a plurality of virtual behaviors of the first participant. The method also includes identifying a virtual trajectory that is most similar to the recorded trajectory of the first participant among the plurality of virtual trajectories of the first participant, the recorded trajectory of the first participant extending from the recorded initial position of the first participant to the recorded final position. The method also includes estimating the accident risk level according to the virtual behaviors associated with the identified virtual trajectories.

[0008] The method of the present invention provides an automatic interpretation of the actions of a first participant from the perspective of interaction with one or more other road traffic participants. Such interpretation is beneficial for automobile insurance because a large number of collisions occur due to too little interaction with one or more other road traffic participants. The disclosed method uses the multiple virtual trajectories associated with the multiple virtual behaviors of the first participant to interpret the actual trajectories (i.e., recorded trajectories) performed by the first participant, thereby more accurately estimating the accident risk level of the first participant. The disclosed method identifies new actions of the first participant and updates the accident risk level of the first participant accordingly. The disclosed method infers the accident risk level of the first participant (e.g., a self-aware car) based on interactions and consultations with one or more other road traffic participants.

[0009] In one implementation, the method of generating multiple virtual trajectories of a first participant includes generating a corresponding virtual trajectory of the first participant for each of the multiple virtual behaviors of the first participant according to the corresponding virtual behaviors of the first participant.

[0010] By generating a corresponding virtual trajectory according to the corresponding virtual behavior of the first participant, a more accurate accident risk level of the first participant is estimated.

[0011] In another implementation, the method of generating multiple virtual trajectories of a first participant includes further generating a corresponding virtual trajectory of the first participant for each of the multiple virtual behaviors of the first participant based on the recorded initial position of each of the one or more other participants.

[0012] By generating a corresponding virtual trajectory of the first participant based on the recorded initial position of each of the one or more other participants, the accident risk level is estimated more accurately to detect how the first participant interacts or negotiates with the one or more other participants.

[0013] In another implementation, a method for generating multiple virtual trajectories of a first participant includes generating a virtual final position for each of one or more other participants. The method also includes generating a first virtual trajectory of the first participant based on a first virtual behavior among the multiple behaviors of the first participant, wherein the first virtual trajectory of the first participant is the first virtual trajectory among the multiple virtual trajectories of the first participant. The method also includes generating a corresponding virtual trajectory of the other participant for each of the one or more other participants based on the virtual behavior of the corresponding other participant, wherein the virtual trajectory of the corresponding other participant extends from the recorded initial position of the corresponding participant to the virtual final position of the corresponding participant. The method also includes identifying one or more proximity areas based on the first virtual trajectory of the first participant and based on the virtual trajectory of each of the one or more other participants, wherein each proximity area is a spatiotemporal area in which the first participant is close to at least one of the one or more other participants, and for each of the one or more proximity areas, and for each of the one or more other virtual behaviors among the multiple virtual behaviors of the first participant, the method also includes generating another virtual trajectory of the first participant based on the corresponding proximity area and based on the corresponding other virtual behavior.

[0014] The method for estimating the accident risk level focuses on the interaction and negotiation (e.g., giving way or occupying the road) of the first participant with each of the one or more other participants to avoid collision. According to the plurality of virtual trajectories of the first participant, a proximity area between the first participant and the one or more other participants is identified. According to the identified proximity area, the plurality of virtual trajectories of the first participant and the one or more other participants are updated to avoid collision.

[0015] In another implementation, a method of generating a virtual final position for each of one or more other participants includes generating a corresponding virtual final position based on a recorded initial position of the corresponding other participant.

[0016] By generating respective virtual final positions from the recorded initial positions of respective other participants, a plurality of virtual trajectories of the first participant can be calculated in order to avoid an accident.

[0017] In another implementation, the method of generating the corresponding virtual final location is further based on a map of the area including the recorded initial location of the first participant and the recorded initial location of each of the other participants.

[0018] By using a map of the area including the recorded initial position of the first participant and the recorded initial position of each of the other participants, multiple virtual trajectories of the corresponding participants are generated in a more accurate manner. In addition, the virtual behavior of the first participant can be easily checked to comply with the traffic rules stored on the area map.

[0019] In another implementation, the method of generating the corresponding virtual final position is further based on traffic rule information, which is information about traffic rules applicable to the area.

[0020] By using traffic rule information to generate the corresponding virtual final position, the overall accident risk level is estimated more accurately.

[0021] In another implementation, the method for estimating the accident risk level is further based on traffic regulation information.

[0022] Based on checking whether the virtual behavior of the first participant is in compliance with traffic rules, the accident risk level is estimated more accurately. For example, in some cases, the virtual behavior of the first participant (such as occupying the road) is incompatible with the yield sign of traffic rules, which in turn may lead to a greater accident risk level.

[0023] It should be understood that all of the above implementations may be combined.

[0024] It should be noted that all devices, elements, circuits, units and modules described in this application can be implemented by software or hardware elements or any type of combination thereof. All steps performed by various entities described in this application and the described functions to be performed by various entities are intended to indicate that the corresponding entities are used to perform the corresponding steps and functions. Although in the description of the following specific embodiments, the specific functions or steps performed by external entities are not reflected in the description of the specific detailed elements of the entities performing the specific steps or functions, it should be clear to the technician that these methods and functions can be implemented by corresponding hardware or software elements or any combination thereof. It should be understood that, without departing from the scope of the present invention defined in the appended claims, various combinations of features of the present invention can be performed.

[0025] Additional aspects, advantages, features and objects of the present invention will become apparent from the accompanying drawings and detailed description of illustrative implementations interpreted in conjunction with the following appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above summary and the detailed description of the following illustrative embodiments may be better understood by reading in conjunction with the accompanying drawings. In order to illustrate the present invention, exemplary structures of the present invention are shown in the accompanying drawings. However, the present invention is not limited to the specific methods and tools disclosed herein. In addition, it should be understood by those skilled in the art that the accompanying drawings are not drawn to scale. Where possible, the same elements are represented by the same numbers.

[0027] Embodiments of the present invention will now be described, by way of example only, with reference to the following drawings, in which:

[0028] Figure 1 is a flow chart of a method for estimating an accident risk level of a road traffic participant according to an embodiment of the present invention;

[0029] Figure 2 is a work flow of various operations of a method for estimating an accident risk level of a road traffic participant according to an embodiment of the present invention;

[0030] Figure 3 is an exemplary driving scenario according to an embodiment of the present invention, showing recorded initial positions of road traffic participants;

[0031] Figure 4 is an exemplary driving scenario according to an embodiment of the present invention, showing the final position of a road traffic participant;

[0032] Figure 5A is an exemplary driving scenario according to an embodiment of the present invention, showing a plurality of virtual trajectories of road traffic participants;

[0033] Figure 5Bis a graphical representation of a non-interaction motion plan of a first participant in a spatiotemporal region according to an embodiment of the present invention;

[0034] Figure 5C is a graphical representation of a non-interaction motion plan of a second participant in a spatiotemporal region according to an embodiment of the present invention;

[0035] Figure 5D is a scenario according to an embodiment of the present invention, showing a trajectory generator for a road traffic participant;

[0036] Fig. 6A is an exemplary driving scenario according to an embodiment of the present invention, showing a collision between road traffic participants;

[0037] Figure 6B is a scenario according to an embodiment of the present invention, showing a trajectory generator for a road traffic participant;

[0038] Fig. 7A is an exemplary driving scenario according to an embodiment of the present invention, showing a plurality of virtual trajectories of road traffic participants for avoiding collision;

[0039] Figure 7B is a scenario according to an embodiment of the present invention, showing a trajectory generator for avoiding collisions of road traffic participants;

[0040] Figure 7C is a scenario according to an embodiment of the present invention, showing a trajectory generator for avoiding collisions of road traffic participants;

[0041] Fig.7D is a graphical representation of a motion plan of a first participant based on a virtual behavior of giving way according to an embodiment of the present invention;

[0042] Fig. 7E is a graphical representation of a motion plan of a second participant based on a virtual behavior of occupying a road according to an embodiment of the present invention;

[0043] Figure 7F is a graphical representation of a motion plan of a first participant based on a virtual behavior of occupying a road according to an embodiment of the present invention;

[0044] Figure 7G is a graphical representation of a motion plan of a second participant based on a virtual behavior of giving way according to an embodiment of the present invention;

[0045] Fig. 8A is an exemplary driving scenario according to an embodiment of the present invention, showing a collision between road traffic participants;

[0046] Figure 8Bis a scenario according to an embodiment of the present invention, showing a trajectory generator for a road traffic participant;

[0047] Figure 8C is an exemplary driving scenario for avoiding collisions between road traffic participants according to an embodiment of the present invention;

[0048] Fig.8D is a scenario according to an embodiment of the present invention, showing a trajectory generator for avoiding collisions of road traffic participants;

[0049] Fig. 8E is a scenario according to an embodiment of the present invention, showing a trajectory generator for avoiding collisions of road traffic participants;

[0050] Fig.8F is a scenario according to an embodiment of the present invention, showing a trajectory generator for avoiding collisions of road traffic participants;

[0051] Figure 8G is a graphical representation of a motion plan of a road traffic participant according to an embodiment of the present invention;

[0052] Figure 8H is a graphical representation of a motion plan of a road traffic participant according to an embodiment of the present invention;

[0053] Fig.9A is an exemplary driving scenario according to an embodiment of the present invention, showing a collision between road traffic participants;

[0054] Fig. 9B is a scenario according to an embodiment of the present invention, showing a trajectory generator for a road traffic participant;

[0055] Fig. 9C is a graphical representation of a motion plan of a road traffic participant according to an embodiment of the present invention;

[0056] Fig.9D is a graphical representation of a count of collision risk features of a first participant according to an embodiment of the present invention;

[0057] Fig. 10A is a graphical representation of a trajectory match of a first participant in terms of a spatial path according to an embodiment of the present invention;

[0058] Fig. 10B is a graphical representation of a trajectory match of a first participant in a spatiotemporal region according to an embodiment of the present invention;

[0059] Fig. 10C is a graphical representation of a match score of a first participant in a spatial path region according to an embodiment of the present invention;

[0060] Fig. 10D is a graphical representation of a match score of a first participant in a spatiotemporal region according to an embodiment of the present invention;

[0061] Fig.11A is a network environment diagram of a system having multiple traffic participants and a server according to an embodiment of the present invention;

[0062] Fig. 11B is a block diagram of various exemplary components of a first participant according to an embodiment of the present invention;

[0063] Fig. 11C is a block diagram of various exemplary components of a server according to an embodiment of the present invention;

[0064] Fig.12 is an exemplary implementation of the calculation of a standardized risk profile of a first participant according to an embodiment of the present invention;

[0065] In the drawings, an underlined number is used to indicate the item in which the underlined number is located or an item adjacent to the underlined number. A non-underlined number refers to the item identified by the line connecting the non-underlined number to the item. When a number is not underlined and has an associated arrow, the non-underlined number is used to identify the general item to which the arrow points. DETAILED DESCRIPTION

[0066] The following detailed description describes embodiments of the invention and ways in which these embodiments may be implemented. Although some modes of implementing the invention have been disclosed, those skilled in the art will recognize that there may be other embodiments for implementing or practicing the invention.

[0067] Figure 1 is a flow chart of a method for estimating the accident risk level of a road traffic participant according to an embodiment of the present invention. Figure 1 , a method 100 for estimating the accident risk level of a road traffic participant is shown. The method 100 includes steps 102 to 106. For example, in one implementation, the method 100 FIG. 11A to FIG. 11C It is carried out among road traffic participants as described in detail in.

[0068] Method 100 estimates the accident risk level of a road traffic participant. The road traffic participant is a first participant among multiple road traffic participants. The multiple road traffic participants include the first participant and one or more other participants. Method 100 estimates the accident risk level of the first participant and one or more other road traffic participants. The accident risk level may also be referred to as the collision risk level of the first participant and one or more other road traffic participants. For example, the first participant may be an autonomous driving vehicle. Alternatively, the first participant may be a non-autonomous driving vehicle (e.g., a human-driven vehicle), or a semi-autonomous driving vehicle. Similarly, one or more other road traffic participants correspond to non-autonomous driving vehicles, autonomous driving vehicles, semi-autonomous driving vehicles, or pedestrians, etc.

[0069] In step 102, the method 100 includes generating a plurality of virtual trajectories of the first participant based on: a recorded initial position of the first participant, a recorded final position of the first participant, and a recorded initial position of each of one or more other participants, wherein each of the virtual trajectories of the first participant extends from the recorded initial position of the first participant to the recorded final position of the first participant, and the plurality of virtual trajectories of the first participant are associated one-to-one with a plurality of virtual behaviors of the first participant. The method 100 estimates the accident risk level of the first participant based on a trajectory generation algorithm for generating a plurality of virtual trajectories of the first participant. The plurality of virtual trajectories of the first participant are generated based on the recorded initial position of the first participant and the recorded final position of the first participant and the recorded initial positions of one or more other participants. In one implementation, the recorded initial position of the first participant may also be referred to as a starting position, and the recorded final position of the first participant may also be referred to as a destination position. The plurality of virtual trajectories of the first participant are associated one-to-one with a plurality of virtual behaviors of the first participant. The plurality of virtual behaviors of the first participant correspond to different actions that the first participant may perform from the recorded initial position to the recorded final position while interacting or negotiating with one or more other road traffic participants. For example, in Fig. 6A , Fig. 7A , Fig. 8A , Figure 8C and Fig.9A Different exemplary scenarios for estimating an accident risk level of a first participant and one or more other road traffic participants are described in detail in .

[0070] In step 104, method 100 also includes identifying a virtual trajectory that is most similar to the recorded trajectory of the first participant among a plurality of virtual trajectories of the first participant, wherein the recorded trajectory of the first participant extends from an initial position of the first participant's record to a final position of the first participant's record. Identifying the virtual trajectory that is most similar to the recorded trajectory of the first participant among a plurality of virtual trajectories can automatically interpret one or more actions of the first participant. In one implementation, the recorded trajectory of the first participant can be characterized according to a sequence of speed and spatial position over time. In such an implementation, a distance-based similarity metric can be used to identify the virtual trajectory that is most similar to the recorded trajectory of the first participant among a plurality of virtual trajectories. For example, in Fig.9A Such implementation scenarios are described in detail in .

[0071] In step 106, method 100 also includes estimating an accident risk level based on the virtual behavior associated with the identified virtual trajectory. The accident risk level (or collision risk level) is estimated based on one or more actions performed by the first participant that are continuously collected, thereby establishing multiple collision risk features. The multiple collision risk features include the number of accidents (or collisions) that the first participant is concerned about, which refers to the number of accidents in which the first participant has performed an action (such as occupying the lane (TW) or giving way (GW) to one or more other road traffic participants). The multiple collision risk features also include the occupying and giving way ratio (TW / GW) performed by the first participant and the TR index, wherein the TR index is the number of times the first participant violates traffic rules for every 100 km of driving.

[0072] According to an embodiment, the method for generating multiple virtual trajectories of the first participant includes generating a corresponding virtual trajectory of the first participant for each of the multiple virtual behaviors of the first participant according to the corresponding virtual behaviors of the first participant. For example, at an intersection, the first participant may have different virtual behaviors, such as the first participant may give way to another traffic participant, or occupy the road from another traffic participant, or not interact with another traffic participant when crossing the intersection. For each virtual behavior of the first participant, a corresponding virtual trajectory is generated. In this way, multiple virtual trajectories are generated according to multiple virtual behaviors of the first participant (such as occupying the road, giving way, or virtual behaviors without interaction).

[0073] According to an embodiment, the method for generating multiple virtual trajectories of a first participant includes further generating a corresponding virtual trajectory of the first participant for each of the multiple virtual behaviors of the first participant based on the recorded initial position of each of the one or more other participants. For example, the recorded initial position of each of the one or more other traffic participants includes an intersection. In this case, the virtual behavior of the first participant includes giving way to one or more other traffic participants at an intersection, taking the road from one or more other traffic participants at an intersection, or a non-interaction trajectory at an intersection. Based on the different types of virtual behaviors of the first participant and the recorded initial position of each of the one or more other participants, the corresponding virtual trajectory of the first participant is generated.

[0074] According to an embodiment, the method for generating multiple virtual trajectories of a first participant includes generating a virtual final position for each of one or more other participants. The virtual final positions of one or more other traffic participants also affect the virtual behavior of the first participant and, accordingly, the virtual trajectory of the first participant.

[0075] According to an embodiment, the method includes generating a first virtual trajectory of the first participant according to a first virtual behavior of a plurality of behaviors of the first participant, wherein the first virtual trajectory of the first participant is the first virtual trajectory of the plurality of virtual trajectories of the first participant. The first virtual behavior of any traffic participant is a non-interactive behavior. For example, at an intersection, the first participant may have a first virtual behavior (or a non-interactive virtual behavior) of keeping the same speed when crossing the intersection. Therefore, the first virtual trajectory is generated according to the first virtual behavior of the first participant (i.e., keeping the same speed or a non-interactive virtual behavior).

[0076] According to an embodiment, the method includes generating a virtual trajectory of a corresponding other participant for each of one or more other participants based on the virtual behavior of the corresponding other participant, wherein the virtual trajectory of the corresponding other participant extends from the recorded initial position of the corresponding participant to the virtual final position of the corresponding participant. The virtual trajectory of each of the one or more other participants is generated based on the virtual behavior of each of the one or more other participants. For example, at an intersection, if the corresponding other traffic participant occupies the road from the first participant, the virtual trajectory of the corresponding other traffic participant is generated based on the virtual behavior of occupying the road. The virtual trajectory of the corresponding other traffic participant starts from the recorded initial position of the corresponding participant and ends at the virtual final position of the corresponding participant.

[0077] According to an embodiment, one or more proximity areas are identified based on the first virtual trajectory of the first participant and the virtual trajectory of each of the one or more other participants, each proximity area being a spatiotemporal area in which the first participant is close to at least one of the one or more other participants. The spatiotemporal area is related to the spatial position of the first participant and the one or more other participants relative to time. One or more proximity areas may also be referred to as one or more virtual proximity areas because the one or more proximity areas are identified (or calculated) using at least two virtual trajectories. Therefore, the spatial position of the first participant and the one or more other participants may also be referred to as the virtual spatial position of the first participant and the one or more other participants relative to time. This refers to the distance between the first participant and the one or more other participants in the virtual space distance at a specific moment on the first virtual trajectory. The first virtual trajectory of the first participant and the virtual trajectory of each of the one or more other participants are used to identify the virtual spatial position of the first participant, and the first participant is close to at least one of the one or more other participants in time.

[0078] According to an embodiment, another virtual trajectory of the first participant is generated for each of the one or more approach areas, and for each of one or more other virtual behaviors of the first participant's multiple virtual behaviors, based on the corresponding approach area and the corresponding another virtual behavior. For example, at an intersection, if the first participant is identified at a virtual space position close to one or more other traffic participants, the first participant can perform further virtual behaviors, such as the first participant giving way to one or more other traffic participants, or taking over the road from one or more other traffic participants to avoid a virtual collision at the intersection. A further virtual trajectory of the first participant is generated based on the corresponding further virtual behavior of the first participant (i.e., giving way or taking over the road) and the identified virtual space position.

[0079] According to an embodiment, a method for generating a virtual final position for each of one or more other participants includes generating a corresponding virtual final position based on a recorded initial position of the corresponding other participant. Generating a corresponding virtual final position of the corresponding other participant based on the recorded initial position of the corresponding other participant, thereby generating a virtual final position of one or more other participants.

[0080] According to an embodiment, generating the corresponding virtual final position is further based on a map of the area including the recorded initial position of the first participant and the recorded initial position of each of the other participants. The corresponding virtual final positions of the corresponding other participants are generated based on a high definition (HD) map of the driving area. The reason is that the HD map of the driving area includes the recorded initial position of the first participant and the recorded initial position of each of the one or more other participants.

[0081] According to an embodiment, generating the corresponding virtual final position is further based on traffic rule information, which is information about traffic rules applicable to the area. In one implementation, the HD map includes traffic rules (e.g., stop signs, yield rules, etc.) applicable to the driving area and used to generate the corresponding virtual final positions of the corresponding other participants.

[0082] According to an embodiment, the accident risk level is further estimated based on traffic rule information. In one implementation, the HD map of the driving area includes traffic rules (e.g., stop signs, yield rules, etc.) for interpreting one or more actions of the first participant and one or more other participants and estimating the accident risk level of the first participant.

[0083] Steps 102, 104, and 106 are merely illustrative, and other alternatives may be provided in which one or more steps are added, one or more steps are deleted, or one or more steps are provided in a different order without departing from the scope of the claims herein.

[0084] Figure 2 1 is a workflow according to an embodiment of the present invention, illustrating various operations of a method for estimating an accident risk level of a road traffic participant. Figure 1 Component Description Figure 2 . refer to Figure 2 , showing a workflow 200, showing a method 100 for estimating an accident risk level of a road traffic participant ( Figure 1In the workflow 200, multiple sensors 202, a driving scene 204, a collision driving trajectory generator 206, a recorded trajectory 208, a trajectory matching 210, a trajectory interpretation 212, and an accident risk level representation 214 are shown. The multiple sensors 202 include a camera 202A and a global navigation satellite system (GNSS) receiver 202B. The driving scene 204 includes multiple road traffic participants, such as a first participant 204A and one or more other participants 204B-204D, a road structure 204E, and a geo-location landmark 204F. The accident risk level representation 214 includes counts of multiple risk features, such as a count of traffic rule violations 214A, a count of lane occupation (TW) 214B, and a count of considered collisions 214C that may be performed by the first participant 204A or one or more other participants 204B-204D.

[0085] The workflow 200 illustrates various operations of the method 100 for estimating an incident risk level of the first participant 204A based on the first participant 204A's interactions and consultations with one or more other participants 204B-204D.

[0086] A plurality of sensors 202 are mounted on a first participant 204A (e.g., a vehicle) to detect and locate one or more other participants 204B-204D on a road structure 204E (i.e., a road portion). For example, the camera 202A may be a large field of view (FOV) camera with a focal length greater than 90 cm for detecting a large number of traffic participants on the road structure 204E. In one implementation, the camera 202A corresponds to a camera mounted on a dashboard or windshield of the first participant 204A and used to continuously record views of the road structure 204E and one or more other participants 204B-204D. In such an implementation, the camera 202A may also be referred to as a dashboard camera. The GNSS receiver 202B is used to locate and track the first participant 204A and one or more other participants 204B-204D by using a high-definition (HD) map. The HD map generated by the GNSS receiver 202B represents the road structure 204E, geo-location landmarks 204F, and road connectivity. Geo-location landmarks 204F include traffic lanes and traffic signs.The HD map is used to align the first participant 204A and one or more other participants 204B-204D.

[0087] The driving scene 204 corresponds to a semantic driving scene and can be explained with the help of words and sentences. The driving scene 204 is generated based on the information received from the plurality of sensors 202. Alternatively, one or more other participants 204B-204D detected and located using the camera 202A and the GNSS receiver 202B and their speed information are represented in the driving scene 204. The driving scene 204 also includes a road structure 204E, a geo-location landmark 204F, and a road connection, which together regulate the movement of the first participant 204A and one or more other participants 204B-204D. One or more other participants 204B-204D can also be represented as a second participant 204B, a third participant 204C, and a fourth participant 204D.

[0088] The track generator 206 generates multiple virtual tracks of the first participant 204A and one or more other participants 204B-204D. The multiple virtual tracks of the first participant 204A and one or more other participants 204B-204D depend on the multiple virtual behaviors of the first participant 204A and one or more other participants 204B-204D. The track generator 206 can have a tree structure with a parent node and multiple child nodes. The parent node stores the virtual behavior and corresponding virtual track of each road traffic participant in a non-interactive environment. This means that the first participant 204A and one or more other participants 204B-204D do not interact and do not move at a constant speed. For example, in one case, the first participant 204A does not interact or negotiate with one or more other participants 204B-204D, and moves at a constant speed. Therefore, the virtual behavior of keeping the same speed (KS) and the corresponding virtual track of the first participant 204A are stored in the parent node. The plurality of child nodes store a plurality of virtual behaviors (e.g., giving way or occupying a lane) and a plurality of virtual trajectories according to the interaction or negotiation between the first participant 204A and one or more other participants 204B-204D. In addition, the trajectory generator 206 stores an intention label with an identifier for each of the plurality of virtual behaviors of the first participant 204A and one or more other participants 204B-204D. For example, for the first participant 204A, the virtual behavior of giving way (GW) to one or more other participants 204B-204D is stored together with the identifier 1. The trajectory generator 206 is also referred to as a trajectory generation algorithm. For example, the trajectory generator 206 is further described in detail in Table 1.

[0089] The recorded trajectory 208 represents the actual trajectory followed by the first participant 204A. The actual trajectory of the first participant 204A is characterized by a sequence of speed and spatial position over time. Alternatively, the actual trajectory of the first participant 204A involves a spatiotemporal region.

[0090] Trajectory matching 210 represents identifying a virtual trajectory most similar to the recorded trajectory 208 of the first participant 204A from among the plurality of virtual trajectories generated by the trajectory generator 206 according to a distance-based similarity metric.

[0091] The track interpretation 212 includes automatic interpretation of the actual action (or behavior) of the first participant 204A based on the comparison between the matched virtual track and the recorded track 208 of the first participant 204A. The virtual behavior associated with the matched virtual track is regarded as the actual action of the first participant 204A. In addition, the actual action of the first participant 204A is compared with the traffic rules (e.g., stop signs, yield rules, etc.) stored on the HD map to detect whether the actual action of the first participant 204A complies with the traffic rules.

[0092] The accident risk level representation 214 includes an estimation of multiple collision risk features based on the actions performed by the first participant 204A collected continuously. The multiple collision risk features include the number of accidents concerned by the first participant 204A and the ratio of the first participant 204A to take the lane (TW) and give way (GW). The number of accidents concerned by the first participant corresponds to the number of accidents in which the first participant 204A performs an action (such as TW or GW). The ratio of the number of times the first participant 204A takes the lane (TW) and the number of times it gives way to one or more other participants 204B-204D. The accident risk level representation 214 also includes a count of traffic rule violations 214A, a count of taking the lane (TW) 214B, and a count of considered collisions 214C, which are performed by the first participant 204A to explain the more accurate actual actions of the first participant 204A.

[0093] Table 1

[0094]

[0095] Line 1 (instruction) refers to identifying multiple targets around the first participant 204A and one or more other participants 204B-204D. The multiple targets correspond to the center lane of the road that can be driven around the first participant 204A, multiple recorded initial positions and multiple recorded final positions of the first participant 204A, and multiple recorded initial positions and multiple virtual final positions of one or more other participants 204B-204D.

[0096] Lines 2 to 4 (instructions) refer to generating an initial non-interaction virtual trajectory for the first participant 204A and for one or more other participants 204B-204D. For example, if an intersection is considered, the initial non-interaction virtual trajectory of the first participant 204A and one or more other participants 204B-204D will advance through the intersection at a constant speed.

[0097] Line 5 (instructions) refers to the initialization of the trajectory generator 206 and the parent (or root) node of the road traffic participants 204A-204D. The parent node stores the virtual behavior of the first participant 204A and one or more other participants 204B-204D when moving through the intersection (ie, keep the same speed (KS)).

[0098] Line 6 (instructions) is to identify a possible number of collisions (or accidents) of the first participant 204A and one or more other participants 204B-204D based on the initial non-interaction virtual trajectories of the first participant 204A and one or more other participants 204B-204D at the intersection.

[0099] Lines 7 to 11 (instructions) refer to calculating multiple new virtual trajectories for each participant based on the possible number of collisions (or accidents) identified by the first participant 204A and one or more other participants 204B-204D. The multiple new virtual trajectories for each participant are calculated based on multiple new virtual behaviors (or intentions or negotiations or interactions) for avoiding collisions. For example, at an intersection, the first participant 204A can occupy the road (TW) or give way (GW) to one or more other participants 204B-204D to avoid an accident. After calculation, the multiple new virtual trajectories (i.e., give way trajectories or occupy the road trajectories) and multiple new virtual behaviors (i.e., give way or occupy the road) of the first participant 204A and one or more other participants 204B-204D are stored in multiple child nodes of the parent node of the trajectory generator 206.

[0100] Lines 12 to 13 (instructions) refer to identifying another possible number of collisions between the first participant 204A and multiple new virtual trajectories of one or more other participants 204B-204D. After identifying another possible number of collisions, iteratively repeat lines 7 to 12 until the identified possible number of collisions is resolved.

[0101] After resolving all identified possible numbers of collisions, the multiple final virtual trajectories and the multiple final virtual behaviors of the first participant 204A and the one or more other participants 204B-204D are stored in the trajectory generator 206. In this way, the generation of the multiple virtual trajectories is performed in a centralized iterative manner to avoid collisions. In addition, the trajectory generator 206 is iteratively updated, which stores the multiple virtual trajectories and the multiple virtual behaviors of the first participant 204A and the one or more other participants 204B-204D to avoid collisions.

[0102] Figure 3 is an exemplary driving scenario according to an embodiment of the present invention, showing the recorded initial positions of road traffic participants. Figure 1 and Figure 2 Component Description Figure 3 . refer to Figure 3 , an exemplary driving scenario 300 is shown, showing a first recorded initial position 302A of a first participant 204A and a second recorded initial position 302B of a second participant 204B on a road structure 204E. Alternatively, the first recorded initial position 302A of the first participant 204A is referred to as the starting position of the first participant 204A. Similarly, the second recorded initial position 302B of the second participant 204B is referred to as the starting position of the second participant 204B. The first recorded initial position 302A of the first participant 204A and the second recorded initial position 302B of the second participant 204B are used to generate a virtual track (or multiple virtual tracks) of the first participant 204A.

[0103] Figure 4 is an exemplary driving scenario according to an embodiment of the present invention, showing the final position of a road traffic participant. Figure 1 , Figure 2 and Figure 3 Component Description Figure 4 . refer to Figure 4 , an exemplary driving scenario 400 is shown, showing the recorded final positions 402A and 402B of the first participant 204A and the virtual final positions 404A and 404B of the second participant 204B. In one example, the virtual final positions 404A and 404B of the second participant 204B refer to possible hypothetical future positions or possible future destinations, etc.

[0104] Figure 5A is an exemplary driving scenario according to an embodiment of the present invention, showing multiple virtual trajectories of road traffic participants. Figure 1 , Figure 2 , Figure 3 and Figure 4 Component Description Figure 5A . refer to Figure 5A, an exemplary driving scenario 500A is shown, showing a first plurality of virtual tracks 502A and 502B for a first participant 204A and a second plurality of virtual tracks 504A and 504B for a second participant 204B. The first plurality of virtual tracks 502A and 502B are generated based on the first recorded initial position 302A of the first participant 204A, the recorded final positions 402A and 402B of the first participant 204A, and the second recorded initial position 302B of the second participant 204B. Similarly, the second plurality of virtual tracks 504A and 504B are generated based on the second recorded initial position 302B of the second participant 204B, the virtual final positions 404A and 404B of the second participant 204B, and the first recorded initial position 302A of the first participant 204A. The first plurality of virtual tracks 502A and 502B and the second plurality of virtual tracks 504A and 504B depend on a plurality of virtual behaviors of the first participant 204A and the second participant 204B, respectively.

[0105] Figure 5B is a graphical representation of a non-interaction motion plan of a first participant in a spatiotemporal region according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5A Component Description Figure 5B . refer to Figure 5B , showing the first participant 204A ( Figure 2 500B is a graphical representation of a non-interactive motion plan in a space-time region. The graphical representation 500B includes an X-axis 506A representing time values ​​in seconds (s) and a Y-axis 508A representing distance values ​​in meters (m).

[0106] In the graphical representation 500B, the first line 510A represents the non-interaction motion plan of the first participant 204A in the space-time region. The space-time region is associated with various spatial positions of the first participant 204A at different times. The non-interaction motion plan of the first participant 204A means that the first participant 204A does not interact or negotiate with one or more other traffic participants (e.g., the second participant 204B). The non-interaction motion plan of the first participant 204A corresponds to a virtual trajectory based on a virtual behavior (based on the virtual behavior), and therefore, the first participant 204A does not interact or negotiate with one or more other traffic participants (e.g., the second participant 204B).

[0107] Figure 5C is a graphical representation of a non-interaction motion plan of a second participant in a spatiotemporal region according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5A and Figure 5B Component Description Figure 5C . refer to Figure 5C , showing the second participant 204B ( Figure 2 500C is a graphical representation of a non-interactive motion plan in a space-time region. The graphical representation 500C includes an X-axis 506B representing time values ​​in seconds (s) and a Y-axis 508B representing distance values ​​in meters (m).

[0108] In graphical representation 500C, first line 510B represents the non-interaction motion plan of second participant 204B in the spatiotemporal region. The spatiotemporal region is associated with various spatial positions of second participant 204B at different times. The non-interaction motion plan of second participant 204B means that second participant 204B does not interact or negotiate with first participant 204A. The non-interaction motion plan of second participant 204B corresponds to a virtual trajectory based on virtual behavior (based on virtual behavior), and therefore, second participant 204B does not interact or negotiate with first participant 204A.

[0109] Figure 5D is a scene according to an embodiment of the present invention, showing a trajectory generator for a road traffic participant. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5A , Figure 5B and Figure 5C Component Description Figure 5D . refer to Figure 5D , a scene 500D is shown, including a first trajectory generator 511A of the first participant 204A and a second trajectory generator 511B of the second participant 204B. A first parent node 512 of the first trajectory generator 511A and another first parent node 514 of the second trajectory generator 511B are also shown.

[0110] The first parent node 512 of the first trajectory generator 511A is associated with the first participant 204A, and stores a plurality of virtual behaviors, a first plurality of virtual trajectories 502A and 502B, a speed profile of the first participant 204A, and a spatial path. Similarly, another first parent node 514 of the second trajectory generator 511B is associated with the second participant 204B, and stores a plurality of virtual behaviors, a second plurality of virtual trajectories 504A and 504B, a speed profile of the second participant 204B, and a spatial path. For example, at the intersection, the first participant 204A and the second participant 204B do not negotiate or interact, and move forward at the same speed. In this case, the first parent node 512 stores a virtual behavior of keeping the speed of the first participant 204A the same (KS) at the root level. Similarly, another first parent node 514 stores a virtual behavior of keeping the speed of the second participant 204B the same (KS) at the root level. The first trajectory generator 511A and the second trajectory generator 511B correspond to a tree structure having a first parent node 512 and another first parent node 514, respectively.

[0111] Fig. 6A is an exemplary driving scenario according to an embodiment of the present invention, showing a collision between road traffic participants. Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5A Component Description Fig. 6A . refer to Fig. 6A , illustrates an exemplary driving scenario 600A showing a first participant 204A and a second participant 204B colliding 602 at a T-intersection.

[0112] In driving scenario 600A, first participant 204A follows first plurality of virtual tracks 502A and 502B ( Figure 5A Similarly, the second participant 204B follows the second plurality of virtual tracks 504A and 504B ( Figure 5A ). The first participant 204A and the second participant 204B do not interact or negotiate and follow their respective virtual tracks at the same speed, which results in a collision 602 at the T-intersection. In another case, the first participant 204A follows the first plurality of virtual tracks 502A and 502B ( Figure 5A The second participant 204B follows the second plurality of virtual tracks 504A and 504B ( Figure 5A The first participant 204A and the second participant 204B do not interact or negotiate, and follow their respective virtual tracks at the same speed, which also results in a collision 602 at the T-intersection.

[0113] Figure 6B FIG. 1 is a scene according to another embodiment of the present invention, showing a trajectory generator for a road traffic participant. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5A , 5D and Fig. 6A Component Description Figure 6B . refer to Figure 6B , a scene 600B is shown, including a first trajectory generator 603A of a first participant 204A and a second trajectory generator 603B of a second participant 204B. A collision 602 associated with a first parent node 512 and another first parent node 514 is also shown.

[0114] The collision 602 is stored in the first parent node 512 of the first participant 204A and is also stored in another first parent node 514 of the second participant 204B. The collision 602 occurs due to the virtual behavior of the first participant 204A and the second participant 204B at the T-intersection (i.e., keeping the speed the same (KS)). The first participant 204A and the second participant 204B can avoid the collision 602 through interaction or negotiation, which is FIG. 7A to FIG. 7G Described in detail in.

[0115] Fig. 7A is an exemplary driving scenario showing multiple virtual trajectories of road traffic participants for avoiding collision according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5A and Fig. 6A Component Description Fig. 7A . refer to Fig. 7A , an exemplary driving scenario 700A is shown, showing a first virtual track 702A for a first participant 204A and a second virtual track 704A for a second participant 204B.

[0116] The first virtual track 702A of the first participant 204A and the second virtual track 704B of the second participant 204B are calculated based on the multiple virtual behaviors of the first participant 204A and the second participant 204B, and these virtual tracks are followed to avoid collision 602. In one example, at the T intersection ( Fig. 6A), the first participant 204A gives way (GW) to the second participant 204B and follows the first virtual track 702A. Therefore, the second participant 204B takes the way (TW) from the first participant 204A and follows the second virtual track 704A. In this way, according to the virtual behavior of the first participant 204A's GW and the second participant 204B's TW, the collision 602 is avoided. For example, Figure 7B The trajectory generator according to the virtual behavior of the first participant 204A's GW and the second participant 204B's TW is described in detail in FIG. Fig. 6A ), the first participant 204A takes the way (TW) from the second participant 204B and follows the first virtual track 702A. Therefore, the second participant 204B gives way (GW) to the first participant 204A and follows the second virtual track 704A. In this way, according to the virtual behavior of the first participant 204A's TW and the second participant 204B's GW, the collision 602 is avoided. For example, Figure 7C The trajectory generator according to the virtual behaviors of the first participant 204A's TW and the second participant 204B's GW is described in detail in . In this way, collision is avoided 602 according to multiple virtual behaviors (ie, GW or TW) of the first participant 204A and the second participant 204B.

[0117] Figure 7B FIG. 1 is a scenario according to an embodiment of the present invention, showing a trajectory generator for avoiding collisions between road traffic participants. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B and Fig. 7A Component Description Figure 7B . refer to Figure 7B , a scene 700B is shown, including a first trajectory generator 705A and a second trajectory generator 705B. The first trajectory generator 705A and the second trajectory generator 705B avoid the first participant 204A and the second participant 204B from colliding 602. Also shown are a first child node 706A of a first parent node 512 of the first trajectory generator 705A and a first child node 708A of another first parent node 514 of the second trajectory generator 705B.

[0118] The first child node 706A is based on the virtual behavior (i.e., give way (GW)) of the first participant 204A for avoiding the collision 602. Therefore, the first child node 706A of the first parent node 512 stores the virtual behavior of GW of the first participant 204A and the first virtual track 702A. Similarly, the first child node 708A of another first parent node 514 is based on the virtual behavior (i.e., stay in the way (TW)) of the second participant 204B for avoiding the collision 602. Therefore, the first child node 708A of another first parent node 514 stores the virtual behavior of TW of the second participant 204B and the second virtual track 704A.

[0119] Figure 7C FIG. 1 is a scenario according to another embodiment of the present invention, showing a trajectory generator for avoiding collisions between road traffic participants. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A and Figure 7B Component Description Figure 7C . refer to Figure 7C , a scene 700C is shown, including a first trajectory generator 707A and a second trajectory generator 707B. The first trajectory generator 707A and the second trajectory generator 707B avoid a collision between the first participant 204A and the second participant 204B. Another first child node 706B of the first parent node 512 and another first child node 708B of another first parent node 514 are also shown.

[0120] Another first child node 706B is based on the virtual behavior (i.e., keep lane (TW)) of the first participant 204A for avoiding collision 602. Therefore, another first child node 706B of the first parent node 512 stores the virtual behavior of TW of the first participant 204A and the first virtual track 702A. Similarly, another first child node 708B of another first parent node 514 is based on the virtual behavior (i.e., give way (GW)) of the second participant 204B for avoiding collision 602. Therefore, another first child node 708B of another first parent node 514 stores the virtual behavior of GW of the second participant 204B and the second virtual track 704A.

[0121] Fig.7D is a graphical representation of a motion plan of a first participant based on a virtual behavior of giving way according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A, Figure 6B , Fig. 7A and Figure 7B Component Description Fig.7D . refer to Fig.7D , showing the first participant 204A ( Figure 2 ) A graphical representation 700D of a motion plan based on a virtual behavior of giving way. The graphical representation 700D includes an X-axis 710A representing time values ​​in seconds (s) and a Y-axis 712A representing distance values ​​in meters (m).

[0122] In graphical representation 700D, first line 714A represents the speed profile of first participant 204A based on the virtual behavior of yielding to second participant 204B at T-intersection 718 to avoid collision 602. Second line 716A represents second participant 204B yielding to second participant 204B at T-intersection 718 to avoid collision 602.

[0123] Fig. 7E is a graphical representation of the motion planning of the second participant based on the virtual behavior of occupying the road according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Figure 7B and Fig.7D Component Description Fig. 7E . refer to Fig. 7E , showing the second participant 204B ( Figure 2 ) A graphical representation 700E of motion planning based on a virtual behavior of occupying a lane. The graphical representation 700E includes an X-axis 710B representing time values ​​in seconds (s) and a Y-axis 712B representing distance values ​​in meters (m).

[0124] In graphical representation 700E, first line 716B represents the speed profile of second participant 204B based on the virtual behavior of moving away from first participant 204A at T-intersection 718 to avoid collision 602. Second line 714B represents first participant 204A moving away from T-intersection 718 to avoid collision 602.

[0125] Figure 7F is a graphical representation of the motion planning of the first participant based on the virtual behavior of occupying the road according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A and Figure 7C Component Description Figure 7F . refer to Figure 7F , showing the first participant 204A ( Figure 2 ) A graphical representation 700F of motion planning based on a virtual behavior of occupying a lane. The graphical representation 700F includes an X-axis 710C representing time values ​​in seconds (s) and a Y-axis 712C representing distance values ​​in meters (m).

[0126] In graphical representation 700F, first line 714C represents the speed profile of first participant 204A based on the virtual behavior of moving away from second participant 204B at T-intersection 718 to avoid collision 602. Second line 716C represents second participant 204B moving away from T-intersection 718 to avoid collision 602.

[0127] Figure 7G is a graphical representation of a motion plan of a second participant based on a virtual behavior of giving way according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Figure 7C and Figure 7F Component Description Figure 7G . refer to Figure 7G , showing the second participant 204B ( Figure 2 ) A graphical representation 700G of motion planning based on a virtual behavior of giving way. The graphical representation 700G includes an X-axis 710D representing time values ​​in seconds (s) and a Y-axis 712D representing distance values ​​in meters (m).

[0128] In graphical representation 700G, first line 716D represents the speed profile of second participant 204B based on the virtual behavior of yielding to first participant 204A at T-intersection 718 to avoid collision 602. Second line 714D represents first participant 204A yielding to first participant 204A at T-intersection 718 to avoid collision 602.

[0129] Fig. 8A FIG. 1 is an exemplary driving scenario according to another embodiment of the present invention, showing a collision between road traffic participants. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5A , Fig. 6A and Fig. 7A Component Description Fig. 8A . refer to Fig. 8A, an exemplary driving scenario 800A including the third participant 204C is shown. A third recorded initial position 802, a third virtual final position 804, and a third virtual trajectory 806 of the third participant 204C are also shown. A collision 808 between the first participant 204A and the third participant 204C is also shown.

[0130] The third recorded initial position 802 is referred to as the starting position of the third participant 204C, and similarly, the third virtual final position 804 is referred to as a possible hypothetical future position or a possible future destination, etc. In the driving scenario 800A, the third participant 204C follows the third virtual trajectory 806 according to the virtual behavior of keeping the same speed (KS) from the third recorded initial position 802 to the third virtual final position 804, and does not negotiate with the first participant 204A. Therefore, the third participant 204C collides 808 with the first participant 204A at the trajectory point.

[0131] Figure 8B FIG. 1 is a scene according to another embodiment of the present invention, showing a trajectory generator of a road traffic participant. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Figure 7B , Figure 7C and Fig. 8A Component Description Figure 8B . refer to Figure 8B , a scene 800B is shown, including the first trajectory generator 707A of the first participant 204A, the second trajectory generator 707B of the second participant 204B, and the third trajectory generator 809A of the third participant 204C. A parent node 810 of the third trajectory generator 809A of the third participant 204C is also shown.

[0132] The parent node 810 is associated with the third participant 204C and stores a plurality of virtual behaviors, a third virtual trajectory 806, a speed curve, and a spatial path of the third participant 204C. For example, at the trajectory point, the third participant 204C does not negotiate or interact with the first participant 204A and moves forward at the same speed. In this case, the parent node 810 of the third trajectory generator 809A stores the virtual behavior of the third participant 204C of keeping the same speed (KS) at the root level.

[0133] Figure 8C is an exemplary driving scenario for avoiding collisions between road traffic participants according to yet another embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5A , Fig. 6A , Fig. 7A and Fig. 8A Component Description Figure 8C . refer to Figure 8C , an exemplary driving scenario 800C including a fourth virtual track 812 of the third participant 204C is shown.

[0134] The fourth virtual trajectory 812 of the third participant 204C is calculated based on the multiple virtual behaviors of the first participant 204A and the third participant 204C for avoiding the collision 808. The first participant 204A and the third participant 204C can avoid the collision through interaction or negotiation. In one example, at the trajectory point ( Fig. 8A ), the first participant 204A gives way to the third participant 204C (GW) and follows the first virtual track 702A. Therefore, the third participant 204C takes the way (TW) from the first participant 204A and follows the fourth virtual track 812. In this way, according to the virtual behavior of the first participant 204A giving way and the third participant 204C taking the way, the collision 808 is avoided. For example, in Fig. 8E The trajectory generator according to the virtual behavior of the first participant 204A giving way and the third participant 204C occupying the road is described in detail in FIG. Fig. 8A ), the first participant 204A takes the lane (TW) from the third participant 204C and follows the first virtual track 702A. Therefore, the third participant 204C gives way (GW) to the first participant 204A and follows the fourth virtual track 812. In this way, according to the virtual behaviors of the first participant 204A taking the lane and the third participant 204C giving way, the collision 808 is avoided. For example, in Fig.8D Detailed description is given in FIG. 8 for a trajectory generator based on the virtual behavior of the first participant 204A occupying the road (ie, TW) and the third participant 204C yielding the road. In this way, collision 808 is avoided based on multiple virtual behaviors (ie, yielding the road or occupying the road) of the first participant 204A and the third participant 204C.

[0135] Fig.8D FIG. 1 is a scenario according to an embodiment of the present invention, showing a trajectory generator for avoiding collisions between road traffic participants. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Fig. 8A , Figure 8B and Figure 8C Component Description Fig.8D. refer to Fig.8D , a scene 800D is shown, including a first trajectory generator 813A of the first participant 204A, a second trajectory generator 813B of the second participant 204B, and a third trajectory generator 813C of the third participant 204C. Also shown are a first child node 814A of the first parent node 512 of the first trajectory generator 813A and a first child node 816A of the parent node 810 of the third trajectory generator 813C. The second trajectory generator 813B corresponds to the second trajectory generator 707B ( Figure 7C of).

[0136] The first child sub-node 814A is based on the virtual behavior of the first participant 204A to stay in the way (TW) for avoiding the collision 808. Therefore, the first child sub-node 814A of the first child node 706A of the first parent node 512 stores the virtual behavior of TW of the first participant 204A and the first virtual trajectory 702. Similarly, the first child node 816A of the parent node 810 is based on the virtual behavior of the third participant 204C to stay in the way (GW) for avoiding the collision 808. Therefore, the first child node 816A of the parent node 810 stores the virtual behavior of GW of the third participant 204C and the fourth virtual trajectory 812.

[0137] Fig. 8E FIG. 1 is a scenario according to another embodiment of the present invention, showing a trajectory generator for avoiding collisions between road traffic participants. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Fig. 8A , Figure 8B , Figure 8C and Fig.8D Component Description Fig. 8E . refer to Fig. 8E , a scene 800E is shown, including a first trajectory generator 815A of the first participant 204A, a second trajectory generator 815B of the second participant 204B, and a third trajectory generator 815C of the third participant 204C. Another first child node 814B of the first parent node 512 of the first trajectory generator 815A and another first child node 816B of the parent node 810 of the third trajectory generator 815C are also shown. The second trajectory generator 815B corresponds to the second trajectory generator 707B ( Figure 7C of).

[0138] Another first child sub-node 814B is based on the virtual behavior of the first participant 204A giving way (GW) to avoid the collision 808. Therefore, another first child sub-node 814B of the first child node 706A stores the virtual behavior of the first participant 204A giving way and the first virtual track 702A. Similarly, another first child sub-node 816B of the parent node 810 is based on the virtual behavior of the third participant 204C taking the road (TW) to avoid the collision 808. Therefore, another first child sub-node 816B of the parent node 810 stores the virtual behavior of the third participant 204C taking the road and the fourth virtual track 812.

[0139] Fig.8F FIG. 1 is a scenario according to another embodiment of the present invention, showing a trajectory generator for avoiding collisions between road traffic participants. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Fig. 8A , Figure 8B , Figure 8C , Fig.8D and Fig. 8E Component Description Fig.8F . refer to Fig.8F , a scene 800F is shown, including a first trajectory generator 817A of the first participant 204A, a second trajectory generator 817B of the second participant 204B, and a third trajectory generator 817C of the third participant 204C.

[0140] Each of the first trajectory generator 817A, the second trajectory generator 817B, and the third trajectory generator 817C stores a plurality of virtual behaviors and a plurality of virtual trajectories of each of the first participant 204A, the second participant 204B, and the third participant 204C, respectively. For example, in the first trajectory generator 817A of the first participant 204A, the first parent node 512 stores a virtual behavior of keeping the first participant 204A and the virtual trajectory 502A at the same speed. The first child node 706A stores the virtual behavior of the first participant 204A giving way and the first virtual trajectory 702A to avoid a collision 602 with the second participant 204B. The first child node 814A stores the virtual behavior of the first participant 204A occupying the road and the first virtual trajectory 702A to avoid a collision 808 with the third participant 204C. The first trajectory generator 817A of the first participant 204A avoids a collision 602 with the second participant 204B ( Fig. 6A ) and collides with the third participant 204C 808. The second trajectory generator 817B of the second participant 204B avoids ( Fig. 6A The third trajectory generator 817C of the third participant 204C avoids a collision 808 with the first participant 204A.

[0141] Figure 8G is a graphical representation of a motion plan of a road traffic participant according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Fig. 8A , Figure 8B , Figure 8C , Fig.8D , Fig. 8E and Fig.8F Component Description Figure 8G . refer to Figure 8G , a graphical representation 800G of the motion planning of road traffic participants (e.g., the first participant 204A, the second participant 204B, and the third participant 204C) in a time-space region is shown. The graphical representation 800G includes an X-axis 818A representing time values ​​in seconds (s) and a Y-axis 820A representing distance values ​​in meters (m).

[0142] In graphical representation 800G, first line 822A represents a speed profile of first participant 204A based on the following virtual behaviors: yielding to second participant 204B at T-intersection 828A to avoid collision 602, and stealing from third participant 204C at trajectory point 830A to avoid collision 808. Second line 824A represents second participant 204B stealing from first participant 204A at T-intersection 828A to avoid collision 602. Third line 826A represents third participant 204C yielding to first participant 204A at trajectory point 830A to avoid collision 808.

[0143] Figure 8H is a graphical representation of a motion plan of a road traffic participant according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Fig. 8A , Figure 8B , Figure 8C , Fig.8D , Fig. 8E , Fig.8F and Figure 8G Component Description Figure 8H . refer to Figure 8H , a graphical representation 800H of the motion planning of road traffic participants (e.g., the first participant 204A, the second participant 204B, and the third participant 204C) in a time-space region is shown. The graphical representation 800H includes an X-axis 818B representing time values ​​in seconds (s) and a Y-axis 820B representing distance values ​​in meters (m).

[0144] In graphical representation 800H, first line 822B represents the speed profile of first participant 204A based on the following virtual behaviors: yielding to second participant 204B at T-intersection 828B to avoid collision 602 and yielding to third participant 204C at trajectory point 830B to avoid collision 808. Second line 824B represents second participant 204B taking over from first participant 204A at T-intersection 828B to avoid collision 602. Third line 826B represents third participant 204C taking over from first participant 204A at trajectory point 830B to avoid collision 808.

[0145] Fig.9A FIG. 1 is an exemplary driving scenario according to another embodiment of the present invention, showing a collision between road traffic participants. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5A , Fig. 6A , Fig. 7A , Fig. 8A and Figure 8C Component Description Fig.9A . refer to Fig.9A , an exemplary driving scenario 900A including a fourth participant 204D is shown. A fourth recorded initial position 902A, a fourth virtual final position 902B, and a fourth virtual trajectory 904 of the fourth participant 204D are also shown. A collision 906 between the first participant 204A and the fourth participant 204D is also shown.

[0146] The fourth recorded initial position 902A is referred to as the starting position of the fourth participant 204D, and similarly, the fourth virtual final position 902B is referred to as a possible hypothetical future position or a possible future destination, etc. In the driving scenario 900A, the fourth participant 204D follows the fourth virtual trajectory 904 according to the virtual behavior of keeping the same speed (KS) from the fourth recorded initial position 902A to the fourth virtual final position 902B, and does not negotiate with the first participant 204A. Therefore, the fourth participant 204D collides 906 with the first participant 204A at another trajectory point.

[0147] Fig. 9Bis a scene according to an embodiment of the present invention, showing a trajectory generator for a road traffic participant. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Figure 7B , Figure 7C , Fig. 8A , Figure 8C and Fig.9A Component Description Fig. 9B . refer to Fig. 9B , a scene 900B including a trajectory generator 907 of the first participant 204A is shown. A second child node 908 of the first parent node 512 of the trajectory generator 907 is also shown.

[0148] The second child sub-node 908 stores the virtual behavior of adaptive cruise control (ACC) of the first participant 204A. Due to the virtual behavior of adaptive cruise control, the first participant 204A decelerates to avoid collision 906 with the fourth participant 204D and follows the fourth participant 204D on the fourth virtual track 904. Therefore, the second child sub-node 908 of the first child sub-node 814 of the first child node 706A of the first parent node 512 of the track generator 907 stores the virtual behavior of adaptive cruise control (ACC) of the first participant 204A.

[0149] Fig. 9C is a graphical representation of a motion plan of a road traffic participant according to an embodiment of the present invention. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5D , Fig. 6A , Figure 6B , Fig. 7A , Figure 7B , Figure 7C , Fig. 8A , Figure 8C , Fig.9A and Fig. 9B Component Description Fig. 9C . refer to Fig. 9C , a graphical representation 900C of the motion planning of road traffic participants (e.g., first participant 204A, second participant 204B, third participant 204C, and fourth participant 204D) in a time-space region is shown. The graphical representation 900C includes an X-axis 910 representing time values ​​in seconds (s) and a Y-axis 912 representing distance values ​​in meters (m).

[0150] In graphical representation 900C, first line 914A represents the speed profile of first participant 204A based on the following virtual behaviors: yielding to second participant 204B at T-intersection 916A to avoid collision 602, taking lane from third participant 204C at trajectory point 916B to avoid collision 808, and finally avoiding collision 906 with fourth participant 204D at trajectory point 916C on adaptive cruise control (ACC). Second line 914B represents second participant 204B taking lane from first participant 204A at T-intersection 916A to avoid collision 602. Third line 914C represents third participant 204C yielding to first participant 204A at trajectory point 916B to avoid collision 808. Fourth line 914D represents fourth participant 204D maintaining the same speed at trajectory point 916C. Additionally, at trajectory point 916C, the first participant 204A decelerates due to the virtual behavior of the adaptive cruise control to avoid collision 906 with the fourth participant 204D and follows the fourth participant 204D on the fourth virtual trajectory 904 .

[0151] Fig.9D is a graphical representation of a count of collision risk features of a first participant according to an embodiment of the present invention. Figure 1 , Figure 2 , Fig.9A , Fig. 9B and Fig. 9C Component Description Fig.9D . refer to Fig.9D , a graphical representation 900D of the counts of the collision risk features of the first participant 204A is shown. The graphical representation 900D includes an X-axis 918 representing a plurality of collision risk features of the first participant 204A and a Y-axis 920 representing a count of a plurality of collision risk features of the first participant 204A.

[0152] In an exemplary implementation, the overall accident risk level is associated with the virtual behavior of the first participant 204A and the corresponding virtual trajectory. Therefore, the overall accident risk level depends on the counts of multiple collision risk features, such as the count of the number of times the first participant 204A violates traffic rules 922A per 100 kilometers traveled (e.g., 1), the count of lane keeping (TW) 922B performed by the first participant 204A (e.g., 1), and the count of accidents 922C (e.g., 3). The overall accident risk level is updated according to the recorded trajectory (i.e., actual action) performed by the first participant 204A, wherein the overall accident risk level is obtained by linearly combining all accident risk levels associated with the first participant 204A. In one example, the overall accident risk level (i.e., collision risk value), each accident risk level is normalized relative to the average group of the overall accident risk level, which is performed in a leveraged large data set commonly available to automobile insurance providers.

[0153] Fig. 10A is a graphical representation of the trajectory matching of the first participant in terms of the spatial path according to an embodiment of the present invention. Figure 1 , Figure 2 , FIG. 8A to FIG. 8H Component Description Fig. 10A . refer to Fig. 10A , showing the first participant 204A ( Figure 2 1. Graphical representation 1000A of a) trajectory matching in terms of a spatial path. Graphical representation 1000A includes a recorded trajectory 1002A, a virtual trajectory 1002B, and a matching curve 1004 of a first participant 204A in a spatial path region.

[0154] The recorded trajectory 1002A corresponds to the actual trajectory performed by the first participant 204A. The virtual trajectory 1002B corresponds to one of the multiple virtual trajectories generated by using a trajectory generator (e.g., trajectory generator 817A). The matching curve 1004 is used to find a trajectory (e.g., virtual trajectory 1002B) that is most similar to the recorded trajectory 1002A among the multiple virtual trajectories. The matching curve 1004 represents the degree to which the recorded trajectory 1002A matches the virtual trajectory 1002B of the first participant 204A. The matching between the recorded trajectory 1002A and the virtual trajectory 1002B is performed based on a distance-based similarity metric. Based on the matching between the recorded trajectory 1002A and the virtual trajectory 1002B, the actual action of the first participant 204A can be automatically interpreted.

[0155] Fig. 10B is a graphical representation of the trajectory matching of the first participant in the space-time region according to an embodiment of the present invention. Figure 1 , Figure 2 , FIG. 8A to FIG. 8H and Fig. 10AComponent Description Fig. 10B . refer to Fig. 10B , showing the first participant 204A ( Figure 2 A) graphical representation 1000B of trajectory matching in a spatiotemporal region. The graphical representation 1000B includes a recorded speed curve 1006A, a virtual speed curve 1006B, another matching curve 1008, and a correlation score 1010 for the first participant.

[0156] The recorded speed curve 1006A corresponds to the actual speed curve (i.e., spatial position relative to time) of the first participant 204A. The recorded speed curve 1006A is based on the recorded track 1002A of the first participant 204A. The virtual speed curve 1006B is based on the virtual track 1002B of the first participant 204A. The virtual speed curve 1006B is also based on multiple virtual behaviors (e.g., giving way, occupying the road, etc.) of the first participant 204A. Another matching curve 1008 is used to find the speed curve (e.g., virtual speed curve 1006B) that is most similar to the recorded speed curve 1006A among multiple virtual speed curves. Another matching curve 1008 represents the matching degree of the recorded speed curve 1006A and the virtual speed curve 1006B of the first participant 204A. According to the matching between the recorded speed curve 1006A and the virtual speed curve 1006B of the first participant 204A, a correlation score 1010 is generated. The correlation score 1010 can be used to automatically interpret the actual action of the first participant 204A.

[0157] Fig. 10C is a graphical representation of the matching score of the first participant in the spatial path area according to an embodiment of the present invention. Figure 1 , Figure 2 , FIG. 8A to FIG. 8H , Fig. 10A and Fig. 10B Component Description Fig. 10C . refer to Fig. 10C , a graphical representation 1000C of a match score 1012 of the first participant 204A in the spatial path region is shown. The match score 1012 is obtained by collecting samples from the recorded track 1002A of the first participant 204A at each time step (e.g., every 1 second). The coordinates of the sampling moment of the recorded track 1002A are compared with the sampling moments of the multiple virtual tracks of the first participant 204A. Based on the comparison, one virtual track (e.g., virtual track 1002B) among the multiple virtual tracks that has the lowest distance to the recorded track 1002A is selected. The selected virtual track has the highest match score with the recorded track 1002A of the first participant 204A.

[0158] Fig. 10Dis a graphical representation of the matching score of the first participant in the spatiotemporal region according to an embodiment of the present invention. Figure 1 , Figure 2 , FIG. 8A to FIG. 8H , Fig. 10A , Fig. 10B and Fig. 10C Component Description Fig. 10C . refer to Fig. 10D , a graphical representation 1000D of a match score 1014 of a first participant 204A in a spatiotemporal region is shown. The match score 1014 is obtained by collecting samples from the recorded speed curve 1006A of the first participant 204A at each time step (e.g., every 1 second). The coordinates of the sampling moment of the recorded speed curve 1006A are compared with the sampling moments of multiple virtual speed curves of the first participant 204A. Based on the comparison, a virtual speed curve (e.g., virtual speed curve 1006B) having the lowest distance to the recorded speed curve 1006A is selected from the multiple virtual speed curves. The selected virtual speed curve has the highest match score with the recorded speed curve 1006A of the first participant 204A. The lowest distance between the recorded speed curve 1006A and the virtual speed curve (e.g., virtual speed curve 1006B) is calculated by using the following formula (Formula 1):

[0159]

[0160] in,

[0161] D = distance (cm);

[0162] t = time (seconds);

[0163] p GT = Recording track of the first participant 204A

[0164] p generated = the virtual trajectory of the first participant 204A.

[0165] Fig.11A is a network environment diagram of a system having multiple traffic participants and a server according to an embodiment of the present invention. Figure 1 and Figure 2 Component Description Fig.11A . refer to Fig.11A , shows a network environment of a system 1100A including a plurality of traffic participants 1102, a server 1104, and a communication network 1106. The plurality of traffic participants 1102 include a first participant 1102A and one or more other participants 1102B-1102N.

[0166] The first participant 1102A and one or more other participants 1102B-1102N correspond to Figure 2 The first participant 204A and one or more other participants 204B-204D of the plurality of traffic participants 1102. In one implementation, each of the plurality of traffic participants 1102 corresponds to a non-autonomous driving vehicle (e.g., a human-driven vehicle). A non-autonomous driving vehicle refers to a two-wheeled vehicle or a vehicle with more than one wheel. One or more other participants 1102B-1102N also include pedestrians. In another implementation, each of the plurality of traffic participants 1102 corresponds to an autonomous driving vehicle (e.g., a robot vehicle or an unmanned vehicle). In yet another implementation, each of the plurality of traffic participants 1102 corresponds to a semi-autonomous driving vehicle.

[0167] The server 1104 includes appropriate logic, circuitry, interfaces and / or code for receiving multiple collision risk updates from multiple traffic participants 1102 via a communication network 1106. The server 1104 is located on the side of the automobile insurance provider. The received multiple collision risk updates are used to detect whether the multiple traffic participants 1102 are tilted relative to each other and to what extent, and to negotiate collision situations, such as merging traffic, leaving a highway, or an unsignalized intersection. The received multiple collision risk updates are also used to estimate the actual actions of traffic participants such as the first participant 1102A. Thereafter, based on the HD map of the GNSS receiver 1118B, the actual actions of the first participant 1102A are used to verify whether the first participant 1102A complies with traffic rules (e.g., yield traffic signs or rules to give way to right-hand vehicles) that regulate the interactions between the multiple traffic participants 1102. Based on this information, the first participant 1102A is provided with a policy premium.

[0168] The communication network 1106 is used to transmit a plurality of collision risk updates from the first participant 1102A to the server 1104. Examples of the communication network 1106 may include, but are not limited to, the Internet, a vehicular ad-hoc network (VANET), an intelligent vehicular ad-hoc network (InVANET), a wireless sensor network (WSN), a cloud network, and / or a wireless fidelity (Wi-Fi) network.

[0169] Fig. 11B is a block diagram of various exemplary components of a first participant according to an embodiment of the present invention. Figure 1 , Figure 2 and Fig.11A Component Description Fig. 11B. refer to Fig. 11B , a first participant 1102A is shown, including an electronic control unit (ECU) 1108, an onboard network 1110, a display 1112, an electric power system 1114, a powertrain control system 1116, and a plurality of sensors 1118. The electronic control unit 1108 includes a microprocessor 1108A and a memory 1108B. The plurality of sensors 1118 include a camera 1118A and a GNSS receiver 1118B.

[0170] The electronic control unit 1108 may include suitable logic, circuitry, interfaces, and / or code that may be operable to monitor and optimize performance of the power system 1114 .

[0171] The microprocessor 1108A of the electronic control unit 1108 may include suitable logic, circuitry, interfaces and / or code for executing a set of instructions stored in the memory 1108B. Examples of the microprocessor 1108A include, but are not limited to, a reduced instruction set computing (RISC) processor, an application-specific integrated circuit (ASIC) processor, a complex instruction set computing (CISC) processor, an explicitly parallel instruction computing (EPIC) processor, a very long instruction word (VLIW) processor, a microcontroller, a central processing unit (CPU), a graphics processing unit (GPU), a state machine, and / or other processors or circuits.

[0172] The memory 1108B includes appropriate logic, circuitry, and / or interfaces for storing machine code and / or a set of instructions, at least one code portion of which can be executed by the microprocessor 1108A. The memory 1108B is also used to store trajectory generation algorithms, one or more text-to-speech conversion algorithms, one or more speech generation algorithms, audio data corresponding to various buzzer sounds, and / or other data. Examples of implementations of the memory 1108B may include, but are not limited to, electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), read only memory (ROM), hard disk drive (HDD), flash memory, secure digital (SD) card, solid-state drive (SSD), and / or CPU cache memory.

[0173] The in-vehicle network 1110 includes a medium through which various control units, components, or systems of the first participant 1102A, such as the electronic control unit 1108 , the powertrain control system 1116 , and the plurality of sensors 1118 , communicate with one another. Examples of wired and wireless communication protocols for the in-vehicle network 1110 may include, but are not limited to, vehicle area network (VAN), CAN bus, domestic digital bus (D2B), time-triggered protocol (TTP), FlexRay, IEEE 1394, inter-integrated circuit (I2C), inter equipment bus (IEBus), Society of Automotive Engineers (SAE) J1708, SAE J1939, international organization for standardization (ISO) 11992, ISO 11783, media oriented systems transport (MOST), MOST25, MOST50, MOST150, plastic optical fiber (POF), power-line communication (PLC), serial peripheral interface (SPI) bus and / or local interconnect network (LIN).

[0174] The trajectory planner 1111 includes suitable logic, circuitry, and / or interfaces for generating and storing a plurality of virtual trajectories for each of the plurality of traffic participants 1102. The trajectory planner 1111 is communicatively coupled to the electronic control unit 1108. Examples of the trajectory planner 1111 include, but are not limited to, a computing device, a microprocessor, a microcontroller, a central processing unit (CPU), a graphics processing unit (GPU), a state machine, and / or other processors or circuits.

[0175] Display 1112 refers to a display screen for displaying different types of information to first participant 1102A. Display 1112 may refer to a touch screen display. Display 1112 is communicatively coupled to microprocessor 1108A. Examples of display 1112 may include, but are not limited to, a heads-up display (HUD) or a head-up display with an augmented reality system (AR-HUD), a driver information console (DIC), a projection-based display, a head unit display, a see-through display, a smart glass display, and / or an electrochromic display. The AR-HUD may be a combiner-based AR-HUD. Display 1112 may be a transparent display or a translucent display.

[0176] The power system 1114 is used to provide power backup for various components of the first participant 1102A. In one example, the first participant 1102A is an autonomous vehicle, and the power system 1114 is used to provide the required voltage for various components of the first participant 1102A. The power system 1114 corresponds to power electronics and may include a microcontroller that is communicatively coupled (shown by a dotted line) to the electronic control unit 1108. The power system 1114 is also communicatively coupled to the vehicle network 1110.

[0177] The powertrain control system 1116 is used to control ignition, fuel injection, and / or fuel exhaust of the first participant 1102A.

[0178] The plurality of sensors 1118 correspond to Figure 2 Similarly, the camera 1118A and the GNSS receiver 1118B correspond to the camera 202A and the GNSS receiver 202B, respectively.

[0179] Those skilled in the art should understand that the first participant 1102A may also include other suitable sensors, components or systems, such as an audio / video interface, but for the sake of brevity, they are not described herein.

[0180] In operation, the trajectory planner 1111 is used to estimate the accident risk level of a road traffic participant. The road traffic participant is a first participant among a plurality of road traffic participants. The plurality of road traffic participants include the first participant and one or more other participants. In order to estimate the accident risk level of the first participant, the trajectory planner 1111 is used to generate a plurality of virtual trajectories of the first participant according to the following items: the recorded initial position of the first participant, the recorded final position of the first participant, and the recorded initial position of each of the one or more other participants. Each virtual trajectory of the first participant extends from the recorded initial position of the first participant to the recorded final position of the first participant. The plurality of virtual trajectories of the first participant are associated one-to-one with the plurality of virtual behaviors of the first participant. The trajectory planner 1111 is also used to identify the virtual trajectory that is most similar to the recorded trajectory of the first participant among the plurality of virtual trajectories of the first participant, the recorded trajectory of the first participant extending from the recorded initial position of the first participant to the recorded final position. The trajectory planner 1111 is also used to estimate the accident risk level according to the virtual behaviors associated with the virtual trajectories identified in the table. The trajectory planner 1111 is also used to generate multiple virtual trajectories of the first participant by generating a corresponding virtual trajectory of the first participant for each of the multiple virtual behaviors of the first participant according to the corresponding virtual behavior of the first participant. The trajectory planner 1111 is also used to generate multiple virtual trajectories of the first participant by generating a corresponding virtual trajectory of the first participant for each of the multiple virtual behaviors of the first participant according to the recorded initial position of each of one or more other participants. The trajectory planner 1111 is also used to generate multiple virtual trajectories of the first participant by generating a virtual final position for each of the one or more other participants. The trajectory planner 1111 is also used to generate multiple virtual trajectories of the first participant by generating a first virtual trajectory of the first participant according to a first virtual behavior of the multiple behaviors of the first participant, wherein the first virtual trajectory of the first participant is the first virtual trajectory of the multiple virtual trajectories of the first participant. The trajectory planner 1111 is also used to generate multiple virtual trajectories of the first participant by generating a corresponding virtual trajectory of the other participant for each of one or more other participants according to the virtual behavior of the corresponding other participants, wherein the virtual trajectory of the corresponding other participants extends from the recorded initial position of the corresponding participant to the virtual final position of the corresponding participant.The trajectory planner 1111 is also used to generate multiple virtual trajectories of the first participant by identifying one or more proximity areas according to the first virtual trajectory of the first participant and according to the virtual trajectory of each of the one or more other participants, wherein each proximity area is a spatiotemporal area in which the first participant is close to at least one of the one or more other participants, and for each of the one or more proximity areas, and for each of the one or more other virtual behaviors of the first participant, another virtual trajectory of the first participant is generated according to the corresponding proximity area and according to the corresponding other virtual behaviors. The trajectory planner 1111 is also used to generate a virtual final position for each of the one or more other participants by generating a corresponding virtual final position according to the recorded initial position of the corresponding other participants. The trajectory planner 1111 is also used to generate a corresponding virtual final position according to a map of an area including the recorded initial position of the first participant and the recorded initial position of each of the other participants. The trajectory planner 1111 is also used to generate a corresponding virtual final position according to traffic rule information, which is information about traffic rules applicable to the area. The trajectory planner 1111 is also used to estimate the accident risk level according to the traffic rule information.

[0181] Fig. 11C is a block diagram of various exemplary components of a server according to an embodiment of the present invention. Figure 1 , Figure 2 , Fig.11A and Fig. 11B Component Description Fig. 11C . refer to Fig. 11C , a server 1104 is shown. The server 1104 includes a microprocessor 1104A and a memory 1104B.

[0182] The microprocessor 1104A may include suitable logic, circuitry, interfaces and / or code for executing a set of instructions stored in the memory 1104B. Examples of the microprocessor 1104A include, but are not limited to, a reduced instruction set computing (RISC) processor, an application-specific integrated circuit (ASIC) processor, a complex instruction set computing (CISC) processor, an explicitly parallel instruction computing (EPIC) processor, a very long instruction word (VLIW) processor, a microcontroller, a central processing unit (CPU), a graphics processing unit (GPU), a state machine, and / or other processors or circuits.

[0183] The memory 1104B includes suitable logic, circuitry, and / or interfaces for storing machine code and / or a set of instructions, at least a portion of which is executable by the microprocessor 1104A. Examples of implementations of the memory 1104B may include, but are not limited to, electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), read only memory (ROM), hard disk drive (HDD), flash memory, secure digital (SD) card, solid-state drive (SSD), and / or CPU cache memory.

[0184] Fig.12 is an exemplary implementation of the calculation of the standardized risk characteristics of the first participant according to an embodiment of the present invention. Figure 1 , Figure 2 , Fig.11A , Fig. 11B and Fig. 11C Component Description Fig.12 . refer to Fig.12, an exemplary implementation 1200 of calculating a standardized risk profile for a first participant 204A is shown. The exemplary implementation 1200 includes an accident risk assessor 1202, a TW / GW ratio 1204, traffic rule violations 1206, a number of accidents of interest 1208, and a plurality of group risk profiles 1210. An overall accident risk 1212 is further shown.

[0185] The accident risk assessor 1202 assesses an overall accident risk 1212. The overall accident risk 1212 may also be referred to as the collision risk of the first participant 204A. The overall accident risk 1212 is assessed based on the collision risk characteristics using the formulas (Formula 2 and Formula 3), the collision risk characteristics being the TW / GW ratio 1204, the number of traffic rule violations 1206, the number of accidents of interest 1208, and the plurality of group risk characteristics 1210 of the first participant 204A, etc.

[0186]

[0187]

[0188] in,

[0189] RF norm = the standardized risk profile of the first participant 204A,

[0190] RF user = the collision risk characteristic of the first participant 204A,

[0191] RF popluation = the group risk profile of the first participant 204A,

[0192] CR = collision risk of the first participant 204A,

[0193] α0TW norm = Count of occupied lanes (TW)

[0194] α1BTR / km norm = Traffic violation count

[0195] α2Ncollision norm =Count of collisions of interest

[0196] The matching of the recorded trajectory of the first participant 204A with the virtual trajectory provides collision risk characteristics, such as the TW / GW ratio 1204, the number of traffic rule violations 1206, and the number of accidents of concern 1208. These collision risk characteristics are used to derive the collision risk (CR) of the first participant 204A using Formula 2 and Formula 3.

[0197] In another implementation, the collision risk of the first participant 204A may be calculated by comparing the collision risk characteristics (or specific risk characteristics) of the first participant 204A with the collision risk characteristics (or specific risk characteristics) of one or more other participants 204B-204D. For example, if the first participant 204A is identified as frequently occupying the road at an intersection (which results in a larger TW / GW ratio) and violating the yield traffic rules (which results in a larger TR index), the collision risk of the first participant 204A will have a larger value, and the driving style of the first participant 204A is considered to be very dangerous.

[0198] Many other technical implementations and practical applications can estimate the accident risk level of the first participant 1102A with one or more other participants 1102B-1102N. In one example, once the accurate accident risk level is estimated, the microprocessor 1108A in the vehicle can be used to generate an alarm in the vehicle (i.e., the first participant 1102A) to avoid an accident with one or more other participants 1102B-1102N. Using the trajectory planner 1111 in the first participant 1102A can help the first participant 1102A drive safely because the microprocessor 1108A enables the trajectory planner 1111 to actively generate an alarm in the vehicle (i.e., the first participant 1102A) to avoid an accident with one or more other participants 1102B-1102N. In another example, using the trajectory generator 1111 in an autonomous vehicle (i.e., a robotic vehicle) can improve the functionality of the vehicle. For example, by utilizing an accurate accident risk level, any potential damage to the vehicle due to a collision, etc., can be avoided, whereas a collision may occur through active actions (e.g., applying brakes at the right moment, choosing the right direction, adjusting speed, etc.). In addition, a vehicle can communicate with another vehicle in a v2v communication to help the other vehicle apply appropriate controls, such as braking, adjusting speed, etc., to actively avoid any accident. In yet another example, in a scenario of hundreds to thousands of traffic participants, a server (e.g., server 1104) owned by a car insurance provider can be used to automatically update a database, wherein the accident risk levels of all traffic participants are updated. This helps to generate accurate, factual, and logical pricing for policyholders with such vehicle policies. In addition, server 1104 can also identify the true cause of the accident, which may be caused by less interaction or negotiation between the first participant 1102A and one or more other participants 1102B-1102N or violation of traffic rules, etc. In addition, server 1104 can also identify who is responsible for the accident among the first participant 1102A and one or more other participants 1102B-1102N. Notifications may be sent to relevant users.

[0199] Without departing from the scope of the invention as defined by the appended claims, the embodiments of the invention described above may be modified. Expressions such as "including", "combined with", "having", "is" etc. used to describe and claim the present invention are intended to be interpreted in a non-exclusive manner, that is, items, parts or elements that are not explicitly described are allowed to exist. References to the singular should also be interpreted as being related to the plural. The word "exemplary" used herein means "as an example, instance or illustration". Any embodiment described as "exemplary" is not necessarily interpreted as being more preferred or more advantageous than other embodiments, nor is it necessarily excluded from the combination of the features of other embodiments. The word "optionally" used herein means "provided in some embodiments and not provided in other embodiments". It should be understood that some features of the present invention described in the context of a separate embodiment for the sake of clarity may also be provided in combination in a single embodiment. On the contrary, the various features of the present invention described in the context of a single embodiment for the sake of brevity may also be provided separately, in any suitable combination, or suitable for any other described embodiment of the present invention.

Claims

1. A method for estimating the accident risk level of road traffic participants, characterized in that: The road traffic participant is a first participant among a plurality of road traffic participants, the plurality of road traffic participants including the first participant and one or more other participants, and the method comprises: generating, according to the recorded initial position of the first participant and the recorded final position of the first participant, a plurality of virtual trajectories of the first participant extending from the recorded initial position of the first participant to the recorded final position of the first participant, wherein the plurality of virtual trajectories of the first participant are associated one-to-one with a plurality of virtual behaviors of the first participant; identifying, among the plurality of virtual trajectories of the first participant, a virtual trajectory that is most similar to a recorded trajectory of the first participant extending from the recorded initial position of the first participant to the recorded final position of the first participant; The accident risk level is estimated based on a virtual behavior associated with the identified virtual trajectory.

2. The method according to claim 1, characterized in that The generating the plurality of virtual trajectories of the first participant comprises: According to the corresponding virtual behavior of the first participant, a corresponding virtual trajectory of the first participant is generated for each of the plurality of virtual behaviors of the first participant.

3. The method according to claim 1 or 2, characterized in that: The generating the plurality of virtual trajectories of the first participant comprises: Further based on the recorded initial position of each of the one or more other participants, a corresponding virtual trajectory of the first participant is generated for each of the multiple virtual behaviors of the first participant.

4. The method according to claim 3, characterized in that: The generating the plurality of virtual trajectories of the first participant comprises: generating a virtual final position for each of the one or more other participants; generating a first virtual trajectory of the first participant according to a first virtual behavior among the plurality of behaviors of the first participant, wherein the first virtual trajectory of the first participant is a first virtual trajectory among the plurality of virtual trajectories of the first participant; generating a virtual trajectory of the corresponding other participant for each of the one or more other participants based on the virtual behavior of the corresponding other participant, wherein the virtual trajectory of the corresponding other participant extends from the recorded initial position of the corresponding participant to the virtual final position of the corresponding participant; identifying one or more proximity regions based on the first virtual trajectory of the first participant and the virtual trajectory of each of the one or more other participants, wherein each proximity region is a spatiotemporal region in which the first participant is in proximity to at least one of the one or more other participants; Based on the corresponding approach area and the corresponding another virtual behavior, another virtual trajectory of the first participant is generated for each of the one or more approach areas, and for each of one or more other virtual behaviors of the multiple virtual behaviors of the first participant.

5. The method according to claim 4, characterized in that Generating a virtual final position for each of the one or more other participants comprises: The corresponding virtual final position is generated according to the recorded initial position of the corresponding other participant.

6. The method according to claim 5, characterized in that The generating of the corresponding virtual final position is further based on: A map of an area including the recorded initial location of the first participant and the recorded initial location of each of the other participants.

7. The method according to claim 6, characterized in that The generation of the corresponding virtual final position is further based on: Traffic regulation information, the traffic regulation information is information on traffic regulations applicable to the area.

8. The method according to claim 7, characterized in that The estimating the accident risk level is further based on the traffic regulation information.

9. A device for estimating the accident risk level of road traffic participants, characterized in that: include: A memory storing instructions; A processor coupled to the memory, wherein the processor calls instructions stored in the memory to execute the method according to any one of claims 1 to 8.

10. A non-transitory computer readable medium, characterized in that The device carries a program code which, when executed by a computer, causes the computer to execute the method according to any one of claims 1 to 8.

Images