Collision warning based on intersection information in map messages

Abstract

The pedestrian collision warning system includes a transceiver, a memory, and a control module. The transceiver receives a PSM and a map message at the vehicle. The memory stores map data. The control module identifies an expected collision box where a vehicle and a pedestrian are expected to exist simultaneously based on the message, determines a most likely path for the vehicle to pass through the intersection from among a plurality of possible intersection paths based on the map data and the map message, determines whether a vehicle and a pedestrian are likely to exist simultaneously in the expected collision box based on the most likely path for the vehicle and the expected collision box, and warns a vehicle occupant or a pedestrian of a possible collision in response to determining that a vehicle and a pedestrian are likely to exist simultaneously in one expected collision box.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Non-provisional Application No. 17 / 710,361, filed March 31, 2022, the entire disclosure of which is incorporated herein by reference. [Technical field]

[0002] The present disclosure relates to vehicle route tracking and broadcast systems. [Background technology]

[0003] The background description provided herein is intended to provide a general overview of the context of the present disclosure. The work of the inventors named herein is not admitted, expressly or impliedly, as prior art to the present disclosure, as are features of the present specification that are not admitted as prior art at the time of filing, to the extent that they are described in this Background section.

[0004] Vehicle-to-everything (V2X) systems implement vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. In a V2X system, map messages may be transmitted that include data indicating the path of a vehicle on roads and between intersections. The map messages may be transmitted from a roadside unit (RSU) and received by the vehicle. The vehicle may use the map data for position and navigation purposes and / or for collision avoidance with other vehicles and / or objects. Summary of the Invention

[0005] This section provides a general summary of the disclosure and is not a comprehensive disclosure of its entire scope or all features.

[0006] The remote station of the present disclosure includes a transceiver, a memory, and a control module. The memory is configured to store (i) a plurality of reference static routes of a vehicle passing through an intersection, and (ii) map data. The control module is configured to obtain road hazard information based on the reference static routes and the map data, determine whether the road hazard information affects one or more reference static routes of the vehicle passing through the intersection, update the one or more reference static routes based on the road hazard information, and broadcast a map message indicating the updated one or more reference static routes via the transceiver.

[0007] In other features, the reference static path is a predicted path of the vehicle through the intersection from an incoming lane toward the intersection to an outgoing lane leaving the intersection. In other features, the reference static path includes two-dimensional or three-dimensional path information. In other features, the control module is configured to determine at a predetermined frequency whether the road hazard information affects any of the plurality of reference static paths.

[0008] In other features, the control module is configured to determine a dynamic path based on at least one of the camera, other sensor data, and the primary safety messages, compare the dynamic path to a reference static path, and update the reference static path based on a result of the comparison between the dynamic path and the reference static path. In other features, the dynamic path is an actual path of the vehicle passing through the intersection from an incoming lane into the intersection to an outgoing lane leaving the intersection.

[0009] In other features, the road hazard information includes at least one of lane closure information and road closure information. In other features, the road hazard information also includes accident information. In other features, the road hazard information also includes road repair information. In other features, the remote station is implemented as an intersection camera, a traffic light, an RSU, a cloud-based server, a back-end server, or an edge computing device.

[0010] In other features, the control module is configured to connect to one or more intersection cameras, track movement of vehicles through the intersection based on signals from the one or more intersection cameras, and update the reference static path based on the tracked movement of the vehicles.

[0011] In other features, the transceiver communicates with the one or more intersection cameras via Ethernet communication, Long-Term Evolution (LTE) communication, 5G communication, or Wi-Fi communication.

[0012] In other features, the remote station further includes a camera configured to capture images of the intersection, and the control module is configured to track movement of the vehicle through the intersection based on the captured images and update the reference static path based on the tracked movement of the vehicle.

[0013] In other features, the control module is configured to (i) connect to a cloud-based server, an edge computing device, or a back-end server, and collect captured imagery from one or more cameras that track vehicles passing through the intersection, and (ii) update the reference static path based on the movement of the tracked vehicles.

[0014] In other features, the control module is configured to (i) receive captured imagery from a camera having a field of view covering at least a portion of the intersection, (ii) transform positions of objects within the intersection into three-dimensional global position system coordinates based on the captured imagery, and (iii) update the reference static path based on the three-dimensional global position system coordinates.

[0015] In other features, the control module is configured to tag vehicle data, track a path of the vehicle through the intersection from an incoming lane to an outgoing lane, determine a speed and a yaw rate of the vehicle through the intersection, calculate a three-dimensional vehicle position within the intersection and in the plurality of frames based on the tracked path of the vehicle and the speed and yaw rate of the vehicle, and update the reference static path based on the three-dimensional vehicle position. In other features, the control module is configured to receive primary safety messages from one or more vehicles and update the reference static path based on the primary safety messages.

[0016] In other features, the control module is configured to receive data from one or more cameras having a field of view covering at least a portion of the intersection, fuse the data received from the one or more cameras with data in the primary safety message to generate an aggregate dataset, and update the reference static route based on the aggregate dataset including at least one of a node list or a radius of curvature of paths of one or more vehicles passing through the intersection.

[0017] In another feature, a remote station is disclosed that includes a transceiver, a memory, and a control module. The memory is configured to store a plurality of reference static routes and a plurality of dynamic routes for a vehicle passing through an intersection, where the reference static routes refer to at least one of a past predetermined route, an averaged route, or a route that has actually been used, and the dynamic route refers to a currently detected route. The control module is configured to (i) compare the dynamic route to the reference static route, (ii) determine whether there is a statistical significance between the dynamic route and the reference static route, (iii) in response to the statistical significance between the dynamic route and the reference static route, broadcast a first map message indicative of the dynamic route via the transceiver, and (iv) in response to the lack of statistical significance between the dynamic route and the reference static route, broadcast a second map message indicative of the reference static route via the transceiver.

[0018] In another feature, the control module is configured to generate a set of nodes or a turning radius by averaging trajectories of a plurality of vehicles to determine one of a plurality of dynamic paths. In another feature, a case where there is statistical significance between the dynamic path and the reference static path is when a difference between the dynamic path and the reference static path is greater than a predetermined amount. In another feature, a case where there is statistical significance between the dynamic path and the reference static path is when at least a portion of the dynamic path deviates from a baseline static path by a predetermined amount or more. In another feature, a case where there is statistical significance between the dynamic path and the reference static path is when an average of differences between a plurality of nodes constituting one dynamic path and a plurality of nodes constituting one reference static path exceeds a predetermined amount. In another feature, a case where there is statistical significance between the dynamic path and the reference static path is when a difference rate between a plurality of nodes constituting one dynamic path and a plurality of nodes constituting one reference static path exceeds a predetermined value.

[0019] In other features, the control module is configured to adjust a window period for tracking the vehicle to determine the dynamic route.In other features, the control module is configured to adjust a frequency of averaging a trajectory of the vehicle to determine the averaged dynamic route, and broadcast a map message including the averaged dynamic route if a difference between the averaged dynamic route and the at least one reference static route is statistically significant.

[0020] In other features, the map message includes intersection box route data indicating a position of the vehicle within the intersection. In other features, the map message is a V2X type map message.

[0021] In other features, the control module is configured to obtain map data and road hazard information, determine whether the road hazard information affects one or more reference static routes of the vehicle through the intersection based on the reference static route and the map data, update the one or more reference static routes based on the road hazard information, and broadcast via the transceiver a third map message indicating the updated one or more reference static routes.

[0022] In another feature, a remote station is disclosed that includes a transceiver, a memory, and a control module. The memory is configured to store first route data for a vehicle passing through an intersection. The control module is configured to (i) receive at least one of road hazard information or current vehicle route information, (ii) update the first route data based on at least one of the road hazard information and the current vehicle route information, and (iii) broadcast, via the transceiver, a first map message including the updated first route data, the map message including a first data element that defines a vehicle route through the intersection.

[0023] In other features, the map message is a V2X type map message. In other features, the first data element includes at least one of: (i) a radius of curvature of the path through the intersection, (ii) a node list of locations of the path through the intersection, and (iii) latitude and longitude coordinates of a point along the path through the intersection.

[0024] In other features, the map message includes a generic lane frame including the second data element and one connecting frame, the connecting frame including a plurality of connecting frames, the one connecting frame including the intersection route frame.

[0025] In other features, the second data element includes two or more of (i) a frame identifier, (ii) a name, (iii) a lane attribute, (iv) an entry approach, (v) an exit approach, (vi) an operation, or (vii) a node list. In other features, the map message has a tree structure including (i) a generic lane frame at a first layer of the tree structure, (ii) a second data element and a connecting frame at a second layer of the tree structure, (iii) a connecting frame at a third layer of the tree structure, (iv) an intersection path frame at a fourth layer of the tree structure, and (v) a first data element at a fifth layer of the tree structure.

[0026] In another feature, the first route data includes a reference static route.The control module is configured to (i) receive road hazard information and (ii) update the first route data based on the road hazard information.

[0027] In other features, the road hazard information includes at least one of lane closure information, road closure information, accident information, and road repair information.

[0028] In another feature, the first route data includes a reference static route and a dynamic route, and the control module is configured to (i) compare the current vehicle route information to the reference static route, (ii) determine whether there is a statistical significance between the current vehicle route information and the reference static route, (iii) in response to there being a statistical significance between the current vehicle route information and the reference static route, broadcast using the transceiver a first map message indicative of the current vehicle route information, and (iv) in response to there being no statistical significance between the current vehicle route information and the reference static route, broadcast via the transceiver a second map message indicative of the reference static route.

[0029] In other features, a remote station is provided that includes a transceiver, a memory, and a control module. The memory is configured to store first route data for a vehicle passing through an intersection. The control module is configured to (i) receive at least one of road hazard information or current vehicle route information, (ii) update the first route data based on at least one of the road hazard information or current vehicle route information, and (iii) broadcast, via the transceiver, a map message including the updated first route data, the map message including (a) a connection frame including an intersection route frame identifier connector to an intersection route frame in the map message, and (ii) an intersection route frame including a first data element defining a vehicle route through the intersection.

[0030] In other features, the map message is a V2X type map message. In other features, the first data element includes at least one of: (i) a radius of curvature of the path through the intersection, (ii) a node list of locations of the path through the intersection, and (iii) latitude and longitude coordinates of a point along the path through the intersection.

[0031] In other features, the map message includes a generic lane frame including the second data element and a connecting frame. The connecting frame includes a plurality of connecting frames, the connecting frame including an intersection path frame identifier connector. In other features, the intersection path frame identifier connector references an intersection path frame that is one of the plurality of frames of the generic lane frame.

[0032] In other features, the map message has a tree structure including: (i) a generic lane frame at a first layer of the tree structure; (ii) a second data element, a connecting frame, and an intersection path frame at a second layer of the tree structure; (iii) a connecting frame at a third layer of the tree structure; and (iv) an intersection path frame identifier, and the first data element at a fourth layer of the tree structure that is separate from the intersection path frame identifier.

[0033] In other features, the second plurality of data elements includes two or more of (i) a frame identifier, (ii) a name, (iii) a lane attribute, (iv) an entry approach, (v) an exit approach, (vi) a maneuver, or (vii) a node list. In other features, the first route data includes a reference static route. The control module is configured to (i) receive road hazard information and (ii) update the first route data based on the road hazard information. In other features, the road hazard information includes at least one of lane closure information, road closure information, accident information, and road repair information.

[0034] In another feature, the first route data includes a reference static route and a dynamic route, and the control module is configured to (i) compare the current vehicle route information to the reference static route, (ii) determine whether there is a statistical significance between the current vehicle route information and the reference static route, (iii) in response to there being a statistical significance between the current vehicle route information and the reference static route, broadcast via the transceiver a first map message indicative of the current vehicle route information, and (iv) in response to there being no statistical significance between the current vehicle route information and the reference static route, broadcast via the transceiver a second map message indicative of the reference static route.

[0035] In another feature, a path prediction system is disclosed that includes a transceiver, a memory, and a control module. The transceiver is configured to receive a map message at a host vehicle, the map message including path information for a vehicle passing through an intersection. The memory is configured to store map data including global positioning satellite system information. The control module is configured to (i) determine whether the host vehicle is at or approaching an intersection based on the map data, (ii) in response to determining that the host vehicle is at or approaching an intersection, predict a path for the host vehicle through the intersection based on the path information, and (iii) perform at least one collision warning action based on the predicted path of the host vehicle.

[0036] In other features, the control module is configured to predict a path for the host vehicle based on at least one of a node list and a radius of curvature of the vehicle path through the intersection and a latitude and longitude of a center point of the radius of curvature. The map message includes at least one of a node list and a radius of curvature of the vehicle path through the intersection.

[0037] In other features, the control module is configured to predict a path independent of a speed and a yaw rate of a host vehicle.In other features, the control module is configured to (i) obtain at least one of a speed and a yaw rate of a vehicle within an intersection, and (ii) predict a path of the host vehicle based on at least one of the speed and the yaw rate of the host vehicle within the intersection.

[0038] In other features, the control module is configured to perform at least one of a forward collision warning action and a pedestrian collision warning action based on a predicted path of the host vehicle. In other features, the control module is configured to determine a position of the host vehicle based on global positioning satellite system information, generate a primary safety message indicating the position of the host vehicle, and transmit the primary safety message.

[0039] In other features, the control module is configured to (i) determine whether map data of the host vehicle includes at least one of a node list and a radius of curvature for a vehicle path through the intersection, and (ii) in response to the map data including at least one of a node list and a radius of curvature for the vehicle path through the intersection, predict a path for the host vehicle using the map data.

[0040] In other features, the control module is configured to predict a path of the host vehicle based on at least one of a speed and a yaw rate of the host vehicle, in response to the map data not including either a node list or a radius of curvature for the vehicle path through the intersection.

[0041] In other features, the control module is configured to generate the primary safety message based on a predicted path of the host vehicle in response to the map data including at least one of a node list and a radius of curvature of the vehicle path through the intersection.

[0042] In other features, the control module is configured to (i) determine whether the host vehicle has left the intersection, and (ii) in response to the host vehicle leaving the intersection, transition from predicting a path for the host vehicle based on map data to predicting a path for the host vehicle based on at least one of a speed and a yaw rate of the host vehicle. In other features, the map message is received from a roadside unit monitoring the intersection.

[0043] In another feature, a path prediction system is disclosed that includes a transceiver, a memory, and a control module. The transceiver is configured to receive a map message at a host vehicle, the map message including path information for a vehicle through an intersection. The memory is configured to store map data including global positioning satellite system information. The control module is configured to (i) determine whether the host vehicle is in or approaching an intersection based on the map data, (ii) in response to determining that the host vehicle is in or approaching an intersection, predict a path for the host vehicle through the intersection based on the path information, and (iii) identify a location of the host vehicle based on the predicted path of the host vehicle, generate a primary safety message indicating the location of the host vehicle, and transmit the primary safety message.

[0044] In other features, the control module is configured to predict a path for the host vehicle based on at least one of a node list or a radius of curvature of the vehicle path through the intersection. The map message includes at least one of the node list and the radius of curvature of the vehicle path through the intersection.

[0045] In other features, the control module is configured to predict a path independent of a speed and a yaw rate of a host vehicle.In other features, the control module is configured to (i) obtain at least one of a speed and a yaw rate of a vehicle within an intersection, and (ii) predict a path of the host vehicle based on at least one of the speed and the yaw rate of the host vehicle within the intersection.

[0046] In other features, the control module is configured to perform at least one of a forward collision warning operation and a pedestrian collision warning operation based on the predicted path of the host vehicle. In other features, the control module is configured to (i) determine whether map data of the host vehicle includes at least one of a node list and a radius of curvature for a vehicle path through the intersection, and (ii) in response to the map data including at least one of a node list and a radius of curvature for the vehicle path through the intersection, predict a path of the host vehicle using the map data. In other features, in response to the map data not including either a node list or a radius of curvature for the vehicle path through the intersection, predict a path of the host vehicle based on at least one of a speed and a yaw rate of the host vehicle.

[0047] In other features, the control module is configured to (i) determine whether the host vehicle has left the intersection, and (ii) in response to the host vehicle leaving the intersection, transition from predicting a path for the host vehicle based on map data to predicting a path for the host vehicle based on at least one of a speed and a yaw rate of the host vehicle. In other features, the map message is received from a roadside unit monitoring the intersection.

[0048] In another aspect, a pedestrian collision warning system is disclosed that includes a transceiver, a memory, and a control module. The transceiver is configured to receive a personal safety message and a map message at a host vehicle. The memory is configured to store map data. The control module (i) identifies a number of potential collision boxes in which the host vehicle and a pedestrian are predicted to be present simultaneously according to a route of the host vehicle based on the personal safety message and the map message, (ii) determines a most likely route for the host vehicle through the intersection from among a number of potential routes through the intersection based on the map data and the map message, (iii) determines whether the host vehicle and a pedestrian may be present simultaneously in any of the multiple potential collision boxes based on the most likely route for the host vehicle and the multiple potential collision boxes, and (iv) in response to determining that the host vehicle and a pedestrian may be present simultaneously in any of the multiple potential collision boxes, alerts at least one of an occupant of the host vehicle or a pedestrian of a possible collision via a vulnerable road user device.

[0049] In other features, the personal safety message is received from a roadside unit separate from the host vehicle, the roadside unit separate from a pedestrian collision warning system implemented in the host vehicle. In other features, the personal safety message is received from a vulnerable road user device separate from the host vehicle, the vulnerable road user device separate from a pedestrian collision warning system implemented in the host vehicle. In other features, the map message is received from a roadside unit monitoring the intersection. In other features, the map message is received from a cloud-based server.

[0050] In other features, the control module is configured to (i) determine whether the host vehicle is moving, and (ii) if the host vehicle is not moving, identify potential collision boxes, which are areas where the host vehicle and a pedestrian are expected to be simultaneously located, according to a path of the host vehicle. In other features, the control module is configured to (i) determine whether the host vehicle has begun to move, and (ii) in response to the host vehicle beginning to move, determine a most plausible path for the host vehicle through the intersection and determine whether the host vehicle and a pedestrian may be simultaneously located in any of a plurality of potential collision boxes.

[0051] In other features, the control module is configured to (i) determine if the host vehicle has begun to move, and (ii) in response to the host vehicle beginning to move, determine a most plausible path for the host vehicle through the intersection and determine in which of a plurality of potential collision boxes the host vehicle and pedestrian may be simultaneously located. In other features, the control module is configured to (i) determine if the host vehicle is approaching an intersection, and (ii) in response to the host vehicle approaching the intersection, identify a plurality of potential collision boxes.

[0052] In another feature, a pedestrian collision warning method is disclosed that includes receiving at a host vehicle a personal safety message and a map message; retrieving map data from a memory; identifying a plurality of potential collision boxes in which the host vehicle and the pedestrian are predicted to be simultaneously present according to a route of the host vehicle based on the personal safety message and the map message; determining a most suitable route for the host vehicle through the intersection from among a plurality of potential routes through the intersection based on the map data and the map message; determining whether the host vehicle and the pedestrian are simultaneously located in any of the plurality of potential collision boxes based on the most suitable route for the host vehicle and the plurality of potential collision boxes; and in response to determining that the host vehicle and the pedestrian are simultaneously located in any of the plurality of potential collision boxes, warning at least one of the pedestrian or an occupant of the host vehicle via a vulnerable road user device of a possible collision.

[0053] In other features, the personal safety message is received from a roadside unit separate from the host vehicle, the roadside unit separate from a pedestrian collision warning system implemented in the host vehicle. In other features, the personal safety message is received from a vulnerable road user device separate from the host vehicle, the vulnerable road user device separate from a pedestrian collision warning system implemented in the host vehicle.

[0054] In other features, the map message is received from a roadside unit monitoring the intersection. In other features, the map message is received from a cloud-based server. In other features, the pedestrian collision warning method further includes determining if the host vehicle is moving, and if the host vehicle is not moving, identifying a plurality of potential collision boxes, which are areas where the host vehicle and a pedestrian are expected to be present simultaneously, according to a path of the host vehicle.

[0055] In other features, the pedestrian collision warning method further includes determining whether the host vehicle is beginning to move, and in response to the host vehicle beginning to move, determining a most plausible path for the host vehicle through the intersection, and determining whether the host vehicle and the pedestrian may be simultaneously located in any of a plurality of potential collision boxes. In other features, the pedestrian collision warning method further includes determining whether the host vehicle is beginning to move, and in response to the host vehicle beginning to move, determining a most plausible path for the host vehicle through the intersection, and determining whether the host vehicle and the pedestrian may be simultaneously located in any of a plurality of potential collision boxes. In other features, the pedestrian collision warning method further includes determining whether the host vehicle is approaching an intersection, and in response to the host vehicle approaching the intersection, identifying the potential collision box.

[0056] Other areas of applicability will become apparent from the description provided herein. The description and specific examples in this Summary section are for illustrative purposes only and are not intended to limit the scope of the present disclosure. [Brief description of the drawings]

[0057] The drawings of the present disclosure illustrate only selected embodiments, do not depict every possible implementation, and are not intended to limit the scope of the present disclosure. [Figure 1] FIG. 1 is a functional block diagram of an example intersection-based vehicle path monitoring and responding system (IVPMRS) according to the present disclosure. [Diagram 2] FIG. 2 is a functional block diagram of a portion of the IVPMRS of FIG. [Diagram 3] FIG. 3 is an example functional block diagram of a vehicle constituting the IVPMRS of FIG. 1 including an intersection path prediction module according to the present disclosure. [Figure 4] FIG. 3 is a functional block diagram of an example remote station that constitutes the IVPMRS of FIG. 1 in accordance with the present disclosure. [Diagram 5] FIG. 5 is a top view of an intersection illustrating an example set of nodes for paths that a vehicle can take through the intersection from one turning lane to two exit lanes in accordance with the present disclosure. [Figure 6] FIG. 6 is a top view of an intersection illustrating an example of a node set of possible paths a vehicle can take through the intersection from two turning lanes to two exit lanes in accordance with the present disclosure. [Figure 7] FIG. 7 is a top view of an intersection illustrating an example of a node set of possible paths a vehicle may take through the intersection from two turning lanes to one exit lane due to lane obstructions in accordance with the present disclosure. [Figure 8] FIG. 8 illustrates an example of a method for a remote station to update a reference static route according to the present disclosure. [Figure 9] FIG. 9 is a top view of an intersection illustrating a road side unit (RSU) monitoring a vehicle's path from a single turning lane to two exit lanes through the intersection in accordance with the present disclosure. [Figure 10]FIG. 10 is a top view of an example intersection showing RSUs monitoring node points of different paths of a vehicle from a single turning lane to two exit lanes through the intersection in accordance with this disclosure. [Figure 11] FIG. 11 is a top view of an intersection showing similar example static and dynamic paths from two turning lanes through the intersection to two exit lanes in accordance with the present disclosure. [Figure 12] FIG. 12 is a top view of an intersection illustrating another example of static and dynamic paths for vehicles from two turning lanes through the intersection to two exit lanes in accordance with the present disclosure. [Figure 13] FIG. 13 illustrates an example of a method for determining whether to broadcast a static route or a dynamic route in the present disclosure. [Figure 14] FIG. 14 is a top view of an example intersection illustrating example node points of a vehicle's path from two turning lanes through the intersection to two exit lanes, including example radii of curvature in accordance with the present disclosure. [Figure 15] FIG. 15 is a block diagram illustrating an example of a tree structure representation of a map message according to this disclosure. [Figure 16] FIG. 16 is a block diagram illustrating an example of a tree structure representation of a map message including level jumpers in the form of intersection box route frame identifiers in the present disclosure. [Figure 17] FIG. 17 is a top view of an intersection showing an example of a predicted first node point for a vehicle determined based on available intersection route information in a map message according to the present disclosure, and an example of a predicted second node point for a vehicle determined without intersection route information provided via a map message. [Figure 18] FIG. 18 illustrates a method for providing intersection-based path prediction and providing collision warning and basic safety messaging based on the path prediction in accordance with the present disclosure. [Figure 19]FIG. 19 is a top view of an example intersection showing a first example predicted route based on map message intersection route information provided via a map message in the present disclosure, a second example predicted route based on vehicle speed and yaw rate, an example actual vehicle route, and corresponding example radii of curvature. [Figure 20] FIG. 20 is a top view of an example intersection showing a predicted path of a vehicle and a collision box in accordance with the present disclosure. [Figure 21] FIG. 21 illustrates an example of a method for implementing pedestrian collision warning based on intersection route information in a map message in the present disclosure.

[0058] Corresponding reference numerals indicate corresponding parts throughout the several views of the drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0059] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings.

[0060] A significant percentage of vehicle accidents (e.g., 40%) occur at intersections. V2X communication can be used to improve intersection safety and can include V2I and V2V applications, such as Red Light Violation Warning (RLVW) and Intersection Mobility Assistance (IMA) applications. V2X communication can also be used to detect potential collisions with vulnerable road users (VRUs), such as pedestrians and cyclists. Because traditional collision warning systems cannot accurately predict the path of a vehicle through an intersection, it can be difficult to warn a driver that the vehicle may collide with a VRU on a pedestrian crossing, especially after stopping. This is mainly due to two factors. The first factor is traditional vehicle path prediction algorithms, which are generally not accurate unless the vehicle's turning radius is constant. The second factor is that traditionally, map messages do not include information about the possible paths a vehicle can take within an intersection.

[0061] Examples described herein include a system that accurately predicts the path of a vehicle through an intersection. An intersection refers to an area (or box) between oncoming and offgoing lanes, and typically includes one or more traffic lights. Traffic enters and exits an intersection from different directions. Oncoming lanes lead to (or connect with) the intersection, and offgoing lanes lead to (or exit) the intersection. An intersection is a road junction where two or more roads meet, branch off, connect, or intersect at the same level. A typical example of an intersection is where two roads intersect at right angles to each other. In this example, the geographic area where the two roads intersect is also called an intersection box, and may include a crosswalk. The perimeter of the intersection box is defined, at least in part, by a white stop line. The white stop line is a line where vehicles must stop while waiting for a green light indicating that they are permitted to proceed through the intersection. Examples of intersections, crosswalks, and white stop lines are shown in Figures 5-7, 9-12, 14, 17, 19, and 20.

[0062] Examples herein further include generating and transmitting map messages including vehicle path information and performing various actions based on the vehicle path information. The vehicle path information includes a reference static path (also simply referred to as a static path) and a dynamic path for the vehicle. A static path for a vehicle through an intersection refers to a predicted or ideal vehicle path based on a predetermined and / or past vehicle paths through the intersection and map information defining the intersection. A static path extends from an incoming lane leading to an intersection to an outgoing lane leading out of the intersection. A dynamic path refers to a current actual path of a vehicle through an intersection. A dynamic path also refers to a path from an incoming lane leading to an intersection to an outgoing lane leading out of the intersection. Static and dynamic path information may include two-dimensional (2D) and / or three-dimensional (3D) path information.

[0063] Exemplary embodiments will now be described in more detail with reference to the accompanying drawings.

[0064] 1 illustrates an IVPMRS 100 including a plurality of connected cars 102, a plurality of non-connected cars 104, a distributed network 106, a cloud-based (or back-end) server 108, a plurality of RSUs 110, and a plurality of VRU devices 112. Each of the plurality of connected cars 102 is configured to connect to and communicate with other network devices in the IVPMRS 100. Each of the plurality of non-connected cars 104 is not configured to connect to and communicate with other network devices. Each of the connected cars 102 may include a control module 120 including a path prediction module 122, a pedestrian collision warning (PCW) module 124, and a vehicle forward collision warning (FCW) module 126. The path prediction module 122 may predict the path of the connected car 102, the path of other surrounding vehicles, and / or the path of an object (e.g., a VRU) through an intersection. These predictions may be based on (i) map messages received from one or more remote stations, such as one or more cloud-based servers 108, RSUs 110, and / or other remote stations disclosed herein, and / or (ii) messages broadcast by other connected cars 102 or VRU devices 112. A remote station may refer to a device that exists separately from the connected car 102 and communicates with the connected car 102, broadcasts messages to the connected car 102, and / or receives information from the connected car 102. The modules 124, 126 and / or other collision warning modules included in the connected car 102 may perform collision warning actions to prevent collisions between the connected car 102 and objects, such as pedestrians, VRUs, vehicles, and / or other objects including the vehicles 102, 104.

[0065] The cloud-based server 108, the RSU 110, and / or other remote stations can generate map messages including map information and intersection path information. Other remote stations can include back-end servers, edge computing devices, and / or roadside or overhead devices (cameras, traffic lights, RSUs, etc.). The intersection path information can include static paths including node points of vehicle positions along a path between an oncoming lane and an offcoming lane, a linear trajectory between the oncoming lane and an offcoming lane, and / or a radius of curvature and a center of rotation of a curved trajectory of a path from a turning lane to an offcoming lane. Turning lanes may be referred to as oncoming lanes, and there may be oncoming lanes that are not turning lanes. Turning lanes may include left and right turn lanes. The path through an intersection may be linear, nonlinear, and / or curvilinear.

[0066] In the illustrated example, the cloud-based server 108 and the RSU 110 may each include a control module (e.g., control module 130, 132) that includes an intersection path module (e.g., intersection path module 134, 136) and a V2X map message module (e.g., V2X map message module 138, 140). The intersection path module is configured to track, store, and / or predict paths of connected cars, non-connected cars, and / or other objects (e.g., VRUs) passing through an intersection. This may be based on past / historic paths of vehicles and objects passing through the intersection, road hazard information, map information, and the number and types of oncoming and outgoing lanes, etc. The road hazard information may include accident information, road repair information, traffic congestion information, road closure information, lane closure information, etc. The road hazard information may indicate which lanes are closed, which lanes are open, and / or which lanes are temporarily blocked, and / or the road hazard information may include stopped traffic. The V2X map message module may generate a map message including the route information, which may be broadcast to the connected car 102 and / or the VRU device 112. V2X communication in this context includes the transmission of map messages and other messages, such as basic safety messages and personal safety messages. These messages may be transmitted in the 5.9 gigahertz (GHz) frequency band.

[0067] A VRU device 112 may be carried by each of a number of VRUs (not shown in FIG. 1 ). The VRU device 112 may include a mobile phone, a tablet, a wearable network device (e.g., a smart watch), and the like. The VRU may include a pedestrian, a bicycle, and the like. The VRU device 112 may communicate with and receive messages from the connected car 102, the cloud-based server 108, and / or the RSU 110. Such communication and message reception may be performed directly or indirectly via the distributed network 106. Similarly, the connected car 102 may communicate with and receive messages from the cloud-based server 108, the RSU 110, and / or the VRU device 112. Such communication and message reception may be performed directly or indirectly via the distributed network 106.

[0068] 2 illustrates an RSU 202, a connected vehicle 204, and a VRU device 206, which may be part of the IVPMRS 100 of FIG. 1. The RSU 202 includes a control module 210, a transceiver 212, and a memory 214 that stores an intersection route application 216 and a V2X message application 218. The connected car 204 includes a control module 220, a transceiver 222, and a memory 224 that stores a route prediction application 226, a PCW application 228, a basic safety message (BSM) application 230, and a FCW application 232. The VRU device 206 includes a control module 240, a transceiver 242, and a memory 244 that stores a PSM application 246 and a collision warning application 248.

[0069] Applications 216, 218, 226, 228, 230, 232, 246, 248 may be executed by control modules 210, 220, 240. Intersection path application 216 is implemented to track, store, and predict paths of connected cars, non-connected cars, and / or other objects through an intersection. Path prediction application 226 is implemented to predict paths of connected car 204, surrounding vehicles, and / or objects (such as VRUs) through an intersection. V2X message application 218 is implemented to map messages containing path information that may be broadcast to connected vehicles 204 and / or VRU devices 206.

[0070] The applications 228, 232 are implemented to perform collision warning operations to prevent collisions between the connected car 102 and objects such as pedestrians, VRUs, vehicles, and / or other objects. The BSM application 230 is implemented to generate and broadcast BSM messages indicating, for example, the speed, path, location, etc. of the connected car 204. The PSM application 246 is implemented to generate and broadcast PSM messages indicating, for example, the speed, heading, location of the VRU device 206 and / or corresponding VRU. The collision warning application 248 may perform collision warning operations to prevent collisions between the VRU carrying the VRU device 206 and objects such as vehicles, pedestrians, VRUs, and / or other objects.

[0071] 3 illustrates a vehicle 300 that may replace one of the connected cars 102 of the IVP MRS 100 of FIG. 1. The vehicle 300 may be a fully or partially autonomous vehicle and includes a sensor system 302, a map module 304, and a vehicle control module 305. The vehicle control module 305 may include a path prediction module 306, a collision warning module 307, an actuator module 308, and a parameter adjustment module 309. The sensor system 302 provides information about the vehicle 300, such as speed, yaw rate, etc.

[0072] The path prediction module 306 may operate similarly to the path prediction modules 122, 226 of FIG. 1-2 and may implement the path prediction application 226 of FIG. 2. The path prediction module 306 is configured to determine a trajectory to be followed by the vehicle 300 passing through an intersection, the trajectory being within the geometric boundaries of the intersection and / or the incoming lanes connecting the intersection and the outgoing lanes exiting the intersection. The path prediction performed by the path prediction module 306 may not guarantee that the trajectory is collision-free or not. The path prediction is used by other collision avoidance modules to predict the possibility of a collision, whether the corresponding host vehicle is within a predetermined lane parameter, and / or whether one or more other parameters are met. The collision warning module 307 may operate similarly to the collision warning modules 124, 126 of FIG. 1 and may implement the collision warning application 228, 232 of FIG. 2. If the vehicle 300 is an autonomous vehicle or a partially autonomous vehicle, the actuator module 308 may be configured to control the movement of the vehicle or a part thereof to follow the planned trajectory of the vehicle 300. If the vehicle 300 is a non-autonomous vehicle (i.e., a vehicle that is fully controlled by a driver), the actuator module 308 or other modules may provide guidance to the driver to follow a planned trajectory, which is determined by one or more of the modules 305-307.

[0073] The sensor system 302 provides dynamic information such as the speed and yaw rate of the host vehicle. This information is provided to modules 305-307. The map generated, acquired, and / or monitored by the map module 304 includes the geometry and characteristics of the surrounding area in a format that allows modules 305-308 to determine where the available (permitted, feasible) driving areas and lanes are. The available driving areas and lanes may be inside and outside intersections, emergency driving areas, non-traffic areas, and other semantic categories of the local road configuration.

[0074] Actuator module 308 can take the plan generated by modules 305-307 and translate the plan into steering, braking, and accelerator commands to affect the speed, acceleration, and heading of the ego-vehicle 300. Map and object (or obstacle) information can be used to determine an optimal trajectory for the ego-vehicle 300 to meet goal conditions (e.g., exit an incoming lane and enter an intersection, traverse the intersection in a specific path, and exit the intersection into a specific outgoing lane).

[0075] Vehicle 300 further includes an infotainment module 312 and other control modules 314 (e.g., a body control module). Modules 305-309, 312 and / or 314 may communicate with each other via a vehicle interface 316, such as a Controller Area Network (CAN) bus, a Local Interconnect Network (LIN), a Clock Enhanced Peripheral Interface (CXPI) bus and / or other vehicle interfaces. In one embodiment, sensor signals are received at vehicle control module 305 from sensor system 302 via a CAN bus.

[0076] Vehicle control module 305 controls the operation of vehicle systems and may include modules 305, 306, 308, 309, and other modules. Vehicle control module 305 may include one or more processors configured to execute instructions stored in a non-transitory computer-readable medium, such as memory 322, which may include read-only memory (ROM) and / or random access memory (RAM).

[0077] The vehicle 300 may further include a display 330, an audio system 331, and one or more transceivers 332 including an antenna module 334. The RF antenna module 334 may include and / or be connected to an RF circuit 336. The map module 304 may communicate with a telematics module 338, a Global Positioning System (GPS) receiver 340, and sensors 342. The one or more transceivers 332 may include the telematics module 338. The vehicle control module 305 and / or the telematics module 338 are configured to receive GPS data and associate the GPS position data of the vehicle 300 with a geographical map location.

[0078] The RF circuitry 336 may be used to communicate with mobile devices, central offices, other vehicles, land stations, cloud-based networks, etc., which may include transmitting Bluetooth, Wi-Fi, or Wi-Fi Direct, and / or other RF signals that comply with various wireless communication protocols. The RF circuitry 336 may include a radio, transmitter, receiver, etc. for transmitting and receiving RF signals. The telematics module 338 may be implemented with a global navigation satellite system (e.g., GPS), an inertial navigation system, a global mobile communications system (GSM), and / or other location information systems. The telematics module 338 may provide map information, including road and object information, such as, for example, vehicle position, speed, acceleration, heading, object positions, distance between objects, distance from the current position to intermediate destinations and / or final destinations, etc. This information may be provided to the map module 304.

[0079] The sensors 342 may include sensors used for path prediction, path planning, and actuator operation. The sensors include a vehicle speed sensor 343, a yaw rate sensor 344, and other sensors 345. The other sensors 345 may be cameras, object detection sensors, temperature sensors, acceleration sensors, etc. The GPS receiver 340 may provide the speed and / or direction (or orientation) of the vehicle 300, and / or global clock timing information.

[0080] The memory 322 can store various sensor data, parameter data, dimensional states, trajectory planning information, and other information. As an example, the memory 322 can store sensor and parameter data 350, PCW application 352, BSM application 354, FCW application 356, path prediction application 358, timing information 360, connection information 362, and other applications 364. The connection information 362 may refer to information for connecting to other vehicles, mobile access devices, cloud-based servers, back-end servers, remote stations, etc. The timing information 360 may refer to the time when the vehicle 300 is at a particular location, the time to a predicted destination (or node point), etc. The transitions may be time-based, mileage-based, or based on other conditions.

[0081] The applications 352, 354, 356, 358, 364 may be implemented by the modules 305-309, 312, 314, 338, and / or the transceiver 332. Other applications 364 include, for example, a planning application and an actuator application. The planning application may be executed by the planning module to plan a trajectory of the vehicle 300. The actuator application may be executed by the actuator module 308 to execute the trajectory plan selected by the planning module. The planning module may determine a target path for the vehicle 300 to follow. The target path may be adjusted in response to changes in the environment. For example, the vehicle 300 may approach or encounter one or more objects, such as fixed objects, pedestrians, and / or other vehicles, and update the target path. If the vehicle 300 is an autonomous vehicle, the vehicle 300 may follow the updated target path to avoid collisions. The parameter adjustment module 309 may be used to adjust parameters of the vehicle 300.

[0082] Although the memory 322 and the vehicle control module 305 are illustrated as separate devices, the memory 322 and the vehicle control module 305 may be implemented as a single device.

[0083] Vehicle control module 305 can control the operation of engine or motor 370, converter / generator 372, transmission 374, window / door system 380, lighting system 382, ​​seat system 384, mirror system 386, braking system 388, electric motor 390, and / or steering system 392 according to parameters set by modules 305-309, 334, and / or 338.

[0084] The vehicle control module 305 can receive power from a power source 394, which can be provided to the engine or motor 370, converter / generator 372, transmission 374, window / door system 380, lighting system 382, ​​seat system 384, mirror system 386, braking system 388, electric motor 390, and / or steering system 392, etc. Some actions as a result of the plan can include enabling fuel and ignition for the engine or motor 370, starting the electric motor 390, providing power to any of the systems mentioned herein, and / or performing other actions as further described herein. In one embodiment, the vehicle 300 does not include an engine and / or transmission, and the electric motor 390 is used for vehicle propulsion and / or running purposes.

[0085] The engine or motor 370, converter / generator 372, transmission 374, window / door system 380, lighting system 382, ​​seating system 384, mirror system 386, braking system 388, electric motor 390, and / or steering system 392 may include actuators controlled by the vehicle control module 305 to adjust, for example, fuel, ignition, air flow, steering wheel angle, throttle position, pedal position, door locks, window position, seat angle, etc. This control may be based on the output of sensors 342, map module 304, GPS receiver 340, and the above mentioned data and information stored in memory 322.

[0086] FIG. 4 illustrates a remote station 400, which may replace and / or operate similarly to the cloud-based server 108, one of the RSUs 110 of FIG. 1, and / or other remote stations, and / or may be implemented in the IVPMRS of FIG. 1. The remote station 400 may be implemented as a back-end server, a cloud-based server, a central office monitoring station, an RSU, a roadside camera (or other sensing device / system), a traffic light, an edge computing device, or other station located remotely independent of a vehicle. The remote station 400 may include a control module 402, a transceiver 404, and a memory 406. The memory 406 may store an intersection route application 408 and a V2X map message application 410. The applications 408, 410 may be configured similarly to the applications 216, 218 of FIG. 2. When implemented as an RSU, the remote station 400 may include a camera 412 for capturing images of the intersection. The camera 412 may be replaced or used in combination with one or more other sensors, such as a lidar sensor or a radar sensor, as well as other intersection cameras mentioned herein. Intersection route information generation

[0087] FIG. 5-13 below is directed to generating valid intersection route information related to a vehicle's route through an intersection (or intersection box). An intersection box is a box that is defined at least in part by, for example, a white stop line drawn across an approach lane leading to the intersection. The white stop line may define at least a portion of the perimeter of the intersection box. The valid intersection route information may be based on the intersection's lane and road geometry, or other existing map information.

[0088] 5 illustrates an intersection 500 with a node set of potential vehicle paths, indicated by dashed arrows, through the intersection 500 from a single left turn lane 506 to two exit lanes 507. The intersection 500 includes a stop line 502. Conventional static map information includes only vehicle path information for the lanes leading to the stop line 502, as provided by the solid arrows in the figure, and path information related to the lanes leading away from the intersection 500. The solid arrows pointing towards the intersection 500 are on the entry lanes. The solid arrows pointing away from the intersection 500 are on the exit lanes. The solid arrows have an associated node set.

[0089] Conventional static map information does not include vehicle path information within the intersection 500. The intersection path module disclosed herein can generate static path information for a vehicle path through an intersection. The static path information can include node information such as longitudinal and latitudinal points (or X, Y coordinates) along the vehicle path, as shown by rectangular node points (or node points) 510. Some node points 510 are associated with a set of available paths, and other node points exist for other available paths through the intersection 500. Each available path through the intersection 500 can have its own unique node set (or list of nodes).

[0090] The intersection route information can be obtained using various techniques, such as, for example, collecting information from manual map surveys performed by surveyors, monitoring the route of the vehicle via an intersection camera that captures images of the intersection to track the route of the vehicle passing through the intersection 500, collecting information from a connected car indicating its position coordinates, collecting information from a map database, collecting information from portable and / or handheld sensors to track the location of the vehicle passing through the intersection 500. The intersection node set can be generated, stored, and / or averaged to predict the route of the vehicle passing through the intersection 500. The route information can include information on available routes and acceptable (or valid) routes for the vehicle. The route information does not include unavailable or invalid routes for the vehicle. In FIG. 5, an example of two available and valid routes for the left turn lane 506 is shown.

[0091] FIG. 6 illustrates an intersection 600 on which a node set of available and valid routes (referred to as candidate routes) for a vehicle from two left-turn lanes 602 through the intersection 600 to two exit lanes 604 is depicted. The candidate routes, which may be referred to as static routes, are indicated by dashed arrows with respective node points 606. In the illustrated example, the static routes are idealized curved routes, which may have a specific radius of curvature for each static route. Although only two candidate routes are shown in FIG. 6, static route information for each candidate route through the intersection 600 may be tracked, determined, and stored. FIG. 6 illustrates an example in which there are no obstacles. Each static route has a corresponding node list. The node list includes coordinates of multiple nodes, and the node list is stored in memory and / or broadcast to the vehicle from any of multiple remote stations mentioned herein.

[0092] FIG. 7 illustrates an intersection 700 with a set of nodes for a potential path for a vehicle extending from two left turn lanes 702 through the intersection 700 to one exit lane 704 due to lane obstructions. The intersection 700 may be the same intersection as the intersection 600 of FIG. 6. In this example, one exit lane is closed. The exit lane 706 is blocked as indicated by an “X” 708. The “X” 708 may be an accident, debris in the exit lane 706, a lane with a closed sign or barricade, and / or other road obstruction. The planned lane closures and obstructions are taken into account in determining and updating static route information and node lists (including node points 710) for the vehicle path through the intersection. Road obstruction information may be received at the vehicle from a central office, a back-end server, a reporting agency, an edge computing device, an RSU, or other remote station. Once the exit lane 706 is unblocked, the static route information may be reverted back to static route information similar to that shown in FIG.

[0093] Although the following methods of FIGS. 8, 13, 18 and 21 are shown as separate methods, two or more of these methods and / or other methods may be combined and performed as part of a single method.

[0094] 8 illustrates a method for updating a reference static route. The method may be performed by any of the remote stations disclosed herein. The method is performed iteratively and periodically, beginning at 800.

[0095] At 802, a control module (e.g., one of the control modules 130, 132, 210, 402 shown in FIGS. 1-2 and 4) can determine and / or obtain a reference static route for an intersection. This includes generating a static route based on road geometry within the intersection. At 803, the control module obtains road obstruction information, which may include any of the road obstruction information mentioned herein, including obstructions and / or closures of roads and / or lanes. Road obstruction information may also indicate roads and / or lanes that are no longer closed and / or obstructed and are already passable. Road obstruction information includes accident information, road and / or lane repair information, etc. This may be obtained by accessing memory at the control module's local station and / or server and / or from a remote station and / or server.

[0096] At 804, the control module compares the obstacle information, including road closures and obstacles, to the reference static route. This comparison and / or the remainder of the method may be performed at a fixed, variable, and / or predetermined frequency (e.g., once per day). At 806, the control module determines whether the road obstacle information warrants traveling on a route different from the static route based on the comparison. If 806 is true, operation 808 is performed, otherwise operation 810 is performed. At 808, the control module updates the static route based on the road obstacle information to generate an updated reference static route. This process is performed as needed. As an example, the static route shown in FIG. 6 may be updated as shown in FIG. 7. At 810, the control module refrains from updating the static route. At 812, the method ends.

[0097] FIG. 9 illustrates an intersection 900 in which an RSU 902 is depicted monitoring a path 903 from a single turning lane 904 through the intersection 900 toward two exit lanes 906. The RSU 902 may be implemented as any of the RSUs mentioned herein and connected to an intersection camera 910. The intersection camera 910 has a field of view (FOV) 912 and captures images of the intersection 900. The RSU 902 may be connected to a back-end server 914. The RSU 902 and the back-end server 914 may share information such as road hazard information, static paths through the intersection, images collected by the intersection camera 910, etc. The RSU 902 may be implemented as part of the intersection camera 910 and / or as one of multiple traffic lights 916.

[0098] The RSU 902 may dynamically update static route information and provide the updated static route information to a back-end server; collect images and / or track vehicle movement through an intersection and / or provide the image and / or tracked vehicle data to a back-end server that updates the static route information; and / or generate dynamic route information and provide the dynamic route information to a back-end server. The RSU 902 may be connected to the camera 910 and the back-end server 914 via an Ethernet connection, a long-term evolution (LTE) connection, a fifth generation (5G) mobile network connection, a Wi-Fi connection, or other wired and / or wireless connections, and / or combinations thereof.

[0099] Although one camera and two traffic lights are shown, any number of cameras and traffic lights may be installed at an intersection. The number and location of the cameras are set so that all entry and exit lanes and the entire intersection are covered by the camera's FOV. Each lane and each portion of the intersection is included in the FOV of at least one of the cameras to track vehicles traveling through that lane or intersection.

[0100] The control module of the RSU 902 and / or the control module of the backend server 914 may store a conversion function for each camera to convert the position of the object in the image captured by the camera into three-dimensional Global Positioning System (GPS) coordinates. The two-dimensional (2D) coordinates may be converted into three-dimensional coordinates. The conversion function may be based on the focal length of the camera and the camera projection. The GPS coordinates are used to update the static route information and generate the dynamic route information. A conversion function may be generated for every object in the intersection, for example, a pedestrian or a bicycle on a crosswalk. This is done to track the movement of the object. A node list may be generated for each object.

[0101] 10 illustrates an intersection 1000 in which an RSU 1002 is depicted monitoring node points 1004 of different vehicle paths from a single turning lane 1008 through the intersection 1000 to two exit lanes 1010. The RSU 1002 is connected to a camera 1012 and a backend server 1014. The RSU 1002 may be implemented as any of the RSUs mentioned herein and is connected to an intersection camera 1012, which has an FOV 1016 and captures images of the intersection 1000 at a suitable frame rate.

[0102] The RSU 1002 may dynamically update static route information and provide the updated static route information to a backend server; collect images and / or track vehicle movement through an intersection and / or provide the image and / or tracked vehicle data to a backend server that updates the static route information; and / or generate dynamic route information and provide the dynamic route information to a backend server.

[0103] In one embodiment, the control module of the RSU 1002 tags each vehicle in the FOV 1016. In other words, the control module assigns an identifier to each vehicle and tracks the movement of each vehicle and records the movement identified by the tag. This also includes tag data of the control module of each vehicle. The tagged data includes the tracked path of the vehicle through the intersection from the entrance lane to the exit lane. The control module can determine the speed and yaw rate of the vehicle through the intersection. The speed and yaw rate can be determined based on the image data, the received GPS data of the vehicle, and / or the speed and yaw rate information broadcast from the vehicle through the BSM. The control module can calculate the speed and yaw rate of the vehicle as it passes through the intersection 1000. Based on the tracked path of the vehicle and the speed and yaw rate information, the control module can calculate the three-dimensional position of the vehicle in the image and in the intersection 1000. The control module can then update the reference static path based on the three-dimensional vehicle position.

[0104] 10 is described with respect to a control module of the RSU 1002, the operations of the control module of the RSU 1002 described above may be performed by a control module of the camera 1012, the back-end server 1014, and / or other remote stations (e.g., edge computing devices). The monitored vehicles may be connected or non-connected cars. The edge computing device may be a multi-access edge computing device located near the intersection 1000.

[0105] If the vehicle is a connected car and transmits a BSM, the BSM data of the BSM signal may be received by the RSU 1002 and / or the backend server 1014 and used in combination with or in place of image data collected by the camera 1012 and / or other intersection cameras at the intersection 1000. The BSM data and the camera data may be integrated together, for example, based on a timestamp of the BSM data and a timestamp of the camera data. By integrating or using both the BSM data and the camera data, an estimate of the vehicle position may be more accurately determined and predicted.

[0106] In one embodiment, for each possible and permitted path of a vehicle passing through the intersection 1000, the control module of the RSU 1002 and / or the backend server 1014 averages the position data (e.g., BSM-based position data and / or camera-based position data) for vehicle position estimation and / or prediction. The position data of multiple vehicles is averaged for each possible and permitted path. The position coordinates of multiple vehicles moving from the same incoming lane to the same outgoing lane are averaged. Each of the multiple vehicles may take a slightly different path. More specifically, the coordinates of corresponding node points are averaged. For example, a list having a predetermined number (e.g., 5 to 50) of node points may be generated for each of multiple vehicles moving from the same specific incoming lane to the same specific outgoing lane. The node points for each of the predetermined number (e.g., 10) of vehicles may be averaged. The averaging process may be performed at a predetermined frequency (e.g., once every 15 minutes). The node point located first in the list for each vehicle may be averaged, then the node point located second in the list may be averaged, etc. The averaging may be performed for each point in the list to generate a node list of averaged node points. The radii of curvature of the paths of vehicles moving from the incoming lane to the outgoing lane in the same combination may also be averaged.

[0107] In one embodiment, the location data may be averaged at a fixed, variable, and / or predefined frequency (e.g., 1-50 times per day). The averaged location data may be referred to as dynamic route data for the vehicle's dynamic route. The averaged location data or dynamic route data may include a node list and / or a radius of curvature for the dynamic route. The node list and / or the radius of curvature may be configured on a per-route basis. In another embodiment, the averaged route data is updated using time-based movement. Both the time window and the update frequency may be fixed, variable, and predefined. Using a moving window, the oldest location data is removed and the newly collected location data is used along with the previously collected location data.

[0108] The control module of the RSU 1002 can broadcast map messages including static and / or dynamic route information at a predetermined frequency (e.g., 10 Hz). The map messages may be broadcast continuously or periodically. The RSU 1002 may simply broadcast the map messages or establish links with nearby vehicles to transmit the map messages and / or corresponding information.

[0109] FIG. 11 shows an intersection 1100 with similar static and dynamic paths drawn from two turning lanes 1102, 1104 through the intersection to two exit lanes 1106, 1108. An RSU 1112 connected to a camera 1114 and a back-end server 1116 monitors the movement of vehicles passing through the intersection 1100. The static paths are solid lines 1120, 1122 and the dynamic paths are dashed lines 1124, 1126. The RSU 1112 can determine the static paths 1120, 1122 and the dynamic paths 1124, 1126 and broadcast this information to the vehicles. The static and / or dynamic paths may not be circular and / or entirely curved, but rather may include curved, straight, and / or semi-linear segments. The segments are serially connected, and each path is provided by a set of serial segments. The static and / or dynamic paths may have points where straight, semi-linear, and / or curved segments connect. The dynamic paths may be identical, partially identical, similar in shape, or different from the corresponding static paths.

[0110] Fig. 12 shows an example where the dynamic route is substantially different from the static route due to the use of different exit lanes. Fig. 12 shows an intersection 1200 where different static and dynamic routes are depicted from two turning lanes 1202, 1204 through the intersection 1200 to two exit lanes 1206, 1208. An RSU 1212 connected to a camera 1214 and a back-end server 1216 monitors the movement of vehicles passing through the intersection 1200. The dynamic route is the solid line 1220, 1222 and the static route is the dashed line 1224, 1226. The RSU 1212 can determine the dynamic route 1220, 1222 and the static route 1224, 1226 and broadcast this information to the vehicles.

[0111] FIG. 13 illustrates a method for determining whether to broadcast a static route or a dynamic route. The operations of FIG. 13 may be performed iteratively. The method may begin at 1300. At 1302, for example, a control module of an RSU may identify a reference static route for a vehicle passing through an intersection. This may include a history of static route information that is an average of routes of vehicles that have passed through the intersection in the past.

[0112] At 1304, the control module can determine a dynamic path for the vehicle currently traveling through the intersection. The dynamic path can be generated based on the tracked vehicle's movement through the intersection using (i) captured images from the camera system, (ii) data from other intersection sensors, and / or (iii) location data contained in a received BSM broadcast from the vehicle in the intersection. The control module can average the trajectories of different vehicles to create a node set and / or calculate turning radii for multiple trajectories to average multiple turning radii. The window duration and frequency of trajectory averaging can be parameters that can be remotely adjusted, for example, by the backend server.

[0113] At 1306, the control module may compare the dynamic route and / or its average to the reference static route to identify differences between the reference static route and the dynamic route. Intersection box route data may be generated based on this comparison and broadcast to surrounding vehicles as part of the V2X map message. The intersection box route data may include the dynamic vehicle route data provided at 1310 or the reference static vehicle route data provided at 1312.

[0114] At 1308, the control module may determine whether there is a statistically significant difference between the reference static path and the dynamic path. One or more different statistical significance algorithms and / or methods may be used to determine whether a statistically significant difference exists. For example, the control module may determine that there is statistical significance between the dynamic path and the reference static path if the difference between the dynamic path and the reference static path is greater than a predetermined amount. As another example, the control module may determine that there is statistical significance between the dynamic path and the reference static path if at least a portion of the dynamic path deviates from the reference static path by more than a predetermined amount.

[0115] As yet another example, the control module may determine that there is statistical significance between a dynamic path and a reference static path when an average value of the difference between a group of nodes constituting one dynamic path and a group of nodes constituting one reference static path exceeds a predetermined value. As yet another example, the control module may determine that there is statistical significance between a dynamic path and a reference static path when a difference rate between a group of nodes constituting one dynamic path and a group of nodes constituting one reference static path is greater than a predetermined value (e.g., 10%).

[0116] The control module may be configured to adjust a window width for tracking the vehicle to determine the dynamic path. The control module may be configured to adjust a frequency for averaging the vehicle's trajectory to (i) determine an averaged dynamic path and / or (ii) if a difference exists between the averaged dynamic path and the static path. The more the dynamic path deviates from the static path, the more likely a statistically significant difference exists.

[0117] An operation of 1310 may be performed if there is a statistically significant difference, and an operation of 1312 may be performed if there is no statistically significant difference.

[0118] At 1310, the control module may use and broadcast the dynamic route data. The dynamic route data may be used to estimate and predict the vehicle's position. The estimated and predicted positions may be broadcast to the vehicle along with the dynamic route data or as an alternative to the dynamic route data.

[0119] At 1312, the control module may use and broadcast the reference static route data. The static route data may be used to estimate and predict a position of the vehicle. The estimated and predicted positions may be broadcast to the vehicle along with the reference static route data or as an alternative to the reference static route data.

[0120] If operation 1310 has been performed, an update of the reference static route data may be required. Operation 1314 may be performed following operation 1310 to update the reference static route data based on the dynamic route data. The control module may replace the reference static route data with the dynamic route data or average the reference static route data with the dynamic route data. The dynamic route data may be averaged with the reference static route data or averaged with static route data within a fixed time period. At 1316, the method ends.

[0121] Note that some intersections may only have reference static route information and no dynamic route information, while other intersections may have both reference static route information and dynamic route information. Map message generation

[0122] Figures 14-16 below are directed to the creation and use of map messages that include valid intersection routing information in addition to other information traditionally included in map messages. Valid intersection routing information may include route information that is available and acceptable. Examples of traditional map message content are shown below. This may also include updating static route data with information defining planned lane closures and other roadway obstructions.

[0123] FIG. 14 illustrates a cross point 1400 where node points 1402, 1404 of a path with an exemplary radius of curvature R are depicted from two turning lanes 1406, 1408 through the intersection 1400 to two exiting lanes 1410, 1412. The control module of the RSU can use road shape information to determine available turning paths through the intersection 1400. The turning paths may be determined based on a history of the position of the vehicle in the intersection moving from the entrance lanes 1406, 1408 to the exiting lanes 1410, 1412. The paths can be generated based on multiple node points and / or the radii of curvature of the lines (or paths) connecting the node points. The control module can average the trajectories of multiple vehicles to create a set of nodes or turning radii to determine each dynamic path. The control module is configured to adjust a window width for tracking the vehicle to determine the dynamic path. The node points and / or curvature radii may be included in a map message broadcast and / or transmitted from the RSU or other station to the vehicle and / or VRU device. The map message may include intersection box path data indicating the location of the vehicle within the intersection. The map message may be a V2X type map message.

[0124] 15 illustrates the tree structure of a map message 1500. The tree structure includes multiple layers, each layer including one or more data elements and / or one or more frames, and each frame is connected to the next layer, which includes one or more data elements and / or one or more frames.

[0125] In the illustrated example, the map message 1500 includes five layers of information, although the map message may include any number of layers of information. The first layer includes a frame 1502 that references a number of frames 1504 and a number of data elements 1506 in a second layer. Although not illustrated, each of the number of frames 1504 references one or more data elements and / or one or more frames. As illustrated, one of the number of frames 1504 (also referred to as a "connecting" frame) may reference an additional number of frames 1508 in the next layer. The connecting frame may include information regarding incoming and outgoing lanes and corresponding attributes of each lane (such as a particular type of traffic signal). One of the number of frames 1508 may reference a frame 1510 and a number of data elements 1512. The frame 1510 may reference a number of data elements 1514.

[0126] As an example, frame 1502 may be a general frame. Frame 1504 may include a lane attribute frame, an operation frame, a node list frame, a connecting frame, an overlay frame, and / or a region frame. Data elements 1506 may include a lane identifier, a name, an entry approach identifier, and / or an exit approach identifier. A connecting frame may reference frame 1508, which may also be referred to as a "connecting" frame. Data elements 1512 may include a connecting lane data element, a remote intersection data element, a signal group data element, a user class data element, and / or a connection identifier.

[0127] Frame 1510 may be an intersection box path frame that references intersection path information, such as vehicle path radius, center point latitude, center point longitude, node list, etc. Center point latitude and center point longitude refer to the coordinates of the center point of a circle with the vehicle path radius. The intersection box path information is added to the map message to indicate the vehicle position within the corresponding intersection. The intersection box information may be used by the vehicle to determine the vehicle's position and for other purposes as further described below.

[0128] As an alternative option to Fig. 15, Fig. 16 illustrates an example of a tree structure of a map message 1600 including level jumpers (or inter-layer links) in the form of intersection box path frame identifiers (IDs). The tree structure includes multiple layers, each layer including one or more data elements and / or one or more frames. Each frame is connected to the next layer including one or more data elements and / or one or more frames.

[0129] In the illustrated example, the map message 1600 includes five layers of information, although the map message may include any number of layers of information. The first layer includes a frame 1602 that references a number of frames 1604 and a number of data elements 1606 in a second layer. Although not shown, each of the number of frames 1604 references one or more data elements and / or one or more frames. As shown, one of the number of frames 1604 may reference additional number of frames 1608, and another may reference a frame 1610 in the next layer. One of the number of frames 1608 may reference a data element 1612 in a fourth layer. The frame 1608 may be referred to as a "connection" frame, or a "path" frame. The frame 1610 may be referred to as a "connection" frame.

[0130] One of the frames 1610 can reference one frame 1614 and a number of data elements 1616. The frame 1614 references a number of data elements 1618. One of the data elements 1618 is a level jumper that jumps from the fifth layer to the second layer and jumps from one of the data elements 1618 (called an "intersection box path identifier") to one of the frames 1604 (called an "intersection box path frame"). The jump is indicated by a dashed arrow 1620. The data elements 1612 can include intersection path information such as an intersection box path ID, a radius of the vehicle path, a center point latitude, a center point longitude, and a node list. The center point latitude and center point longitude refer to the coordinates of the center point of a circle having a radius of the vehicle path. The intersection box path information is added to the map message to indicate the vehicle position within the corresponding intersection. The intersection box information can be used by the vehicle to determine the vehicle's position and for other purposes as further described below.

[0131] The tree structure of the map messages 1500, 1600 of Figures 15-16 may be used to quickly access intersection box route information while traversing a minimum number of layers and accessing and / or referencing a minimum number of frames and data elements. For each approach lane of the intersection, the map messages 1500, 1600 may indicate the available exit lanes for a vehicle in the approach lane. The map messages 1500, 1600 may indicate which traffic signals apply to the vehicle while in the approach lane. For example, it may indicate whether a left turn signal, a right turn signal, or a straight through signal applies to the approach lane.

[0132] The map messages 1500, 1600 may be generated by the remote station and broadcast and / or transmitted to the vehicles. The vehicles may then use the map and / or intersection box route information to determine the vehicle's location, where the vehicle is located within a lane, which lane the vehicle is in, etc. This information may be used to determine whether one or more vehicles are, for example, about to run a red light, collide with another vehicle, misroute through an intersection, or perform other improper maneuvers. A corresponding vehicle control module may detect that a vehicle is about to run a red light based on the time it takes for the light to change from red to green, the vehicle's location, the vehicle's speed, and the vehicle's orientation information. Improved route prediction

[0133] Figures 17-18 below are directed to an improved path prediction algorithm that utilizes valid intersection path information where appropriate and under certain conditions. This includes generating dynamic vehicle path data for vehicles passing through an intersection using images (and / or other sensor data) captured by an intersection camera and / or basic safety messages generated by the connected car as described above. A prerequisite for enhanced path prediction is the receipt of a map message and the existence of an intersection with an available path through the intersection.

[0134] FIG. 17 is a top view of an example intersection 1700 illustrating a number of predicted first node points 1702 for a vehicle based on available intersection route information included in a map message, and a number of predicted second node points 1704 for a vehicle without intersection route information provided via a map message.

[0135] A route prediction algorithm that does not use intersection route information may require inputs of yaw rate, vehicle speed, and Global Navigation Satellite System (GNSS) to predict the route of the vehicle. The yaw rate and speed of a vehicle are generally not constant, especially during turns and when moving from a stop. Therefore, route prediction based on yaw rate, vehicle speed, and GNSS data may be inaccurate, especially when making sharp turns or moving from a stationary state. As disclosed herein, static and dynamic route information may be implemented in the map message to improve the route prediction. Route prediction may be based on static and / or dynamic route information and / or based on yaw rate, vehicle speed, and GNSS data. Since static and dynamic route information are more likely indicators of the vehicle route, the static and dynamic route information may be weighted more heavily than yaw rate, vehicle speed, and GNSS data when weighting the parameters based on the prediction of the vehicle route. 17, due to prediction inaccuracies associated with using yaw rate, vehicle speed, and GNSS data, the second node points (or path predictions) 1704 result in a predicted path that does not lead to the exit lane 1720. This differs from the first node points (or paths) 1702, which lead to the evacuation lane 1720.

[0136] In one embodiment, the vehicle's control module uses the map message data for route prediction operations instead of relying on yaw rate and vehicle speed when the GNSS position data indicates that the vehicle is traveling along the node path indicated by the map message. For route prediction, the CAN data, including yaw rate and vehicle speed data, may be ignored when approaching an intersection and validated and / or trusted after exiting the intersection.

[0137] FIG. 18 illustrates a method for providing intersection-based path prediction and providing collision warning and basic safety message transmission based on the path prediction. The operations of FIG. 18 may be performed repeatedly. The method may start at 1800. At 1802, a control module of the vehicle (e.g., one of the control modules 120, 220, 307 of FIG. 1-3) may be used to receive a map message from a remote station. The remote station here may be any of the remote stations mentioned herein, including the cloud-based server 108, the RSU 110, the RSU 202, the remote station 400 of FIG. 1-4, etc.

[0138] At 1804, the control module may determine whether the host vehicle is at an intersection and / or approaching an intersection. If 1804 is true, operations 1806, 1808 are performed, and if not, operation 1812 is performed. In one embodiment, operations 1806, 1808 are performed in sequence such that one of operations 1806, 1808 is performed prior to the other of operations 1806, 1808. At 1806, the control module uses the intersection box data, including a node list and / or a radius of curvature of the vehicle path through the intersection, for path prediction and / or collision warning.

[0139] The host vehicle's location may be determined based on vehicle speed, vehicle yaw rate, and other information such as GNSS (or GPS) data. Use of map message information including node list and / or vehicle path curvature radius provides a fundamentally better prediction of the host vehicle's path than using the host vehicle's speed and yaw rate alone for path prediction. The control module may receive GNSS data and identify when the host vehicle is located at or approaching a node included in the map message's static or dynamic node set. As an example, the GNSS location is likely correct and the host vehicle may not be at the center of the path. Correlation with multiple nodes indicates that the host vehicle is traveling a similar path.

[0140] The predicted route information and / or node positions on the static or dynamic route are wirelessly broadcast as primary safety messages to other vehicles to prevent collisions. Route data may be sent in map messages to other vehicles to prevent collisions. Collision warnings may include forward collision warnings, pedestrian collision warnings, and / or other collision warnings (such as side collision warnings). Collision warning actions are performed based on the predicted route of the host vehicle as determined by the control module.

[0141] At 1808, the control module uses the node list and / or the intersection box data, including the radius of curvature of the vehicle path through the intersection, to generate a BSM. The control module determines a best route for the host vehicle based on the node list and / or the radius of curvature, and generates a BSM that indicates a predicted path for the host vehicle. This determination may be based on other information, such as vehicle speed, vehicle yaw rate, GNSS (or GPS) data, etc. The BSM indicates the predicted path of the host vehicle and may be transmitted from the host vehicle to (i) nearby connected cars and (ii) VRU devices to support collision avoidance applications.

[0142] At 1810, the control module determines whether the host vehicle has exited the intersection. If 1810 is true, then 1812 may be performed, otherwise 1806, 1808 may be repeated. At 1812, the control module uses vehicle data for path prediction. The vehicle data may be CAN data including vehicle yaw rate and speed. This does not include using the node list or radius of curvature from the map message. The process of 1802 may be performed after the process of 1812. Enhanced pedestrian collision warning

[0143] Figures 19-21 below are directed to PCW enhancements using the path prediction provided above, which allows for more accurate detection and avoidance of VRU collision threats.

[0144] 19 illustrates an intersection 1900 depicting an example of a first predicted path 1902 based on map message intersection route information, a second predicted path based on vehicle speed and yaw rate, a third actual vehicle path 1906, and corresponding radii of curvature R. The first predicted path 1902 has a number of nodal points 1910. The second nodal path has a number of corresponding points 1912.

[0145] When the host vehicle starts from a stop, e.g., in the left turn lane before turning left, the speed and yaw rate are not accurate enough to accurately predict the host vehicle's path through the intersection. Using the map message information including the node list and / or curvature radius of the vehicle path through the intersection provides a high probability path that the host vehicle may follow, such as path 1902. This high probability path may be used to predict the host vehicle's path. If the vehicle speed and yaw rate are used alone, the host vehicle control module may predict the host vehicle to follow a second path, as shown by point 1912. The radius may be set if the path is circular, semicircular, or arc-shaped. The use of the map message information including the intersection data set including the node list and / or radius improves the accuracy of the path prediction. The path prediction is made more quickly and may be used for collision warning purposes, such as identifying pedestrian collision boxes. A pedestrian collision box refers to an area where a host vehicle and a pedestrian may be located at the same moment. Some examples of pedestrian collision boxes are shown in FIG. 20.

[0146] FIG. 20 illustrates an intersection 2000 with a predicted path 2002, 2004 of a vehicle and a collision box 2006. The intersection includes an RSU 2010 connected to a camera 2012 and a backend server 2014. In this example, the depicted vehicle can travel through the intersection 2000 from the left turn lane 2016 along path 2002 to an exit lane 2018 or from the left turn lane 2016 along path 2004 to an exit lane 2020. The collision box 2006 is sometimes referred to as a pedestrian collision box. The collision box 2006 refers to an area where a vehicle and a pedestrian (e.g., pedestrian 2022) may be located at the same time and thus a collision is possible.

[0147] 21 illustrates a method for performing pedestrian collision warning in a vehicle based on intersection route information in a map message received at the vehicle. The following operations may be performed iteratively. The method may start at 2100. At 2102, a control module of the vehicle may receive a map message including intersection box data from a remote station (e.g., RSU 2010 of FIG. 20).

[0148] At 2104, the control module may receive a personal safety message (PSM) from an RSU or a VRU device. The PSM may indicate the motion state of the VRU device when the VRU device is carried by the VRU. The PSM may include the speed, location, and orientation of the VRU. As an example, the VRU device may be a mobile device held or worn by a pedestrian walking on a crosswalk at an intersection, as shown in FIG. 20. Examples of mobile devices include mobile phones, laptops, tablets, and smart watches. The RSU receives the PSM from the VRU device and relays the PSM to the RSU. The RSU may also generate a PSM upon detection of the VRU by a camera or other detection device connected to the RSU.

[0149] At 2108, the control module may calculate a projected collision box (e.g., collision box 2006 in FIG. 20) based on the intersection box data. It can be difficult to determine the vehicle's position and predict the collision box based solely on vehicle speed and yaw rate because it is difficult to measure speed and yaw rate when a vehicle is stopped or starting to move and they take time to stabilize.

[0150] At 2110, the control module may determine whether the vehicle is moving. If so, operation 2112 is performed; if not, operation 2016 is performed. At 2112, the control module may receive GNSS (or GPS) data and CAN data including vehicle speed and yaw rate.

[0151] At 2114, the control module can correlate the intersection box path from the map message with the area map using the GNSS data. At 2116, the control module can determine a most likely trajectory for the vehicle based on the correlation results. At 2118, the control module can identify a first collision box of the multiple potential collision boxes, which is based on the collected data and / or calculated data. The first collision box is the collision box with the highest probability of collision, which is based on the known speeds, positions, orientations, and / or predicted trajectories of the vehicle and the VRU, respectively.

[0152] At 2120, the control module can predict whether the VRU and the vehicle are in the same collision box (i.e., in the same geographic area at the same time). If so, process 2122 is performed; if not, process 2102 is performed.

[0153] At 2122, the control module can take measures to avoid the collision, including generating warning messages inside and / or outside the vehicle. The control module can control the operation of the vehicle to adjust the speed, acceleration, and / or deceleration of the vehicle to avoid the collision. The control module can send a signal to the VRU device so that the VRU device can take measures, including warning the VRU. The VRU can take action to avoid the collision.

[0154] 8, 13, 18, and 21 are intended to be illustrative. The illustrated operations may be performed sequentially, synchronously, simultaneously, consecutively, at overlapping time periods, or in a different order depending on the application. Also, some operations may not be performed or may be omitted depending on the implementation and / or sequence of events.

[0155] Although various different features and embodiments have been described above with respect to Figures 1-21, any or all of the embodiments of Figures 1-21 may be combined and implemented as a single embodiment.

[0156] The foregoing description is merely exemplary in nature and is not intended to limit the disclosure, its application, or uses in any way. The broad teachings of the disclosure may be embodied in various forms. Thus, while the disclosure includes specific examples, other variations will become apparent upon study of the drawings, specification, and the following claims, and the true scope of the disclosure should not be so limited. It should be understood that one or more steps included in a method may be performed in different orders (or simultaneously) without altering the principles of the disclosure. Furthermore, although each embodiment is described above as having specific features, any one or more of those features described with respect to any embodiment of the disclosure may be implemented and / or combined with any feature of any other embodiment, even if that combination is not explicitly described. In other words, the described embodiments are not mutually exclusive, and permutations of one or more embodiments with other embodiments are within the scope of the disclosure.

[0157] Spatial or functional relationships between components (e.g., between modules, between circuit elements, between semiconductor layers, etc.) are described using various terms, such as "connected," "engaged," "coupled," "adjacent," "next to," "on," "above," "below," "disposed," etc. In the above disclosure, when a relationship between a first element and a second element is described, the relationship may be a direct relationship in which there is no other intervening element between the first element and the second element, but unless expressly described as "direct," the relationship may be an indirect relationship in which there is one or more intervening elements (spatially or functionally) between the first element and the second element. In this specification, the expression "at least one of A, B, and C" should be interpreted as meaning a logical (AorBorC) using a non-exclusive logical OR, and should not be interpreted as meaning "at least one of A, at least one of B, and at least one of C."

[0158] In the diagrams, the direction of the arrows, indicated by the arrowheads, generally indicates the flow of information (such as data or instructions) that is of interest to the diagram. For example, elements A and B exchange various information, but an arrow may point from element A to element B if the information sent from element A to element B is relevant to the diagram. This unidirectional arrow does not imply that no other information is sent from element B to element A. In response to information sent from element A to element B, element B may send element A a request for information or an acknowledgment of receipt.

[0159] The term "module" or "controller" in this disclosure, including the definitions below, may be substituted for the term "circuitry." The term "module" may refer to, be a part of, or include the following: application specific integrated circuits (ASICs), digital, analog, or mixed analog / digital discrete circuits, digital, analog, or mixed analog / digital integrated circuits, combinatorial logic circuits, field programmable gate arrays (FPGAs), processor circuits (shared, dedicated, or groups) that execute code, memory circuits (shared, dedicated, or groups) that store code executed by the processor circuits, other suitable hardware components that provide the described functionality, or a system on a chip, any or all of the above.

[0160] A module may include one or more interface circuits. In some examples, the interface circuits may include a wired or wireless interface that is connected to a local area network (LAN), the Internet, a wide area network (WAN), or a combination thereof. The functionality of any module of the present disclosure may be distributed among multiple modules that are connected via the interface circuits. For example, load balancing may be performed among multiple modules. In a further example, a server (also called remote, or cloud) module may perform some functionality on behalf of a client module.

[0161] The term code as used above includes software, firmware, and / or microcode and may refer to programs, routines, functions, classes, data structures, and / or objects. The term shared processor circuit encompasses a single processor circuit that executes some or all code from multiple modules. The term group processor circuit encompasses a processor circuit that executes some or all code from one or more modules in combination with additional processor circuits. Multiple processor circuits include multiple processor circuits on separate dies, multiple processor circuits on a single die, multiple cores of a single processor circuit, multiple threads of a single processor circuit, or combinations of the above. The term shared memory circuit encompasses a single memory circuit that stores some or all code from multiple modules. The term group memory circuit encompasses a memory circuit that stores some or all code from one or more modules in combination with additional memory.

[0162] The term storage circuitry is a subset of the term computer-readable medium. As used herein, the term computer-readable medium does not encompass a transitory electrical or electromagnetic signal propagating through a medium (such as on a carrier wave). Thus, the term computer-readable medium may be considered a tangible, non-transient medium. Non-limiting examples of non-transient, tangible computer-readable media include non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, masked read-only memory circuits, etc.), volatile memory circuits (such as static random access memory circuits, dynamic random access memory circuits, etc.), magnetic storage media (such as analog or digital magnetic tape, hard disk drives, etc.), and optical storage media (such as CDs, DVDs, Blu-ray discs, etc.).

[0163] The apparatus and method described in this disclosure may be partially or completely implemented by a special-purpose computer created by configuring a general-purpose computer to execute one or more specific functions embodied in a computer program. The above-described functional blocks, flow chart elements, and other elements may function as software specifications and may be converted into a computer program by routine work by a skilled engineer or programmer.

[0164] A computer program includes processor-executable instructions stored on at least one non-transitory, tangible, computer-readable medium. A computer program may also include or depend on stored data. A computer program may include a basic input / output system (BIOS) that interacts with the hardware of a special-purpose computer, device drivers that interact with specific devices of a special-purpose computer, one or more operating systems, user applications, background services, background applications, and the like.

[0165] Computer programs include: (i) parsed descriptive text such as HTML (Hypertext Markup Language), XML (Extensible Markup Language), JSON (JavaScript Object Notation), (ii) assembly code, (iii) object code generated from source code by a compiler, (iv) source code for execution by an interpreter, (v) source code for compilation and execution by a just-in-time compiler, etc. For example, C, C++, C#, Objective C, Swift, Haskell, Go, SQL, R, Lisp, Java®, Fortran, Perl, Pascal, Curl, OCaml, Javascript®, HTML5 (Hypertext Markup Language 5th revision), Ada, ASP (Active Server Pages), PHP (PHP: Hypertext Preprocessor), Scala, Eiffel, Smalltalk, Erlang, Ruby, Flash®, Visual Basic®, Lua, MATLAB, SIMULINK, Python®.

Claims

1. 1. A pedestrian collision warning system, comprising: a transceiver configured to receive personal safety messages and map messages at a host vehicle; a memory configured to store map data; (i) based on the personal safety message and the map message, identify a number of potential collision boxes in which a host vehicle and a pedestrian are predicted to be present simultaneously, depending on a route of the host vehicle; (ii) based on the map data and the map message, determine a most likely route for the host vehicle passing through the intersection from among a number of potential routes passing through the intersection; (iii) based on the most likely route for the host vehicle and the number of potential collision boxes, determine whether the host vehicle and the pedestrian are likely to be present simultaneously in any one of a number of potential collision boxes; and (iv) in response to determining that the host vehicle and the pedestrian are likely to be present simultaneously in any one of a number of potential collision boxes, warn the pedestrian via a vulnerable road user device, warn an occupant of the host vehicle of a possible collision, or both.

2. The personal safety message is received from a roadside unit separate from the host vehicle; The pedestrian collision warning system of claim 1 , wherein the roadside unit is separate from the pedestrian collision warning system implemented in the host vehicle.

3. the personal safety message is received from the vulnerable road user device that is separate from the host vehicle; The pedestrian collision warning system of claim 1 or 2, wherein the vulnerable road user device is separate from the pedestrian collision warning system implemented in the host vehicle.

4. 4. A pedestrian collision warning system according to claim 1, wherein the map message is received from a roadside unit monitoring the intersection.

5. The pedestrian collision warning system of claim 1 , wherein the map message is received from a cloud-based server.

6. 6. The pedestrian collision warning system of claim 1, wherein the control module is configured to: (i) determine whether the host vehicle is moving; and (ii) if the host vehicle is not moving, determine the expected collision box in which the host vehicle and a pedestrian are predicted to be present simultaneously according to a path of the host vehicle.

7. 7. The pedestrian collision warning system of claim 6, wherein the control module is configured to: (i) determine whether the host vehicle has begun to move; and (ii) in response to the host vehicle beginning to move, determine a most likely path for the host vehicle through the intersection and determine whether the host vehicle and the pedestrian are likely to be in one of a plurality of the potential collision boxes simultaneously.

8. 8. The pedestrian collision warning system of claim 1, wherein the control module is configured to: (i) determine whether the host vehicle has begun to move; and (ii) in response to the host vehicle beginning to move, determine a most likely path for the host vehicle through the intersection and determine whether the host vehicle and the pedestrian are likely to be present in one of a plurality of the potential collision boxes simultaneously.

9. 9. The pedestrian collision warning system of claim 1, wherein the control module is configured to: (i) determine whether the host vehicle is approaching the intersection; and (ii) identify the expected collision box in response to the host vehicle approaching the intersection.

10. receiving a personal safety message and a map message by a host vehicle; Retrieving map data from the memory; Identifying a number of potential collision boxes in which the host vehicle and pedestrians are predicted to be present simultaneously according to a route of the host vehicle based on the personal safety message and the map message; determining a most likely route for the host vehicle through the intersection from a plurality of potential routes through the intersection based on the map data and the map message; determining whether the host vehicle and the pedestrian are likely to be simultaneously present in one of a plurality of the potential collision boxes based on a most likely path of the host vehicle and the potential collision boxes; in response to determining that the host vehicle and the pedestrian are likely to be in one of the potential collision boxes simultaneously, alerting the pedestrian via a vulnerable road user device, alerting an occupant of the host vehicle, or both, of a possible collision.

11. The personal safety message is received from a roadside unit separate from the host vehicle; The pedestrian collision warning method of claim 10, wherein the roadside unit is separate from a pedestrian collision warning system implemented in the host vehicle.

12. the personal safety message is received from the vulnerable road user device that is separate from the host vehicle; 12. The pedestrian collision warning method of claim 10 or 11, wherein the vulnerable road user device is separate from a pedestrian collision warning system implemented in the host vehicle.

13. 13. A pedestrian collision warning method according to any one of claims 10 to 12, wherein the map message is received from a roadside unit monitoring the intersection.

14. The pedestrian collision warning method of any one of claims 10 to 13, wherein the map message is received from a cloud-based server.

15. determining if the host vehicle is moving; Identifying the expected collision box in which the host vehicle and a pedestrian are expected to exist simultaneously according to a route of the host vehicle when the host vehicle is not moving; 15. The pedestrian collision warning method of claim 10, further comprising:

16. determining whether the host vehicle has begun to move; responsive to the host vehicle beginning to move, determining a most likely path for the host vehicle through the intersection and determining whether the host vehicle and the pedestrian are likely to be simultaneously present in one of the potential collision boxes; The pedestrian collision warning method of claim 15 further comprising:

17. determining whether the host vehicle has begun to move; responsive to the host vehicle beginning to move, determining a most likely path for the host vehicle through the intersection and determining whether the host vehicle and the pedestrian are likely to be simultaneously present in one of the potential collision boxes; The pedestrian collision warning method of claim 11 further comprising:

18. determining whether the host vehicle is approaching an intersection; identifying the potential collision box in response to the host vehicle approaching the intersection; The pedestrian collision warning method of claim 11 further comprising:

Images