VEHICLE MOVEMENT PLANNING USING A VARIETY DESCRIPTION OF ROAD SURFACE GEOMETRY

Abstract

Vehicle motion planning system, wherein the system comprises an electronic control device designed to access a manifold from a memory describing a driving surface in three dimensions, to perform parameterization of the manifold to obtain a multitude of local maps describing the driving surface in two dimensions, to determine a route for a vehicle using the multitude of local maps, and to generate a command to navigate the vehicle along the route, characterized in that two successive local maps from the multitude of local maps share a common boundary and that the route is determined based on a transformation over the common boundary between the two successive local maps.

Description

[0001] The present invention relates to a vehicle motion planning system according to the preamble of claim 1 and a method for planning a vehicle motion according to the preamble of claim 8, based on the local road surface geometry as known from EP 1 662 457 B1 or from DE 11 2017 004 047 T5. STATE OF THE ART

[0002] Vehicle movements, such as direction of travel, turning maneuvers, reversing, etc., are currently planned in two dimensions for autonomous vehicles. Often, the vehicle's driving environment is projected onto a linear surface to enable planning in two-dimensional ("2-D") Euclidean space. For example, the vehicle's driving environment can be projected along a local gravitational direction. The vehicle's path is planned based on a reference point of the vehicle in the plane on which it travels. However, modern vehicle motion planning systems do not take into account the local geometry of the road surface. SUMMARY

[0003] Therefore, one of the objects of the invention is to improve the state of the art in vehicle motion planning systems by approximating the local road surface geometry and incorporating it into the vehicle motion planning. This helps to increase the accuracy of distance and speed calculations (or determinations) in the motion planning phase without additional computational overhead. The local road surface geometry is described by a mathematical manifold or a topological space that locally resembles a Euclidean space near each point in the manifold. The use of manifold descriptions of the road surface helps an autonomous vehicle plan a route along complex road geometries and contributes to taking gradient-dependent distance differences into account while simultaneously reducing the computational overhead of the vehicle motion planning system.

[0004] The invention provides a vehicle motion planning system. The system includes an electronic control device designed to access a manifold from a memory that describes a driving surface in three dimensions, to parameterize the manifold to obtain a plurality of local maps that describe the driving surface in two dimensions, to determine a vehicle's path based on the use of the plurality of local maps, and to generate a command to navigate the vehicle along the path, wherein two successive local maps from the plurality of local maps share a common boundary, and wherein the path is determined based on a transformation over the common boundary between the two successive local maps.

[0005] The invention also provides a method for planning a vehicle movement. The method comprises accessing a manifold from a memory that describes a driving surface in three dimensions by an electronic control device, and performing parameterization of the manifold by the electronic control device to obtain a plurality of local maps that describe the driving surface in two dimensions.The method also includes determining a vehicle's route by the electronic control device based on the use of the plurality of local maps and generating a command with the electronic control device to navigate the vehicle along the route, wherein two successive local maps from the plurality of local maps share a common boundary and wherein the route is determined based on a transformation over the common boundary between the two successive local maps.

[0006] These and other features, aspects, and advantages will become apparent from reading the following detailed description and reviewing the accompanying drawings. It is understood that both the preceding general description and the following detailed description serve only to clarify the claims and do not constitute a limitation of the claimed aspects. List of characters •Fig. Figure 1 illustrates a vehicle motion planning system according to one embodiment. • Fig. Figure 2 illustrates an electronic control device according to one embodiment. • Fig. Figure 3A illustrates a driving surface in three dimensions according to one embodiment. • Fig. Figure 3B illustrates a driving surface in two dimensions according to one embodiment. • Fig. Figure 4A illustrates a helical driving surface in three dimensions according to one embodiment. • Fig. Figure 4B illustrates a helical driving surface in two dimensions according to one embodiment. • Fig. Figure 5 illustrates a vehicle motion planning method according to one embodiment. DETAILED DESCRIPTION

[0007] The following description and accompanying drawings describe and illustrate one or more embodiments. These embodiments are not limited to the specific details provided here and can be modified in various ways. Furthermore, other embodiments may exist that are not described here. Additionally, the functionality described here as being performed by a single component can be distributed among multiple components. Likewise, functionalities performed by multiple components can be consolidated and performed by a single component. Similarly, a component described as performing a specific functionality can also perform additional functionalities not described here.For example, a device or structure that is “designed” in a certain way may be designed at least in that way, but may also be designed in ways not listed. Furthermore, some embodiments described herein may include one or more electronic processors designed to perform the described functionality by executing instructions stored on a non-volatile, computer-readable medium. Similarly, the embodiments described herein may be implemented as a non-volatile, computer-readable medium that stores instructions executable by one or more electronic processors to perform the described functionality. As used in this application, the term “non-volatile, computer-readable medium” includes all computer-readable media but does not consist of a volatile, propagating signal.Accordingly, a non-volatile, computer-readable medium can be, for example, a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a ROM (read-only memory), a RAM (random access memory), a register memory, a processor cache, or any combination thereof.

[0008] Furthermore, the language and terminology used here serve a descriptive purpose and should not be considered restrictive. For example, the use of "containing," "encompassing," "exhibiting," and variations thereof is intended to include the elements listed below and their equivalents, as well as additional elements. The terms "connected" and "coupled" are used broadly and include both direct and indirect connections and couplings. Moreover, "connected" and "coupled" are not limited to physical or mechanical connections or couplings and may also include electrical connections or couplings, whether direct or indirect.Furthermore, electronic communications and notifications can be made via wired connections, wireless connections, or a combination thereof, and can be transmitted directly or through one or more intermediaries over various types of networks, communication channels, and connections. Additionally, relational terms such as "first" and "second," "above" and "below," and the like may be used here only to distinguish one facility or measure from another, without necessarily requiring or implying any actual relationship or order between such facilities or measures.

[0009] Fig. Figure 1 illustrates a vehicle motion planning system 100 for a vehicle 105 according to one embodiment. The vehicle includes wheels 106, 107, 108, and 109. The vehicle motion planning system 100 includes a plurality of vehicle systems 110 and an electronic control device 115.

[0010] The multitude of vehicle systems 110 includes, for example, a steering system, a braking system, a propulsion system, a navigation system, and other systems used to operate and / or control the vehicle 105. In one example, the multitude of vehicle systems 110 are designed to guide the vehicle 105 along a roadway, maintain the correct vehicle speed (e.g., propelling the vehicle 105 at a speed permitted for a section of road), control the vehicle 105 to stop and start at appropriate times (e.g., at crosswalks, traffic lights, stop signs, and other locations) along the roadway, maintain the correct lane position for the vehicle 105, and plan vehicle maneuvers along the roadway (e.g., when to turn, positioning the vehicle 105 in the correct lane for turning, activating the turn signals, and the like), and perform other functions.The multitude of vehicle systems 110 can also include a multitude of sensors used for object detection, weather detection, light detection and other functions.

[0011] An embodiment of the electronic control device 115 is shown in Fig. Figure 2 illustrates this. The electronic control device 115 is communicatively coupled with other vehicle systems 110. The electronic control device 115 includes a communication interface 205, an electronic processor 210, and a memory 215. The communication interface 205 enables the electronic processor 210 to communicate with external hardware, such as the vehicle systems 110. The electronic processor 210 is communicatively coupled with the communication interface 205 and the memory 215. The electronic processor 210 is designed to access the memory 215 and, among other things, to execute instructions for the system 100. The electronic processor 210 can be a microprocessor, an application-specific integrated circuit, or a similar processing circuit.The memory 215 is a non-volatile, computer-readable medium and contains instructions which, when executed by the electronic processor 210, perform, among other things, the procedures and functions described here.

[0012] In one embodiment, the memory 215 includes vehicle motion planning software 220. The vehicle motion planning software 220 enables the electronic control device 115 to plan a route for the vehicle 105 based on inputs from the multitude of vehicle systems 110 and other inputs. For example, the vehicle motion planning software 220 can include a manifold that describes the surface on which the vehicle 105 travels.

[0013] A manifold is an n-dimensional topological space in which every point is locally Euclidean. In other words, for every point in the manifold, there exists a neighborhood for that point that locally represents Euclidean space. For example, the Earth's surface is a two-dimensional closed surface representing a sphere. However, if you stand at a point on Earth, the local topography appears as a two-dimensional plane. In general, the surface is a two-dimensional, generally Euclidean space embedded in a three-dimensional space.

[0014] A manifold can therefore be described by a set of n-dimensional maps. Since the driving surface is represented as a two-dimensional space in this case, a set of local two-dimensional maps can be obtained to represent the driving surface. For planning the vehicle's movement, the driving surface can be divided into a series of segments, each corresponding to a local map of the manifold.

[0015] The local maps typically contain some overlap. However, this parameterization assumes that a common boundary exists between successive local maps (e.g., between successive road segments). Because we assume a common boundary between successive local maps, there is a transformation between the boundaries. Therefore, local maps are chosen such that these corresponding boundaries are similar to each other and the transformation between each successive local map is approximately length-preserving, which reduces or minimizes the distortion around the vehicle's path. A vehicle movement is then planned using the transformation between successive local maps. Since only successive maps share a common boundary, vehicle movements can only be planned between successive maps.

[0016] Fig. Figure 3A illustrates a manifold 300 representing a three-dimensional driving surface according to one embodiment. The manifold 300 describes the three-dimensional driving surface by a plurality of road segments S1-S5. The road segments S1-S5 are then parameterized to obtain a plurality of two-dimensional local maps U1-U5, as shown in Fig. Figure 3B illustrates this. Each local map among the multitude of two-dimensional local maps U1-U5 depicts a plane close to the road surface. The plane of each local map can vary between successive road segments, resulting in gaps between the newly projected segments. These gaps correspond to the incrementally changing roll and pitch positions along the road surface. However, the error of these gaps can be kept small by assuming the road surface is not very wide and by choosing short segments.

[0017] This parameterization also allows for the visualization of more complex road geometries. Fig. Figure 4A illustrates, for example, a manifold 400 representing a three-dimensional helical road surface according to one embodiment. The road segments S1-S6 are represented by the manifold 400. After parameterization, a plurality of local maps U1-U6 is obtained, as shown in Fig. Figure 4B illustrates this. While different maps can overlap, such as U2 and U4, they do not share a common boundary and are not consecutive local maps, so vehicle movement between the two cannot be planned. This corresponds to the respective road segments being located at different vertical positions in the three-dimensional manifold 400, but essentially in the same place in the two-dimensional projection. Therefore, vehicle movements can be determined based on a transformation between U2 and U3, and U3 and U4, but not between U2 and U4.

[0018] Fig. Figure 5 illustrates a method 500 for determining a vehicle motion according to one embodiment. The example method 500 involves accessing, with the electronic control device 115, a manifold that describes a driving surface in three dimensions (block 505). In one embodiment, the manifold is stored in memory 215 together with the vehicle motion planning software 220. In another embodiment, the electronic control device 115 uses the communication interface 205 to communicate wirelessly with a remote server to access the manifold that describes the driving surface on which the vehicle 105 is currently driving.Since the manifold is stored as a three-dimensional representation of the driving surface, it is not necessary to store individual two-dimensional maps for each road segment of the driving surface, which saves storage space and computing resources when planning vehicle movements.

[0019] Method 500 also involves performing a parameterization of the accessed manifold using the electronic control device 115 to obtain a variety of local maps describing the driving surface in two dimensions (Block 510). In one example, the driving surface can be stored in memory 215 as a combination of a polygon chain or a connected series of line segments and surface normals. This parameterization defines a frame at the beginning of each segment of the polygon chain by aligning each segment with the X-direction and each surface normal with the Z-direction of the frame. This yields frame transformations for successive segments of the polygon chain, which are then converted into two-dimensional transformations. Concatenating the two-dimensional transformations for each segment of the polygon chain yields a parameterization of the driving surface.

[0020] Method 500 also includes determining a route for the vehicle 105 using the electronic control device 115 based on the plurality of local maps (Block 515). After the plurality of local maps has been obtained via parameterization, the electronic control device 115 determines, for example, a movement for the vehicle 105. This route can be defined by two or more successive local maps (e.g., maps U2 and U3 in [reference]). Fig. 4B) must be between consecutive maps, not between intersecting maps. Vehicle movement and trajectory can include any number of vehicle maneuvers, such as lane changes, turning onto another road surface, braking and stopping at a stop sign, and other maneuvers.

[0021] Once the vehicle movement and route are determined, the electronic control device 115 is designed to generate a command to navigate along the route and / or execute the vehicle movement (block 520). If the route includes, for example, a lane change, the electronic control device 115 generates a command to the multitude of vehicle systems 110 to activate the right turn signal of the vehicle 105, to check the desired lane for objects (e.g., other vehicles) using a sensor, and then to execute the lane change using a steering system.In another example, if the route involves a right turn onto a different driving surface, the electronic control device 115 generates a command to the multitude of vehicle systems 110 to brake the vehicle 105, activate a right turn signal of the vehicle 105, check with a sensor whether the turn is safe, execute the right turn onto the new driving surface and then accelerate on the new driving surface.

Claims

[1] Vehicle motion planning system, wherein the system comprises an electronic control device designed to access a manifold from a memory describing a driving surface in three dimensions, to perform parameterization of the manifold to obtain a plurality of local maps describing the driving surface in two dimensions, to determine a route for a vehicle using the plurality of local maps, and to generate a command to navigate the vehicle along the route, characterized by that two successive local maps from the multitude of local maps share a common boundary and that the route is determined based on a transformation over the common boundary between the two successive local maps. [2] System according to claim 1, wherein the parameterization is approximately length-preserving. [3] System according to claim 1, wherein each local map from the plurality of local maps corresponds to a road segment of the driving surface. [4] System according to claim 3, wherein two successive local maps from the plurality of local maps correspond to two successive road segments of the driving surface. [5] System according to claim 4, wherein the roadway can only pass between two successive road segments. [6] System according to claim 1, wherein the parameterization projects a point of the manifold onto a plane of the driving surface to generate at least one local map from the plurality of local maps. [7] System according to claim 6, wherein the change of the planes of two successive local maps from the plurality of local maps corresponds to the change of the roll and pitch attitude along the driving surface. [8] Method for planning a vehicle movement, comprising: accessing a manifold from a memory describing a driving surface in three dimensions by an electronic control device; performing parameterization of the manifold by the electronic control device to obtain a plurality of local maps describing the driving surface in two dimensions; determining a driving path of a vehicle by the electronic control device based on the use of the plurality of local maps; and generating a command with the electronic control device to navigate the vehicle along the driving path. characterized by that two successive local maps from the multitude of local maps share a common boundary and that the route is determined based on a transformation over the common boundary between the two successive local maps. [9] Method according to claim 8, wherein the parameterization is approximately length-preserving. [10] Method according to claim 8, wherein each local map from the plurality of local maps corresponds to a road segment of the driving surface. [11] Method according to claim 10, wherein two successive local maps from the plurality of local maps correspond to two successive road segments of the driving surface. [12] Method according to claim 11, wherein the roadway can only pass between two successive road segments. [13] Method according to claim 8, wherein the parameterization projects a point of the manifold onto a plane of the driving surface to generate at least one local map from the plurality of local maps. [14] Method according to claim 13, wherein the change of the planes of two successive local maps from the plurality of local maps corresponds to changing the roll and pitch attitude along the driving surface.

Images