Object-oriented navigation system for vehicles and related methods

Through the goal-oriented navigation system, the general navigation system components and artificial potential field arrays are used to solve the complexity and cost of the existing autonomous driving system of vehicles, and the safe and economical autonomous navigation capabilities are achieved.

CN113465618BActive Publication Date: 2024-11-26DENSO CORP +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110327974.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2020-03-30
Filing Date
2021-03-26
Publication Date
2024-11-26
Estimated Expiration
2041-03-26

AI Technical Summary

Technical Problem

The autonomous driving system of existing vehicles is complex and costly. Although the active safety system provides some autonomous functions, it does not have the ability to operate completely autonomously, and the additional sensors and computing hardware increase system complexity and cost.

Method used

The goal-oriented navigation system is adopted to receive perceptual data using components of the general navigation system, discrete and generate collision probability arrays and purpose score arrays, guide transportation navigation through processors, and combine artificial potential field arrays to achieve safe and economical autonomous navigation.

Benefits of technology

It provides a cost-effective autonomous navigation solution that reduces system complexity and costs and achieves safe and goal-oriented driving capabilities of transportation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113465618B_ABST
    Figure CN113465618B_ABST
Patent Text Reader

Abstract

Embodiments of the present disclosure relate to a target-oriented navigation system and related methods for a vehicle. A target-oriented navigation system and related methods for a vehicle with a general navigation system, the target-oriented navigation system comprising one or more processors and a memory. The memory comprises one or more modules, which enable the processor to receive sensory data, discretize the sensory data into a plurality of grids, generate a collision probability array having a plurality of cells corresponding to the plurality of grids, determine which cells of the collision probability array meet safety criteria, receive an artificial potential field array, the plurality of cells of the artificial potential field array correspond to the plurality of cells of the collision probability array, generate a target score array, the plurality of cells of the target score array correspond to the cells of the collision probability array, and instruct a vehicle control system of the vehicle to guide the vehicle to a position representing a cell with the highest value in the target score array.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The subject matter described herein generally relates to a system and method for driving a vehicle using a goal-directed navigation system that utilizes common components of the vehicle, such as a common perception system. Background Art

[0002] The background description is provided to generally present the context of the present disclosure. The inventor's work within the scope that may be described in this background section, as well as aspects of this description that may not otherwise qualify as prior art at the time of filing, are not explicitly or implicitly admitted to be prior art to the present technology.

[0003] Some vehicles are equipped with fully autonomous systems that can pilot the vehicle with little or no input from the occupants. These systems can be very complex, expensive, and require the use of a large number of specialized sensors, computing hardware, etc.

[0004] Alternatively, some vehicles have one or more active safety systems that can provide warnings and / or control the vehicle in certain situations. These active safety systems can include systems such as lane keeping assist, adaptive cruise control, object detection, emergency braking. These active safety systems may not provide a fully autonomous type of operation. However, although these systems may not provide fully autonomous operation, these systems do perform some actions that may be required by a fully autonomous system. For example, these systems collect information from one or more perception sensors and relay this information to a general navigation decision system. Summary of the invention

[0005] This section generally summarizes the disclosure, and is not a comprehensive explanation of its full scope or all of its features.

[0006] In one embodiment, a goal-oriented navigation system for a vehicle with a general navigation system includes one or more processors and a memory in communication with the one or more processors. The memory includes a receiving module, a discretization module, a collision probability module, a target score array module, and a vehicle control module. The receiving module has instructions that, when executed by the one or more processors, cause the one or more processors to receive perception data from the vehicle perception system. The discretization module includes instructions that, when executed by the one or more processors, cause the one or more processors to discretize the perception data into an area adjacent to the current location of the vehicle, the area including a plurality of grids.

[0007] The collision probability module includes instructions that, when executed by one or more processors, cause the one or more processors to generate a collision probability array having a plurality of cells corresponding to a plurality of grids. The cells of the collision probability array indicate the likelihood of a collision if the vehicle moves to an area represented by the cells of the collision probability array. The collision probability module may also cause the one or more processors to determine which cells of the collision probability array satisfy a safety criterion.

[0008] The target score array module includes instructions that, when executed by one or more processors, cause the one or more processors to generate a target score array having a plurality of cells corresponding to cells in the collision probability array that satisfy the safety criteria. The values ​​for the cells of the target score array are based on the values ​​of the corresponding cells of the collision probability array and the values ​​of the corresponding cells of the artificial potential field array. The vehicle control module includes instructions that, when executed by the one or more processors, cause the one or more processors to direct a vehicle control system of a vehicle to guide the vehicle to a location.

[0009] In another embodiment, a method for operating a vehicle having a general navigation control system and a goal-directed navigation system includes the following steps: receiving perception data from a vehicle perception system of the vehicle, discretizing the perception data into an area adjacent to a current position of the vehicle and including a plurality of grids, generating a collision probability array having a plurality of cells corresponding to the plurality of grids, determining which cells in the collision probability array satisfy safety criteria, generating a target score array having a plurality of cells corresponding to the cells in the collision probability array that satisfy the safety criteria, and directing the vehicle control system of the vehicle to guide the vehicle to a position representing a cell in the target score array having a most desired value.

[0010] The cells of the collision probability array indicate the likelihood of a collision if the vehicle moves into the area represented by the cells of the collision probability array. The values ​​for the plurality of cells of the artificial potential field array are a function of the proximity of the current location of the vehicle to the location of the target. The values ​​for the cells of the destination score array are based on the values ​​of the corresponding cells of the collision probability array and the values ​​of the corresponding cells of the artificial potential field array.

[0011] In yet another embodiment, a non-transitory computer-readable medium for operating a vehicle having a general navigation control system and a goal-oriented navigation system includes instructions that, when executed by one or more processors, cause the one or more processors to perform the following operations: receive perception data from a vehicle perception system of the vehicle, discretize the perception data into an area adjacent to a current location of the vehicle, generate a collision probability array having a plurality of cells corresponding to a plurality of grids, determine which cells in the collision probability array satisfy safety criteria, generate a destination score array having a plurality of cells corresponding to the cells in the collision probability array that satisfy the safety criteria, and direct the vehicle control system of the vehicle to guide the vehicle to a location representing a cell in the destination score array having a highest value.

[0012] Similar to the previous text, the cells of the collision probability array indicate the possibility of collision if the vehicle moves to the area represented by the cells of the collision probability array. The values ​​of multiple cells of the artificial potential field array are functions of the proximity of the current location of the vehicle to the target location. The values ​​of the cells of the target score array are based on the values ​​of the corresponding cells of the collision probability array and the values ​​of the corresponding cells of the artificial potential field array.

[0013] Further areas of applicability and various methods of enhancing the disclosed technology will become apparent from the description provided.The description and specific examples in this summary are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings illustrate various systems, methods and other embodiments of the present disclosure, and the accompanying drawings are incorporated into and constitute a part of the specification. It will be appreciated that the element boundaries (e.g., frames, groups of frames or other shapes) illustrated in the accompanying drawings represent an embodiment of boundaries. In some embodiments, an element may be designed as a plurality of elements, or a plurality of elements may be designed as an element. In some embodiments, an element shown as an internal component of another element may be implemented as an external component, and vice versa. In addition, the elements may not be drawn to scale.

[0015] Figure 1 A block diagram of a vehicle incorporating a goal-directed navigation system is illustrated;

[0016] Figure 2 yes Figure 1 A more detailed block diagram of the goal-directed navigation system;

[0017] Figure 3 A flow chart illustrating a conventional general navigation system for a vehicle;

[0018] Figure 4A flow chart illustrating a goal-directed navigation system utilizing components of a common navigation system of a vehicle;

[0019] Figure 5A-5G An example scenario of a vehicle utilizing a goal-directed navigation system is illustrated;

[0020] Figure 6 An example scenario of a vehicle utilizing a goal-directed navigation system performing a switching operation between the goal-directed navigation system and a general navigation system is illustrated;

[0021] Figure 7 A method for using a goal-directed navigation system with a general navigation system is illustrated;

[0022] Figure 8 A method for using a goal-directed navigation system with a general navigation system to reach a final goal location using intermediate goal locations is illustrated; and

[0023] Fig. 9 A method for using a goal-directed navigation system with a general navigation system is illustrated, which performs a switching operation between the goal-directed navigation system and the general navigation system. DETAILED DESCRIPTION

[0024] Disclosed is a system, method, and non-transitory medium that utilizes a common navigation system of a vehicle to drive a vehicle from one location to another by a goal-directed navigation system. In addition, the goal-directed navigation system uses information from the common navigation system to determine a collision probability array. Each cell in the cells of the collision probability array indicates the likelihood of a collision if the vehicle is driven to the location corresponding to the cell of the collision probability array. The system can determine which cells of the collision probability array satisfy a safety criterion. The safety criterion can be satisfied when the likelihood of the vehicle colliding with another object is extremely low (such as less than 5%).

[0025] The goal-oriented navigation system considers the units that meet the safety criteria in the collision probability array, together with the artificial potential field array. The artificial potential field array is an array of units representing the proximity of the vehicle to the destination. The system generates a purpose score array comprising multiple units, and the values ​​of these units represent where the vehicle should be driven towards, which meets the collision probability array (the safety of the vehicle) and the artificial potential field (the destination to which the vehicle hopes to travel). One or more vehicle control systems can then be actuated to drive the vehicle to the unit with the most desired score in the purpose score array. In this way, the goal-oriented navigation system provides a cost-effective solution for providing autonomous navigation of a vehicle using common hardware components.

[0026] refer to Figure 1 , a vehicle 100 incorporating a goal-oriented navigation system 200 is shown. The vehicle 100 may be any form of powered transport that allows for the transportation of occupants and / or items from one location to another. Thus, the vehicle 100 may be an automobile, but may also be a light truck, a heavy truck, an agricultural vehicle such as a tractor, a sport utility vehicle, a tractor trailer, a military vehicle, a mining vehicle, etc. Furthermore, the vehicle 100 is not limited to land-based vehicles, but may also include other types of vehicles, such as marine vessels and aircraft.

[0027] Vehicle 100 may include Figure 1 In this example, the vehicle 100 includes processor(s) 110 that can communicate with other vehicle systems and subsystems via one or more buses 111. As will be described later in this specification, some or all of the processor(s) 110 can be located within the vehicle 100, or can be located external to the vehicle 100 and assist in performing one or more calculations.

[0028] The vehicle 100 may include one or more perception sensors 120. The perception sensor(s) 120 may detect the environment in which the vehicle 100 operates and / or any objects in the environment. For example, the perception sensor(s) 120 may include one or more different types of sensors for detecting the environment and any objects within the environment external to the vehicle 100.

[0029] In one example, the vehicle 100 may include sensors such as LIDAR (Light Detection and Ranging) sensors 121, (multiple) cameras 122, (multiple) radar sensors 123, (multiple) sonar sensors 124. (Multiple) cameras 122 may be (multiple) high dynamic range imaging cameras. In addition, the camera 122 may include one or more single cameras or one or more stereo cameras. The sensors constituting the (multiple) perception sensors 120 are typically mounted on the vehicle 100 so that they can perceive the environment outside the vehicle 100.

[0030] The vehicle 100 may also include a general navigation system 130. The general navigation system 130 may include a general perception system 131 and a general navigation decision system 132. The general perception system 131 receives information from the perception sensor(s) 120, such as RGB images, radar data, sonar data, three-dimensional point clouds, and the like.

[0031] After receiving information from the perception sensor(s) 120, the general perception system 131 may then output the perception information to the general navigation decision system 132. The perception information may include the presence, location, and other information about one or more objects in the environment near the vehicle 100. The general navigation decision system 132 receives the perception information from the general perception system 131 and makes one or more decisions based on the information.

[0032] The general navigation decision system 132 can be one of several different systems that utilizes information from the general perception system 131 and takes some type of action. As such, the general navigation decision system 132 can be a lane keeping assist system. A lane keeping assist system can be a system that is capable of detecting the positioning of the vehicle 100 relative to one or more road markings that define a lane. Based on the position of the vehicle 100 relative to the lane, the lane keeping assist system can provide a warning to the occupants of the vehicle 100 that the vehicle 100 has deviated from the lane or is in the process of deviating from the lane, and / or a warning to control the vehicle 100 in order to keep the vehicle in the lane. The lane keeping assist system typically does not drive the vehicle 100 to the destination, but rather keeps the vehicle 100 in the lane and requires the occupants of the vehicle 100 to control the vehicle 100 at the appropriate time to drive the vehicle 100 to the intended destination.

[0033] The universal navigation system 130 may also be other types of systems. For example, the universal navigation system 130 may also include an object detection and emergency braking system, which essentially uses the universal perception system 131 to detect the presence of an object, and determines the position of the vehicle 100 relative to the detected object, and performs emergency braking or steering to avoid an imminent collision with the detected object.

[0034] The universal navigation system 130 may also be an adaptive cruise control system, wherein when the cruise control is activated, the vehicle 100 is able to detect objects external to the vehicle and adjust the speed of the vehicle so as not to collide with any detected objects. When the detected objects move away from the vehicle 100, the vehicle 100 may then regain the speed set by the occupants of the vehicle 100 when the cruise control system was activated. The adaptive cruise control system may also include a lane keeping assist feature that not only adjusts the speed of the vehicle relative to other vehicles or objects, but also acts to keep the vehicle 100 in its designated lane.

[0035] In another example, the universal navigation system 130 may also be a free space following system that receives input from a free space estimation system. For example, the free space estimation system may receive information from the perception sensor(s) 120 to determine the presence of free space in front of the vehicle 100. Based on the presence of free space in front of the vehicle 100, the free space following system may steer the vehicle to follow another vehicle and / or free space.

[0036] The examples given above regarding the general navigation system 130 are merely examples. The general navigation system 130 may take any of several different forms, including elements of the examples given above or other elements not specifically described.

[0037] The vehicle 100 may include one or more positioning sensors 140 that allow one or more systems or subsystems of the vehicle 100 to determine the location of the vehicle 100. For example, these positioning sensors may include sensors that measure acceleration, speed, steering wheel angle, etc. of the vehicle 100. In one example, the positioning sensors 140 may include accelerometers, compass sensors, wheel speed sensors, steering angle sensors, combinations thereof, etc.

[0038] The vehicle 100 may also include a global navigation satellite system (GNSS) 145. The GNSS 145 may be any type of global navigation satellite system, such as GPS (Global Positioning System), GLONASS (Global Navigation Satellite System), Galileo, and / or BeiDou. The GNSS 145 receives signals from one or more satellites and may determine the location of the vehicle 100 based on the signals received from the satellites. As will be explained later, the GNSS 145 may be used to determine the location of the vehicle 100 relative to an intermediate or final target.

[0039] The vehicle 100 may also include a route planning system 150 and a map database 160. The route planning system 150 may determine a route for the vehicle 100 to take to travel from an initial location to a destination. The route planning system 150 may receive input of a destination from an occupant of the vehicle 100. The occupant of the vehicle 100 may provide destination information using an input system 180 of the vehicle 100. The input system 180 of the vehicle 100 may be any type of input system that allows an occupant to input information. As such, the input system 180 may be a voice input microphone, a touch screen, a keyboard, an analog input, etc.

[0040] After receiving the destination from the input system 180, the route planning system 150 can receive vehicle location information from the GNSS 145. Thus, after receiving this information, the route planning system 150 has both the initial location of the vehicle as well as the destination location. Using this information, along with map information from the map database 160, the route planning system 150 can then determine one or more routes from the initial location of the vehicle 100 to the destination location. In one example, these routes can be displayed along with directions to the output system 181, which can be a display and / or an auditory output device, to provide instructions to guide the vehicle 100 to the destination.

[0041] The vehicle 100 may also include a vehicle motion controller 190 that is capable of controlling one or more vehicle systems and subsystems related to the movement of the vehicle 100. For example, the vehicle motion controller 190 may communicate with an actuator controller 185 that actuates one or more systems that control the movement of the vehicle 100. For example, the actuator controller 185 is capable of controlling pedal position, brakes, steering wheel angle, transmission selection, etc. The vehicle motion controller 190 may receive information from the universal navigation system 130 to control the movement of the vehicle 100 by sending instructions to the actuator controller 185. For example, if the universal navigation system 130 is a lane keeping assist system, the vehicle motion controller 190 may send a signal to the actuator controller 185 to control the positioning of the vehicle 100 within the lane.

[0042] The vehicle 100 may also include a potential field imaging system 195. The potential field imaging system 195 may generate an artificial potential field image (sometimes referred to as a potential field image) using the methodology disclosed in U.S. Patent Application No. 16 / 502,602, entitled "Systems and Methods for Controlling an Autonomous Vehicle Using Target-Orientated Artificial Intelligence," which is incorporated herein by reference in its entirety. An artificial potential field image is a virtual potential field emitted by a "target state." The target state is the target that the system is trying to reach. For example, in autonomous navigation, the target may be the destination location that the vehicle is trying to reach. A potential field image is conceptually similar to an electric potential field in that the closer an object is to a potential source, the stronger the potential field experienced by the object. In the case of a potential field image, the closer the vehicle 100 is to the target state, the stronger the potential experienced by the vehicle 100. Intuitively, the potential experienced by the vehicle 100 represents how close the vehicle 100 is to the target location graphically.

[0043] There are several advantages to graphically representing how close a vehicle 100 is to a target, particularly because it involves improved computational performance. Recent developments in graphics processing units (GPUs) have enabled GPUs to process large amounts of graphical data. With the subsequent development of artificial intelligence ("AI") libraries and frameworks that can handle these large amounts of data, surprisingly accurate results can be achieved. Thus, this allows innovations in computer technology, namely digital image processing in the form of a graph of how close a vehicle 100 is to a target location, which in this case reflects improvements in both the functionality of computers and target-oriented navigation technology.

[0044] The vehicle 100 may also include a goal-directed navigation system 200. The goal-directed navigation system 200 may use common components within the vehicle 100 to provide goal-directed navigation for the vehicle 100. More simply, the navigation system 200 may use the common perception system 131 of the common navigation system 130 to provide goal-directed navigation for the vehicle 100. To provide a broad overview of how this occurs, refer to Figure 3 , Figure 3 A conventional system flow 300 utilizing a universal navigation system 130 is illustrated. In addition, the conventional system flow 300 provides information captured from the perception sensor(s) 120 to the universal navigation system 130. The universal navigation system 130 may convert the information from the perception sensor 120 into information that may be utilized by the universal navigation decision system 132. As previously stated, the universal navigation decision system 132 may be a lane keeping assist system that keeps the vehicle 100 within a lane. The universal navigation decision system 132 provides this information to the vehicle motion controller 190, which sends instructions to the actuator controller 185. Upon receiving the instructions from the vehicle motion controller 190, the actuator controller 185 controls one or more actuators to keep the vehicle 100 in a designated lane, and the one or more actuators control the movement of the vehicle 100.

[0045] Figure 4 The system flow 400 is illustrated including a goal directed navigation system 200 that utilizes common components of the common perception system 13, such as the common navigation system 130. Here, the goal directed navigation system 200 receives the output of the common perception system 131. By doing so, separate (multiple) perception sensors 120 and / or the common perception system 131 do not need to be implemented to utilize the goal directed navigation system 200. This can be advantageous because additional sensors and perception systems are not required, which reduces the cost and complexity of the system. Figure 4In the example shown, the potential field imaging system 195 receives information from the positioning sensor 140 and / or the data repository 210 to generate a potential field. As previously stated, the generation of the potential field is described in U.S. Patent Application No. 16 / 502,602, entitled "Systems and Methods for Controlling an Autonomous Vehicle Using Target-Orientated Artificial Intelligence," which is incorporated by reference in its entirety as previously mentioned. The potential field is then provided to the target-oriented navigation system 200.

[0046] The goal-oriented navigation system 200 also receives information from the general perception system 131. As will be explained in more detail later in this specification, the goal-oriented navigation system 200 uses the information from the general perception system 131 to determine a collision probability array. Each cell of the collision probability array indicates the likelihood of a collision if the vehicle 100 is driven toward a position corresponding to that cell of the collision probability array. The goal-oriented navigation system 200 can determine which cells of the collision probability array meet safety criteria. The safety criteria can make the likelihood of the vehicle 100 colliding with another object extremely low, such as less than 5%.

[0047] The goal-oriented navigation system 200 considers the unit that meets safety criteria in the collision probability array, together with the artificial potential field array.The artificial potential field array is an array of units representing the proximity of the vehicle 100 to the destination.The goal-oriented navigation system 200 generates a purpose score array comprising multiple units, and the value of these units represents where the vehicle should be driven towards, to meet the collision probability array (safety of the vehicle) and the artificial potential field (the destination that the vehicle wishes to travel to).The vehicle motion controller 190 can actuate the actuator via the actuator controller 185, so that the vehicle 100 is driven towards the unit with the most desired score in the purpose score array.Like this, the goal-oriented navigation system 200 provides a cost-effective solution, to be used for using the universal hardware components of the universal perception system 13 such as the universal navigation system 130, to provide the autonomous navigation of the vehicle.

[0048] refer to Figure 2, one embodiment of a goal-oriented navigation system 200 is further illustrated. As shown, the goal-oriented navigation system 200 includes (multiple) processors 110. Therefore, (multiple) processors 110 can be part of the goal-oriented navigation system 200, or the goal-oriented navigation system 200 can access (multiple) processors 110 through a data bus or another communication path. In one or more embodiments, the processor 110 is an application-specific integrated circuit that is configured to implement the functions associated with the receiving module 241, the discretization module 242, the collision probability module 243, the purpose score array module 244, the vehicle control module 245, the target update module 246 and / or the switching module 247. More generally, in one or more aspects, the (multiple) processors 110 are electronic processors such as microprocessors that can perform the various functions described herein when loading the modules 241-247 and executing the encoded functions associated therewith.

[0049] In one embodiment, the goal-oriented navigation system 200 includes a memory 240 that stores modules 241-247. The memory 240 is a random access memory (RAM), a read-only memory (ROM), a hard drive, a flash memory, or other suitable memory for the memory modules 241-247. For example, the modules 241-247 are computer-readable instructions that, when executed by the (multiple) processors 110, cause the (multiple) processors 110 to perform the various functions disclosed herein. Although in one or more embodiments, the modules 241-247 are instructions embodied in the memory 240, in other aspects, the modules 241-247 include hardware, such as processing components (e.g., controllers), circuits, etc., for independently performing one or more of the mentioned functions.

[0050] In addition, in one embodiment, the target-oriented navigation system 200 includes a data repository 210. In one embodiment, the data repository 210 is an electronic-based data structure for storing information. In at least one scheme, the data repository 210 is a database, which is stored in a memory 240 or another suitable medium, and is configured with a routine that can be executed by (multiple) processors 110, for analyzing the stored data, providing the stored data, organizing the stored data, and the like. In either case, in one embodiment, the data repository 210 stores the data used by the modules 241-247 in performing various functions. In one embodiment, the data repository 210 includes sensor data 220, which can be data collected by (multiple) perception sensors 120 and / or processed by the general perception system 131. The data repository 210 can also include target information 230, which can include intermediate and / or final target information for the vehicle 100 and / or the current positioning information of the vehicle 100.

[0051] With respect to modules 241-247, receiving module 241 may include instructions that, when executed by processor(s) 110, cause processor(s) 110 to receive perception data from a general perception system 131 of vehicle 100. The perception data from general perception system 131 may be in the form of one or more images, point clouds, sonar data, and / or radar data, or may be processed data that provides information about the presence of one or more objects located in one or more images, point clouds, sonar data, and / or radar data. For example, referring to Figure 5A , this figure illustrates a vehicle 100 traveling on a road, and this figure also includes other vehicles traveling on the same road. Figure 5B , the perception data 501 is in the form of information about the presence of one or more objects related to the vehicle 100 .

[0052] The discretization module 242 may include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to discretize the sensory data into an area adjacent to the current location of the vehicle 100. Figure 5C As best shown in Figure 5B The perception data 501 is discretized into a plurality of grids 502. The discretization module 242 may also include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to divide a K-by-K area in front of the vehicle into a grid having a plurality of grids along two or more axes, the K-by-K area being an area adjacent to the current position of the vehicle 100.

[0053] The collision probability module 243 may include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to generate a collision probability array having a plurality of cells corresponding to the plurality of grids 502. The cells of the collision probability array indicate the likelihood of a collision if the vehicle 100 moves into the area represented by the cells of the collision probability array, and determine which cells of the collision probability array satisfy the safety criteria. For example, referring to Figure 5D , illustrated is a collision probability array 503. The collision probability array 503 includes a portion of cells (hereinafter, referred to as a "specific area") that indicate that they meet the safety criterion. The safety criterion may be such that if the vehicle 100 moves to a location represented by one or more cells in the collision probability array 503 that meet the safety criterion, the vehicle 100 is unlikely to collide with another object. In this way, the specific area of ​​the collision probability array 503 indicates the cells that meet the safety criterion, and indicates that if the vehicle 100 moves to the location represented by the cells that meet the safety criterion, the vehicle 100 is unlikely to collide with any other object.

[0054] The receiving module 241 may also include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to receive the artificial potential field array. Figure 5E , illustrated is an artificial potential field array 504, which indicates a destination to which the vehicle 100 wishes to travel. As stated previously, the artificial potential field array is an array of cells that represent the proximity of the vehicle 100 to the destination. The values ​​for the plurality of cells of the artificial potential field array are a function of the proximity of the current location of the vehicle 100 to the target location or destination. The destination may be an intermediate destination or a final destination. An intermediate destination is a destination between the current location of the vehicle and the final destination. An intermediate destination may serve as a stepping stone to a final destination.

[0055] The target score array module 244 may include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to generate a target score array having a plurality of cells corresponding to cells in the collision probability array that satisfy the safety criteria. The values ​​for the cells in the target score array are based on the values ​​of the corresponding cells in the collision probability array and the values ​​of the corresponding cells in the artificial potential field array. For example, referring to Fig. 5F, illustrated is a purpose score array 505 including cells having values ​​based on the values ​​of corresponding cells of the collision probability array 503 and the values ​​of corresponding cells of the artificial potential field array 504. Also illustrated is a position 506, which is represented by the cell determined to have the most desired value. The most desired value represents a position towards which the vehicle 100 should travel to avoid colliding with another object but also moving toward an intermediate goal or a final goal. The most desired value can be a high value, but can also be a low value.

[0056] The values ​​for multiple cells of the target score array can be:

[0057]

[0058] β∈[0,1]; and

[0059] Among them, i is the value of multiple cells of the target score array, is the value of multiple units of the artificial potential field array, S′ i is the value for a number of cells in the collision probability array, and β is the aggressiveness factor, which indicates the relative importance of safety. The cell with the highest value in the goal score array is expressed as:

[0060] T′ t = argmax i oi

[0061] The vehicle control module 245 may include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to direct the vehicle motion controller 190 of the vehicle 100 to steer the vehicle 100 to the location representing the cell having the highest value in the goal score array. Fig. 5F and Figure 5G , the vehicle motion controller 190 of the vehicle 100 guides the vehicle 100 to a position 506, which represents the most desired value of the goal score array 505. In this way, the goal-oriented navigation system 200 can drive the vehicle 100 toward a goal that satisfies both the collision probability array 503 (the safety of the vehicle) and the artificial potential field array 504 (the destination to which the vehicle wishes to travel).

[0062] The target update module 246 may include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to update the target location to a new target location when the vehicle 100 has reached the target location. Figure 5G, after the vehicle has arrived at location 506, the goal-oriented navigation system 200 can again perform the methodology disclosed above to determine a new target location to which the vehicle 100 is to travel. In this way, the goal-oriented navigation system 200 can determine the final destination to be traveled to, and can then use the route planning system 150 to determine a route. The route can be broken down into intermediate goals, which represent locations to which the vehicle 100 is to travel. As the vehicle travels from one intermediate goal to another, the vehicle 100 becomes closer and closer to its final destination.

[0063] For example, Figure 6 The vehicle 100 is illustrated as having a starting position 602 and a final target 604. Thus, the starting position 602 is the position where the vehicle 100 starts, and then the final target 604 is the position where the destination of the vehicle 100 ends. Here, the route planning system 150 of the vehicle 100 has designed a route along the road. The route includes several intermediate targets 606, 608, 610, 612. Here, the intermediate target 606 can represent the center of the artificial potential field. As previously described, the goal-oriented navigation system 200 utilizes the artificial potential field, together with information from a general navigation system, to drive the vehicle to a target, which in this case is the intermediate target 606. After arriving at the intermediate target 606, the goal-oriented navigation system 200 adds another intermediate target 608. After arriving at the intermediate target 608, the goal-oriented navigation system sets the distance for the intermediate target 610, followed by the intermediate target 612, and finally to the final target 604.

[0064] The switching module 247 may include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to switch control between the goal-oriented navigation system 200 of the vehicle 100 and the general navigation system 130. Figure 6 , the route from the starting location 602 to the final destination 604 can be decomposed into intermediate destinations 606, 608, 610, and 612, each of which has an artificial potential field around it. Depending on where the vehicle 100 is located along the route, either the goal-oriented navigation system 200 can control the vehicle 100 or the general navigation system 130 can control the vehicle 100.

[0065] For example, Figure 6The route shown in includes a time period 621 between the starting location 602 and the intermediate destination 606. During this period (time periods 621 and 622), the switching module 247 may cause the processor(s) 110 to determine that the goal-directed navigation system 200 should take control of the vehicle 100. This may be because the vehicle 100 is merging onto a highway, which has many vehicles located on the highway, and the goal-directed navigation system can manage highway entry, while the general navigation system 130, which may be a simple lane keeping system, generally cannot.

[0066] As the vehicle 100 continues along the route, the vehicle will eventually reach the intermediate destination 608. At the intermediate destination 608, the switching module 247 can cause the processor(s) 110 to determine that since the vehicle 100 is traveling along a straight road, the goal-directed navigation system 200 is no longer necessary, and instead the general navigation system 130 can be utilized (time period 623). Here, since the vehicle 100 is simply traveling along a straight road, the switching module 247 can cause the processor(s) 110 to determine that the lane keeping assist system is sufficient to steer the vehicle along the lane of the road.

[0067] As the vehicle 100 continues along the road toward the intermediate destination 610, the switching module 247 may cause the processor(s) 110 to determine that the goal-directed navigation system 200 should take over command of the vehicle 100 from the general navigation system 130 (time periods 624, 625, and 626). Here, because the vehicle 100 is now changing lanes and moving toward an exit ramp that leads to the final destination 604, the switching module 247 may cause the processor(s) 110 to determine that the goal-directed navigation system 200 should now take control of the vehicle 100, taking into account both the safety of the vehicle 100 and the destination to which the vehicle 100 wishes to travel.

[0068] Thus, the switching module 247 enables the processor(s) 110 to determine situations in which the vehicle's general navigation system 130 is sufficient to drive the vehicle 100, and other situations in which the goal-oriented navigation system 200 should be utilized to drive the vehicle 100. In the example mentioned above, when the vehicle 100 is traveling along a straight road, or otherwise intends to stay in the same lane, the general navigation system 130 can be utilized. However, when the vehicle 100 needs to perform more complex maneuvers in order to reach a final or intermediate destination, the switching module 247 can enable the processor(s) 110 to transfer control of the vehicle 100 to the goal-oriented navigation system 200.

[0069] Figure 7A method 700 is illustrated for a vehicle having a universal navigation control system and a goal-oriented navigation system. The method 700 will start with Figure 1 100 means of transport, and Figure 2 The method 700 is described from the perspective of the target positioning navigation system 200. However, the method 700 can be suitable for execution in any of a number of different situations and is not necessarily performed by Figure 1 100 and / or Figure 2 The goal-oriented navigation system 200 is implemented.

[0070] Here, the method 700 begins at step 702, where the target update module 246 causes the processor(s) 110 to receive a target location. The target location may be an intermediate target location between the start point of the route and the end point of the route, or may be a final target representing the end point of the route. In step 704, the receiving module 241 causes the processor(s) 110 to receive the location of the vehicle 100. The location of the vehicle 100 may be generated by the GNSS 145 of the vehicle 100.

[0071] In step 706, the target update module 246 causes the processor(s) 110 to determine whether the vehicle 100 has reached the location indicated in step 702. This can be done by comparing the target location with the vehicle location. If there is a substantial match, the method 700 can end. However, if the vehicle has not yet reached the target location, the method proceeds to method 710. The method 710 is related to a series of steps for utilizing a target-oriented navigation system 200. The method 710 may include all steps 712-722 or a subset of the steps. In addition, the method 710 may not be performed in the order described.

[0072] Here, the method 710 begins at step 712, where the receiving module 241 causes the processor(s) 110 to receive perception data from the universal perception system 131 of the vehicle 100. As previously described, the perception data includes information about one or more objects external to the vehicle 100.

[0073] In step 714, the discretization module 242 causes the processor(s) 110 to discretize the sensory data into an area adjacent to the current location of the vehicle 100. Figure 5C best shown in Figure 5B The perception data 501 is discretized into a plurality of grids 502. The discretization module 242 may also include instructions that, when executed by the processor(s) 110, cause the processor(s) 110 to divide a K by K area in front of the vehicle 100 along two or more axes into a grid having a plurality of grids, the K by K area being an area adjacent to the current position of the vehicle 100.

[0074] In step 716, the collision probability module 243 causes the processor(s) 110 to generate a collision probability array having a plurality of cells corresponding to the plurality of grids. The cells of the collision probability array indicate the likelihood of a collision if the vehicle 100 moves into the area represented by the cells of the collision probability array, and determines which cells of the collision probability array satisfy the safety criteria. For example, referring to Figure 5D , illustrated is a collision probability array 503 .

[0075] In step 718, the collision probability module 243 causes the (multiple) processors 110 to determine which cells of the collision probability array meet the safety criteria. The collision probability array 503 includes a portion of cells (hereinafter, referred to as "specific areas") that indicate that they meet the safety criteria. The safety criteria may be such that if the vehicle 100 moves to a position represented by one or more cells in the collision probability array 503 that meet the safety criteria, the vehicle 100 is unlikely to collide with another object. In this way, the specific area of ​​the collision probability array 503 indicates such a cell that meets the safety criteria, and if the vehicle 100 moves to a location represented by a cell that meets the safety criteria, the vehicle 100 is unlikely to collide with any other object.

[0076] In step 719, the receiving module 241 may cause the processor(s) 110 to receive an artificial potential field array. As previously stated, the artificial potential field array is an array of cells that represent the proximity of the vehicle 100 to the destination. The values ​​for the plurality of cells of the artificial potential field array are a function of the proximity of the current location of the vehicle 100 to the target location or destination. The destination may be an intermediate destination, or may be a final destination.

[0077] In step 720, the purpose score array module 244 can make (multiple) processors 110 generate the purpose score array. The purpose score array can include a plurality of units corresponding to the units that meet the safety criteria in the collision probability array. The value of the unit for the purpose score array is based on the value of the corresponding unit of the collision probability array and the value of the corresponding unit of the artificial potential field array. For example, with reference to 5F, illustrated is the purpose score array 505 comprising a unit, the value that the unit has is based on the value of the corresponding unit of the collision probability array 503 and the value of the corresponding unit of the artificial potential field array 504. Position 506 is also illustrated, and position 506 is represented by the unit determined to have the most desired value. The most desired value represents a position, and wherein the vehicle 100 should travel to this position, to avoid colliding with another object but also moving towards an intermediate target or a final target. The most desired value can be a high value, but can also be a low value.

[0078] In step 722, the vehicle control module 245 causes the processor(s) 110 to direct the vehicle motion controller 190 of the vehicle 100 to guide the vehicle 100 to a location that represents the cell in the target score array having the most desired value. Fig. 5F and Figure 5G , the vehicle motion controller 190 of the vehicle 100 guides the vehicle 100 to a position 506, which represents the most desired value of the goal score array 505. In this way, the goal-oriented navigation system 200 can drive the vehicle 100 toward a goal that satisfies both the collision probability array 503 (the safety of the vehicle) and the artificial potential field array 504 (the destination to which the vehicle wishes to travel).

[0079] After method 710 has been completed, method 700 returns to step 702, and the process begins again from step 702. In this example, the target location received after completing method 700 may be a new target location.

[0080] refer to Figure 8 , another method 800 for a vehicle having a universal navigation control system and a goal-oriented navigation system. The method 800 will start with Figure 1 100 means of transport, and Figure 2 The method 800 is described from the perspective of the target positioning navigation system 200. However, the method 800 can be suitable for execution in any of a number of different situations and is not necessarily performed by Figure 1 100 and / or Figure 2 The goal-oriented navigation system 200 is implemented.

[0081] Method 800 describes a methodology for utilizing an ultimate goal and a series of intermediate goals, similar to Figure 6 As shown and described in , a series of intermediate targets ultimately lead to a final target. Here, the method 800 begins at step 802, where the target update module 246 causes the (multiple) processors 110 to receive the final target location. The final target location can be provided by an occupant of the vehicle 100 via the input system 180. In step 804, the target update module 246 causes the (multiple) processors 110 to receive the current vehicle location. The current vehicle location can be provided by the GNSS 145.

[0082] In step 806, the target update module 246 causes the processor(s) 110 to determine whether the vehicle 100 has reached the final destination. If the vehicle 100 has reached the final destination, the method 800 ends. Otherwise, the method proceeds to step 808. In step 808, the target update module 246 causes the processor(s) 110 to determine a route from the current vehicle location to the final destination location. This can be performed by the route planning system 150, which utilizes the final destination, the current vehicle location, and a map from the map database 160 to generate a route for the vehicle 100 to travel to reach the final destination. In addition, the processor(s) 110 may also determine one or more intermediate destination locations, as shown in step 810.

[0083] In step 812, the receiving module 241 receives the artificial potential field array based on the target orientation. The target orientation may be an intermediate target orientation, or may be a final target. As previously stated, the artificial potential field array may be generated as described in U.S. Patent Application No. 16 / 502,602 entitled "Systems and Methods for Controlling an Autonomous Vehicle Using Target-Orientated Artificial Intelligence", which is incorporated by reference in its entirety as previously mentioned.

[0084] In step 814, Figure 7 The method 710 is executed. As stated above, Figure 7 The method 710 can utilize the artificial potential field array and information from the universal perception system 131 of the universal navigation system 130 of the vehicle 100 to guide the vehicle 100 to the target.

[0085] In step 816, once the vehicle 100 has reached the intermediate target location, the intermediate target location can be erased and the method 800 returns to step 804, where the method 800 determines the current vehicle location and determines whether the vehicle has reached the final target. As stated above, if the vehicle has reached the final target, the method 800 ends, otherwise, the method 800 continues until the vehicle reaches the final target.

[0086] refer to Fig. 9 , another method 900 for a vehicle having a universal navigation control system and a goal-oriented navigation system. The method 900 will Figure 1 100 means of transport, and Figure 2 The method 900 is described from the perspective of the target positioning navigation system 200. However, the method 900 can be suitable for execution in any of a number of different situations and is not necessarily performed by Figure 1 100 and / or Figure 2 The goal-oriented navigation system 200 is implemented.

[0087] Method 900 is somewhat similar to Figure 8 As such, similar steps will be briefly described, but it should be understood that the previous description is equally applicable to method 900. Here, the target update module 246 causes the processor(s) 110 to receive the final target location and the current vehicle location, as indicated in steps 902 and 904, respectively. If the vehicle 100 has reached the final target, then the method 900 ends.

[0088] However, if the final destination has not been reached, as determined in step 906, the method 900 proceeds to step 908. In step 908, the switching module 247 causes the processor(s) 110 to decide whether control of the vehicle 100 should be switched from the generic navigation system 130 to the goal-oriented navigation system 200, or vice versa. For example, if the vehicle 100 is traveling on a straight road, the method 900 may determine that it is more appropriate for the generic navigation system 130 to drive the vehicle 100 along the road, and the method 900 will proceed to step 917.

[0089] However, if the switching module 247 causes the processor(s) 110 to determine that a more complex maneuver is required by the vehicle 100, the method 900 may proceed to step 910, where control of the vehicle 100 is handed over to the goal-oriented navigation system 200, and an intermediate target position is determined. Thereafter, in step 912, as described, the artificial potential field array is based on the target position of 910, and as indicated in step 914, the method 710 is executed. After the method 710 is executed, as indicated in step 916, the intermediate target position may be erased, and the method returns to step 904.

[0090] It should be appreciated that any system described in this specification can be configured with various arrangements of separate integrated circuits and / or chips. The circuits are connected via connection paths to provide for signal transmission between separate circuits. Of course, although separate integrated circuits are discussed, in various embodiments, these circuits can be integrated into a common integrated circuit board. Additionally, the integrated circuits can be combined into fewer integrated circuits or divided into more integrated circuits.

[0091] In another embodiment, the described method and / or its equivalent may be implemented with computer executable instructions. Thus, in one embodiment, a non-transitory computer readable medium is configured with stored computer executable instructions that, when executed by a machine (e.g., a processor, a computer, etc.), cause the machine (and / or associated components) to perform the method.

[0092] Although the methodology illustrated in the figure is shown and described as a series of blocks for simplicity of explanation, it should be appreciated that the methodology is not limited by the order of the blocks, as some blocks may occur in different orders and / or simultaneously with other blocks shown and described. In addition, less than all of the illustrated blocks may be used to implement the example methodology. The blocks may be combined or separated into multiple components. In addition, additional and / or alternative methodologies may employ additional blocks not shown.

[0093] Detailed embodiments are disclosed herein. However, it should be understood that the disclosed embodiments are intended to be examples only. Therefore, the specific structural and functional details disclosed herein should not be interpreted as limiting, but only as the basis of the claims, and as a representative basis for teaching those skilled in the art to adopt the aspects described herein in various ways with virtually any appropriate detailed structure. In addition, the terms and phrases used herein are not intended to be limiting, but are intended to provide an understandable description that may be implemented.

[0094] The flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functionality and operation of the system, method and computer program product according to various embodiments. In this regard, each box in the flow chart or block diagram can represent a module, segment or part of the code, which includes one or more executable instructions for implementing the specified (multiple) logical functions. It should also be noted that in some alternative implementations, the functions indicated in the box may not occur in the order indicated in the figure. For example, depending on the functionality involved, two consecutive boxes can actually be executed substantially simultaneously, or these boxes can sometimes be executed in reverse order.

[0095] The above-mentioned systems, components and / or processes can be implemented in hardware or a combination of hardware and software, and can be implemented in a centralized manner in one processing system or in a distributed manner, in which different elements are spread over several interconnected processing systems. Any kind of processing system or other device suitable for performing the methods described herein is suitable. The combination of hardware and software can be a processing system with a computer-usable program code, which controls the processing system when loaded and executed so that it performs the methods described herein. The system, components and / or process can also be embedded in a computer-readable storage device, such as a computer program product or other data program storage device readable by a machine, so as to tangibly embody an instruction program executable by a machine to perform the methods and processes described herein. These elements can also be embedded in an application product, which includes all the features that can implement the methods described herein and can perform these methods after being loaded into a processing system.

[0096] In addition, the apparatus described herein may take the form of a computer program product, which is embodied in one or more computer-readable media, and the computer-readable medium has a computer-readable program code embodied (e.g., stored) thereon. Any combination of one or more computer-readable media may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The phrase "computer-readable storage medium" refers to a non-temporary storage medium. The computer-readable medium may take the form of, but is not limited to, non-volatile media and volatile media. Non-volatile media may include, for example, optical disks, magnetic disks, etc. Volatile media may include, for example, semiconductor memory, dynamic memory, etc. Examples of such computer-readable media may include, but are not limited to, floppy disks, floppy disks, hard disks, tapes, other magnetic media, ASICs, graphics processing units (GPUs), CDs, other optical media, RAM, ROM, memory chips or cards, memory sticks, and other media, which may be read by a computer, a processor, or other electronic devices. In the context of this article, a computer-readable storage medium may be any tangible medium that may contain or store a program for use by, or in conjunction with, an instruction execution system, an apparatus, or a device.

[0097] The following includes definitions of selected terms used herein. The definitions include various examples and / or forms of components that fall within the scope of the terms and can be used in various implementations. These examples are not intended to be limiting. Both singular and plural forms of the terms may be within the definitions.

[0098] References to "one embodiment," "an embodiment," "an example," "an example," etc. indicate that the embodiment(s) or examples so described may include particular features, structures, characteristics, properties, elements, or limitations, but not every embodiment or example must include the particular features, structures, characteristics, properties, elements, or limitations. Furthermore, although the phrase "in one embodiment" may be used repeatedly, use of the phrase does not necessarily refer to the same embodiment.

[0099] As used herein, a "module" includes a computer or (multiple) electrical hardware components, firmware, a non-transitory computer-readable medium storing instructions, and / or a combination of these components, which is configured to perform (multiple) functions or (multiple) actions, and / or is configured to cause functions or actions from another logic, method and / or system. A module may include a microprocessor controlled by an algorithm, discrete logic (e.g., ASIC), an analog circuit, a digital circuit, a programmed logic device, a memory device including instructions for executing the algorithm when executed, and the like. In one or more embodiments, a module may include one or more CMOS gates, a combination of gates, or other circuit components. In the case of describing multiple modules, one or more embodiments may include incorporating multiple modules into one physical module component. Similarly, in the case of describing a single module, one or more embodiments distribute the single module between multiple physical components.

[0100] Additionally, the module used herein includes routines, programs, objects, components, data structures, etc. that perform tasks or implement data types. In other aspects, memory generally stores the modules mentioned. The memory associated with the module can be a buffer or cache, RAM, ROM, flash memory or other suitable electronic storage medium embedded in the processor. In further aspects, the module contemplated by the present disclosure is implemented as an application specific integrated circuit (ASIC), a hardware component of a system on a chip (SoC), a programmable logic array (PLA), a graphics processing unit (GPU), or is implemented as another suitable hardware component of an embedded definition configuration set (e.g., instruction) for performing the disclosed functions.

[0101] In one or more devices, one or more of the modules described herein may include artificial or computational intelligence elements, such as neural networks, fuzzy logic or other machine learning algorithms. In addition, in one or more arrangements, one or more of the modules may be distributed among multiple modules described herein. In one or more devices, two or more of the modules described herein may be combined into a single module.

[0102] Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber, cable, RF, etc., or any suitable combination of the foregoing. Computer program code for performing operations of various aspects of the present arrangement may be written in any combination of one or more programming languages, including such as Java. TM , Smalltalk, C++, and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or a connection may be established with an external computer (e.g., through the Internet using an Internet service provider).

[0103] As used herein, the terms "one" and "an" are defined as one or more than one. As used herein, the term "plurality" is defined as two or more than two. As used herein, the term "another" is defined as at least a second or more. As used herein, the terms "include" and / or "have" are defined as including (i.e., open language). As used herein, the phrase "at least one of ... and ... " refers to and encompasses all possible combinations of one or more of the associated listed items. As an example, the phrase "at least one of A, B, and C" includes only A, only B, only C, or any combination thereof (e.g., AB, AC, BC, or ABC).

[0104] The various aspects of the present invention may be embodied in other forms without departing from its spirit or essential attributes. Accordingly, reference should be made to the appended claims, rather than to the foregoing specification, as indicating the scope thereof.

Claims

1. A goal-oriented navigation system for a vehicle having a general navigation system, the goal-oriented navigation comprising: one or more processors; and a memory in communication with the one or more processors, the memory comprising: a receiving module having instructions that, when executed by the one or more processors, cause the one or more processors to receive perception data from a vehicle perception system of the vehicle, a discretization module, the discretization module having the following instructions, which, when executed by the one or more processors, cause the one or more processors to discretize the sensed data into an area adjacent to the current location of the vehicle, the area including a plurality of grids; a collision probability module having instructions that, when executed by the one or more processors, cause the one or more processors to generate a collision probability array and determine which cells of the collision probability array satisfy a safety criterion, the collision probability array having a plurality of cells corresponding to the plurality of grids, the cells of the collision probability array indicating a likelihood of a collision if the vehicle moves into the area represented by the cells of the collision probability array; a receiving module, the receiving module having the following instructions, when the instructions are executed by the one or more processors, causing the one or more processors to receive an artificial potential field array, the artificial potential field array having a plurality of cells corresponding to the plurality of cells of the collision probability array, the values ​​of the plurality of cells of the artificial potential field array being a function of the proximity between the current location of the vehicle and a target location, and a plurality of target locations of the vehicle being arranged on a predetermined travel route of the vehicle; a target score array module having instructions that, when executed by the one or more processors, cause the one or more processors to generate a target score array having a plurality of cells corresponding to the cells in the collision probability array that satisfy the safety criterion, wherein values ​​for the cells in the target score array are based on values ​​of corresponding cells in the collision probability array and values ​​of corresponding cells in the artificial potential field array; and a vehicle control module having instructions that, when executed by the one or more processors, cause the one or more processors to direct a vehicle control system of the vehicle to direct the vehicle to a location representing a cell having a highest value in the destination score array, wherein the values ​​for the plurality of cells of the target score array are: β∈[0,1]; and wherein oi is the value of the plurality of cells of the target score array, is the value of the plurality of units of the artificial potential field array, s′ i are the values ​​for the plurality of cells of the collision probability array, and β is an aggressiveness factor representing the relative importance of safety.

2. The goal-oriented navigation system according to claim 1, wherein the discretization module further comprises the following instructions, which, when executed by the one or more processors, cause the one or more processors to divide the K by K area in front of the vehicle into the multiple grids along two or more axes, the K by K area being the area adjacent to the current position of the vehicle.

3. A goal-oriented navigation system according to claim 1, wherein the collision probability module further comprises the following instructions, which, when executed by the one or more processors, cause the one or more processors to specify the cells of the collision probability array to indicate the cells of the collision probability array that satisfy the safety criteria.

4. The goal-oriented navigation system of claim 1, wherein the cell with the highest value in the goal score array is expressed as: T t ′=argmax i o i 。 5. A target-oriented navigation system according to claim 1, wherein the memory also includes a target update module, and the target update module includes the following instructions, which, when executed by the one or more processors, cause the one or more processors to update the target location to a new target location when the vehicle has reached the target location.

6. The goal-directed navigation system of claim 5, wherein the new target location is determined based on a route to a final target location.

7. The goal-oriented navigation system according to any one of claims 1 to 6, wherein the memory further comprises a switching control module, the switching control module comprising the following instructions, which, when executed by the one or more processors, cause the one or more processors to: determining the position of the vehicle along the route, and The vehicle control system is directed by a switching control system to utilize commands from the goal-directed navigation system or the general navigation system based on the position of the vehicle along the route.

8. A method for operating a vehicle having a general navigation system and a target-oriented navigation system, the method comprising the following steps: receiving perception data from a vehicle perception system of the vehicle; discretizing, by the goal-oriented navigation system, the sensed data into an area adjacent to a current location of the vehicle, the area comprising a plurality of grids; generating, by the goal-directed navigation system, a collision probability array having a plurality of cells corresponding to the plurality of grids, the cells of the collision probability array indicating a likelihood of collision if the vehicle moves to the area represented by the cells of the collision probability array; determining, by the goal-oriented navigation system, which cells of the collision probability array satisfy a safety criterion; receiving, by the goal-directed navigation system, an artificial potential field array having a plurality of cells corresponding to the plurality of cells of the collision probability array, the values ​​for the plurality of cells of the artificial potential field array being a function of proximity of the current location of the vehicle to a target location, a plurality of target locations of the vehicle being arranged on a predetermined travel route of the vehicle; generating, by the goal-directed navigation system, a target score array having a plurality of cells corresponding to the cells in the collision probability array that satisfy the safety criterion, wherein values ​​for the cells in the target score array are based on values ​​of corresponding cells in the collision probability array and values ​​of corresponding cells in the artificial potential field array; as well as directing a vehicle control system of the vehicle by the goal-directed navigation system to guide the vehicle to a location representing a cell having a highest value in the objective score array, wherein the values ​​for the plurality of cells of the target score array are: β∈[0,1]; and wherein oi is the value of the plurality of cells of the target score array, is the value of the plurality of units of the artificial potential field array, s′ i are the values ​​for the plurality of cells of the collision probability array, and β is an aggressiveness factor representing the relative importance of safety.

9. The method according to claim 8, further comprising the steps of: A K by K area in front of the vehicle is divided into the plurality of grids along two or more axes by the goal-oriented navigation system, the K by K area being the area adjacent to the current position of the vehicle.

10. The method according to claim 8, further comprising the steps of: The values ​​of the plurality of cells of the collision probability array are transformed to determine which cells of the collision probability array satisfy the safety criterion.

11. The method of claim 8, wherein the cell with the highest value in the target score array is expressed as: T t ′=argmax i o i 。 12. The method according to claim 8, further comprising the steps of: When the vehicle has reached the target location, the target location is updated to a new target location.

13. The method of claim 12, wherein the new target location is determined based on a route to a final target location.

14. The method according to any one of claims 8 to 13, further comprising the steps of: determining a position of the vehicle along a route; as well as The vehicle control system is directed by a switching control system to utilize commands from the goal-directed navigation system or the general navigation system based on the position of the vehicle along the route.

15. A non-transitory computer readable medium for operating a vehicle having a general navigation system and a goal-oriented navigation system, and comprising instructions that, when executed by one or more processors, cause the one or more processors to: receiving perception data from a vehicle perception system of the vehicle; discretizing, by the goal-oriented navigation system, the sensed data into an area adjacent to a current location of the vehicle, the area comprising a plurality of grids; generating, by the goal-directed navigation system, a collision probability array having a plurality of cells corresponding to the plurality of grids, the cells of the collision probability array indicating a likelihood of collision if the vehicle moves to the area represented by the cells of the collision probability array; determining, by the goal-oriented navigation system, which cells of the collision probability array satisfy a safety criterion; receiving, by the goal-directed navigation system, an artificial potential field array having a plurality of cells corresponding to the plurality of cells of the collision probability array, the values ​​for the plurality of cells of the artificial potential field array being a function of proximity of the current location of the vehicle to a target location, a plurality of target locations of the vehicle being arranged on a predetermined travel route of the vehicle; generating, by the goal-directed navigation system, a target score array having a plurality of cells corresponding to the cells in the collision probability array that satisfy the safety criterion, wherein values ​​for the cells in the target score array are based on values ​​of corresponding cells in the collision probability array and values ​​of corresponding cells in the artificial potential field array; as well as directing a vehicle control system of the vehicle by the goal-directed navigation system to guide the vehicle to a location representing a cell having a highest value in the objective score array, wherein the values ​​for the plurality of cells of the target score array are: β∈[0,1]; and wherein oi is the value of the plurality of cells of the target score array, is the value of the plurality of units of the artificial potential field array, s′ i are the values ​​for the plurality of cells of the collision probability array, and β is an aggressiveness factor representing the relative importance of safety.

16. The non-transitory computer-readable medium of claim 15, further comprising instructions that, when executed by one or more processors, cause the one or more processors to update the target location to a new target location when the vehicle has reached the target location.

17. The non-transitory computer-readable medium of claim 16, wherein the new target location is determined based on a route to a final target location.

18. The non-transitory computer-readable medium of any one of claims 15 to 17, further comprising instructions that, when executed by one or more processors, cause the one or more processors to: determining the position of the vehicle along the route; and The vehicle control system is directed by a switching control system to utilize commands from the goal-directed navigation system or the general navigation system based on the position of the vehicle along the route.