CN116878532A - Path planning method and device for mobile object and related equipment - Google Patents
Path planning method and device for mobile object and related equipment Download PDFInfo
- Publication number
- CN116878532A CN116878532A CN202310876558.5A CN202310876558A CN116878532A CN 116878532 A CN116878532 A CN 116878532A CN 202310876558 A CN202310876558 A CN 202310876558A CN 116878532 A CN116878532 A CN 116878532A
- Authority
- CN
- China
- Prior art keywords
- node
- target
- key
- path
- mobile object
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 105
- 238000013439 planning Methods 0.000 title claims abstract description 93
- 230000008569 process Effects 0.000 claims abstract description 43
- 230000006870 function Effects 0.000 claims description 51
- 230000006872 improvement Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 5
- 230000004888 barrier function Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002250 progressing effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
The disclosure provides a path planning method and device for a mobile object and related equipment, and relates to the technical field of computers. The method comprises the following steps: obtaining a rasterized map of a path to be planned, wherein the rasterized map comprises: a plurality of key nodes marked in advance and a starting node and a target node of a path to be planned; selecting at least one key node which is routed in the process that the mobile object moves from the initial node to the target node from a plurality of key nodes; generating path planning information of the mobile object according to the starting node, the target node and each key node in the path of the mobile object in the process of moving from the starting node to the target node. The method and the device can overcome the problem that the path searching efficiency is low due to the fact that too many unnecessary nodes are searched when the related technology is used for path planning to a certain extent.
Description
Technical Field
The disclosure relates to the field of computer technology, and in particular, to a method and a device for planning a path of a mobile object, and related equipment.
Background
The path planning of the unmanned automobile refers to that when an obstacle is found in the driving environment, the path is autonomously decided to avoid the obstacle, so that the unmanned automobile can safely reach the destination. The path planning of the unmanned automobile is quite different from the navigation of a common GPS (Global Positioning System ), and the two states of motion and static are required to be judged respectively and intelligent decision is made, so that the driving task is ensured to be completed smoothly. The quality of the path planning algorithm directly influences the driving safety, and plays a decisive role in the unmanned automobile navigation system.
The path planning algorithm commonly used in the related technology is an A-Star algorithm, and when the A-Star algorithm is adopted for path planning, under the condition of more path turning, the node selection cannot well bypass the obstacle, so that the problems of lower safety, incapability of adapting to the path planning of a complex map, low path searching efficiency and the like are caused.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The disclosure provides a path planning method, a path planning device and related equipment for a mobile object, which at least overcome the problem that the path searching efficiency is low due to the fact that excessive unnecessary nodes are searched when path planning is performed in the related technology to a certain extent.
Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.
According to one aspect of the present disclosure, there is provided a path planning method of a moving object, including: obtaining a rasterized map of a path to be planned, wherein the rasterized map comprises: a plurality of key nodes marked in advance and a starting node and a target node of a path to be planned; selecting at least one key node from the plurality of key nodes, wherein the key node is routed in the process that the mobile object moves from the starting node to the target node; generating path planning information of the mobile object according to the starting node, the target node and each key node in the path of the mobile object in the process of moving from the starting node to the target node.
In some exemplary embodiments of the present disclosure, based on the foregoing solution, selecting at least one key node from the plurality of key nodes that is routed in a process of moving the moving object from the starting node to the target node, includes: acquiring a current node of the mobile object, wherein the current node is a node where the mobile object is currently located in a grid map; determining a target vector for the moving object to move from the current node to the target node; selecting the next key node of the path of the moving object in the process of moving from the current node to the target node from the plurality of key nodes according to the target vector; repeating the steps until the next key node of the path of the mobile object is the target node.
In some exemplary embodiments of the present disclosure, based on the foregoing solution, selecting, from the plurality of key nodes, a next key node along which the mobile object moves from the current node to the target node according to the target vector, includes: selecting one target key node closest to the target node from the plurality of key nodes according to the target vector; judging whether the target key node is the target node or not; if the target key node is not the target node, judging whether an obstacle exists between the current node and the target key node; and if no obstacle exists between the current node and the target key node, determining the target key node as the next key node in the process of moving the moving object from the current node to the target node.
In some exemplary embodiments of the present disclosure, based on the foregoing scheme, after determining whether there is an obstacle between the current node and the target key node, the method further includes: if an obstacle exists between the current node and the target key node, determining barrier-free planning path information of the moving object moving from the current node to the target key node based on a cost function after the A star algorithm improvement, wherein the cost function based on the A star algorithm improvement comprises a collision distance cost factor of the moving object to the obstacle; and determining the next key node of the moving object path according to the barrier-free planning path information of the moving object moving from the current node to the target key node.
In some exemplary embodiments of the present disclosure, based on the foregoing solution, before determining the barrier-free planned path information for the moving object to move from the current node to the target critical node based on the cost function after the improvement of the a-star algorithm, the method further includes: obtaining a cost function f (N) based on an A star algorithm after improvement through the following formula;
f(N)＝g(N)+k 1 h(N)+k 2 O(N)
wherein g (N) is the minimum cost function from the starting node of the mobile object to the target key node N, h (N) is the minimum estimated cost function of the path from the target key node N to the target node of the mobile object, O (N) is the collision distance cost function at the target key node N of the mobile object, k 1 Weight, k, of the first cost function 2 Is the weight of the second cost function.
In some exemplary embodiments of the disclosure, based on the foregoing solution, the plurality of key nodes includes a steering node and a dead angle node, and if the target key node is not the target node, before determining whether there is an obstacle between the current node and the target key node, the method further includes: judging whether a key node closest to the target node is the dead angle node or not selected from the plurality of key nodes; if the key node is the dead angle node, the target key node is determined again; and if the key node is the steering node, judging whether an obstacle exists between the current node and the target key node.
In some exemplary embodiments of the disclosure, based on the foregoing scheme, the method further includes: inputting the moving speed of the moving object into a pre-trained anti-collision safe distance model, and outputting the safe distance between the moving object and an obstacle; and determining a collision distance cost function of the mobile object at the target key node according to the safety distance.
According to another aspect of the present disclosure, there is also provided a path planning apparatus of a moving object, the apparatus including: the grid map obtaining module is used for obtaining a grid map of a path to be planned, wherein the grid map comprises the following components: a plurality of key nodes marked in advance and a starting node and a target node of a path to be planned; a key node selection module, configured to select at least one key node that is routed in a process that the mobile object moves from the start node to the target node from the plurality of key nodes; and the path planning module is used for generating path planning information of the mobile object according to the starting node, the target node and each key node in the path of the mobile object in the process of moving from the starting node to the target node.
According to still another aspect of the present disclosure, there is also provided an electronic apparatus including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the path planning methods of moving objects described above via execution of the executable instructions.
According to yet another aspect of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the path planning method of any one of the moving objects described above.
The method, the device and the related equipment for planning the path of the mobile object provided by the embodiment of the disclosure firstly acquire a rasterized map containing a plurality of key nodes marked in advance and a start node and a target node of the path to be planned; and then, selecting at least one key node which is routed in the process of moving the mobile object from the starting node to the target node from a plurality of key nodes, and finally, generating path planning information of the mobile object according to the starting node, the target node and each key node which is routed in the process of moving the mobile object from the starting node to the target node.
Compared with the prior art that when a path is planned, too many unnecessary nodes are searched, so that the path searching efficiency is low, in the embodiment of the present disclosure, a plurality of key nodes are marked on a grid map of the path to be planned, when the path is planned, no other unnecessary nodes are required to be searched in a large range, and only the necessary key nodes of the route in the process of moving from the initial node to the target node need to be determined, so that the searching process of the unnecessary nodes is reduced, and the path planning efficiency is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.
FIG. 1 illustrates a schematic diagram of an application system architecture in an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a path planning method for a mobile object according to an embodiment of the disclosure;
FIG. 3 illustrates a rasterized map of a path to be planned in an embodiment of the present disclosure;
FIG. 4 illustrates a key node selection policy map based on a target vector in an embodiment of the present disclosure;
FIG. 5 illustrates a schematic diagram of an obstacle detection zone in an embodiment of the disclosure;
FIG. 6 is a graph showing a relationship model between a safe distance and a road friction coefficient, and a moving speed of a moving object in an embodiment of the present disclosure;
FIG. 7 illustrates a collision field based distance expanded grid graph in an embodiment of the present disclosure;
FIG. 8 is a flowchart illustrating an overall path planning algorithm for a moving object in an embodiment of the present disclosure;
FIG. 9 is a schematic diagram of a path planning apparatus for a moving object according to an embodiment of the disclosure;
fig. 10 shows a schematic diagram of an electronic device applying a path specification method of a moving object in an embodiment of the disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the disclosed aspects may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
Fig. 1 illustrates an exemplary application system architecture diagram to which a path planning method of a moving object in an embodiment of the present disclosure may be applied. As shown in fig. 1, the system architecture may include a terminal device 101, a network 102, and a server 103.
The medium used by the network 102 to provide a communication link between the terminal device 101 and the server 103 may be a wired network or a wireless network.
Alternatively, the wireless network or wired network described above uses standard communication techniques and/or protocols. The network is typically the Internet, but may be any network including, but not limited to, a local area network (Local Area Network, LAN), metropolitan area network (Metropolitan Area Network, MAN), wide area network (Wide Area Network, WAN), mobile, wired or wireless network, private network, or any combination of virtual private networks. In some embodiments, data exchanged over a network is represented using techniques and/or formats including HyperText Mark-up Language (HTML), extensible markup Language (Extensible MarkupLanguage, XML), and the like. All or some of the links may also be encrypted using conventional encryption techniques such as secure sockets layer (Secure Socket Layer, SSL), transport layer security (Transport Layer Security, TLS), virtual private network (Virtual Private Network, VPN), internet protocol security (Internet ProtocolSecurity, IPsec), etc. In other embodiments, custom and/or dedicated data communication techniques may also be used in place of or in addition to the data communication techniques described above.
The terminal device 101 may be a variety of electronic devices including, but not limited to, smart phones, tablet computers, laptop portable computers, desktop computers, wearable devices, augmented reality devices, virtual reality devices, and the like.
Alternatively, the clients of the applications installed in different terminal devices 101 are the same or clients of the same type of application based on different operating systems. The specific form of the application client may also be different based on the different terminal platforms, for example, the application client may be a mobile phone client, a PC client, etc.
The server 103 may be a server providing various services, such as a background management server providing support for devices operated by the user with the terminal apparatus 101. The background management server can analyze and process the received data such as the request and the like, and feed back the processing result to the terminal equipment.
Optionally, the server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligence platforms, and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the disclosure is not limited herein.
Those skilled in the art will appreciate that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative, and that any number of terminal devices, networks, and servers may be provided as desired. The embodiments of the present disclosure are not limited in this regard.
Next, each step of the path planning method of the moving object in the present exemplary embodiment will be described in more detail with reference to the drawings and examples.
Firstly, the embodiment of the disclosure provides a method for planning a path of an automatic driving vehicle in a 5G intelligent park, but in the prior art, when an obstacle is found in a driving environment, the path is autonomously decided to avoid the obstacle, so that the vehicle can safely reach a destination, and the path planning of the automatic driving vehicle is greatly different from a common global positioning system (Global Positioning System, GPS) navigation, and needs to respectively judge dynamic and static states and make an intelligent decision so as to ensure that a driving task is successfully completed. The quality of the path planning algorithm directly affects the driving safety, and plays a decisive role in the unmanned car navigation system, wherein the common path planning algorithm has the corresponding application range and advantages and disadvantages, in particular, the common path planning algorithm has the Dijkstra algorithm, the Best-First-search algorithm (BFS) and the a star (a-stat, a) algorithm, and the specific advantages and disadvantages of the three common path planning algorithms are as follows:
The Dijkstra algorithm is an optimization algorithm form with single source property, and the shortest distance which can be passed between any node and another node can be obtained by applying the Dijkstra algorithm. The algorithm is characterized by starting from a starting node, then slowly extending and progressing around and finally extending to a predetermined target node, so that the method generally has very long loss time.
The BFS algorithm is similar to the Dijkstra algorithm, the most critical difference being that the algorithm is more focused on the time penalty incurred in searching for a path. Therefore, the algorithm does not consider the position close to the departure point, but preferentially examines the position around the preset target, so that the searching path of the final BFS algorithm is not the optimal path, which is also a shortcoming of the algorithm, and the advantage of the BFS algorithm is that the speed of the algorithm is remarkably improved.
The A algorithm is an artificial intelligence algorithm which can be suitable for various road conditions, and has excellent robustness. The most remarkable advantage of the algorithm a is that Dijkstra algorithm and BFS algorithm are combined, and the current node is analyzed by heuristic evaluation of initial point and node cost and node to target point, but too many unnecessary nodes are searched during path planning of the algorithm a, so that path searching efficiency is low.
In the embodiment of the disclosure, a plurality of key nodes are marked in advance in the rasterized map of the path to be planned, and only the plurality of key nodes marked in advance are required to be searched when the path is planned, so that the problem of low path searching efficiency caused by excessive unnecessary nodes in path planning and searching in the prior art is avoided.
Fig. 2 is a schematic diagram of a path planning method of a mobile object in an embodiment of the disclosure, and as shown in fig. 2, the path planning method of the mobile object provided in the embodiment of the disclosure includes the following steps:
s201, acquiring a rasterized map of a path to be planned, wherein the rasterized map comprises: a plurality of key nodes marked in advance, and a start node and a target node of a path to be planned.
In some embodiments, as shown in fig. 3, the rasterized map of the path to be planned, which is obtained in the embodiment of the present disclosure, may be obtained by performing rasterization processing on an actual map including a moving object starting node and a target node, where the moving object starting node is a starting point at which the moving object starts to move, the target node is an ending point at which the moving object finally reaches the target, and a plurality of key nodes marked in advance are further included on the rasterized map, and the key nodes in the embodiment of the present disclosure include a turning node and/or a dead angle node and an obstacle point marked according to the actual map.
S202, selecting at least one key node in the process of moving the mobile object from the initial node to the target node from a plurality of key nodes.
In some embodiments, a key node selected from a plurality of key nodes in the embodiments of the present disclosure is a key node searched for by performing path planning on a moving object.
S203, generating path planning information of the mobile object according to the starting node, the target node and each key node in the path of the mobile object in the process of moving from the starting node to the target node.
In some embodiments, the disclosed embodiments determine path planning information of a mobile object according to a grid map including a start node and a target node of a path to be planned and a key node along which the selected mobile object is routed in a process of moving from the start node to the target node, so as to plan a moving path of the mobile object.
The path planning method of the mobile object provided in the embodiment of the present disclosure includes first obtaining a rasterized map including a plurality of key nodes marked in advance and a start node and a target node of a path to be planned; and then, selecting at least one key node which is routed in the process of moving the mobile object from the starting node to the target node from a plurality of key nodes, and finally, generating path planning information of the mobile object according to the starting node, the target node and each key node which is routed in the process of moving the mobile object from the starting node to the target node. Compared with the prior art that when a path is planned, too many unnecessary nodes are searched, so that the path searching efficiency is low, in the embodiment of the present disclosure, a plurality of key nodes are marked on a grid map of the path to be planned, when the path is planned, no other unnecessary nodes are required to be searched in a large range, and only the key nodes which are marked in advance and are necessary in the process of moving from the initial node to the target node are required to be searched, so that the technical effects of reducing the searching process of the unnecessary nodes and improving the path planning efficiency are achieved.
In some embodiments, selecting at least one key node from a plurality of key nodes along which a mobile object moves from an originating node to a target node, comprises: acquiring a current node of a mobile object, wherein the current node is a node where the mobile object is currently located in a grid map; determining a target vector of the moving object moving from the current node to the target node; selecting the next key node in the process of moving the moving object from the current node to the target node from a plurality of key nodes according to the target vector; the above steps are repeatedly executed until the next key node of the path of the moving object is the target node. Only the key nodes around the target vector need to be searched, so that the searching process of unnecessary nodes is reduced, and the path planning efficiency is greatly improved.
In some embodiments, selecting a next key node from the plurality of key nodes along which the mobile object moves from the current node to the target node according to the target vector comprises: selecting one target key node closest to the target node from a plurality of key nodes according to the target vector; judging whether the target key node is a target node or not; if the target key node is not the target node, judging whether an obstacle exists between the current node and the target key node; if no obstacle exists between the current node and the target key node, determining the target key node as the next key node in the process that the mobile object moves from the current node to the target node.
Specifically, in the embodiment of the present disclosure, as shown in fig. 3, an initial node of a mobile object in a grid map is set as S, a target node is set as G, and a target vector SG of the mobile object moving from a current node to the target node is determined, as shown in fig. 4, if A, B, C, D is a key node around the target vector SG, a key node N approaching to the target node G is selected based on the target vector SG, manhattan distance between each key node and the target node G is calculated A, B, C, D, and then a key node N with the minimum distance is selected, and according to a flag in the grid map, it is determined that the key node N is not the target node G, and then it is determined whether an obstacle exists in a path between the SN two nodes, and if no obstacle exists in the path between the SN two nodes, the key node of the next path is repeatedly determined according to the above execution steps until the next key node along which the mobile object is routed is the target node, so that the path planning efficiency is further improved.
As shown in fig. 4, the distance between the starting node S and the target node G is calculated by the formula (1), and the manhattan distances between other key nodes and the target node G can be calculated by the formula (1):
d m ＝|G x -S x |+|G y -S y | (1)
Wherein d m For Manhattan distance S from the start node S to the target node G x For the coordinates of the start node S on the x-axis S y G is the coordinate of the start node S on the y-axis x For the coordinates of the target node G on the x-axis, G y For the coordinates of the target node G on the y-axis, |G x -S x I is the distance between the start node S and the target node G in the x-axis direction, and i G y -S y I is the distance between the start node S and the target node G in the y-axis direction.
In some embodiments, after determining whether an obstacle exists between the current node and the target critical node, the method further comprises: if an obstacle exists between the current node and the target key node, determining barrier-free planning path information of the moving object moving from the current node to the target key node based on the cost function after the A star algorithm improvement, wherein the cost function after the A star algorithm improvement comprises a collision distance cost factor of the moving object to the obstacle; and determining the next key node of the path of the mobile object according to the barrier-free planning path information of the mobile object moving from the current node to the target key node. According to the cost function based on the A star algorithm improvement in the embodiment of the disclosure, by marking the key nodes on the rasterized map, only the key nodes need to be searched during path planning, the number of times of searching the nodes by the increment expansion of the A star algorithm is greatly reduced, the path planning efficiency is improved, and the problems of overlarge turning angle, multiple turning times, long path planning distance and the like in the path planning process of the traditional A star algorithm are solved.
In some embodiments, before determining the barrier-free planned path information for the moving object to move from the current node to the target critical node based on the modified cost function of the a-star algorithm, the method further comprises: obtaining a cost function f (N) based on an A star algorithm after improvement through a formula (2);
f(N)＝g(N)+k 1 h(N)+k 2 O(N) (2)
where g (N) is the minimum cost function from the starting node of the mobile object to the target key node N, h (N) is the minimum estimated cost function of the path from the target key node N to the target node of the mobile object, O (N) is the collision distance cost function at the target key node N at the mobile object, k 1 Weight, k, of the first cost function 2 Is the weight of the second cost function.
In more detail, k in embodiments of the present disclosure 1 The larger the path is, the faster the path is towards the target node, the shorter the computation time is, but this will affect the path optimality, and k 2 The value directly influences the distance between the planned path and the boundary of the obstacle, thereby influencing the movement of the moving objectAccording to multiple simulations and verifications by those skilled in the art, k in the presently disclosed embodiments 1 ＝2，k 2 Of course, k in the embodiments of the present disclosure =2 1 And k 2 The value is not limited to the above value 2, and a person skilled in the art can apply k to the actual situation 1 And k 2 The value is flexibly adjusted.
In addition, in the embodiment of the disclosure, the collision distance cost is added based on the cost function after the A star algorithm is improved, so that the collision rate of the moving object and the obstacle is reduced, and the safety of path planning is greatly improved.
In the embodiment of the disclosure, for example, the star A algorithm gradually selects the key node with the minimum cost value through repeated iteration, so as to generate an unobstructed planning path from S to N.
In some embodiments, the plurality of key nodes includes a steering node and a dead angle node, and if the target key node is not the target node, before determining whether an obstacle exists between the current node and the target key node, the method further includes: judging whether a key node closest to a target node is a dead angle node or not selected from a plurality of key nodes; if the key node is a dead angle node, the target key node is redetermined; if the key node is a steering node, judging whether an obstacle exists between the current node and the target key node.
In some embodiments, after determining the key node N with the smallest distance from the target node G, determining whether N is a dead node of the path, if so, selecting the key node N again; if not, continuing to judge whether barrier points exist in the search areas of the starting node S and the key node N. As shown in fig. 5, the search area for the start node S and the key node N is |n in length x -S x The width is the road length, for example, the road length is set to 7m. N (N) x Is the x-axis coordinate of the selected node. If no obstacle node exists in the search area, the vehicle can directly move to the key node N, and if the obstacle node exists, an unobstructed path to the key node N is planned based on the cost function after the A star algorithm is improved.
Further, the embodiments of the present disclosure divide the obstacles in the search area into two types, the first, for example, the obstacle with high probability of small-sized movement, such as a pedestrian stationary beside a road, with a length l e (1, 2) m; second, for example, obstacles with low probability of movement but large size, such as roadside parking, length l e (3, 4) m.
In some embodiments, the above method in embodiments of the disclosure further comprises: inputting the moving speed of the moving object into a pre-trained anti-collision safe distance model, and outputting the safe distance between the moving object and the obstacle; and determining a collision distance cost function of the mobile object at the target key node according to the safety distance.
Specifically, the embodiment of the disclosure designs an anti-collision safe distance model based on the moving speed, the safe distance of the moving object and a large amount of simulation test analysis, wherein the safe distance between the moving object and the obstacle is related to the moving speed of the moving object and the road friction coefficient, and in more detail, the embodiment of the disclosure obtains the anti-collision safe distance model through a formula (3):
ds＝k 3 v 2 /(2μg)+(2-μ)du (3)
Where ds is the safe distance between the moving object and the obstacle, k 3 For the weight of different types of obstacles, k is the weight of the obstacle when the obstacle is larger 3 =1.5, k when the obstacle is small 3 =1.2; v is the moving speed of the moving object; μ is the coefficient of friction of the moving object with the ground; g is gravity acceleration, and the value is 10m/s 2 The method comprises the steps of carrying out a first treatment on the surface of the du is the unit distance and takes a value of 1m.
In more detail, when the moving object is a vehicle in the embodiment of the present disclosure, based on simulation test experiments of a large number of vehicle collision scenarios, a person skilled in the art obtains a relationship model diagram of a safety distance, a road friction factor and a vehicle driving speed as shown in fig. 6, and as the road friction coefficient decreases and the vehicle driving speed increases, the safety collision distance gradually increases, which also conforms to the collision avoidance habit of the driver in the real world vehicle driving process.
The total number of layers c of the expanded grid can be obtained from equation (4) as:
wherein in formula (4)And (3) carrying out upward rounding, reassigning the collision field distance to 10m multiplied by c, and carrying out decremental assignment on the collision field distance as the cost value of the innermost grid of the expanded grid by a multiple of 10m sequentially outwards, wherein if the obstacle expanded grid comprises an obstacle grid, the collision field distance is not assigned. As shown in FIG. 7, when the moving speed of the moving object is 15m/s and the friction coefficient of the moving object with the ground is 0.8, d can be obtained by the formula (3) s Since c=2 is obtained from equation (4) =18.075 m, O (N) =20m in the embodiment of the present disclosure can be determined, the barrier boundary outer layer 1 grid is given, and the cost value O (N) =10m is given to the barrier boundary outer layer 2 grid.
In one embodiment, the overall flow of the path planning algorithm for a mobile object according to the embodiment of the present disclosure is shown in fig. 8, and specifically includes the following steps:
s801, acquiring a rasterized map of a path to be planned, and determining a starting node S and a target node G of a mobile object;
s802, marking a steering node and a dead angle node at a position in a grid map according to an actual map;
s803, generating a current target vector SG based on the starting node S and the target node G, and determining a next path key node N;
s8031, if the selected key node N is the target node G, selecting the key node N and directly outputting a path;
s8032, if the selected key node N is not the target node G, forming a search area according to the current starting node S and the selected key node N;
s804, determining whether an obstacle exists in the search area;
s8041, if no obstacle exists in the search area, directly moving the moving object to a key node N, determining a next target vector SN according to the two nodes S and N, and repeatedly determining the key node of the next path until the next key node of the path of the moving object is a target node G;
S8042, if the search area has an obstacle, performing incremental expansion search on the minimum cost node based on the cost function after the A star algorithm improvement;
s805, determining whether to generate a path from the current starting node S to the key node N; if the path from the current starting node S to the key node N cannot be generated, returning to the step S8042, and continuing to search the minimum cost node by incremental expansion based on the cost function after the A star algorithm improvement until a proper key node is generated, so as to form the path from the current starting node S to the proper key node; if a path from the current starting node S to the key node N can be generated, returning to the step S803, determining the next target vector SN according to the two nodes S and N, and repeatedly determining the key node of the next path until the next key node of the path of the moving object is the target node, so as to generate an obstacle-free planning path from the starting node S to the target node G.
Based on the same inventive concept, the embodiments of the present disclosure also provide a path planning apparatus for a moving object, as follows. Since the principle of solving the problem of the embodiment of the device is similar to that of the embodiment of the method, the implementation of the embodiment of the device can be referred to the implementation of the embodiment of the method, and the repetition is omitted.
Fig. 9 is a schematic diagram of a path planning apparatus for a moving object according to an embodiment of the disclosure, where, as shown in fig. 9, the apparatus includes:
the grid map acquisition module is used for acquiring a grid map of a path to be planned, wherein the grid map comprises: a plurality of key nodes marked in advance, and a start node and a target node of a path to be planned.
And the key node selection module is used for selecting at least one key node which is routed in the process of moving the mobile object from the initial node to the target node from a plurality of key nodes.
And the path planning module is used for generating path planning information of the mobile object according to the starting node, the target node and each key node in the path of the mobile object in the process of moving from the starting node to the target node.
The path planning device for the mobile object provided by the embodiment of the disclosure obtains a rasterized map comprising a plurality of key nodes marked in advance and a start node and a target node of a path to be planned through a grid map obtaining module; and selecting at least one key node which is routed in the process of moving the mobile object from the starting node to the target node from the plurality of key nodes through the key node selection module, and generating path planning information of the mobile object through the path planning module according to the starting node, the target node and each key node which is routed in the process of moving the mobile object from the starting node to the target node. Compared with the prior art that when a path is planned, too many unnecessary nodes are searched, so that the path searching efficiency is low, in the embodiment of the present disclosure, a plurality of key nodes are marked on a grid map of the path to be planned, when the path is planned, no other unnecessary nodes are required to be searched in a large range, and only the necessary key nodes of the route in the process of moving from the initial node to the target node need to be determined, so that the searching process of the unnecessary nodes is reduced, and the path planning efficiency is improved.
In some embodiments, the key node selection module in the embodiments of the present disclosure includes: the method comprises the steps of obtaining a node sub-module, determining a node sub-module, selecting the node sub-module and repeatedly executing the sub-module, wherein the node sub-module is used for obtaining a current node of a mobile object, and the current node is a current node of the mobile object in a grid map; the determining quantum module is used for determining a target vector of the moving object moving from the current node to the target node; the node selecting submodule is used for selecting the next key node in the process that the mobile object moves from the current node to the target node from a plurality of key nodes according to the target vector; and the repeated execution sub-module is used for repeatedly executing the steps until the next key node in the path of the moving object is the target node.
In some embodiments, the selecting node sub-module in the embodiments of the present disclosure is further configured to select, according to the target vector, a target key node closest to the target node from the plurality of key nodes; judging whether the target key node is a target node or not; if the target key node is not the target node, judging whether an obstacle exists between the current node and the target key node; if no obstacle exists between the current node and the target key node, determining the target key node as the next key node in the process that the mobile object moves from the current node to the target node.
In some embodiments, after determining whether there is an obstacle between the current node and the target key node, the path planning apparatus for a moving object in the embodiments of the present disclosure further includes: the system comprises an accessible path planning module and a key node determining module, wherein the accessible path planning module is used for determining accessible planning path information of a moving object moving from a current node to a target key node based on a cost function after A star algorithm improvement if an obstacle exists between the current node and the target key node, and the cost function after A star algorithm improvement comprises a collision distance cost factor of the moving object to the obstacle; and the key node determining module is used for determining the next key node of the path of the mobile object according to the barrier-free planning path information of the mobile object moving from the current node to the target key node.
In some embodiments, before determining the barrier-free planned path information of the moving object moving from the current node to the target key node based on the cost function after the a-star algorithm improvement, the path planning apparatus of the moving object in the embodiments of the present disclosure further includes: a cost function determining module, wherein the cost function determining module is configured to obtain an improved cost function based on an a-star algorithm according to a formula (1), where g (N) is a minimum cost function from a start node of a moving object to a target key node N, h (N) is a minimum estimated cost function of a path from the target key node N to a target node of the moving object, and O (N) is a target point of the moving object Collision distance cost function, k, of key node N 1 Weight, k, of the first cost function 2 Is the weight of the second cost function.
In some embodiments, the plurality of key nodes include a steering node and a dead angle node, and before determining whether an obstacle exists between the current node and the target key node if the target key node is not the target node, the path planning apparatus for a moving object in the embodiments of the present disclosure further includes: the system comprises a dead angle judging module, a redetermining node module and an obstacle determining module, wherein the dead angle judging module is used for judging whether a key node closest to a target node is selected from a plurality of key nodes or not; the redetermining node module is used for redefining the target key node if the key node is a dead angle node; and the obstacle determining module is used for judging whether an obstacle exists between the current node and the target key node if the key node is a steering node.
In some embodiments, the path planning apparatus for a moving object in an embodiment of the present disclosure further includes: the system comprises a safety distance determining module and a collision distance cost function determining module, wherein the safety distance determining module is used for inputting the moving speed of a moving object into a pre-trained anti-collision safety distance model and outputting the safety distance between the moving object and an obstacle; and the collision distance cost function determining module is used for determining the collision distance cost function of the mobile object at the target key node according to the safety distance.
Those skilled in the art will appreciate that the various aspects of the present disclosure may be implemented as a system, method, or program product. Accordingly, various aspects of the disclosure may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 10 according to such an embodiment of the present disclosure is described below with reference to fig. 10. The electronic device 10 shown in fig. 10 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 10, the electronic device 10 is in the form of a general purpose computing device. Components of the electronic device 10 may include, but are not limited to: the at least one processing unit 11, the at least one memory unit 12, a bus 13 connecting the different system components, including the memory unit 12 and the processing unit 11.
Wherein the storage unit stores program code executable by the processing unit 11 such that the processing unit 11 performs steps according to various exemplary embodiments of the present disclosure described in the above-described "exemplary methods" section of the present specification.
In some embodiments, when the electronic device is used to control, for example, the knowledge-graph-based question-answering method described above in the present disclosure, the processing unit 11 may perform the following steps of the method embodiments described above:
obtaining a rasterized map of a path to be planned, wherein the rasterized map comprises: a plurality of key nodes marked in advance, and a start node and a target node of a path to be planned.
At least one key node is selected from the plurality of key nodes along which the mobile object moves from the originating node to the target node.
Generating path planning information of the mobile object according to the starting node, the target node and each key node in the path of the mobile object in the process of moving from the starting node to the target node.
The memory unit 12 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 121 and/or cache memory 122, and may further include Read Only Memory (ROM) 123.
The storage unit 12 may also include a program/utility 124 having a set (at least one) of program modules 125, such program modules 125 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 13 may be a local bus representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a memory unit using any of a variety of bus architectures.
The electronic device 10 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 10, and/or any device (e.g., router, modem, etc.) that enables the electronic device 10 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 15. Also, the electronic device 10 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 16. As shown, the network adapter 16 communicates with other modules of the electronic device 10 over the bus 13. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with the electronic device 10, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
In particular, according to embodiments of the present disclosure, the process described above with reference to the flowcharts may be implemented as a computer program product comprising: and the computer program realizes the path planning method of the mobile object when the computer program is executed by the processor.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium, which may be a readable signal medium or a readable storage medium, is also provided. On which a program product is stored which enables the implementation of the method described above of the present disclosure. In some possible implementations, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal device.
More specific examples of the computer readable storage medium in the present disclosure may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In this disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Alternatively, the program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
In particular implementations, the program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order or that all illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.
From the description of the above embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (10)
1. A path planning method for a moving object, comprising:
obtaining a rasterized map of a path to be planned, wherein the rasterized map comprises: a plurality of key nodes marked in advance and a starting node and a target node of a path to be planned;
selecting at least one key node from the plurality of key nodes, wherein the key node is routed in the process that the mobile object moves from the starting node to the target node;
generating path planning information of the mobile object according to the starting node, the target node and each key node in the path of the mobile object in the process of moving from the starting node to the target node.
2. The path planning method of a mobile object according to claim 1, wherein selecting at least one key node from the plurality of key nodes that is routed in a process of moving the mobile object from the start node to the target node, comprises:
acquiring a current node of the mobile object, wherein the current node is a node where the mobile object is currently located in a grid map;
determining a target vector for the moving object to move from the current node to the target node;
Selecting the next key node of the path of the moving object in the process of moving from the current node to the target node from the plurality of key nodes according to the target vector;
repeating the steps until the next key node of the path of the mobile object is the target node.
3. The path planning method of a mobile object according to claim 2, wherein selecting a next key node from the plurality of key nodes along which the mobile object moves from a current node to the target node according to the target vector comprises:
selecting one target key node closest to the target node from the plurality of key nodes according to the target vector;
judging whether the target key node is the target node or not;
if the target key node is not the target node, judging whether an obstacle exists between the current node and the target key node;
and if no obstacle exists between the current node and the target key node, determining the target key node as the next key node in the process of moving the moving object from the current node to the target node.
4. A path planning method of a mobile object according to claim 3, characterized in that after judging whether there is an obstacle between the current node and the target key node, the method further comprises:
if an obstacle exists between the current node and the target key node, determining barrier-free planning path information of the moving object moving from the current node to the target key node based on a cost function after the A star algorithm improvement, wherein the cost function based on the A star algorithm improvement comprises a collision distance cost factor of the moving object to the obstacle;
and determining the next key node of the moving object path according to the barrier-free planning path information of the moving object moving from the current node to the target key node.
5. The path planning method of a mobile object according to claim 4, wherein before determining the barrier-free planned path information for the mobile object to move from the current node to the target critical node based on the cost function after the improvement of the a-star algorithm, the method further comprises:
obtaining a cost function f (N) based on an A star algorithm after improvement through the following formula;
f(N)＝g(N)+k 1 h(N)+k 2 O(N)
Wherein g (N) is the minimum cost function from the starting node of the mobile object to the target key node N, h (N) is the minimum estimated cost function of the path from the target key node N to the target node of the mobile object, O (N) is the collision distance cost function at the target key node N of the mobile object, k 1 Weight, k, of the first cost function 2 Is the weight of the second cost function.
6. The path planning method of a mobile object according to claim 3, wherein the plurality of key nodes include a steering node and a dead angle node, and if the target key node is not the target node, before determining whether there is an obstacle between the current node and the target key node, the method further comprises:
judging whether a key node closest to the target node is the dead angle node or not selected from the plurality of key nodes;
if the key node is the dead angle node, the target key node is determined again;
and if the key node is the steering node, judging whether an obstacle exists between the current node and the target key node.
7. The path planning method of a mobile object according to claim 6, characterized in that the method further comprises:
Inputting the moving speed of the moving object into a pre-trained anti-collision safe distance model, and outputting the safe distance between the moving object and an obstacle;
and determining a collision distance cost function of the mobile object at the target key node according to the safety distance.
8. A path planning apparatus for a moving object, comprising:
the grid map obtaining module is used for obtaining a grid map of a path to be planned, wherein the grid map comprises the following components: a plurality of key nodes marked in advance and a starting node and a target node of a path to be planned;
a key node selection module, configured to select at least one key node that is routed in a process that the mobile object moves from the start node to the target node from the plurality of key nodes;
and the path planning module is used for generating path planning information of the mobile object according to the starting node, the target node and each key node in the path of the mobile object in the process of moving from the starting node to the target node.
9. An electronic device, comprising:
a processor; and
A memory for storing executable instructions of the processor;
wherein the processor is configured to perform the path planning method of the mobile object of any one of claims 1 to 7 via execution of the executable instructions.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the path planning method of a moving object according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310876558.5A CN116878532A (en) | 2023-07-17 | 2023-07-17 | Path planning method and device for mobile object and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310876558.5A CN116878532A (en) | 2023-07-17 | 2023-07-17 | Path planning method and device for mobile object and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116878532A true CN116878532A (en) | 2023-10-13 |
Family
ID=88260113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310876558.5A Pending CN116878532A (en) | 2023-07-17 | 2023-07-17 | Path planning method and device for mobile object and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116878532A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118031997A (en) * | 2024-04-15 | 2024-05-14 | 航天广通科技(深圳)有限公司 | GIS-based space geographic information service method and device |
-
2023
- 2023-07-17 CN CN202310876558.5A patent/CN116878532A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118031997A (en) * | 2024-04-15 | 2024-05-14 | 航天广通科技(深圳)有限公司 | GIS-based space geographic information service method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11400959B2 (en) | Method and system to predict one or more trajectories of a vehicle based on context surrounding the vehicle | |
| US10614592B2 (en) | Three-dimensional posture estimating method and apparatus, device and computer storage medium | |
| US11594011B2 (en) | Deep learning-based feature extraction for LiDAR localization of autonomous driving vehicles | |
| US11531110B2 (en) | LiDAR localization using 3D CNN network for solution inference in autonomous driving vehicles | |
| US11427215B2 (en) | Systems and methods for generating a task offloading strategy for a vehicular edge-computing environment | |
| US11308391B2 (en) | Offline combination of convolutional/deconvolutional and batch-norm layers of convolutional neural network models for autonomous driving vehicles | |
| US10824153B2 (en) | Cost design for path selection in autonomous driving technology | |
| US11364931B2 (en) | Lidar localization using RNN and LSTM for temporal smoothness in autonomous driving vehicles | |
| US10053091B2 (en) | Spring system-based change lane approach for autonomous vehicles | |
| US10429849B2 (en) | Non-linear reference line optimization method using piecewise quintic polynomial spiral paths for operating autonomous driving vehicles | |
| US20180075647A1 (en) | Scalable curve visualization for conformance testing in vehicle simulation | |
| CN116878532A (en) | Path planning method and device for mobile object and related equipment | |
| CN111680747A (en) | Method and apparatus for closed loop detection of occupancy grid subgraph | |
| US20210188308A1 (en) | A qp spline path and spiral path based reference line smoothing method for autonomous driving | |
| CN114771570A (en) | Control method and device for automatic driving vehicle | |
| US20230294684A1 (en) | Method of controlling autonomous vehicle, electronic device, and storage medium | |
| CN116734878A (en) | Path planning method, path planning device, electronic equipment, medium and automatic driving vehicle | |
| CN115583254A (en) | Path planning method, device and equipment and automatic driving vehicle | |
| CN111830957A (en) | Path planning method and device | |
| CN115565374A (en) | Logistics vehicle driving optimization method and device, electronic equipment and readable storage medium | |
| CN114581869A (en) | Method and device for determining position of target object, electronic equipment and storage medium | |
| CN109917781A (en) | For dispatching the method, apparatus and system of automated guided vehicle | |
| CN113449798A (en) | Port unmanned driving map generation method and device, electronic equipment and storage medium | |
| CN113483770A (en) | Path planning method and device in closed scene, electronic equipment and storage medium | |
| CN111402148A (en) | Information processing method and device for automatic driving vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |