CN110789520A - Driving control method and device and electronic equipment - Google Patents
Driving control method and device and electronic equipment Download PDFInfo
- Publication number
- CN110789520A CN110789520A CN201910763508.XA CN201910763508A CN110789520A CN 110789520 A CN110789520 A CN 110789520A CN 201910763508 A CN201910763508 A CN 201910763508A CN 110789520 A CN110789520 A CN 110789520A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- collision
- directed graph
- vehicles
- target
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
Abstract
The embodiment of the invention discloses a driving control method, a driving control device and electronic equipment, wherein the method comprises the following steps: the method comprises the steps of obtaining a vehicle directed graph of a target internet of vehicles and predicted collision information between a first vehicle and a second vehicle in the target internet of vehicles, wherein each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle; correcting the predicted collision information according to the vehicle directed graph to obtain a collision risk between the first vehicle and the second vehicle; controlling travel of the first vehicle and the second vehicle in accordance with a risk of collision between the first vehicle and the second vehicle. The embodiment of the invention can prevent the collision between vehicles and improve the driving safety of the vehicles.
Description
Technical Field
The present invention relates to the field of safety technologies, and in particular, to a driving control method, a driving control device, and an electronic apparatus.
Background
With the development of traffic technology and the improvement of living standard of people, the driving trip mode becomes the best choice for most people with the unique superiority, and brings convenience and comfort level for people to trip. However, as vehicles on roads increase, frequent traffic accidents also seriously threaten the life safety and property safety of people. The traffic accidents caused by the collision of the vehicles in the traffic accidents are counted to have a large proportion, so how to better prevent the collision between the vehicles so as to reduce the probability of the occurrence of the traffic accidents is a problem to be solved urgently in the field of the current vehicle driving safety.
Disclosure of Invention
The technical problem to be solved by the embodiments of the present invention is to provide a driving control method, a driving control device, and an electronic device, which can prevent collision between vehicles and improve the safety of vehicle driving.
In one aspect, an embodiment of the present invention provides a driving control method, including:
the method comprises the steps of obtaining a vehicle directed graph of a target internet of vehicles and predicted collision information between a first vehicle and a second vehicle in the target internet of vehicles, wherein each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle;
correcting the predicted collision information according to the vehicle directed graph to obtain a collision risk between the first vehicle and the second vehicle;
controlling travel of the first vehicle and the second vehicle in accordance with a risk of collision between the first vehicle and the second vehicle.
In one aspect, an embodiment of the present invention provides a travel control apparatus, including:
the vehicle collision prediction method comprises an acquisition unit, a collision prediction unit and a judgment unit, wherein the acquisition unit is used for acquiring a vehicle directed graph of a target vehicle network and predicted collision information between a first vehicle and a second vehicle in the target vehicle network, each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle;
the correction unit is used for correcting the predicted collision information according to the vehicle directed graph to obtain the collision risk between the first vehicle and the second vehicle;
a control unit for controlling travel of the first vehicle and the second vehicle in accordance with a risk of collision between the first vehicle and the second vehicle.
In another aspect, an embodiment of the present invention provides an electronic device, including an input device and an output device, further including:
a processor adapted to implement one or more instructions; and the number of the first and second groups,
a computer storage medium storing one or more instructions adapted to be loaded by the processor and to perform the steps of:
the method comprises the steps of obtaining a vehicle directed graph of a target internet of vehicles and predicted collision information between a first vehicle and a second vehicle in the target internet of vehicles, wherein each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle;
correcting the predicted collision information according to the vehicle directed graph to obtain a collision risk between the first vehicle and the second vehicle;
controlling travel of the first vehicle and the second vehicle in accordance with a risk of collision between the first vehicle and the second vehicle.
In yet another aspect, an embodiment of the present invention provides a computer storage medium storing one or more instructions adapted to be loaded by a processor and perform the following steps:
the method comprises the steps of obtaining a vehicle directed graph of a target internet of vehicles and predicted collision information between a first vehicle and a second vehicle in the target internet of vehicles, wherein each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle;
correcting the predicted collision information according to the vehicle directed graph to obtain a collision risk between the first vehicle and the second vehicle;
controlling travel of the first vehicle and the second vehicle in accordance with a risk of collision between the first vehicle and the second vehicle.
In the embodiment of the invention, the electronic equipment corrects and predicts the collision information according to the vehicle directed graph of the target internet of vehicles to obtain the collision risk between the first vehicle and the second vehicle. Furthermore, by controlling the running of the first vehicle and the second vehicle according to the risk of collision between the first vehicle and the second vehicle, the first vehicle and the second vehicle can be prevented from colliding, and the safety of the running of the vehicle is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a vehicle networking system according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a driving control method according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating another driving control method according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of a vehicle directed graph of a target Internet of vehicles provided by an embodiment of the present invention;
FIG. 5 is a schematic diagram of a vehicle directed acyclic graph of a target Internet of vehicles according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of another target Internet of vehicles directed acyclic graph provided by an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a travel control apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The vehicle to electrical (V2X) network is a network that implements environmental awareness, information interaction, and cooperative control by sensors, electronic tags, and the like mounted on a vehicle, and provides various services to the vehicle in motion. For example, the internet of vehicles can provide real-time navigation for vehicles to improve the efficiency of vehicle travel; alternatively, the internet of vehicles can control the distance between vehicles to reduce the probability of a collision accident between vehicles, and the like. In one embodiment, a system architecture for a vehicle networking is shown in fig. 1, including a transportation device 11 and a plurality of vehicles 12. The traffic device 11 may refer to a device for controlling the vehicle to run, such as a traffic control platform, and may specifically include a camera device, a communication device, and the like. The camera device is used for acquiring the driving information of the vehicle and the road condition state of the road, and the communication device is used for communicating between the traffic equipment and the vehicle. The travel information includes a travel speed, a travel direction, position information, and the like. The road condition state comprises a congestion state, a slow running state or a smooth state, wherein the congestion state refers to a state that vehicles on the road can only run at a very low speed or stop running, the slow running state refers to a state that vehicles on the road can only run at a low speed, and the smooth state refers to a state that vehicles on the road can run at a normal speed. The vehicle 12 may include, but is not limited to: cars, trucks, off-road vehicles, taxis, buses, and vehicles 12 may include vehicle terminals that may be used to obtain driving information of the vehicles and to communicate with the transportation devices 11. The vehicle-mounted terminal may refer to a device connected to a vehicle, such as a smart phone, and the vehicle-mounted terminal may also refer to a device provided in the vehicle, such as a car navigation system.
The internet of vehicles can realize the running control of vehicles, and the running control method mainly comprises the following steps of 1-3: 1. the traffic equipment acquires the running information of each vehicle in the internet of vehicles, wherein the running information can be sent to the traffic equipment by the vehicle-mounted terminal of the vehicle, or the running information can be acquired by the traffic equipment through the camera device. 2. And the traffic equipment determines the probability of collision among vehicles in the Internet of vehicles according to the running information. 3. The traffic equipment sends control instructions to the vehicles according to the probability of collision between the vehicles, and the control instructions are used for adjusting the running information of the vehicles, such as reducing the running speed of the vehicles, changing the running direction of the vehicles, changing the running lanes and the like. Therefore, collision between vehicles can be avoided, and the driving safety of the vehicles is improved. For example, if the first vehicle and the second vehicle are included in the internet of vehicles, the first vehicle travels in front of the second vehicle, and if it is determined that the probability that the first vehicle collides with the second vehicle is high, the transportation device may send a control instruction for increasing the travel speed to the first vehicle, or send a control instruction for decreasing the travel speed to the second vehicle, so that the first vehicle and the second vehicle can be prevented from colliding.
Fig. 2 is a schematic flow chart of a driving control method according to an embodiment of the present disclosure, where the driving control method can be applied to an electronic device. The electronic device may refer to the transportation device in fig. 1, and the method may include the following steps S101 to S104.
S101, obtaining a vehicle directed graph of a target vehicle network and predicted collision information between a first vehicle and a second vehicle in the target vehicle network, wherein each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle.
The target vehicle networking system may be any vehicle networking system on a road, and the target vehicle networking system may include a plurality of vehicles, where the plurality of vehicles includes at least a first vehicle and a second vehicle, the first vehicle is any vehicle in the plurality of vehicles, and the second vehicle is any vehicle in the plurality of vehicles except the first vehicle. In order to improve the safety of vehicle driving, the electronic device may acquire a vehicle directed graph of the target internet of vehicles, each vertex of the vehicle directed graph corresponds to one vehicle, a connecting line between the vertices is a directed edge of the vehicle directed graph, and the directed edge is used for indicating a collision relationship between the vehicles. The collision relationship here includes no collision or collision. The collision may in particular comprise a passive collision, i.e. a collision of the first vehicle by a second vehicle, or an active collision, i.e. a collision of the first vehicle by the second vehicle. That is, two vertexes in the vehicle directed graph are connected to indicate that the corresponding vehicles have a collision relationship, that is, two vertexes in the vehicle directed graph are not connected to indicate that the corresponding vehicles do not collide with each other. Specifically, the electronic device may abstract each vehicle in the target internet of vehicles as a vertex, and generate a vehicle directed graph according to the driving information between the vehicles. The collision relation is dynamically changed according to the running information of the first vehicle and the second vehicle, namely the vehicle directed graph is dynamically changed according to the running information between the first vehicle and the second vehicle, namely the vehicle directed graph can represent the running randomness of the first vehicle and the second vehicle, such as the running speed, the running direction and the like. Meanwhile, the electronic device may obtain predicted collision information between the first vehicle and the second vehicle in the target internet of vehicles, and the predicted collision information may include, but is not limited to: predicted collision probability, predicted collision time, predicted collision location, and the like. The predicted collision information may be predicted from traveling information of the first vehicle and the second vehicle by a collision prediction model. Due to the large randomness of the vehicle in the driving process, the collision prediction model is difficult to describe the driving randomness, so that the accuracy of the predicted collision information is low. The collision prediction model may specifically include a vehicle networking dynamics model that predicts collision information according to a movement relationship between vehicles or a kinematics model that predicts collision information according to a change in position of a vehicle.
S102, correcting the predicted collision information according to the vehicle directed graph to obtain the collision risk between the first vehicle and the second vehicle.
Since the vehicle directed graph can show the driving randomness of the first vehicle and the second vehicle, in order to improve the accuracy of the collision information, the electronic device may correct the predicted collision information according to the vehicle directed graph to obtain the risk of collision between the first vehicle and the second vehicle. Here, the collision risk may specifically refer to final collision information of the first vehicle and the second vehicle, i.e. the collision risk includes a target collision probability, a target collision time, a target collision location, and the like. The predicted collision information and the predicted collision risk both include the collision probability, the collision time, the collision position and the like of the collision between the first vehicle and the second vehicle, but the predicted collision information and the predicted collision risk are different in that the driving randomness of the first vehicle and the second vehicle is considered in the process of determining the collision risk, so that the collision risk can more accurately represent the real situation of the collision between the first vehicle and the second vehicle.
S103, controlling the first vehicle and the second vehicle to run according to the collision risk between the first vehicle and the second vehicle.
The electronic equipment can control the first vehicle and the second vehicle to run according to the collision risk between the first vehicle and the second vehicle, so that the first vehicle and the second vehicle can be prevented from colliding, and the running safety of the vehicles is improved.
In the embodiment of the invention, the electronic equipment corrects and predicts the collision information according to the vehicle directed graph of the target internet of vehicles to obtain the collision risk between the first vehicle and the second vehicle. Furthermore, by controlling the running of the first vehicle and the second vehicle according to the risk of collision between the first vehicle and the second vehicle, the first vehicle and the second vehicle can be prevented from colliding, and the safety of the running of the vehicle is improved.
In one embodiment, the step S101 of obtaining the predicted collision information between the first vehicle and the second vehicle in the target internet of vehicles may specifically include the following steps S11 and 12.
s11, acquiring the running information of the first vehicle and the running information of the second vehicle.
s12, inputting the running information of the first vehicle and the running information of the second vehicle into a vehicle collision prediction model for prediction, and obtaining the predicted collision information between the first vehicle and the second vehicle.
In steps s11 and 12, the electronic device may capture a road image of the traveling road by the capture device, and perform recognition processing on the road image to obtain the traveling information of the first vehicle and the traveling information of the second vehicle. Alternatively, the electronic device may receive the travel information transmitted by the in-vehicle terminal of the first vehicle and receive the travel information transmitted by the in-vehicle terminal of the second vehicle. Further, the electronic device may input the traveling information of the first vehicle and the traveling information of the second vehicle into a vehicle collision prediction model for prediction, and obtain predicted collision information between the first vehicle and the second vehicle.
In one embodiment, the target internet of vehicles includes a plurality of vehicles, the first vehicle is any one of the plurality of vehicles, the second vehicle is any one of the plurality of vehicles except the first vehicle, and the step S101 of obtaining the vehicle directed graph of the target internet of vehicles may specifically include the following steps S21-23.
And s21, acquiring the running information of each vehicle in the target internet of vehicles.
And s22, determining the collision relation among the vehicles in the target vehicle network according to the running information.
And s23, generating a vehicle directed graph of the target vehicle network according to the collision relation among the vehicles in the target vehicle network.
In steps s 21-23, the electronic device may obtain the driving information of each vehicle in the target internet of vehicles, and determine the collision relationship between each vehicle in the target internet of vehicles according to the driving information. And abstracting each vehicle in the internet of vehicles into a vertex, and connecting the vertices with collision relations among corresponding vehicles to obtain a vehicle directed graph. For example, if it is determined that the first vehicle and the second vehicle are located in the same lane and the first vehicle is located ahead of the second vehicle and the traveling speed of the second vehicle is greater than that of the second vehicle, it is determined that there is a collision relationship between the first vehicle and the second vehicle. Further, the vertex corresponding to the first vehicle is connected with the vertex corresponding to the second vehicle, and the vertex corresponding to the second vehicle points to the vertex corresponding to the second vehicle, which indicates that the second vehicle actively collides with the first vehicle.
In one embodiment, the step S102 may specifically include the following steps S31-33.
s31, transforming the vehicle directed graph to obtain at least one candidate topological sequence, wherein the candidate topological sequence comprises each vertex in the vehicle directed graph and indicating information used for indicating the collision relationship among the vehicles.
s32, screening the target topological sequence from the at least one candidate topological sequence.
And s33, correcting the predicted collision information according to the target topological sequence to obtain the collision risk between the first vehicle and the second vehicle.
In steps s 31-s 33, the vehicle directed graph is transformed to obtain at least one candidate topological sequence. The candidate topological sequence comprises all vertexes in the vehicle directed graph and indicating information used for indicating the collision relation among all vehicles, namely vehicles corresponding to two adjacent vertexes in the candidate topological sequence have a collision relation, and vehicles corresponding to non-adjacent vertexes do not have a collision relation. And screening out a target topological sequence from the at least one candidate topological sequence. The target topological sequence may indicate a candidate topological sequence with a minimum risk of collision between vehicles in the target internet of vehicles.
In this embodiment, step s31 may specifically include the following steps s 41-44.
s41, obtaining the adjacency matrix of the vehicle directed graph.
s42, judging whether the vehicle directed graph comprises a ring structure according to the adjacency matrix.
s43, if the vehicle directed graph comprises a ring structure, performing a ring removal process on the vehicle directed graph to obtain a vehicle directed acyclic graph, and performing a linear process on the vehicle directed acyclic graph to obtain at least one candidate topological sequence.
s44, if the vehicle directed graph does not include the ring structure, performing linear processing on the vehicle directed graph to obtain at least one candidate topological sequence.
In steps s 41-s 44, the electronic device may obtain a adjacency matrix of the vehicle directed graph, where the adjacency matrix may refer to a two-dimensional array for describing connection relationships between vertices of the vehicle directed graph. The electronic device may acquire attribute information of the adjacency matrix, where the attribute information includes one or both of a rank of the adjacency matrix and an element in the adjacency matrix, and determine whether the vehicle directed graph includes a ring structure according to the rank of the adjacency matrix or the element in the adjacency matrix. The directed graph of the vehicle has a ring structure, namely, the directed graph of the vehicle can return to a vertex after starting from the vertex and passing through a plurality of edges to form a ring. And if the vehicle directed graph comprises a ring structure, performing ring removal processing on the vehicle directed graph to obtain a vehicle directed acyclic graph, and performing linear processing on the vehicle directed acyclic graph to obtain at least one candidate topological sequence. If the vehicle directed graph does not comprise a ring structure, indicating that the vehicle directed graph is a vehicle directed acyclic graph, performing linear processing on the vehicle directed graph to obtain at least one candidate topological sequence.
In this embodiment, step s42 may specifically include: if all elements of each row of the adjacent matrix are not all zero and all elements of each column are not all zero, determining that the vehicle directed graph comprises a ring structure; if the row or column of the adjacency matrix has all zero elements, it is determined that the vehicle directed graph does not include a ring structure. Optionally, if the rank of the adjacent matrix is a full rank, determining that the vehicle directed graph includes a ring structure; if the rank of the adjacent matrix is not the full rank, determining that the vehicle directed graph does not include a ring structure. The number of vectors in the maximal irrelevant group in the adjacent matrix is referred to as the rank of the adjacent matrix, and the rank of the adjacent matrix being full rank means that the rank of the adjacent matrix is equal to the number of rows of the adjacent matrix, that is, the number of vectors in the maximal irrelevant group in the adjacent matrix is equal to the number of rows of the adjacent matrix, that is, each row of the adjacent matrix is the maximal irrelevant vector.
In this embodiment, step s43 may specifically include: and removing at least one edge in the annular structure in the vehicle directed graph, and/or replacing at least one edge in the vehicle directed graph to obtain a vehicle directed acyclic graph, wherein the vehicle directed acyclic graph does not comprise unconnected vertexes, and the out-degree of each vertex in the vehicle directed acyclic graph is smaller than or equal to a first preset threshold value.
The electronic device may remove at least one edge of the ring structure in the vehicle directed graph and ensure that no unconnected vertices are included in the vehicle directed acyclic graph, such as ensuring that no isolated vertices are included in the vehicle directed acyclic graph. And/or replacing at least one edge in the vehicle directed acyclic graph to obtain a vehicle directed acyclic graph, and ensuring that the out-degree of each vertex in the vehicle directed acyclic graph is less than or equal to a first preset threshold value, for example, ensuring that the out-degree of each vertex in the vehicle directed acyclic graph is less than or equal to 1, and the in-degree can be any value. That is, the out-degree of each vertex in the vehicle directed acyclic graph is less than or equal to 1, and the in-degree can be any value: at the same time, the vehicle can actively collide with one vehicle, but can be collided with by a plurality of vehicles.
Optionally, the target topological sequence is a candidate topological sequence in which the number of relevant vehicle pairs in the at least one candidate topological sequence is smaller than a second preset threshold; the related vehicle pair refers to two vehicles which have a collision relation indicated by the indicating information in the candidate topological sequence and have a connection relation between corresponding vertexes in the vehicle directed graph.
The smaller the number of relevant vehicle pairs in the candidate topological sequence is, the lower the risk of collision between vehicles is, so that the electronic device may determine the candidate topological sequence in which the number of relevant vehicle pairs in the at least one candidate topological sequence is smaller than the second preset threshold as the target topological sequence. That is, the target topological sequence may refer to a candidate topological sequence with a low risk of collision between vehicles in the at least one candidate topological sequence, for example, the target topological sequence may refer to a candidate topological sequence with a minimum number of related vehicle pairs in the at least one candidate topological sequence. The related vehicle pair refers to two vehicles which are adjacent to corresponding vertexes of the candidate topological sequence and have a connection relation between the corresponding vertexes in the vehicle directed graph. That is, the related vehicle pair may refer to two vehicles in the internet of vehicles, such as two front and rear vehicles located on the same lane in the internet of vehicles, or two vehicles located on adjacent lanes and having a closest distance, where the probability of collision is higher than a preset probability threshold.
In this example, the predicted collision information includes a predicted collision probability, the collision risk includes a target collision probability; step s33 includes the following steps s51 to s 53.
And s51, judging whether the first vehicle and the second vehicle are a related vehicle pair according to the target topological sequence.
s52, if the first vehicle and the second vehicle are the relevant vehicle pair, determining the product of the predicted collision probability and the first weight value as the target collision probability.
s53, if the first vehicle and the second vehicle are not the associated vehicle pair, determining the product of the predicted collision probability and a second weight value as the target collision probability, the first weight value being greater than the second weight value.
In steps s 51-s 53, whether the first vehicle and the second vehicle are a related vehicle pair is judged, and if the first vehicle and the second vehicle are adjacent in the target topological sequence and have a connection relation between the vertex corresponding to the first vehicle and the vertex corresponding to the second vehicle in the vehicle directed graph, the first vehicle and the second vehicle are determined to be the related vehicle pair. And determining the product of the predicted collision probability and the first weight as the target collision probability if the probability that the first vehicle and the second vehicle collide is higher. And if the corresponding vertexes of the first vehicle and the second vehicle in the target topological sequence are not adjacent or the vertex corresponding to the first vehicle and the vertex corresponding to the second vehicle in the vehicle directed graph have no connection relation, determining that the first vehicle and the second vehicle are not the related vehicle pair. And determining the product of the predicted collision probability and a second weight value as a target collision probability if the probability that the first vehicle and the second vehicle collide is lower, wherein the first weight value is larger than the second weight value.
In an example, step S203 may specifically include: and if the target collision probability is greater than a preset probability threshold value, sending a control instruction to the first vehicle and the second vehicle, wherein the control instruction is used for adjusting the running information of the first vehicle and the second vehicle.
If the target collision probability is greater than the preset probability threshold, it indicates that the risk of collision between the first vehicle and the second vehicle is relatively high, and therefore, the electronic device may send a control instruction to the first vehicle and the second vehicle, where the control instruction is used to adjust the traveling information of the first vehicle and the second vehicle, for example, adjust the traveling speed, the traveling lane, and the like of the first vehicle and the second vehicle.
The following describes a travel control method according to an embodiment of the present invention, taking an example in which 5 vehicles are included in the target internet of vehicles, and as shown in fig. 3, the travel control method includes the following steps s1-s 6.
And s1, acquiring the target Internet of vehicles. The electronic equipment can obtain a road image according to the shooting of the driving road, identify the road image and obtain the driving information of each vehicle in the target internet of vehicles, wherein the vehicles comprise the vehicles 1-5. And inputting the running information of each vehicle into a collision prediction model for prediction to obtain predicted collision information among the vehicles.
And s2, abstracting the target internet of vehicles into a vehicle directed graph, namely abstracting the vehicles in the target internet of vehicles into the vehicle directed graph. The electronic equipment can generate a vehicle directed graph according to the driving position of each vehicle included in the driving information, namely abstracting each vehicle into a vertex, and abstracting connecting lines of a rear vehicle and a left vehicle in the same lane into directed edges to obtain the vehicle directed graph. The vehicle directed graph is used for indicating the collision relation among vehicles, the in degree of each vertex in the vehicle directed graph can be multiple, and the out degree is less than or equal to 1, namely, one vehicle can be collided by multiple vehicles at the same time, but the vehicle can only be collided with one vehicle actively. For example, as shown in fig. 4, the vertex 1 of the vehicle directed graph corresponds to the vehicle 1, and the vertex 2 of the vehicle directed graph corresponds to the vehicle 2. Vertex 3 of the vehicle directed graph corresponds to vehicle 3, vertex 4 of the vehicle directed graph corresponds to vehicle 4, and vertex 5 of the vehicle directed graph corresponds to vehicle 5. As can be seen from the vehicle directed graph, for the vehicle 1, the probability that the vehicle 1 actively collides with the vehicle 3 is high, that is, the vehicle 1 and the vehicle 3 have a collision relationship; with respect to the vehicle 2, the probability that the vehicle 2 is collided with by the vehicle 3 is large, and the probability that the vehicle 2 actively collides with the vehicle 4 is large, that is, the vehicle 2 has a collision relationship with the vehicles 3 and 4.
s3, judging whether the vehicle directed graph has an annular structure, if so, executing a step s 4; if not, step s5 is performed. The electronic device can acquire an adjacency matrix of the vehicle directed graph and judge whether the vehicle directed graph has a ring structure according to the adjacency matrix. The adjacency matrix of the vehicle directed graph shown in fig. 4 can be expressed by equation (1).
Where a represents an adjacency matrix of the vehicle directed graph, the adjacency matrix is used to indicate the connection relationship between the corresponding vertices of each vehicle, for example, element 0 in the first row and the first column represents that vertex 1 does not have a connection relationship with vertex 1 in the vehicle directed graph, and element 1 in the third row and the third column represents that vertex 1 is connected to vertex 3 in the vehicle directed graph. As can be seen from equation (1), the elements in the first column and the fifth column of the adjacency matrix are both 0, indicating that the vehicle directed graph includes a ring structure.
And s4, acquiring a new vehicle directed graph, namely performing ring removal processing on the vehicle directed graph to obtain a vehicle directed acyclic graph. As can be seen from fig. 4, a ring structure is included between vertices 2, 3, and 4 in the vehicle directed graph, and the electronic device may remove an edge between vertices 2 and 4 in the ring structure in fig. 4, so as to obtain the vehicle directed acyclic graph shown in fig. 5. As can be seen from fig. 5, the vehicle directed graph in fig. 5 does not include a ring structure, and the vehicle directed graph cannot return to any vertex after passing through a plurality of edges. Alternatively, the electronic device may connect vertex 2 and vertex 5 in fig. 4, remove the edge between vertex 5 and vertex 4, and remove the edge between vertex 2 and vertex 4, resulting in the vehicle directed acyclic graph shown in fig. 6. As can be seen from fig. 6, after starting from any vertex, the vehicle directed graph in fig. 6 does not return to the vertex to form a ring after passing through a plurality of edges, that is, the vehicle directed graph in fig. 6 does not include a ring-shaped structure. That is, when there is a ring structure in the vehicle directed graph, the vehicle directed graph may be subjected to a ring removal process to obtain a plurality of vehicle directed acyclic graphs, and then any one of the vehicle directed five-ring graphs may be selected for processing, which is exemplified by the vehicle directed acyclic graph shown in fig. 5 below.
And s5, acquiring a target topological sequence of the Internet of vehicles. The electronic device may perform linear arrangement on each vertex in the vehicle directed acyclic graph to obtain at least one candidate topological sequence. As in fig. 5, scanning from vertex 1 to the end of the path yields sequence 1, where sequence 1 is: vertex 1, vertex 3, vertex 2; then, scanning from the vertex 5 to the end of the path to obtain a sequence 2, where the sequence 2 is: vertex 5, vertex 4, vertex 3, and vertex 2. After all paths in the vehicle directed acyclic graph are scanned, combining the sequence 1 and the sequence 2 to obtain at least one candidate topological sequence, wherein the combining principle is as follows: when a vertex is arranged behind another vertex in the vehicle undirected graph, the vertex is still behind that vertex in the candidate topological sequence. If the sequence 1 and the sequence 2 are combined to obtain two candidate topological sequences, which are respectively a candidate topological sequence 1 and a candidate topological sequence 2, the candidate topological sequence 1 is: vertex 5, vertex 4, vertex 1, vertex 3, and vertex 2, and the topology sequence candidate 2 is vertex 1, vertex 5, vertex 4, vertex 3, and vertex 2. That is, vertex 3 is arranged after vertex 1 and vertex 4 in the vehicle directed acyclic, and therefore, both of candidate topological sequence 1 and candidate topological sequence 2 in vertex 3 are arranged after vertex 1 and vertex 4.
And s6, acquiring the relative vehicle logarithm, and screening out a target topological sequence from at least one candidate topological sequence according to the relative vehicle logarithm. The related vehicle pairs are adjacent to corresponding vertexes in the candidate topological sequence, and have a connection relation between the corresponding vertexes in the vehicle directed graph, namely, the target topological sequence is the topological sequence with the least related vehicle pairs in the candidate topological sequence. For example, the relevant vehicle pairs obtained from the candidate topological sequence 1 include vehicle 5 and vehicle 4, vehicle 3, and vehicle 2. The relevant vehicle pairs obtained from the candidate topological sequence 2 include vehicle 5 and vehicle 4, vehicle 3 and vehicle 2, and vehicle 3 and vehicle 4. Namely, the number of the relevant vehicle pairs obtained according to the candidate topological sequence 2 is greater than the number of the relevant vehicle pairs obtained according to the candidate topological sequence 1, so that the candidate topological sequence 1 can be selected as the target topological sequence.
And s7, acquiring the collision risk of each vehicle in the target Internet of vehicles, namely correcting the predicted collision information among the vehicles according to the target topological sequence to obtain the collision risk among the vehicles. Assuming that the predicted collision information includes the predicted collision probability, the collision risk is the target collision probability, the first weight is 0.8, and the second weight is 0.2. If the predicted collision probability between the vehicle 1 and the vehicle 2 is 0.3, the predicted collision probability between the vehicle 3 and the vehicle 2 is 0.6. According to the target topological sequence, the vehicle 1 and the vehicle 2 are not related vehicle pairs, and the target collision probability between the vehicle 1 and the vehicle 2 is 0.3 × 0.2 ═ 0.06; the vehicle 2 and the vehicle 3 are the relevant vehicle pair, and the target collision probability between the vehicle 2 and the vehicle 3 is 0.6 × 0.8 — 0.48.
And S8, controlling the running of the vehicle according to the collision risk. If the target collision probability of the vehicle 2 and the vehicle 3 is greater than the preset probability threshold value, and the vehicle 2 and the vehicle 3 are located in the same lane, the vehicle 2 is located in front of the vehicle 3, and this can control the vehicle 2 to run at an accelerated speed and the vehicle 3 to run at a decelerated speed. Further, if the relative travel information between the vehicles in the target internet of vehicles changes, for example, the relative position information changes, the above steps s1-s8 are repeatedly executed to reacquire the collision risk between the vehicles, and the travel of the vehicles is controlled according to the redetermined collision risk.
An embodiment of the present invention provides a driving control device, which can be disposed in an electronic device, please refer to fig. 7, and the device includes:
an obtaining unit 701, configured to obtain a vehicle directed graph of a target internet of vehicles, where each vertex of the vehicle directed graph corresponds to one vehicle, and predicted collision information between a first vehicle and a second vehicle in the target internet of vehicles, and a directed edge of the vehicle directed graph is used to indicate a collision relationship between the first vehicle and the second vehicle.
A correcting unit 702, configured to correct the predicted collision information according to the vehicle directed graph, so as to obtain a collision risk between the first vehicle and the second vehicle.
A control unit 703 for controlling the travel of the first vehicle and the second vehicle according to a risk of collision between the first vehicle and the second vehicle.
Optionally, the target internet of vehicles includes a plurality of vehicles, the first vehicle is any one of the plurality of vehicles, and the second vehicle is any one of the plurality of vehicles except the first vehicle; an obtaining unit 701, configured to specifically obtain driving information of each vehicle in the target internet of vehicles; determining collision relations among vehicles in the target vehicle networking according to the running information; and generating a vehicle directed graph of the target vehicle networking according to the collision relation among the vehicles in the target vehicle networking.
Optionally, the modifying unit 702 is specifically configured to perform transformation processing on the vehicle directed graph to obtain at least one candidate topology sequence, where the candidate topology sequence includes each vertex in the vehicle directed graph and indication information used for indicating a collision relationship between vehicles; screening out a target topological sequence from the at least one candidate topological sequence; and correcting the predicted collision information according to the target topological sequence to obtain the collision risk between the first vehicle and the second vehicle.
Optionally, the correcting unit 702 is specifically configured to obtain an adjacency matrix of the vehicle directed graph; judging whether the vehicle directed graph comprises a ring-shaped structure or not according to the adjacency matrix; if the vehicle directed graph comprises an annular structure, performing ring removal processing on the vehicle directed graph to obtain a vehicle directed acyclic graph, and performing linear processing on the vehicle directed acyclic graph to obtain at least one candidate topological sequence; and if the vehicle directed graph does not comprise a ring structure, performing linear processing on the vehicle directed graph to obtain at least one candidate topological sequence.
Optionally, the correcting unit 702 is specifically configured to remove at least one edge of the ring structure in the vehicle directed graph, and/or replace at least one edge of the vehicle directed graph to obtain a vehicle directed acyclic graph, where the vehicle directed acyclic graph does not include unconnected vertices, and an out-degree of each vertex in the vehicle directed acyclic graph is less than or equal to a first preset threshold.
Optionally, the target topology sequence is a candidate topology sequence in which the number of related vehicle pairs in the at least one candidate topology sequence is smaller than a second preset threshold; the related vehicle pair refers to two vehicles which are adjacent to corresponding vertexes in the candidate topological sequence and have a connection relation between the corresponding vertexes in the vehicle directed graph.
Optionally, the predicted collision information includes a predicted collision probability, and the collision risk includes a target collision probability; a correcting unit 702, configured to determine whether the first vehicle and the second vehicle are a related vehicle pair according to the target topology sequence; if the first vehicle and the second vehicle are a related vehicle pair, determining the product of the predicted collision probability and a first weight as a target collision probability; and if the first vehicle and the second vehicle are not related vehicle pairs, determining the product of the predicted collision probability and a second weight as a target collision probability, wherein the first weight is larger than the second weight.
Optionally, the obtaining unit 701 is specifically configured to obtain the driving information of the first vehicle and the driving information of the second vehicle; and inputting the running information of the first vehicle and the running information of the second vehicle into a vehicle collision prediction model for prediction to obtain predicted collision information between the first vehicle and the second vehicle.
In the embodiment of the invention, the electronic equipment corrects and predicts the collision information according to the vehicle directed graph of the target internet of vehicles to obtain the collision risk between the first vehicle and the second vehicle. Furthermore, by controlling the running of the first vehicle and the second vehicle according to the risk of collision between the first vehicle and the second vehicle, the first vehicle and the second vehicle can be prevented from colliding, and the safety of the running of the vehicle is improved.
An embodiment of the invention provides an electronic device, please refer to fig. 8. The electronic device includes: the processor 151, the user interface 152, the network interface 154, and the storage device 155 are connected via a bus 153.
A user interface 152 for enabling human-computer interaction, which may include a display screen or a keyboard, among others. And a network interface 154 for communication connection with an external device. A storage device 155 is coupled to processor 151 for storing various software programs and/or sets of instructions. In particular implementations, storage 155 may include high speed random access memory and may also include non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid state storage devices. The storage device 155 may store an operating system (hereinafter referred to simply as a system), such as an embedded operating system like ANDROID, IOS, WINDOWS, or LINUX. The storage 155 may also store a network communication program that may be used to communicate with one or more additional devices, one or more application servers, one or more network devices. The storage device 155 may further store a user interface program, which may vividly display the content of the application program through a graphical operation interface, and receive a user's control operation of the application program through input controls such as menus, dialog boxes, and buttons. The storage device 155 may also store video data and the like.
In one embodiment, the storage 155 may be used to store one or more instructions; the processor 151 may be capable of implementing a video processing method when invoking the one or more instructions, and specifically, the processor 151 invokes the one or more instructions to perform the following steps:
the method comprises the steps of obtaining a vehicle directed graph of a target internet of vehicles and predicted collision information between a first vehicle and a second vehicle in the target internet of vehicles, wherein each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle;
correcting the predicted collision information according to the vehicle directed graph to obtain a collision risk between the first vehicle and the second vehicle;
controlling travel of the first vehicle and the second vehicle in accordance with a risk of collision between the first vehicle and the second vehicle.
Optionally, the target internet of vehicles includes a plurality of vehicles, the first vehicle is any one of the plurality of vehicles, and the second vehicle is any one of the plurality of vehicles except the first vehicle; the processor calls the one or more instructions and executes the following steps:
acquiring running information of each vehicle in the target Internet of vehicles;
determining collision relations among vehicles in the target vehicle networking according to the running information;
and generating a vehicle directed graph of the target vehicle networking according to the collision relation among the vehicles in the target vehicle networking.
Optionally, the processor calls the one or more instructions to perform the following steps:
carrying out transformation processing on the vehicle directed graph to obtain at least one candidate topological sequence, wherein the candidate topological sequence comprises each vertex in the vehicle directed graph and indicating information used for indicating collision relations among vehicles;
screening out a target topological sequence from the at least one candidate topological sequence;
and correcting the predicted collision information according to the target topological sequence to obtain the collision risk between the first vehicle and the second vehicle.
Optionally, the processor calls the one or more instructions to perform the following steps:
acquiring an adjacency matrix of the vehicle directed graph;
judging whether the vehicle directed graph comprises a ring-shaped structure or not according to the adjacency matrix;
if the vehicle directed graph comprises an annular structure, performing ring removal processing on the vehicle directed graph to obtain a vehicle directed acyclic graph, and performing linear processing on the vehicle directed acyclic graph to obtain at least one candidate topological sequence;
and if the vehicle directed graph does not comprise a ring structure, performing linear processing on the vehicle directed graph to obtain at least one candidate topological sequence.
Optionally, the processor calls the one or more instructions to perform the following steps:
removing at least one edge in the ring-shaped structure in the vehicle directed graph, and/or replacing at least one edge in the vehicle directed graph to obtain a vehicle directed acyclic graph, wherein the vehicle directed acyclic graph does not include unconnected vertexes, and the out-degree of each vertex in the vehicle directed acyclic graph is smaller than or equal to a first preset threshold.
The target topological sequence is a candidate topological sequence of which the number of related vehicle pairs in the at least one candidate topological sequence is smaller than a second preset threshold value; the related vehicle pair refers to two vehicles which are adjacent to corresponding vertexes in the candidate topological sequence and have a connection relation between the corresponding vertexes in the vehicle directed graph.
Optionally, the processor calls the one or more instructions to perform the following steps:
judging whether the first vehicle and the second vehicle are related vehicle pairs or not according to the target topological sequence;
if the first vehicle and the second vehicle are a related vehicle pair, determining the product of the predicted collision probability and a first weight as a target collision probability;
and if the first vehicle and the second vehicle are not related vehicle pairs, determining the product of the predicted collision probability and a second weight as a target collision probability, wherein the first weight is larger than the second weight.
Optionally, the processor calls the one or more instructions to perform the following steps:
acquiring the running information of the first vehicle and the running information of the second vehicle;
and inputting the running information of the first vehicle and the running information of the second vehicle into a vehicle collision prediction model for prediction to obtain predicted collision information between the first vehicle and the second vehicle.
In the embodiment of the invention, the electronic equipment corrects and predicts the collision information according to the vehicle directed graph of the target internet of vehicles to obtain the collision risk between the first vehicle and the second vehicle. Furthermore, by controlling the running of the first vehicle and the second vehicle according to the risk of collision between the first vehicle and the second vehicle, the first vehicle and the second vehicle can be prevented from colliding, and the safety of the running of the vehicle is improved.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the implementation and the beneficial effects of the program for solving the problems may refer to the implementation and the beneficial effects of the driving control method described in fig. 2, and repeated details are not repeated.
The above disclosure is intended to be illustrative of only some embodiments of the invention, and is not intended to limit the scope of the invention.
Claims (10)
1. A running control method, characterized by comprising:
the method comprises the steps of obtaining a vehicle directed graph of a target internet of vehicles and predicted collision information between a first vehicle and a second vehicle in the target internet of vehicles, wherein each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle;
correcting the predicted collision information according to the vehicle directed graph to obtain a collision risk between the first vehicle and the second vehicle;
controlling travel of the first vehicle and the second vehicle in accordance with a risk of collision between the first vehicle and the second vehicle.
2. The method of claim 1, wherein the target networking of vehicles includes a plurality of vehicles, the first vehicle being any one of the plurality of vehicles, the second vehicle being any one of the plurality of vehicles other than the first vehicle;
the method for acquiring the vehicle directed graph of the target Internet of vehicles comprises the following steps:
acquiring running information of each vehicle in the target Internet of vehicles;
determining collision relations among vehicles in the target vehicle networking according to the running information;
and generating a vehicle directed graph of the target vehicle networking according to the collision relation among the vehicles in the target vehicle networking.
3. The method of claim 2, wherein said modifying the predicted collision information from the vehicle directed graph to derive a risk of collision between the first vehicle and the second vehicle comprises:
carrying out transformation processing on the vehicle directed graph to obtain at least one candidate topological sequence, wherein the candidate topological sequence comprises each vertex in the vehicle directed graph and indicating information used for indicating collision relations among vehicles;
screening out a target topological sequence from the at least one candidate topological sequence;
and correcting the predicted collision information according to the target topological sequence to obtain the collision risk between the first vehicle and the second vehicle.
4. The method according to claim 3, wherein the transforming the vehicle directed graph to obtain at least one candidate topological sequence comprises:
acquiring an adjacency matrix of the vehicle directed graph;
judging whether the vehicle directed graph comprises a ring-shaped structure or not according to the adjacency matrix;
if the vehicle directed graph comprises an annular structure, performing ring removal processing on the vehicle directed graph to obtain a vehicle directed acyclic graph, and performing linear processing on the vehicle directed acyclic graph to obtain at least one candidate topological sequence;
and if the vehicle directed graph does not comprise a ring structure, performing linear processing on the vehicle directed graph to obtain at least one candidate topological sequence.
5. The method of claim 4, wherein the subjecting the vehicle directed graph to a ring removal process to obtain a vehicle directed acyclic graph comprises:
removing at least one edge in the ring-shaped structure in the vehicle directed graph, and/or replacing at least one edge in the vehicle directed graph to obtain a vehicle directed acyclic graph, wherein the vehicle directed acyclic graph does not include unconnected vertexes, and the out-degree of each vertex in the vehicle directed acyclic graph is smaller than or equal to a first preset threshold.
6. The method according to any one of claims 3-5, wherein the target topological sequence is a candidate topological sequence in which the number of relevant vehicle pairs in the at least one candidate topological sequence is less than a second preset threshold;
the related vehicle pair refers to two vehicles which are adjacent to corresponding vertexes in the candidate topological sequence and have a connection relation between the corresponding vertexes in the vehicle directed graph.
7. The method of claim 6, wherein the predicted collision information comprises a predicted collision probability, the collision risk comprises a target collision probability;
the correcting the predicted collision information according to the target topological sequence to obtain the collision risk between the first vehicle and the second vehicle includes:
judging whether the first vehicle and the second vehicle are related vehicle pairs or not according to the target topological sequence;
if the first vehicle and the second vehicle are a related vehicle pair, determining the product of the predicted collision probability and a first weight as a target collision probability;
and if the first vehicle and the second vehicle are not related vehicle pairs, determining the product of the predicted collision probability and a second weight as a target collision probability, wherein the first weight is larger than the second weight.
8. The method of claim 1, wherein the obtaining predicted collision information between a first vehicle and a second vehicle in the target internet of vehicles comprises:
acquiring the running information of the first vehicle and the running information of the second vehicle;
and inputting the running information of the first vehicle and the running information of the second vehicle into a vehicle collision prediction model for prediction to obtain predicted collision information between the first vehicle and the second vehicle.
9. A travel control apparatus characterized by comprising:
the vehicle collision prediction method comprises an acquisition unit, a collision prediction unit and a judgment unit, wherein the acquisition unit is used for acquiring a vehicle directed graph of a target vehicle network and predicted collision information between a first vehicle and a second vehicle in the target vehicle network, each vertex of the vehicle directed graph corresponds to one vehicle, and a directed edge of the vehicle directed graph is used for indicating a collision relation between the first vehicle and the second vehicle;
the correction unit is used for correcting the predicted collision information according to the vehicle directed graph to obtain the collision risk between the first vehicle and the second vehicle;
a control unit for controlling travel of the first vehicle and the second vehicle in accordance with a risk of collision between the first vehicle and the second vehicle.
10. An electronic device comprising an input device and an output device, further comprising:
a processor adapted to implement one or more instructions; and the number of the first and second groups,
a computer storage medium having one or more instructions stored thereon, the one or more instructions adapted to be loaded by the processor and to perform the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910763508.XA CN110789520B (en) | 2019-08-19 | 2019-08-19 | Driving control method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910763508.XA CN110789520B (en) | 2019-08-19 | 2019-08-19 | Driving control method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110789520A true CN110789520A (en) | 2020-02-14 |
| CN110789520B CN110789520B (en) | 2022-07-12 |
Family
ID=69427036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910763508.XA Active CN110789520B (en) | 2019-08-19 | 2019-08-19 | Driving control method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110789520B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111267845A (en) * | 2020-03-31 | 2020-06-12 | 东风柳州汽车有限公司 | Truck turning risk prediction evasion method and system |
| CN112232581A (en) * | 2020-10-26 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Driving risk prediction method and device, electronic equipment and storage medium |
| US11392128B1 (en) * | 2019-04-19 | 2022-07-19 | Zoox, Inc. | Vehicle control using directed graphs |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105774800A (en) * | 2016-03-28 | 2016-07-20 | 清华大学 | Collision relieving method and device between vehicles in hybrid vehicle queue |
| CN107346612A (en) * | 2016-05-06 | 2017-11-14 | 中国科学院微电子研究所 | A kind of vehicle collision avoidance method and system based on car networking |
| CN107415942A (en) * | 2016-05-23 | 2017-12-01 | 福特全球技术公司 | Accident mitigates system and method |
| WO2019150459A1 (en) * | 2018-01-31 | 2019-08-08 | 住友電気工業株式会社 | Vehicle-mounted device, communication path information generation method, and computer program |
| CN110111602A (en) * | 2019-04-30 | 2019-08-09 | 浙江吉利控股集团有限公司 | A kind of vehicle collision prewarning method, device and equipment |
-
2019
- 2019-08-19 CN CN201910763508.XA patent/CN110789520B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105774800A (en) * | 2016-03-28 | 2016-07-20 | 清华大学 | Collision relieving method and device between vehicles in hybrid vehicle queue |
| CN107346612A (en) * | 2016-05-06 | 2017-11-14 | 中国科学院微电子研究所 | A kind of vehicle collision avoidance method and system based on car networking |
| CN107415942A (en) * | 2016-05-23 | 2017-12-01 | 福特全球技术公司 | Accident mitigates system and method |
| WO2019150459A1 (en) * | 2018-01-31 | 2019-08-08 | 住友電気工業株式会社 | Vehicle-mounted device, communication path information generation method, and computer program |
| CN110111602A (en) * | 2019-04-30 | 2019-08-09 | 浙江吉利控股集团有限公司 | A kind of vehicle collision prewarning method, device and equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11392128B1 (en) * | 2019-04-19 | 2022-07-19 | Zoox, Inc. | Vehicle control using directed graphs |
| CN111267845A (en) * | 2020-03-31 | 2020-06-12 | 东风柳州汽车有限公司 | Truck turning risk prediction evasion method and system |
| CN112232581A (en) * | 2020-10-26 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Driving risk prediction method and device, electronic equipment and storage medium |
| CN112232581B (en) * | 2020-10-26 | 2024-04-12 | 腾讯科技（深圳）有限公司 | Driving risk prediction method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110789520B (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10347131B2 (en) | Collision determination device | |
| CN110789520B (en) | Driving control method and device and electronic equipment | |
| US20220410939A1 (en) | Collision detection method, electronic device, and medium | |
| CN110910673B (en) | Method and system for reminding pedestrian to collide with vehicle, camera and mobile terminal | |
| US10435017B2 (en) | Method for providing an object prediction representation | |
| CN112889100B (en) | Moving body behavior prediction device | |
| CN113139696B (en) | Trajectory prediction model construction method and trajectory prediction method and device | |
| CN113189989B (en) | Vehicle intention prediction method, device, equipment and storage medium | |
| CN114030486A (en) | Trajectory prediction method and apparatus for dynamic obstacle, electronic device, and storage medium | |
| CN111915892B (en) | Data request response method, device, computer equipment and medium | |
| US20210398014A1 (en) | Reinforcement learning based control of imitative policies for autonomous driving | |
| CN111583716B (en) | Vehicle obstacle avoidance method and device, electronic equipment and storage medium | |
| CN110949380A (en) | Location prediction for dynamic objects | |
| CN114906170A (en) | Motion planning method and device, electronic equipment and storage medium | |
| CN114655254A (en) | Automatic driving vehicle control method and device and electronic equipment | |
| CN111731285B (en) | Vehicle anti-collision method and device based on V2X technology | |
| CN111401564A (en) | Model updating method and device for machine learning, electronic equipment and storage medium | |
| CN113744566B (en) | Early warning method and device | |
| CN112166458B (en) | Target detection and tracking method, system, equipment and storage medium | |
| CN114407916B (en) | Vehicle control and model training method and device, vehicle, equipment and storage medium | |
| CN113415271A (en) | Driving assistance method, device, computer-readable storage medium and processor | |
| KR20220058166A (en) | Method and apparatus for determining collision risk of car based on precise map information | |
| CN117842043A (en) | Method, medium and equipment for predicting vehicle track and selecting dangerous target | |
| CN116449356A (en) | Aggregation-based LIDAR data alignment | |
| CN116451482A (en) | Method and device for determining functional safety parameters, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40022039 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |