CN113366399A - Vehicle control method and device based on remote takeover and computer equipment - Google Patents
Vehicle control method and device based on remote takeover and computer equipment Download PDFInfo
- Publication number
- CN113366399A CN113366399A CN201980037715.5A CN201980037715A CN113366399A CN 113366399 A CN113366399 A CN 113366399A CN 201980037715 A CN201980037715 A CN 201980037715A CN 113366399 A CN113366399 A CN 113366399A
- Authority
- CN
- China
- Prior art keywords
- remote
- vehicle
- information
- remote takeover
- takeover
- 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 53
- 230000002159 abnormal effect Effects 0.000 claims abstract description 168
- 230000005856 abnormality Effects 0.000 claims description 42
- 238000001514 detection method Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 17
- 238000013468 resource allocation Methods 0.000 claims description 17
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 12
- 230000000903 blocking effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
Abstract
A method for vehicle control based on remote takeover, comprising: receiving remote takeover requests sent by a plurality of vehicles, wherein the remote takeover requests carry abnormal information; calculating the remote takeover weight of the remote takeover request according to the abnormal information; acquiring current load information of a plurality of control nodes (106), and calculating node idle resources according to the current load information; distributing a corresponding target control node (106) for the remote takeover request according to the remote takeover weight and the node idle resources; and generating a remote takeover task according to the remote takeover request, and distributing the remote takeover task to the target control node (106), so that the target control node (106) can remotely take over the corresponding vehicle.
Description
The application relates to a vehicle control method and device based on remote control and computer equipment.
The unmanned automobile is an intelligent automobile which senses road environment and vehicle surrounding environment through a vehicle-mounted sensing system, and controls the steering and speed of the automobile to reach a preset target according to the road, vehicle position and obstacle information obtained through sensing, so that the automobile can safely and reliably run on the road.
When the unmanned automobile inevitably has abnormal conditions in the automatic driving process, a control person who needs to take over the platform remotely usually processes the automobile when the automobile has the abnormal conditions or emergency conditions, so that the safety of the automobile is ensured. The remote takeover platform generally needs to supervise a large number of unmanned vehicles, the pressure of the remote takeover platform is higher when a plurality of vehicles meet abnormal conditions, and the processing efficiency of abnormal vehicles is lower.
Disclosure of Invention
According to various embodiments disclosed in the application, a vehicle control method, a vehicle control device and a computer device based on remote control are provided.
A method for vehicle control based on remote takeover, comprising:
receiving remote takeover requests sent by a plurality of vehicles, wherein the remote takeover requests carry abnormal information;
calculating the remote takeover weight of the remote takeover request according to the abnormal information;
acquiring current load information of a plurality of control nodes, and calculating node idle resources according to the current load information;
distributing a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resource; and
and generating a remote takeover task according to the remote takeover request, and distributing the remote takeover task to the target control node, so that the target control node remotely takes over the corresponding vehicle.
A method for vehicle control based on remote takeover, comprising:
acquiring running state information of a vehicle, and performing abnormality detection according to the running state information;
when the driving state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal driving state information;
sending the remote takeover request to a central server; enabling the central server to generate a remote take-over task according to the remote take-over request, and distributing the remote take-over task to a corresponding target control node;
acquiring a remote takeover instruction sent by the target control node, and sending vehicle return information to the target control node according to the remote takeover instruction; and
and receiving a remote control instruction issued by the target control node according to the vehicle return information, and controlling the vehicle according to the remote control instruction.
A remote take-over based vehicle control apparatus comprising:
the system comprises a request receiving module, a request receiving module and a processing module, wherein the request receiving module is used for receiving remote takeover requests sent by a plurality of vehicles, and the remote takeover requests carry abnormal information;
the resource calculation module is used for calculating the remote takeover weight of the remote takeover request according to the abnormal information; acquiring current load information of a plurality of control nodes, and calculating node idle resources according to the current load information; distributing a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resource; and
and the task distribution module is used for generating a remote takeover task according to the remote takeover request and distributing the remote takeover task to the target control node so that the target control node remotely takes over the corresponding vehicle.
A remote take-over based vehicle control apparatus comprising:
the abnormality detection module is used for acquiring the running state information of the vehicle and carrying out abnormality detection according to the running state information; when the driving state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal driving state information;
the request sending module is used for sending the remote takeover request to a central server; enabling the central server to generate a remote take-over task according to the remote take-over request, and distributing the remote take-over task to a corresponding target control node;
the information uploading module is used for acquiring a remote takeover instruction sent by the target control node and sending vehicle return information to the target control node according to the remote takeover instruction; and
and the remote take-over module is used for receiving a remote control instruction issued by the target control node according to the vehicle return information and controlling the vehicle according to the remote control instruction.
A computer arrangement comprising a memory storing a computer program and a processor implementing the steps of a remote take-over based vehicle control method as provided in any one of the embodiments of the application when the computer program is executed.
One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to implement the steps of a remote takeover-based vehicle control method provided in any one of the embodiments of the present application when the readable storage media is executed.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the application will be apparent from the description and drawings, and from the claims.
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a diagram illustrating an application scenario of a vehicle control method based on remote takeover according to one or more embodiments.
FIG. 2 is a schematic flow diagram of a method for remote takeover-based vehicle control in accordance with one or more embodiments.
FIG. 3 is a flow diagram illustrating steps for computing node free resources in accordance with one or more embodiments.
FIG. 4 is a flow diagram illustrating a remote takeover queue assignment procedure in accordance with one or more embodiments.
FIG. 5 is a flowchart illustrating a vehicle control method based on remote takeover in another embodiment.
FIG. 6 is a flow diagram illustrating steps for remotely identifying exception information in accordance with one or more embodiments.
FIG. 7 is a block diagram of a vehicle control apparatus based on remote takeover in accordance with one or more embodiments.
Fig. 8 is a block diagram of a vehicle control device based on remote takeover in another embodiment.
FIG. 9 is a block diagram of a computer device in accordance with one or more embodiments.
Fig. 10 is a block diagram of a computer device in another embodiment.
In order to make the technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, the vehicle control method based on network monitoring provided by the application can be particularly applied to the field of automatic driving, for example, the vehicle control method based on network monitoring can be applied to the application environment shown in fig. 1. The vehicle 102 communicates with a central server 104 over a network, and the central server 104 communicates with a control node 106 over the network. The central server 104 receives remote takeover requests sent by the vehicles 102, and the central server 104 calculates remote takeover weights of the remote takeover requests according to abnormal information carried by the remote takeover requests. The central server 104 obtains current load information of the plurality of control nodes, calculates node idle resources according to the current load information, and allocates corresponding target control nodes 106 for the remote takeover requests according to the remote takeover weight and the node idle resources. The central server 104 generates a remote takeover task according to the remote takeover request, and distributes the remote takeover task to the target control node 106, so that the target control node 106 performs remote takeover on the corresponding vehicle 102. The central server 104 and the control node 106 may be implemented as separate servers or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a vehicle control method based on remote control is provided, which is described by taking the method as an example applied to the central server in fig. 1, and includes the following steps:
The vehicle can be an unmanned vehicle, and the unmanned vehicle is an intelligent vehicle which senses the road environment through a vehicle-mounted sensing system, automatically plans a driving route and controls the vehicle to reach a preset target. The vehicle is provided with a vehicle-mounted sensing system, an automatic driving system and a remote take-over system.
In the automatic driving process of the vehicle, the vehicle can communicate with the control server through the central server, so that a remote control person can take over the vehicle remotely through the control server. The central server may be used to manage remote takeover requests for multiple vehicles and multiple control servers. For example, when there is an abnormal situation or a fault in the vehicle, the vehicle needs to be remotely taken over to ensure the safety of the vehicle during driving.
The vehicle can automatically detect the abnormality during the automatic running process, and when the abnormality is detected, the abnormality is, for example, a vehicle fault, a road fault or an obstacle blocking. The vehicle can send a remote takeover request to a control server of the remote control platform, and the control server issues a remote takeover instruction to the vehicle based on the remote takeover request sent by the vehicle so as to remotely take over the vehicle. The control server of the remote control platform can also directly issue a remote takeover instruction to the vehicle according to the remote takeover requirement or when the automatic driving system has a fault so as to carry out remote takeover on the vehicle.
The automatic driving vehicles can simultaneously send remote control requests to the central server, the central server receives the remote takeover requests sent by the automatic driving vehicles, each remote takeover request is dispatched and distributed to the corresponding target control server, and therefore the target control server can conduct remote takeover on the corresponding remote takeover requests and the corresponding automatic driving vehicles. The control server may be a server corresponding to the control node.
And step 204, calculating the remote takeover weight of the remote takeover request according to the abnormal information.
The remote takeover request sent by the vehicle carries the abnormal information of the vehicle. And after receiving the remote takeover requests sent by the vehicles, the central server calculates the remote takeover weight of the corresponding remote takeover request according to the abnormal information of each vehicle. The remote takeover weight may identify the importance and urgency of the current remote takeover request. For example, the central server may determine a vehicle abnormal degree value and a take-over emergency degree value according to the vehicle fault information and the abnormality type in the abnormality information, and calculate a remote take-over weight of the remote take-over request according to the vehicle abnormal degree value and the take-over emergency degree value.
For example, when the vehicle stops on a dangerous road and cannot move ahead, or when the fault part of the vehicle is serious and has a great danger, the vehicle needs to be remotely taken over as soon as possible, and the abnormal condition of the vehicle needs to be relieved.
And step 206, acquiring current load information of the plurality of control nodes, and calculating idle resources of the nodes according to the current load information.
The central server can manage the states of all vehicles and control nodes in real time, each control node comprises corresponding load information, the load information can represent the current load working state information of the control server, and the node idle resources can represent available resources which can be used for processing remote takeover requests by the control server currently.
The central server obtains the current load information of the plurality of control nodes, and calculates the node idle resources of each control node according to the current load information of each control node. For example, the central server may utilize a dynamic load balancing algorithm to control the real-time load status information of the server to distribute the plurality of remote takeover requests, such as a minimum connection method, a weighted minimum connection method, and the like. The central server can also obtain the task to be processed of each control node, and then calculate the node idle resources of each control node according to the current load information of the control node and the task to be processed.
And step 208, distributing a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resource.
After the central server obtains the node idle resources of the plurality of control nodes, the resource consumption of the remote takeover request is determined according to the remote takeover weight of the remote takeover request, and the resource consumption can be expressed as the resource of the control node required to be consumed by the remote takeover request. And the central server further allocates a corresponding target control node for the remote takeover request according to the remote takeover weight and the resource consumption of the remote takeover request.
For example, the central server may schedule a plurality of remote takeover requests through a resource allocation model. The central server can poll the current load weights of the plurality of control nodes through a resource allocation model by using a polling algorithm to obtain the current load balance of each control node, select a corresponding control node identifier for the resource acquisition request according to the current load balance of each control node, perform smoothing processing on the current load weight corresponding to the selected control node identifier, and select a control node identifier corresponding to the next remote takeover request by using a smoothed result until the corresponding control node identifier is selected for the plurality of remote takeover requests. And determining the selected control node identification as a target control node corresponding to the corresponding remote takeover request.
And step 210, generating a remote takeover task according to the remote takeover request, and distributing the remote takeover task to the target control node, so that the target control node remotely takes over the corresponding vehicle.
The central server may generate the remote takeover task immediately after receiving the remote takeover request, or may generate the corresponding remote takeover task after determining the target control node corresponding to the remote takeover request. And after the central server determines the target control node corresponding to the remote takeover request, the remote takeover task is distributed to the corresponding target control node. After the remote takeover task is successfully distributed, namely after the target control node confirms takeover, a communication channel between the vehicle of the remote takeover task and the target control node is established, so that the control platform corresponding to the target control node remotely takes over the corresponding vehicle.
And if the remote takeover task is not successfully distributed, the central server distributes the remote takeover task again. If the remote takeover task is successfully distributed, the vehicle can also resend the remote takeover request to the central server after the interval preset frequency.
In another embodiment, if the remote takeover task is not successfully allocated, the central server may further generate a plurality of remote takeover queues according to current load information of the plurality of control nodes, and allocate the remote takeover request to a corresponding remote takeover queue according to a remote takeover weight of the remote takeover request, so as to queue up for a free control node.
And after the target control node successfully takes over the remote take-over task, the target control node issues a remote control instruction to the vehicle corresponding to the remote take-over task. After the vehicle acquires a remote takeover instruction issued by a control server corresponding to the target control node, the vehicle uploads road image information and vehicle state information to the control server, the road image information may include video data around the vehicle and road picture video data, and the road image information may be continuous video frames. The vehicle state information may include vehicle positioning information, vehicle navigation information, in-vehicle temperature information, vehicle instrument information, sensor information, and other vehicle state information. And the road image information and the vehicle state information are transmitted to be used for remote takeover control of the vehicle by a remote takeover person according to the road condition and the vehicle state. Therefore, remote taking over can be timely and effectively carried out on the automatic driving vehicle with the abnormality, danger caused by disordered driving of the vehicle can be prevented, and the safety of the vehicle under the abnormal condition can be effectively guaranteed.
In the vehicle control method based on remote takeover, after the central server receives remote takeover requests sent by a plurality of vehicles, the remote takeover weight of the remote takeover requests is calculated according to abnormal information carried by the remote takeover requests, so that the importance degree and the emergency degree of the remote takeover requests can be effectively identified, the remote takeover requests with the emergency importance degree and the emergency degree can be processed as soon as possible in time, and dangerous accidents are prevented. The central server acquires the current load information of the plurality of control nodes, calculates the node idle resources according to the current load information, and distributes corresponding target control nodes for the remote takeover request according to the remote takeover weight and the node idle resources, so that the remote takeover request can be effectively and reasonably distributed according to the remote takeover weight and the node idle resources. And the central server further generates a remote takeover task according to the remote takeover request, and distributes the remote takeover task to the target control node, so that the target control node remotely takes over the corresponding vehicle. By identifying the remote takeover weight of the remote takeover request and distributing the corresponding control node for the remote takeover request according to the remote takeover weight and the node idle resource, the load balance of a plurality of control nodes can be effectively carried out, and the resource distribution efficiency and the processing efficiency of the remote takeover request can be effectively improved.
In one embodiment, calculating the remote takeover weight of the remote takeover request according to the anomaly information comprises: extracting the abnormal type and the vehicle fault information in the abnormal information; determining a vehicle abnormal degree value and a takeover emergency degree value according to the abnormal type and the vehicle fault information; and calculating the remote takeover weight of the remote takeover request according to the vehicle abnormal degree value and the takeover emergency degree value.
The abnormal information comprises vehicle fault information, and after the vehicle sends a remote takeover request carrying the abnormal information to the central server, the central server extracts the abnormal type and the vehicle fault information in the abnormal information. The vehicle failure information includes vehicle state failure information and road state abnormality information. The vehicle state failure information may include sensor failures such as laser radar, camera, IMU (inertial measurement unit), GPS, etc., and vehicle state failure information such as vehicle PC failures, and automatic driving program anomalies, among others. The road condition abnormality information includes abnormality information such as abnormal road conditions including road obstacles and road traffic congestion. For example, when the vehicle stops on a dangerous road and cannot move ahead, or when the fault part of the vehicle is serious and has a great danger, the vehicle needs to be remotely taken over as soon as possible, and the abnormal condition of the vehicle needs to be relieved.
The central server can be configured with a vehicle abnormal configuration table in advance, and the vehicle abnormal configuration table is configured with the mapping relation between the abnormal type and the vehicle fault information and the abnormal range value and the takeover emergency range value. And the central server extracts the vehicle fault information in the abnormal information, determines a corresponding abnormal type, then matches the abnormal type and the vehicle fault information of the remote takeover request with a vehicle abnormal high configuration table, determines a vehicle abnormal degree value and a takeover emergency degree value according to a matching result, and further calculates the remote takeover weight of the remote takeover request according to the vehicle abnormal degree value and the takeover emergency degree value. Therefore, the importance degree and the emergency degree of the remote takeover request can be effectively identified, so that the remote takeover request with the emergency importance degree and the emergency degree can be processed as soon as possible in time, dangerous accidents are prevented, and the safety of abnormal vehicles is improved.
In one embodiment, as shown in fig. 3, the step of obtaining current load information of a plurality of control nodes and calculating idle resources of the nodes according to the current load information specifically includes the following steps:
And 304, acquiring the tasks to be processed of the control nodes, and calculating the node resource utilization rate of each control node according to the current load weight and the tasks to be processed.
And step 306, calculating the node idle resources of the plurality of control nodes according to the current load weight and the node resource utilization rate.
The resource allocation model may be a decision model based on a neural network, and the resource allocation model may be a neural network model obtained by pre-training and used for calculating control node resources and allocating resources to a remote takeover request.
After receiving remote takeover requests sent by a plurality of vehicles, the central server acquires current load information of a plurality of control nodes bound by the central server, and can also acquire node performance parameters of each control node. The node performance parameters may represent various performance index parameters of the control node, and the node performance parameters may be current performance parameters of the control node. The central server can also obtain the tasks to be processed of each control node. Some control nodes may also have allocated remote takeover tasks pending, and the expected load of these nodes is relatively high. For example, the node performance parameters may include index parameters such as the number of CPUs, the CPU frequency, the memory capacity, the disk rate, and the network throughput. The current load information of the control node may include indexes such as CPU occupancy, memory occupancy, and network broadband occupancy.
And the central server calls the resource distribution model, analyzes the current load information and the node performance parameters of the plurality of control nodes through the resource distribution model, and obtains the current load weights of the plurality of control nodes. Specifically, the current load weight may be a ratio of the current load information to the node performance parameter.
The central server further calculates the node resource utilization rate of each control node according to the current load weight of the control node and the task to be processed, and the central server further calculates the node idle resources of the plurality of control nodes according to the current load weight and the node resource utilization rate. For example, the central server may also predict the load of the control node based on the current load weight of the control node and the tape processing task. The central server can also calculate the load increment of the control node by using the task to be processed of each control node, and calculate the node idle resources of the control node according to the current load weight and the load increment of the control node. The node idle resources of the control nodes are calculated according to the remote takeover weight and the node states of the control nodes, so that the resource calculation and the resource distribution can be effectively carried out, and the remote takeover request can be effectively and reasonably distributed according to the remote takeover weight and the node idle resources.
In one embodiment, allocating a corresponding target control node for a remote takeover request according to a remote takeover weight and node idle resources includes: predicting a corresponding resource consumption value according to the remote takeover weight by using a resource distribution model; calculating matched node idle resources according to the remote takeover weight and the resource consumption value of the remote takeover request; and determining a target control node corresponding to the remote takeover request according to the matched node idle resources, and distributing the remote takeover request to the corresponding target control node.
After obtaining the current load information of the plurality of control nodes, the central server calls the resource allocation model, analyzes the current load information and the node performance parameters of the plurality of control nodes through the resource allocation model, and obtains the current load weights of the plurality of control nodes. The central server may also predict a corresponding resource consumption value based on the remote takeover weight of the remote takeover request using a resource allocation model. The resource consumption value may represent a control node resource that is expected to be consumed by the remote takeover request, for example, resource consumption information such as time, duration, difficulty, and the like that require remote takeover.
The central server can also predict the load of the control node according to the current load weight of the control node and the belt processing task. The central server can also calculate the load increment of the control node by using the task to be processed of each control node, and calculate the node idle resources of the control node according to the current load weight and resource consumption value of the control node and the load increment.
And the central server further determines a target control node corresponding to the remote takeover request according to the matched node idle resources, and distributes the remote takeover request to the corresponding target control node, so that the target control node remotely takes over the corresponding vehicle. The corresponding target control node is allocated to the remote takeover request according to the remote takeover weight and the node idle resource, so that the remote takeover request can be effectively and reasonably allocated according to the remote takeover weight and the node idle resource, and the resource allocation efficiency and the processing efficiency of the remote takeover request can be effectively improved.
In one embodiment, as shown in fig. 4, the method further includes a step of allocating a remote takeover queue, where the step specifically includes the following steps:
And step 406, calculating resource consumption states of the plurality of control nodes, allocating the plurality of control nodes to corresponding remote takeover queues according to the resource consumption states of the plurality of control nodes, and allocating the remote takeover requests to corresponding target control nodes in the corresponding remote takeover queues.
After the central server obtains the current load information of the plurality of control nodes, the central server calls a resource distribution model, corresponding resource consumption values are predicted according to the remote takeover weights by using the resource distribution model, and matched node idle resources are calculated according to the remote takeover weights and the resource consumption values of the remote takeover requests. And distributing a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resource.
Further, if no node idle resource exists currently, that is, each control node is in a load state, and there is no idle control node. At this time, the central server generates a plurality of remote takeover queues according to the plurality of remote takeover requests and current load information of the plurality of control nodes, and the central server may generate a plurality of remote takeover queues of a corresponding number according to the number of the remote takeover requests and the current load information of the plurality of control nodes. The central server can further distribute the remote takeover requests to corresponding remote takeover queues according to the abnormal types of the remote takeover requests, the remote takeover weights and the resource consumption values. For example, a remote takeover request with a higher exception type or a higher remote takeover weight may be allocated to a remote takeover queue with a higher processing priority, so that the remote takeover request with the higher remote takeover weight can be timely and effectively allocated for processing.
The central server further calculates resource consumption states of the plurality of control nodes, distributes the plurality of control nodes to corresponding remote takeover queues according to the resource consumption states of the plurality of control nodes, and distributes the remote takeover requests to corresponding target control nodes in the corresponding remote takeover queues, so that the target control nodes remotely take over corresponding vehicles. Therefore, even when no idle node resource exists currently, the remote takeover requests can be distributed to the corresponding remote takeover queues according to the remote takeover weights and the resource consumption values, and the plurality of control nodes can be distributed to the corresponding remote takeover queues according to the resource consumption states of the plurality of control nodes. When idle node resources are available, the remote takeover request can be timely and effectively distributed to the corresponding target control node in the remote takeover queue. Therefore, the remote takeover request can be reasonably distributed according to the remote takeover weight and the node idle resources, and the resource distribution efficiency and the processing efficiency of the remote takeover request can be effectively improved.
In one embodiment, as shown in fig. 5, a vehicle control method based on remote control is provided, which is described by taking the vehicle in fig. 1 as an example, and includes the following steps:
The vehicle can automatically detect the abnormality during the automatic running process, and when the abnormality is detected, the abnormality such as vehicle failure, road failure or obstacle blocking is detected. The vehicle can send a remote takeover request to a central server of the central control platform, and the vehicle can communicate with the control server through the central server, so that remote control personnel can take over the vehicle remotely through the control server. The control server may be a server corresponding to the control node. And the control server issues a remote takeover instruction to the vehicle based on a remote takeover request sent by the vehicle so as to remotely take over the vehicle.
The method comprises the steps of acquiring running state information of a vehicle in the running process of the vehicle. The running state information of the vehicle may include state information of the vehicle such as a vehicle state, a vehicle state parameter, and the like. The vehicle state may include states of vehicle online, vehicle offline, normal autopilot, abnormal take-over, etc. The vehicle state parameters may include current position information, current vehicle speed, light, gear, acceleration information, vehicle navigation information, temperature information in the vehicle, vehicle meter information, sensor information, and other parameter information. The running state information may also include log information generated by an automatic driving system in automatic driving of the vehicle, and may also include road state information and the like. During the automatic running of the vehicle, abnormality detection is continuously performed on the running state information.
The vehicle may detect vehicle state failure information and road state abnormality information. The vehicle state failure information may include sensor failures such as laser radar, camera, IMU (inertial measurement unit), GPS, etc., and vehicle state failure information such as vehicle PC failures, and automatic driving program anomalies, among others. The road condition abnormality information includes abnormality information such as abnormal road conditions including road obstacles and road traffic congestion.
And step 504, when the driving state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal driving state information.
When the vehicle detects that the driving state is abnormal through the driving state information, the vehicle generates a vehicle control command for parking and controls the vehicle to park according to the vehicle control command. The vehicle generates a remote takeover request according to the abnormal running state information so as to send the remote takeover request carrying the abnormal information to the central server, and the central server distributes the remote takeover request to the corresponding target control node. For example, when the vehicle stops on a dangerous road and cannot move ahead, or when a fault part of the vehicle is serious and has a great risk, the vehicle needs to be remotely taken over as soon as possible, and the abnormality of the vehicle needs to be relieved.
The vehicle generates detailed abnormal information according to the abnormal driving state information, and after a remote takeover request carrying the abnormal information is generated, the remote takeover request is sent to the central server, so that the central server generates a remote takeover task according to the remote takeover request, and the remote takeover task is distributed to a corresponding target control node, so that the target control node remotely takes over the vehicle.
Further, a plurality of automatic driving vehicles can simultaneously send remote control requests to the central server, the central server receives the remote takeover requests sent by the plurality of vehicles, each remote takeover request is dispatched and distributed to the corresponding target control server, and therefore the target control server corresponding to the target control node can remotely take over the corresponding remote takeover requests and the vehicles.
And step 508, acquiring a remote takeover instruction sent by the target control node, and sending vehicle return information to the target control node according to the remote takeover instruction.
After receiving the remote takeover requests sent by the vehicles, the central server can calculate the remote takeover weight of the remote takeover requests according to abnormal information carried by the remote takeover requests, so that the importance degree and the emergency degree of the remote takeover requests can be effectively identified, the remote takeover requests with the emergency importance degree and the emergency degree can be processed as soon as possible in time, and dangerous accidents are prevented. The central server acquires the current load information of the plurality of control nodes, calculates the node idle resources according to the current load information, and distributes corresponding target control nodes for the remote takeover request according to the remote takeover weight and the node idle resources, so that the remote takeover request can be effectively and reasonably distributed according to the remote takeover weight and the node idle resources. And the central server further generates a remote takeover task according to the remote takeover request, and distributes the remote takeover task to the target control node, so that the target control node remotely takes over the corresponding vehicle and issues a remote control instruction to the vehicle.
After receiving the target control node instruction, the vehicle can switch the automatic driving mode to the control mode corresponding to the remote takeover mode, and upload vehicle return information to the target control node according to the remote control instruction. The vehicle return information may include vehicle state information and road image information. The vehicle state information may include vehicle positioning information, vehicle navigation information, in-vehicle temperature information, vehicle meter information, and other vehicle state information. The road image information may include video data of surroundings of the vehicle and road picture video data, and the road image information may be a continuous video frame. And the road image information and the vehicle state information are transmitted to a remote takeover personnel for carrying out remote takeover on the vehicle according to the road condition and the vehicle state.
And step 510, the receiving target control node issues a remote control instruction according to the vehicle return information, and the vehicle is controlled according to the remote control instruction.
After the vehicle uploads the road image information and the vehicle state information to the control server, the remote control platform sends a remote control instruction to the vehicle through the control server corresponding to the target control node according to the road image information and the vehicle state information, and the remote control instruction is used for controlling the vehicle to run. And after the vehicle acquires the remote control instruction, executing the remote control instruction, and controlling the vehicle to perform corresponding control operation according to the remote control instruction, so that the vehicle is remotely taken over. For example, the remote control instruction may include an instruction to control the vehicle to travel by accelerating travel, decelerating travel, activating a lamp, stopping a vehicle, and the like. Therefore, remote taking over can be timely and effectively carried out on the automatic driving vehicle with the abnormality, danger caused by disordered driving of the vehicle can be prevented, and the safety of the vehicle under the abnormal condition can be effectively guaranteed.
In the present embodiment, the vehicle acquires the running state information of the vehicle, and performs abnormality detection based on the running state information. And when monitoring that the running state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal running state information. The vehicle sends the remote takeover request to the central server, so that the central server generates a remote takeover task according to the remote takeover request, and the remote takeover task is distributed to the corresponding target control node, and therefore the remote takeover request can be effectively and reasonably distributed according to node idle resources. The vehicle further obtains a remote takeover instruction sent by the target control node, and sends vehicle return information to the target control node according to the remote takeover instruction. And after the vehicle receiving target control node issues a remote control instruction according to the vehicle return information, controlling the vehicle according to the remote control instruction. The central server performs resource allocation of the control nodes for the remote takeover request, and can timely and effectively allocate the corresponding control nodes for the remote takeover request, so that the resource allocation efficiency and the processing efficiency of the remote takeover request can be effectively improved.
In one embodiment, the driving state information includes vehicle state information, and the abnormality detection is performed based on the driving state information, and includes: sending a fault monitoring instruction to an automatic driving system according to a preset frequency; detecting abnormal states and driving abnormal states of the sensors according to the fault monitoring instruction and the vehicle state information to obtain a detection result; and if the detection result comprises abnormal information, determining vehicle fault information in the abnormal information, and determining the abnormal information to identify the abnormal type and the abnormal grade.
During the running process of the vehicle, the running state information of the vehicle can be continuously acquired, and the abnormality detection can be continuously carried out on the running state information. Specifically, the vehicle can also send a fault monitoring instruction to an automatic driving system according to a preset frequency in the automatic driving process, and the vehicle detects abnormal states and driving abnormal states of the sensors according to the fault monitoring instruction and the vehicle state information and feeds back corresponding detection results. And the vehicle identifies whether the vehicle state is abnormal or not according to the feedback detection result.
If abnormal information exists in the detection result, vehicle fault information is determined according to the detected abnormal index parameters, corresponding abnormal information is generated, and the abnormal information can comprise a plurality of items of vehicle current state information such as the abnormal index parameters, vehicle fault positions and current position information. The vehicle may also determine a corresponding anomaly type and anomaly level based on the anomaly index parameter. The abnormal level can be used for determining an abnormal degree value and a takeover emergency degree value corresponding to the abnormal information, and represents the current abnormal state degree and the emergency degree of the vehicle. The importance degree and the emergency degree of the remote takeover request are identified by identifying and determining the abnormal type and the abnormal grade of the vehicle, so that the central server can timely process the remote takeover request with the emergency importance degree and the emergency degree as soon as possible, and dangerous accidents are prevented.
In one embodiment, the driving state information includes road image information, and the performing the abnormality detection according to the driving state information includes: performing road identification and obstacle identification on the road image information through a road identification model to obtain a road identification result; and when the road identification result has road abnormity or road obstacles, controlling the vehicle to stop, and generating road abnormity information according to the identification result.
The vehicle monitors road state information in real time in the automatic driving process so as to detect road abnormal conditions. For example, if an abnormal road condition such as an unrecognizable front road, a road obstacle, and an excessively long stay in place is recognized, it indicates that the current road condition is abnormal, and it is necessary to control the vehicle to stop. The vehicle can perform road recognition and obstacle recognition on road image information acquired by the vehicle through the trained road recognition model. Specifically, the vehicle may identify the road information and information in the road image information through the road identification model, for example, by acquiring a current frame point cloud image and a previous frame point cloud image in the road image information, identifying detailed road information in the point cloud image, identifying a key point cloud and a motion track in the point cloud image, identifying an obstacle in the road image information according to the abnormal key point cloud and the motion track, and performing abnormality detection on the obstacle. When there is an abnormality in the obstacle, abnormality information including obstacle information is generated.
And when the road identification result has road abnormity or road obstacles, controlling the vehicle to stop, and generating road abnormity information according to the identification result. And the vehicle generates a remote take-over request according to the road abnormal information, and sends the remote take-over request to the central server, so that the central server generates a remote take-over task according to the remote take-over request, and the remote take-over task is distributed to a corresponding target control node, so that the target control node remotely takes over the vehicle. Therefore, remote taking over can be timely and effectively carried out on the automatic driving vehicle with the abnormality, danger caused by disordered driving of the vehicle can be prevented, and the safety of the vehicle under the abnormal condition can be effectively guaranteed.
In one embodiment, as shown in fig. 6, after the remote takeover task is distributed to the corresponding target control node, the method further includes a step of remotely identifying abnormal information, where the step specifically includes the following steps:
And step 604, controlling the automatic driving of the vehicle according to the abnormal information identification result and the operation prompt information.
And 606, continuously detecting the running state information of the vehicle until the abnormal information is removed and the running state of the vehicle is a normal state, and ending the remote takeover task.
And the vehicle carries out abnormity detection according to the running state information, controls the vehicle to stop when the running state information is monitored to be abnormal, and generates a remote takeover request according to the abnormal running state information. The vehicle sends the remote takeover request to the central server, so that the central server generates a remote takeover task according to the remote takeover request, and the remote takeover task is distributed to the corresponding target control node, so that the target control node remotely takes over the vehicle.
The vehicle further obtains a remote takeover instruction sent by the target control node, and sends vehicle return information to the target control node according to the remote takeover instruction. Further, after the target control node acquires the abnormal information and the vehicle return information of the vehicle, the target control node performs abnormal analysis according to the abnormal information and the vehicle return information, and judges whether the abnormal condition of the vehicle needs to be remotely taken over. For example, when an obstacle exists in front of the vehicle or the vehicle cannot autonomously identify the road, a controller corresponding to the target control node may not directly remotely control the vehicle, the controller may label the type and processing mode of the obstacle according to the vehicle return information, and may also label correct road information, and the vehicle autonomously identifies and automatically drives according to the labeled abnormal information identification result and the operation prompt information. And the target control node generates an abnormal information identification result and operation prompt information according to the abnormal information and the vehicle return information, and the vehicle controls the vehicle to automatically drive according to the abnormal information identification result and the operation prompt information.
The vehicle continuously detects the driving state information of the vehicle until the abnormal information release is detected and the driving state of the vehicle is a normal state, for example, the vehicle has already driven an obstacle or the vehicle leaves the current position and can autonomously identify the road, which may indicate the abnormal information release or the driving state of the vehicle is a normal state, and at this time, the vehicle may end the remote takeover task. The abnormal condition of the vehicle is timely identified through the control node, the corresponding abnormal information identification result and the corresponding operation prompt information are analyzed, so that the vehicle can be automatically identified and automatically driven, and remote takeover is finished when the abnormality is relieved and the driving state is recovered to be normal, so that the remote takeover resource can be effectively saved, and meanwhile, the processing efficiency of the remote takeover request is effectively improved.
In one embodiment, the method further comprises: sending vehicle return information to the target control node according to the remote takeover instruction, so that the target control node performs anomaly analysis according to the anomaly information and the vehicle return information; if the abnormal condition of the vehicle is that remote intervention is not needed, receiving a takeover ending instruction issued by the target control node, wherein the takeover ending instruction comprises prompt information; and switching the remote takeover mode to an automatic driving mode, and controlling the automatic driving of the vehicle according to the driving state information and the prompt information.
The vehicle acquires the driving state information of the vehicle and performs abnormality detection based on the driving state information. And when monitoring that the running state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal running state information. And the vehicle sends the remote takeover request to the central server, so that the central server generates a remote takeover task according to the remote takeover request, and the remote takeover task is distributed to the corresponding target control node, so that the target control node remotely takes over the vehicle.
The vehicle further obtains a remote takeover instruction sent by the target control node, and sends vehicle return information to the target control node according to the remote takeover instruction. Further, after the target control node acquires the abnormal information and the vehicle return information of the vehicle, the target control node performs abnormal analysis according to the abnormal information and the vehicle return information, and judges whether the abnormal condition of the vehicle needs to be remotely taken over. For example, if the abnormal condition of the vehicle driving state is that a small obstacle exists in front of the road, and the target control node analyzes that the obstacle can directly drive past without affecting the vehicle and the driving state, it may be determined that the abnormal condition is an intervention that does not require remote takeover. At this time, the target control node may directly send a prompt message to the vehicle, where the prompt message may include information about the type of the obstacle and the processing method, so as to prompt the vehicle to continue to run along the original route or to prompt the obstacle not to affect the vehicle. And the target control node issues a takeover ending instruction to the vehicle to end the remote takeover.
And after receiving a takeover ending instruction issued by the target control node, the vehicle switches the remote takeover mode to the automatic driving mode, continues to identify the road picture, and controls the automatic driving of the vehicle through the automatic driving system according to the driving state information and the prompt information. By identifying the abnormal condition of the vehicle in time, if the abnormal condition of the vehicle is identified as not needing remote intervention, prompt information is sent in time and remote take-over is ended, so that remote take-over resources are saved, and meanwhile, the processing efficiency of remote take-over requests is effectively improved.
In another embodiment, if the abnormal condition of the vehicle driving state is that an obstacle exists in front and the vehicle needs to go around the obstacle, the target control node may analyze the prompt information of going around the obstacle or parking and avoiding, so that the vehicle performs autonomous road identification according to the prompt information. And sending prompt information to the target control node until the vehicle can automatically identify the road condition and normally run through the automatic driving system so that the target control node sends a takeover ending instruction to the vehicle to end remote takeover. Therefore, the processing efficiency of the remote takeover request can be effectively improved.
It should be understood that although the various steps in the flow charts of fig. 2-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-6 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 7, there is provided a remote take-over-based vehicle control apparatus including: a request receiving module 702, a resource calculating module 704, and a task allocating module 706, wherein:
a request receiving module 702, configured to receive remote takeover requests sent by multiple vehicles, where the remote takeover requests carry abnormal information;
a resource calculation module 704, configured to calculate a remote takeover weight of the remote takeover request according to the exception information; acquiring current load information of a plurality of control nodes, and calculating node idle resources according to the current load information; distributing a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resource; and
and the task allocation module 706 is configured to generate a remote takeover task according to the remote takeover request, and allocate the remote takeover task to the target control node, so that the target control node performs remote takeover on the corresponding vehicle.
In one embodiment, the resource calculation module 704 is further configured to extract the abnormality type and the vehicle failure information from the abnormality information; determining a vehicle abnormal degree value and a take-over emergency degree value according to the abnormal type and the vehicle fault information; and calculating the remote takeover weight of the remote takeover request according to the vehicle abnormal degree value and the takeover emergency degree value.
In one embodiment, the resource calculation module 704 is further configured to invoke a resource allocation model, and analyze current load information and node performance parameters of the plurality of control nodes through the resource allocation model to obtain current load weights of the plurality of control nodes; acquiring a task to be processed of a control node, and calculating the node resource utilization rate of each control node according to the current load weight and the task to be processed; and calculating the node idle resources of the plurality of control nodes according to the current load weight and the node resource utilization rate.
In one embodiment, the resource calculation module 704 is further configured to predict a corresponding resource consumption value according to the remote takeover weight using the resource allocation model; calculating matched node idle resources according to the remote takeover weight and the resource consumption value of the remote takeover request; and the task allocation module 706 is further configured to determine a target control node corresponding to the remote takeover request according to the matched node idle resource, and allocate the remote takeover request to the corresponding target control node.
In one embodiment, the resource calculating module 704 is further configured to generate a remote takeover queue according to the multiple remote takeover requests and current load information of the multiple control nodes if there is no node idle resource currently; distributing the remote takeover request to a corresponding remote takeover queue according to the remote takeover weight and the resource consumption value of the remote takeover request; and calculating the resource consumption states of the plurality of control nodes, distributing the plurality of control nodes to corresponding remote takeover queues according to the resource consumption states of the plurality of control nodes, and distributing the remote takeover requests to corresponding target control nodes in the corresponding remote takeover queues.
In one embodiment, as shown in fig. 8, there is provided a remote take-over-based vehicle control apparatus including: an anomaly detection module 802, a request sending module 804, an information uploading module 806, and a remote takeover module 808, wherein:
an abnormality detection module 802, configured to obtain driving state information of a vehicle, and perform abnormality detection according to the driving state information; when the driving state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal driving state information;
a request sending module 804, configured to send the remote takeover request to the central server; enabling the central server to generate a remote take-over task according to the remote take-over request, and distributing the remote take-over task to a corresponding target control node;
the information uploading module 806 is configured to acquire a remote takeover instruction sent by the target control node, and send vehicle return information to the target control node according to the remote takeover instruction; and
and the remote take-over module 808 is configured to receive a remote control instruction issued by the target control node according to the vehicle return information, and control the vehicle according to the remote control instruction.
In one embodiment, the driving status information includes vehicle status information, and the anomaly detection module 802 is further configured to send a fault monitoring command to the automatic driving system according to a preset frequency; detecting abnormal states and driving abnormal states of the sensors according to the fault monitoring instruction and the vehicle state information to obtain a detection result; and if the detection result comprises abnormal information, determining vehicle fault information in the abnormal information, and determining the abnormal information to identify the abnormal type and the abnormal grade.
In one embodiment, the driving status information includes road image information, and the anomaly detection module 802 is further configured to perform road identification and obstacle identification on the road image information through a road identification model to obtain a road identification result; and controlling the vehicle to stop when the road identification result has road abnormity or road obstacles, and generating road abnormity information according to the identification result.
In one embodiment, the remote takeover module 808 is further configured to receive an abnormal information identification result and operation prompt information sent by the target control node; controlling the automatic driving of the vehicle according to the abnormal information identification result and the operation prompt information; and continuously detecting the running state information of the vehicle until the abnormal information is detected to be removed and the running state of the vehicle is a normal state, and ending the remote takeover task.
In one embodiment, the remote takeover module 808 is further configured to send the vehicle return information to the target control node according to the remote takeover instruction, so that the target control node performs anomaly analysis according to the anomaly information and the vehicle return information; if the abnormal condition of the vehicle is that remote intervention is not needed, receiving a takeover ending instruction issued by the target control node, wherein the takeover ending instruction comprises prompt information; and switching the remote takeover mode to an automatic driving mode, and controlling the automatic driving of the vehicle according to the driving state information and the prompt information.
For specific definition of the vehicle control device based on remote take-over, reference may be made to the above definition of the vehicle control method based on remote take-over, which is not described herein again. The various modules in the remote take-over based vehicle control apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a central server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operating system and execution of computer-readable instructions in the non-volatile storage medium. The database of the computer device is used for storing data such as remote takeover requests, driving state information, control node information and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions, when executed by a processor, implement a remote takeover-based vehicle control method.
In one embodiment, a computer device is provided, which may be a vehicle, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operating system and execution of computer-readable instructions in the non-volatile storage medium. The database of the computer device is used for storing data such as driving state information, road image information and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions, when executed by a processor, implement a remote takeover-based vehicle control method.
Those skilled in the art will appreciate that the configurations shown in fig. 9 and 10 are merely block diagrams of some configurations relevant to the present disclosure, and do not constitute a limitation on the computing devices to which the present disclosure may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
One or more non-transitory computer-readable storage media storing computer-readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the above-described method embodiments.
It will be understood by those of ordinary skill in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a non-volatile computer readable storage medium, and when executed, can include processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (20)
- A method for vehicle control based on remote takeover, comprising:receiving remote takeover requests sent by a plurality of vehicles, wherein the remote takeover requests carry abnormal information;calculating the remote takeover weight of the remote takeover request according to the abnormal information;acquiring current load information of a plurality of control nodes, and calculating node idle resources according to the current load information;distributing a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resource; andand generating a remote takeover task according to the remote takeover request, and distributing the remote takeover task to the target control node, so that the target control node remotely takes over the corresponding vehicle.
- The method of claim 1, wherein calculating a remote takeover weight for the remote takeover request based on the anomaly information comprises:extracting the abnormal type and the vehicle fault information in the abnormal information;determining a vehicle abnormal degree value and a take-over emergency degree value according to the abnormal type and the vehicle fault information; andand calculating the remote takeover weight of the remote takeover request according to the vehicle abnormal degree value and the takeover emergency degree value.
- The method of claim 1, wherein obtaining current load information of a plurality of control nodes and calculating node idle resources according to the current load information comprises:calling a resource allocation model, and analyzing the current load information and the node performance parameters of the plurality of control nodes through the resource allocation model to obtain the current load weights of the plurality of control nodes;acquiring a task to be processed of a control node, and calculating the node resource utilization rate of each control node according to the current load weight and the task to be processed; andand calculating the node idle resources of the plurality of control nodes according to the current load weight and the node resource utilization rate.
- The method according to claim 3, wherein said allocating a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resources comprises:predicting a corresponding resource consumption value according to the remote takeover weight by utilizing the resource distribution model;calculating matched node idle resources according to the remote takeover weight and the resource consumption value of the remote takeover request; and determining a target control node corresponding to the remote takeover request according to the matched node idle resources, and distributing the remote takeover request to the corresponding target control node.
- The method of claim 4, further comprising:if no node idle resource exists at present, generating a remote takeover queue according to a plurality of remote takeover requests and current load information of a plurality of control nodes;distributing the remote takeover request to a corresponding remote takeover queue according to the remote takeover weight and the resource consumption value of the remote takeover request; andand calculating the resource consumption states of the plurality of control nodes, distributing the plurality of control nodes to corresponding remote takeover queues according to the resource consumption states of the plurality of control nodes, and distributing the remote takeover requests to corresponding target control nodes in the corresponding remote takeover queues.
- A method for vehicle control based on remote takeover, comprising:acquiring running state information of a vehicle, and performing abnormality detection according to the running state information;when the driving state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal driving state information;sending the remote takeover request to a central server; enabling the central server to generate a remote take-over task according to the remote take-over request, and distributing the remote take-over task to a corresponding target control node;acquiring a remote takeover instruction sent by the target control node, and sending vehicle return information to the target control node according to the remote takeover instruction; andand receiving a remote control instruction issued by the target control node according to the vehicle return information, and controlling the vehicle according to the remote control instruction.
- The method according to claim 6, wherein the running state information includes vehicle state information, and the performing abnormality detection based on the running state information includes:sending a fault monitoring instruction to an automatic driving system according to a preset frequency;detecting abnormal states and driving abnormal states of a plurality of sensors according to the fault monitoring instruction and the vehicle state information to obtain a detection result; andand if the detection result comprises abnormal information, determining vehicle fault information in the abnormal information, and determining the abnormal information to identify the abnormal type and the abnormal grade.
- The method according to claim 6, wherein the driving state information includes road image information, and the performing abnormality detection based on the driving state information includes:performing road identification and obstacle identification on the road image information through a road identification model to obtain a road identification result;and when the road identification result has road abnormity or road obstacles, controlling the vehicle to stop, and generating road abnormity information according to the identification result.
- The method according to claim 6, wherein after the allocating the remote takeover task to the corresponding target control node, further comprising:receiving an abnormal information identification result and operation prompt information sent by the target control node;controlling the automatic driving of the vehicle according to the abnormal information identification result and the operation prompt information; andand continuously detecting the running state information of the vehicle until the abnormal information is removed and the running state of the vehicle is a normal state, and ending the remote takeover task.
- The method of claim 6, further comprising:sending vehicle return information to the target control node according to the remote takeover instruction, so that the target control node performs anomaly analysis according to the anomaly information and the vehicle return information;if the abnormal condition of the vehicle is that remote intervention is not needed, receiving a takeover ending instruction issued by the target control node, wherein the takeover ending instruction comprises prompt information; andand switching the remote takeover mode to an automatic driving mode, and controlling the automatic driving of the vehicle according to the driving state information and the prompt information.
- A remote take-over based vehicle control apparatus comprising:the system comprises a request receiving module, a request receiving module and a processing module, wherein the request receiving module is used for receiving remote takeover requests sent by a plurality of vehicles, and the remote takeover requests carry abnormal information;the resource calculation module is used for calculating the remote takeover weight of the remote takeover request according to the abnormal information; acquiring current load information of a plurality of control nodes, and calculating node idle resources according to the current load information; distributing a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resource; andand the task distribution module is used for generating a remote takeover task according to the remote takeover request and distributing the remote takeover task to the target control node so that the target control node remotely takes over the corresponding vehicle.
- A remote take-over based vehicle control apparatus comprising:the abnormality detection module is used for acquiring the running state information of the vehicle and carrying out abnormality detection according to the running state information; when the driving state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal driving state information;the request sending module is used for sending the remote takeover request to a central server; enabling the central server to generate a remote take-over task according to the remote take-over request, and distributing the remote take-over task to a corresponding target control node;the information uploading module is used for acquiring a remote takeover instruction sent by the target control node and sending vehicle return information to the target control node according to the remote takeover instruction; andand the remote take-over module is used for receiving a remote control instruction issued by the target control node according to the vehicle return information and controlling the vehicle according to the remote control instruction.
- A computer device comprising a memory and one or more processors, the memory having stored therein computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform the steps of:receiving remote takeover requests sent by a plurality of vehicles, wherein the remote takeover requests carry abnormal information;calculating the remote takeover weight of the remote takeover request according to the abnormal information;acquiring current load information of a plurality of control nodes, and calculating node idle resources according to the current load information;distributing a corresponding target control node for the remote takeover request according to the remote takeover weight and the node idle resource; andand generating a remote takeover task according to the remote takeover request, and distributing the remote takeover task to the target control node, so that the target control node remotely takes over the corresponding vehicle.
- The computer device of claim 13, wherein the processor, when executing the computer readable instructions, further performs the steps of: predicting a corresponding resource consumption value according to the remote takeover weight by utilizing the resource distribution model; calculating matched node idle resources according to the remote takeover weight and the resource consumption value of the remote takeover request; and determining a target control node corresponding to the remote takeover request according to the matched node idle resources, and distributing the remote takeover request to the corresponding target control node.
- The computer device of claim 14, wherein the processor, when executing the computer readable instructions, further performs the steps of: if no node idle resource exists at present, generating a remote takeover queue according to a plurality of remote takeover requests and current load information of a plurality of control nodes; distributing the remote takeover request to a corresponding remote takeover queue according to the remote takeover weight and the resource consumption value of the remote takeover request; and calculating the resource consumption states of the plurality of control nodes, distributing the plurality of control nodes to corresponding remote takeover queues according to the resource consumption states of the plurality of control nodes, and distributing the remote takeover requests to corresponding target control nodes in the corresponding remote takeover queues.
- A computer device comprising a memory and one or more processors, the memory having stored therein computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform the steps of:acquiring running state information of a vehicle, and performing abnormality detection according to the running state information;when the driving state information is abnormal, controlling the vehicle to stop, and generating a remote takeover request according to the abnormal driving state information;sending the remote takeover request to a central server; enabling the central server to generate a remote take-over task according to the remote take-over request, and distributing the remote take-over task to a corresponding target control node;acquiring a remote takeover instruction sent by the target control node, and sending vehicle return information to the target control node according to the remote takeover instruction; andand receiving a remote control instruction issued by the target control node according to the vehicle return information, and controlling the vehicle according to the remote control instruction.
- The computer device of claim 16, wherein the processor, when executing the computer readable instructions, further performs the steps of: receiving an abnormal information identification result and operation prompt information sent by the target control node; controlling the automatic driving of the vehicle according to the abnormal information identification result and the operation prompt information; and continuously detecting the running state information of the vehicle until the abnormal information is removed and the running state of the vehicle is a normal state, and ending the remote takeover task.
- The computer device of claim 16, wherein the processor, when executing the computer readable instructions, further performs the steps of: sending vehicle return information to the target control node according to the remote takeover instruction, so that the target control node performs anomaly analysis according to the anomaly information and the vehicle return information; if the abnormal condition of the vehicle is that remote intervention is not needed, receiving a takeover ending instruction issued by the target control node, wherein the takeover ending instruction comprises prompt information; and switching the remote takeover mode to an automatic driving mode, and controlling the automatic driving of the vehicle according to the driving state information and the prompt information.
- One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of any of claims 1-5.
- One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of any of claims 6 to 10.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2019/129923 WO2021134217A1 (en) | 2019-12-30 | 2019-12-30 | Vehicle control method and apparatus based on remote takeover, and computer device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113366399A true CN113366399A (en) | 2021-09-07 |
Family
ID=76687136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980037715.5A Pending CN113366399A (en) | 2019-12-30 | 2019-12-30 | Vehicle control method and device based on remote takeover and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113366399A (en) |
| WO (1) | WO2021134217A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114035559A (en) * | 2021-11-17 | 2022-02-11 | 联通智网科技股份有限公司 | Remote driving take-over method, device and system, storage medium and electronic equipment |
| CN114326727A (en) * | 2021-12-24 | 2022-04-12 | 广州小鹏自动驾驶科技有限公司 | Driving method and system |
| CN114387802A (en) * | 2021-12-27 | 2022-04-22 | 江苏徐工工程机械研究院有限公司 | Remote pipe connection system and method for unmanned mining truck of surface mine |
| CN114464006A (en) * | 2022-04-13 | 2022-05-10 | 新石器慧通（北京）科技有限公司 | Method and device for allocating autonomous vehicles |
| CN114550476A (en) * | 2021-11-30 | 2022-05-27 | 深圳元戎启行科技有限公司 | Data processing method, vehicle management platform and computer readable storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105007998A (en) * | 2012-06-06 | 2015-10-28 | 通用电气公司 | System and method for computing |
| CN105959395A (en) * | 2016-06-15 | 2016-09-21 | 徐州医科大学 | Cluster self-feedback type load balancing scheduling system and method |
| CN106232444A (en) * | 2014-03-03 | 2016-12-14 | 谷歌公司 | Remote assistance to the autonomous vehicle in predetermined case |
| CN107505944A (en) * | 2017-09-27 | 2017-12-22 | 驭势科技（北京）有限公司 | A kind of method and apparatus for being used to carry out vehicle remote assistance |
| CN107784850A (en) * | 2016-08-26 | 2018-03-09 | 中兴通讯股份有限公司 | A kind of automatic driving vehicle control method, terminal, server and system |
| CN108819945A (en) * | 2018-05-25 | 2018-11-16 | 吉利汽车研究院（宁波）有限公司 | A kind of automatic driving vehicle adapter tube suggestion device and method |
| CN110032176A (en) * | 2019-05-16 | 2019-07-19 | 广州文远知行科技有限公司 | Long-range adapting method, device, equipment and the storage medium of pilotless automobile |
| CN110083161A (en) * | 2019-05-16 | 2019-08-02 | 广州文远知行科技有限公司 | Long-range adapting method, device, equipment and the storage medium of pilotless automobile |
| CN110377000A (en) * | 2018-04-13 | 2019-10-25 | 北京智行者科技有限公司 | A kind of long-range dispensing control system of automatic driving vehicle and method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008042451A (en) * | 2006-08-04 | 2008-02-21 | Nec Corp | Wireless lan network system, policy control device, access point, and load control method |
| JP6042794B2 (en) * | 2013-12-03 | 2016-12-14 | 本田技研工業株式会社 | Vehicle control method |
| CN105578527B (en) * | 2015-12-11 | 2019-04-16 | 迈普通信技术股份有限公司 | Realize the method, apparatus and system of cloud AC load balancing |
| CN108282502B (en) * | 2017-01-05 | 2020-07-10 | 上海竺程信息科技有限公司 | Vehicle network message optimization broadcasting method based on dynamic priority |
| CN109116720A (en) * | 2018-08-31 | 2019-01-01 | 百度在线网络技术（北京）有限公司 | Long-range control method, device and the server of automatic driving vehicle |
-
2019
- 2019-12-30 CN CN201980037715.5A patent/CN113366399A/en active Pending
- 2019-12-30 WO PCT/CN2019/129923 patent/WO2021134217A1/en active Application Filing
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105007998A (en) * | 2012-06-06 | 2015-10-28 | 通用电气公司 | System and method for computing |
| CN106232444A (en) * | 2014-03-03 | 2016-12-14 | 谷歌公司 | Remote assistance to the autonomous vehicle in predetermined case |
| CN105959395A (en) * | 2016-06-15 | 2016-09-21 | 徐州医科大学 | Cluster self-feedback type load balancing scheduling system and method |
| CN107784850A (en) * | 2016-08-26 | 2018-03-09 | 中兴通讯股份有限公司 | A kind of automatic driving vehicle control method, terminal, server and system |
| CN107505944A (en) * | 2017-09-27 | 2017-12-22 | 驭势科技（北京）有限公司 | A kind of method and apparatus for being used to carry out vehicle remote assistance |
| CN110377000A (en) * | 2018-04-13 | 2019-10-25 | 北京智行者科技有限公司 | A kind of long-range dispensing control system of automatic driving vehicle and method |
| CN108819945A (en) * | 2018-05-25 | 2018-11-16 | 吉利汽车研究院（宁波）有限公司 | A kind of automatic driving vehicle adapter tube suggestion device and method |
| CN110032176A (en) * | 2019-05-16 | 2019-07-19 | 广州文远知行科技有限公司 | Long-range adapting method, device, equipment and the storage medium of pilotless automobile |
| CN110083161A (en) * | 2019-05-16 | 2019-08-02 | 广州文远知行科技有限公司 | Long-range adapting method, device, equipment and the storage medium of pilotless automobile |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114035559A (en) * | 2021-11-17 | 2022-02-11 | 联通智网科技股份有限公司 | Remote driving take-over method, device and system, storage medium and electronic equipment |
| CN114550476A (en) * | 2021-11-30 | 2022-05-27 | 深圳元戎启行科技有限公司 | Data processing method, vehicle management platform and computer readable storage medium |
| CN114326727A (en) * | 2021-12-24 | 2022-04-12 | 广州小鹏自动驾驶科技有限公司 | Driving method and system |
| CN114387802A (en) * | 2021-12-27 | 2022-04-22 | 江苏徐工工程机械研究院有限公司 | Remote pipe connection system and method for unmanned mining truck of surface mine |
| CN114464006A (en) * | 2022-04-13 | 2022-05-10 | 新石器慧通（北京）科技有限公司 | Method and device for allocating autonomous vehicles |
| CN114464006B (en) * | 2022-04-13 | 2022-06-28 | 新石器慧通（北京）科技有限公司 | Method and device for allocating automatic driving vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021134217A1 (en) | 2021-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113366399A (en) | Vehicle control method and device based on remote takeover and computer equipment | |
| US11657718B2 (en) | Method for controlling vehicle platoon, device, and internet of vehicles system | |
| US20200074769A1 (en) | Vehicle Fault Handling Method, Apparatus, Device and Storage Medium | |
| US10991177B2 (en) | Method for processing vehicle fault, apparatus, device, and storage medium | |
| CN110949406B (en) | Intelligent driving system and method | |
| US20190047581A1 (en) | Method and apparatus for supporting mission-critical applications via computational cloud offloading | |
| US20150207859A1 (en) | Vehicle-specific computation management system for cloud computing | |
| US10916072B2 (en) | Self-maintaining autonomous vehicle procedure | |
| CN107464416B (en) | Semi-automatic driving method and system for bus | |
| CN113424023A (en) | Vehicle control method and device based on network monitoring and computer equipment | |
| US20230040713A1 (en) | Simulation method for autonomous vehicle and method for controlling autonomous vehicle | |
| CN115257810A (en) | Unmanned vehicle parallel connection pipe control method and device, cloud control platform and electronic equipment | |
| CN108820247B (en) | Unmanned aerial vehicle cluster monitoring method and system suitable for cluster waypoint task | |
| CN116868248A (en) | Method for supporting a plurality of motor vehicles by an infrastructure | |
| CN113341955A (en) | Control method, device and equipment for automatic driving vehicle and storage medium | |
| CN113844465B (en) | Automatic driving method and system | |
| US20220147394A1 (en) | Concept for data processing for an at least partially automated guidance of a motor vehicle | |
| EP4074562A1 (en) | Control system and control method for intelligent connected vehicle | |
| CN113442948A (en) | Automatic driving method and device based on cloud reasoning service and computer equipment | |
| US11955010B2 (en) | System and method for providing situational awareness interfaces for autonomous vehicle operators | |
| US20230311941A1 (en) | Server device, control circuit, storage medium, and traffic support method | |
| US20240119765A1 (en) | Log management apparatus, log management method, and non-transitory computer readable recording medium | |
| US20240067216A1 (en) | Verification of vehicle prediction function | |
| KR20180058196A (en) | Method and apparatus for providing service of traffic safety based on decision layer model | |
| CN117775011A (en) | Automatic driving vehicle exception handling method, device, equipment and storage medium |
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 |