CN114280960A - Automatic driving simulation method and device, storage medium and electronic equipment - Google Patents
Automatic driving simulation method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN114280960A CN114280960A CN202111633464.2A CN202111633464A CN114280960A CN 114280960 A CN114280960 A CN 114280960A CN 202111633464 A CN202111633464 A CN 202111633464A CN 114280960 A CN114280960 A CN 114280960A
- Authority
- CN
- China
- Prior art keywords
- simulation
- simulation object
- simulated
- motion data
- motion
- 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
Images
Abstract
The specification discloses an automatic driving simulation method and device, a storage medium and electronic equipment. Can be applied to the field of automatic driving. By configuring the corresponding control strategy for each simulated obstacle generated in the simulation environment, the motion track of the simulated obstacle can be planned according to the control strategy corresponding to each simulated obstacle in the simulation process according to the predicted track of each simulated obstacle, so that the simulated obstacle can react according to the real-time motion state of other obstacles in the simulation environment, the intelligence of the simulated obstacle is improved, and the unmanned vehicle to be tested can obtain more accurate test data.
Description
Technical Field
The present disclosure relates to the field of simulation testing, and in particular, to an automatic driving simulation method, an automatic driving simulation device, a storage medium, and an electronic device.
Background
In order to ensure the safety of a vehicle (hereinafter referred to as an unmanned vehicle) using an automatic driving technology during driving, a large number of tests are generally required for a control strategy and an algorithm of the unmanned vehicle.
In the prior art, besides real vehicle testing, an unmanned vehicle can be placed in a simulation environment in a mode of establishing the simulation environment, and a control strategy and an algorithm of the unmanned vehicle are debugged by utilizing a running condition of the unmanned vehicle in the simulation environment.
Generally speaking, the simulated obstacles in the simulated environment can be generated by two ways, including real vehicle acquisition, simulated obstacles generated by the acquired data of real obstacles, simulated obstacles which do not actually exist and set the motion trail in the simulated scene by artificial design or according to machine learning algorithm.
However, the simulation barrier generated by the two modes cannot interact with the unmanned vehicle when moving in a simulation environment, namely, the simulation barrier cannot react according to the real-time motion state of the unmanned vehicle to be tested, and the accuracy of the simulation system is poor.
Disclosure of Invention
The present specification provides an automatic driving simulation method, an automatic driving simulation apparatus, a storage medium, and an electronic device, which partially solve the above problems in the prior art.
The technical scheme adopted by the specification is as follows:
the present specification provides an automatic driving simulation method, including:
loading a pre-constructed simulation environment by a simulation system; generating a plurality of simulated obstacles based on the pre-configured obstacle parameters; generating a simulated main vehicle corresponding to the unmanned vehicle based on the unmanned vehicle to be detected;
taking the generated simulated main vehicle and each simulated obstacle as a simulated object in the simulated environment, and placing each simulated object in the simulated environment;
for each simulation object, controlling the simulation object to move in the simulation environment according to the control strategy of the simulation object, and determining the motion data of the simulation object in the motion process of the simulation object;
predicting the future motion track of each simulation object according to the determined motion data of each simulation object to obtain the predicted track of each simulation object;
and controlling each simulation object to plan a motion track according to the control strategy of the simulation object and to move according to the planned reference track according to the predicted tracks of other simulation objects.
Optionally, for each simulation object, the control strategy of the simulation object is not identical to the control strategies of the other simulation objects.
Optionally, in the process of the motion of the simulation object, determining the motion data of the simulation object specifically includes:
during the process of the motion of the simulation object, determining the current motion data of the simulation object at a preset period, wherein the motion data at least comprises a position and a speed.
Optionally, predicting a future motion trajectory of each simulation object according to the determined motion data of each simulation object, specifically including:
and for each simulation object, determining the motion data of the simulation object as the basic motion data of the simulation object, determining the motion data of other simulation objects except the simulation object as the environmental motion data of the simulation object, and predicting the motion trail of the simulation object in the future according to the basic motion data and the environmental motion data of the simulation object.
Optionally, the motion data comprises at least a location;
determining the motion data of other simulation objects except the simulation object as the environment motion data of the simulation object, specifically including:
and determining the motion data of other simulation objects with the distance between the other simulation objects and the simulation object smaller than a specified distance threshold value as the environment motion data of the simulation object according to the position of each simulation object contained in the motion data.
Optionally, controlling the simulation object to plan a motion trajectory according to the control strategy of the simulation object itself according to the predicted trajectories of other simulation objects specifically includes:
and controlling the simulation object to plan the motion track by taking the simulation object not to be at the same position with other simulation objects at the same time according to the predicted track of other simulation objects and the bounding boxes preset for other simulation objects.
Optionally, the simulation system is a distributed system.
Optionally, each simulation object is controlled by a different node in the simulation system.
Optionally, the simulation system at least includes a sensing node shared by the simulation objects, where the sensing node is configured to determine, for each simulation object, motion data of the simulation object in a process of motion of the simulation object.
Optionally, the simulation system at least includes a prediction node shared by each simulation object, where the prediction node is configured to predict a future motion trajectory of each simulation object according to the determined motion data of each simulation object, so as to obtain a predicted trajectory of each simulation object.
The present specification provides an automatic driving simulation apparatus including:
the generating module is used for loading a pre-constructed simulation environment; generating a plurality of simulated obstacles based on the pre-configured obstacle parameters; generating a simulated main vehicle corresponding to the unmanned vehicle based on the unmanned vehicle to be detected;
the placement module is used for taking the generated simulated main vehicle and each simulated obstacle as a simulated object in the simulation environment and placing each simulated object in the simulation environment;
the sensing module is used for controlling each simulation object to move in the simulation environment according to the control strategy of the simulation object per se and determining the motion data of the simulation object in the motion process of the simulation object;
the prediction module is used for predicting the future motion trail of each simulation object according to the determined motion data of each simulation object to obtain the predicted trail of each simulation object;
and the control module is used for controlling each simulation object to plan a motion track according to the predicted track of other simulation objects and the control strategy of the simulation object, and moving according to the planned reference track.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described automatic driving simulation method.
The present specification provides an unmanned aerial vehicle comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above described autopilot simulation method when executing the program.
The technical scheme adopted by the specification can achieve the following beneficial effects:
in the automatic driving simulation method provided by the specification, a corresponding control strategy is configured for each simulated obstacle generated in the simulation environment, and in the simulation process, the motion trajectory of the simulated obstacle can be planned according to the predicted trajectory of each simulated obstacle and the control strategy corresponding to each simulated obstacle, so that the simulated obstacle can react according to the real-time motion state of other obstacles in the simulation environment, the intelligence of the simulated obstacle is improved, and the unmanned vehicle to be tested can obtain more accurate test data.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:
FIG. 1 is a schematic flow chart of an automatic driving simulation method of the present disclosure;
FIG. 2 is a schematic structural diagram of a simulation system provided in the present specification;
FIG. 3 is a schematic diagram of an autopilot simulation apparatus provided herein;
fig. 4 is a schematic structural diagram of the unmanned aerial vehicle provided in this specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
The automatic driving simulation method provided by the embodiment of the specification aims to replace a real vehicle test with large debugging cost and period by running a virtual unmanned vehicle to be tested in a constructed simulation environment including a simulation obstacle, and debug a control strategy and a control algorithm of the unmanned vehicle according to an obtained simulation result (for example, whether the unmanned vehicle to be tested collides with the simulation obstacle).
On the basis, the automatic driving simulation method provided by the embodiment of the specification allocates a corresponding control strategy for each generated simulated obstacle, and in the simulation process, the motion trajectory of the simulated obstacle can be planned according to the predicted trajectory of each simulated obstacle and the control strategy corresponding to each simulated obstacle, so that the simulated obstacle can react according to the real-time motion state of other obstacles in the simulation environment, the intelligence of the simulated obstacle is improved, and the unmanned vehicle to be tested can obtain more accurate test data.
Fig. 1 is a schematic flow chart of an automatic driving simulation method in this specification, which specifically includes the following steps:
s100: loading a pre-constructed simulation environment by a simulation system; generating a plurality of simulated obstacles based on the pre-configured obstacle parameters; and generating a simulated main vehicle corresponding to the unmanned vehicle based on the unmanned vehicle to be detected.
The execution main body of the automatic driving simulation method provided by the present specification is a simulation system, the simulation system may be a single server or a single terminal device, for example, may be an unmanned vehicle to be tested, and the simulation system may also be a distributed system composed of distributed servers or distributed terminal devices, in which case, the simulation system may include a node composed of the unmanned vehicle to be tested. In an embodiment of the present specification, a distributed system formed by a plurality of nodes is taken as an example for description. Further, the simulation system may be as shown in FIG. 2.
Before executing the automatic driving simulation method provided in this specification, it is necessary to complete the construction of the simulation environment and configure parameters of each simulated obstacle.
For example, a collection vehicle may be used to run on a real road in advance, and environmental data and obstacle data during the running process of the collection vehicle may be recorded by a sensor (e.g., a camera, a radar, etc.) mounted on the collection vehicle, where the environmental data may include traffic road data, traffic light data, etc., the obstacle data may include the type of an obstacle (e.g., a motor vehicle, a non-motor vehicle, a pedestrian, etc.), the position of the obstacle, etc., and since a bounding box (i.e., a geometric body that is slightly larger in volume and simple in shape compared with the obstacle itself) is usually used to replace the volume of the obstacle, the bounding box corresponding to the obstacle may also be included in the obstacle data. The present specification does not limit what kind of data is specifically included in the environment data and the obstacle data.
Then, the real environment and the real obstacles in reality can be reproduced according to the acquired environment data and the acquired obstacle data, and the constructed simulation environment and each simulation obstacle in the simulation environment are obtained.
For another example, the parameters of the simulated obstacle may be configured and the virtual simulation environment may be constructed by human design or by using a machine learning model. The parameters of the simulated obstacle may be similar to the obstacle data collected by the above-mentioned collection vehicle, and the virtual simulated environment may be obtained by combining several environmental elements, which may include traffic roads, traffic signs, signal lights, roadside buildings, overpasses, and so on.
Of course, a virtual simulated obstacle obtained by considering design or machine learning model generation may also be placed in a simulated environment obtained by restoring the acquired real environment, the above is only an exemplary method for constructing the simulated environment and configuring the simulated obstacle parameters exemplarily shown in this specification, and the present specification does not limit how to construct the simulated environment and how to configure the parameters of the simulated obstacle.
It should be noted that, in the automatic driving simulation method provided in this specification, what kind of trajectory the simulated obstacle moves in is not preset for the simulated obstacle when the simulated obstacle is generated, but a corresponding control strategy is configured for each simulated obstacle, so that in the simulation process, the simulated obstacle can be controlled to move according to the control strategy corresponding to each simulated obstacle. In an embodiment of the present specification, for each simulation object, the control policy of the simulation object may not be identical to the control policies of other simulation objects.
In addition, a virtual simulated main vehicle corresponding to the unmanned vehicle needs to be generated based on the unmanned vehicle to be detected.
The unmanned vehicle described in this specification may include an autonomous vehicle and a vehicle having a driving assistance function. The unmanned vehicle may be a delivery vehicle applied to the delivery field.
In the embodiment of the present specification, after the simulation is performed by using the automatic driving simulation method provided by the present specification, the control strategy and algorithm of the unmanned vehicle to be tested are debugged according to the simulation result, for example, the control strategy and algorithm of the unmanned vehicle to be tested may be debugged with a goal that the simulated master vehicle corresponding to the unmanned vehicle to be tested does not collide with each simulated obstacle in the simulation process, and for example, the control strategy and algorithm of the unmanned vehicle to be tested may also be debugged with a goal that the simulated master vehicle corresponding to the unmanned vehicle to be tested does not violate traffic rules in the simulation process when the simulated master vehicle runs based on the control strategy of the simulated master vehicle. The embodiments of the present specification do not limit how the debugging is specifically performed.
In the embodiment of the present specification, when the simulation master vehicle is generated, a motion trail may not be set for the simulation master vehicle, but only data information of the simulation master vehicle, such as maximum speed, maximum acceleration, vehicle shape or bounding box, control strategy, and the like, may be loaded, and during the simulation, the simulation master vehicle is controlled to control the simulation master vehicle to move in the simulation environment based on the data information of the simulation master vehicle itself, so as to obtain a simulation result close to a real vehicle test. It should be noted that the control strategy of the unmanned vehicle to be tested may not be exactly the same as the control strategy of each simulated obstacle.
S102: and taking the generated simulated main vehicle and each simulated obstacle as a simulated object in the simulated environment, and placing each simulated object in the simulated environment.
S104: and for each simulation object, controlling the simulation object to move in the simulation environment according to the control strategy of the simulation object, and determining the motion data of the simulation object in the motion process of the simulation object.
Then, the generated simulated main vehicle and each simulated obstacle may be used as simulated objects in the simulated environment, and a corresponding initial state may be determined for each simulated object, where the initial state at least includes an initial position of the simulated object, and the initial position may be a relative position of the object in the simulated environment, and of course, the initial state may also include an initial velocity, an initial acceleration, and the like of the simulated object.
According to the initial state of each simulation object, each simulation object can be placed in the simulation environment, and for each simulation object, the simulation object is controlled to move in the simulation environment according to the control strategy of the simulation object. For example, the simulation object may be controlled to move in the initial state of the simulation object according to the control strategy of the simulation object itself.
For each simulated object, motion data for the simulated object may be determined during motion of the simulated object. The motion data may include a position, a velocity, an acceleration, a bounding box, etc. of the simulation object, which is not limited by the embodiments herein. Specifically, the current motion data of the simulation object may be determined at a preset first period.
In an embodiment of the present specification, as shown in fig. 2, the automatic driving simulation method provided by the present specification, which is executed by the simulation system, may be divided into a plurality of units, where each node in the simulation system may be used to execute only the function of one unit, or may be used to execute the functions of a plurality of units. The description below takes as an example the function that each node in the simulation system is only used to execute one unit. The node may be a node in a distributed system, and of course, when the simulation system is a single server or terminal device, the node may also refer to a module integrated in the single server or terminal device.
In this case, when the function of the sensing unit is performed, the motion data of the simulation object may be determined in the course of the motion of the simulation object. In an embodiment of this specification, a node (hereinafter referred to as a sensing node) in the simulation system, which executes a function of the sensing unit, may include a sensing pool for storing motion data of the simulation object, and after the motion data of each simulation object is determined each time, the motion data of each simulation object stored in the sensing pool of the node may be updated according to the determined motion data of each simulation object.
S106: and predicting the future motion track of each simulation object according to the determined motion data of each simulation object to obtain the predicted track of each simulation object.
Then, the simulation system can predict the future motion trajectory of each simulation object according to the determined motion data of each simulation object, so as to obtain the predicted trajectory of each simulation object.
In an embodiment of the present specification, a unit that predicts a future motion trajectory of each simulation object based on motion data of each simulation object may be used as the prediction unit, and a node that runs the prediction unit may be used as the prediction node.
In this case, the sensing node sends the motion data of each simulation object included in the sensing pool stored by the sensing node to the prediction node at a preset second period, so that the prediction node predicts the motion trajectory of each simulation object in the future according to the determined motion data of each simulation object.
In the embodiment of the present specification, how to predict the future motion trajectory of each simulation object is not limited, but for example, for each simulation object, the motion data of the simulation object may be determined as the basic motion data of the simulation object, the motion data of other simulation objects except the simulation object may be determined as the environmental motion data of the simulation object, and the future motion trajectory of the simulation object may be predicted according to the basic motion data and the environmental motion data of the simulation object. Of course, the environment motion data may include data of the simulation environment, such as road data, traffic light data, etc., in addition to the motion data of the other simulation objects other than the simulation object.
For example only, the motion tendency of the simulation object may be predicted based on the basic motion data of the simulation object, the motion tendency may include straight running, turning around, turning, etc., then, the road where the simulation object is located in the future may be predicted according to the environmental motion data of the simulation object, and the motion trajectory of the simulation object may be fitted based on the vehicle dynamics model according to the predicted road where the simulation object is located in the future and the current basic motion data of the simulation object as the predicted trajectory of the simulation object.
Of course, the above is merely an example, and the embodiment of the present specification does not limit how to predict the predicted trajectory of the simulation object.
In general, since only the environment around the position of the simulation object is considered when the simulation object moves, in an embodiment of the present specification, when the motion data includes the position of the simulation object, when the motion trajectory of the simulation object is predicted for each simulation object, the motion data of another simulation object whose distance from the simulation object is smaller than a predetermined distance threshold may be determined as the environment motion data of the simulation object, and the motion data of another simulation object whose distance from the simulation object is smaller than 20 meters, for example, may be determined as the environment motion data of the simulation object, based on the position of each simulation object included in the motion data.
In addition, when the motion tendency of the simulation object is determined first, in predicting the motion trajectory of the simulation object, only the other simulation obstacle in the driving tendency direction of the simulation object may be considered, and the motion data of the other simulation obstacle in the driving tendency direction of the simulation object may be determined as the environmental motion data of the simulation object. It can be seen that, the manner of predicting the motion trajectory of each simulation object according to the motion data of each simulation object is various, and the description of this specification is not repeated below.
In any of the above manners, the prediction node may predict the predicted trajectory of each simulation object.
S108: and controlling each simulation object to plan a motion track according to the control strategy of the simulation object and to move according to the planned reference track according to the predicted tracks of other simulation objects.
In an embodiment of this specification, each simulation object corresponds to its own control policy, and then, the simulation system may control, for each simulation object, the simulation object to plan a motion trajectory according to the predicted trajectory of another simulation object except the simulation object according to the own control policy of the simulation object, and to move according to the planned reference trajectory.
In an embodiment of this specification, for each simulation object, a node controlling the simulation object may be referred to as a control node corresponding to the simulation object, where the control node of each simulation object may be a different node. In this case, the node executing the control strategy of the unmanned vehicle to be tested may be the unmanned vehicle to be tested.
In this case, the sensing pool of the sensing node stores the determined motion data of each simulation object, that is, each control node shares the motion data of the corresponding simulation object with the sensing node, and then the prediction node predicts the prediction track of each simulation object according to the motion data of each simulation object in the sensing pool, and shares the predicted prediction track of each simulation object with each control node. Of course, each simulation object may be considered to share the sensing node and the prediction node.
Based on this, the simulation system for executing the automatic driving simulation method described in this specification may be as shown in fig. 2, where the simulation system includes a sensing node for determining motion data of each simulation object, a prediction node for predicting a motion trajectory of each simulation object according to the motion data of each simulation object sent by the sensing node, and a plurality of control nodes for controlling the simulation objects corresponding to the simulation objects, and under the control of the control nodes, the simulation objects plan the motion trajectory according to the control strategy of the simulation objects themselves, and move with the planned reference trajectory. Of course, the simulation system may further include a build node, not shown in FIG. 2, for generating simulation objects, loading the simulation environment, and placing the simulation objects in the simulation environment.
In the embodiment of the present specification, how each control node controls its corresponding simulation object to plan a motion trajectory according to the control strategy of the simulation object is not limited, and for example only, the simulation object may be controlled to plan a motion trajectory according to the control strategy of the simulation object itself, with the motion trajectory not being at the same position as another simulation object at the same time.
In another embodiment of the present specification, for each simulation object, the motion data of the simulation object further includes a bounding box set for the simulation object in advance, specifically, the type of the simulation object may be determined when the simulation object is generated, where the type may include a motor vehicle, a non-motor vehicle, a pedestrian, and the like, and then the corresponding bounding box is determined for each type of simulation object, in which case, when the motion data of the simulation object is determined, the bounding box of the simulation object may be determined.
Then, the sensing node can send the bounding box of each simulation object to the prediction node, so that the prediction node sends the bounding box of each simulation object and the predicted track of each simulation object to each control node, so that each control node controls the simulation object to plan the motion track according to the control strategy of the simulation object by taking the situation that the control node is not at the same position as other simulation objects at the same time according to the predicted track and the bounding box of other simulation objects as a target, and moves by the planned reference track.
In one embodiment of the present description, the reference trajectory may not be a smooth curve, but may be a connection line of several sequential trajectory points, and reference information indicating when, in what state, and where along the reference trajectory the simulation object travels. That is, the reference trajectory described in the present specification may include: the reference time of each track point of the reference track, the reference time of each track point of the simulated object, and the reference state (such as speed, acceleration and the like) of the simulated object when each track point is approached.
It should be noted that, in the simulation process of the automatic driving simulation method provided in this specification, the simulation of the automatic driving process may be implemented by executing the above-mentioned S104-S108 in a loop until the simulation result required for testing the unmanned vehicle to be tested is obtained.
Based on the automatic driving simulation method shown in fig. 1, a corresponding control strategy is configured for each simulated obstacle generated in the simulation environment, and in the simulation process, the motion trajectory of the simulated obstacle can be planned according to the predicted trajectory of each simulated obstacle and the control strategy corresponding to each simulated obstacle, so that the simulated obstacle can react according to the real-time motion state of other obstacles in the simulation environment, the intelligence of the simulated obstacle is improved, and the unmanned vehicle to be tested can obtain more accurate test data.
Based on the same idea, the present specification further provides a corresponding automatic driving simulation apparatus, as shown in fig. 3.
Fig. 3 is a schematic diagram of an automatic driving simulation apparatus provided in the present specification, the apparatus including:
a generating module 300, configured to load a pre-constructed simulation environment; generating a plurality of simulated obstacles based on the pre-configured obstacle parameters; generating a simulated main vehicle corresponding to the unmanned vehicle based on the unmanned vehicle to be detected;
a placement module 302, which takes the generated simulated main vehicle and each simulated obstacle as a simulated object in the simulation environment, and places each simulated object in the simulation environment;
a sensing module 304, configured to control, for each simulation object, the simulation object to move in the simulation environment according to a control policy of the simulation object itself, and determine motion data of the simulation object in a process of the motion of the simulation object;
the prediction module 306 is configured to predict a future motion trajectory of each simulation object according to the determined motion data of each simulation object, so as to obtain a predicted trajectory of each simulation object;
and the control module 308 is configured to, for each simulation object, control the simulation object to plan a motion trajectory according to the predicted trajectory of another simulation object and according to the control strategy of the simulation object itself, and move according to the planned reference trajectory.
Optionally, for each simulation object, the control strategy of the simulation object is not identical to the control strategies of the other simulation objects.
Optionally, the sensing module 304 is specifically configured to determine, in a preset period during the motion of the simulation object, current motion data of the simulation object, where the motion data at least includes a position and a speed.
Optionally, the predicting module 306 is specifically configured to, for each simulation object, determine the motion data of the simulation object as the basic motion data of the simulation object, determine the motion data of other simulation objects except the simulation object as the environmental motion data of the simulation object, and predict a future motion trajectory of the simulation object according to the basic motion data and the environmental motion data of the simulation object.
Optionally, the motion data comprises at least a location; the prediction module 306 is specifically configured to determine, according to the position of each simulation object included in the motion data, the motion data of other simulation objects whose distance from the simulation object is smaller than a specified distance threshold as the environmental motion data of the simulation object.
Optionally, the control module 308 is specifically configured to control the simulation object to plan the motion trajectory with the position different from that of the other simulation object at the same time as the other simulation object as a target according to the control strategy of the simulation object itself, based on the predicted trajectory of the other simulation object and the bounding box preset for the other simulation object.
The present specification also provides a computer-readable storage medium storing a computer program operable to execute the above-described automatic driving simulation method.
The present specification also provides a schematic diagram of the structure of the drone shown in figure 4. As shown in fig. 4, at the hardware level, the drone includes a processor, internal bus, memory, and non-volatile storage, although it may also include hardware needed for other services. The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to realize the automatic driving simulation method.
Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (13)
1. An automated driving simulation method, comprising:
loading a pre-constructed simulation environment by a simulation system; generating a plurality of simulated obstacles based on the pre-configured obstacle parameters; generating a simulated main vehicle corresponding to the unmanned vehicle based on the unmanned vehicle to be detected;
taking the generated simulated main vehicle and each simulated obstacle as a simulated object in the simulated environment, and placing each simulated object in the simulated environment;
for each simulation object, controlling the simulation object to move in the simulation environment according to the control strategy of the simulation object, and determining the motion data of the simulation object in the motion process of the simulation object;
predicting the future motion track of each simulation object according to the determined motion data of each simulation object to obtain the predicted track of each simulation object;
and controlling each simulation object to plan a motion track according to the control strategy of the simulation object and to move according to the planned reference track according to the predicted tracks of other simulation objects.
2. The method of claim 1, wherein, for each simulation object, the control strategy of the simulation object is not identical to the control strategies of other simulation objects.
3. The method of claim 1, wherein determining motion data of the simulated object during the motion of the simulated object comprises:
during the process of the motion of the simulation object, determining the current motion data of the simulation object at a preset period, wherein the motion data at least comprises a position and a speed.
4. The method of claim 1, wherein predicting the future motion trajectory of each simulation object based on the determined motion data of each simulation object comprises:
and for each simulation object, determining the motion data of the simulation object as the basic motion data of the simulation object, determining the motion data of other simulation objects except the simulation object as the environmental motion data of the simulation object, and predicting the motion trail of the simulation object in the future according to the basic motion data and the environmental motion data of the simulation object.
5. The method of claim 4, wherein the motion data includes at least a location;
determining the motion data of other simulation objects except the simulation object as the environment motion data of the simulation object, specifically including:
and determining the motion data of other simulation objects with the distance between the other simulation objects and the simulation object smaller than a specified distance threshold value as the environment motion data of the simulation object according to the position of each simulation object contained in the motion data.
6. The method of claim 1, wherein controlling the simulation object to plan a motion trajectory according to the control strategy of the simulation object itself based on the predicted trajectories of other simulation objects comprises:
and controlling the simulation object to plan the motion track by taking the simulation object not to be at the same position with other simulation objects at the same time according to the predicted track of other simulation objects and the bounding boxes preset for other simulation objects.
7. The method of claim 1, wherein the simulation system is a distributed system.
8. The method of claim 7, wherein each simulation object is controlled by a different node in the simulation system.
9. The method of claim 1, wherein the simulation system comprises at least a sensing node shared by the simulation objects, wherein the sensing node is configured to determine, for each simulation object, motion data of the simulation object during motion of the simulation object.
10. The method of claim 1, wherein the simulation system comprises at least a prediction node shared by the simulation objects, wherein the prediction node is configured to predict a future motion trajectory of each simulation object according to the determined motion data of each simulation object, so as to obtain a predicted trajectory of each simulation object.
11. An automatic driving simulation device, characterized in that, the device specifically includes:
the generating module is used for loading a pre-constructed simulation environment; generating a plurality of simulated obstacles based on the pre-configured obstacle parameters; generating a simulated main vehicle corresponding to the unmanned vehicle based on the unmanned vehicle to be detected;
the placement module is used for taking the generated simulated main vehicle and each simulated obstacle as a simulated object in the simulation environment and placing each simulated object in the simulation environment;
the sensing module is used for controlling each simulation object to move in the simulation environment according to the control strategy of the simulation object per se and determining the motion data of the simulation object in the motion process of the simulation object;
the prediction module is used for predicting the future motion trail of each simulation object according to the determined motion data of each simulation object to obtain the predicted trail of each simulation object;
and the control module is used for controlling each simulation object to plan a motion track according to the predicted track of other simulation objects and the control strategy of the simulation object, and moving according to the planned reference track.
12. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 10.
13. An unmanned aerial vehicle comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method of any of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111633464.2A CN114280960A (en) | 2021-12-29 | 2021-12-29 | Automatic driving simulation method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111633464.2A CN114280960A (en) | 2021-12-29 | 2021-12-29 | Automatic driving simulation method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114280960A true CN114280960A (en) | 2022-04-05 |
Family
ID=80877562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111633464.2A Pending CN114280960A (en) | 2021-12-29 | 2021-12-29 | Automatic driving simulation method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114280960A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116882122A (en) * | 2023-03-17 | 2023-10-13 | 北京百度网讯科技有限公司 | Method and device for constructing simulation environment for automatic driving |
-
2021
- 2021-12-29 CN CN202111633464.2A patent/CN114280960A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116882122A (en) * | 2023-03-17 | 2023-10-13 | 北京百度网讯科技有限公司 | Method and device for constructing simulation environment for automatic driving |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111190427B (en) | Method and device for planning track | |
| CN111208838B (en) | Control method and device of unmanned equipment | |
| CN110414098B (en) | Generation method and device of simulation test environment | |
| CN112766468B (en) | Trajectory prediction method and device, storage medium and electronic equipment | |
| CN110262486B (en) | Unmanned equipment motion control method and device | |
| CN111076739B (en) | Path planning method and device | |
| CN113296541B (en) | Future collision risk based unmanned equipment control method and device | |
| CN111062372B (en) | Method and device for predicting obstacle track | |
| CN112306059A (en) | Training method for control model, control method and device | |
| CN111912423B (en) | Method and device for predicting obstacle trajectory and training model | |
| CN111126362A (en) | Method and device for predicting obstacle track | |
| CN111238523A (en) | Method and device for predicting motion trail | |
| CN113419547A (en) | Multi-vehicle cooperative control method and device | |
| CN113341941A (en) | Control method and device of unmanned equipment | |
| CN113343425B (en) | Simulation test method and device | |
| CN113968243B (en) | Obstacle track prediction method, device, equipment and storage medium | |
| CN114280960A (en) | Automatic driving simulation method and device, storage medium and electronic equipment | |
| CN110895406B (en) | Method and device for testing unmanned equipment based on interferent track planning | |
| CN111123957B (en) | Method and device for planning track | |
| CN114019971B (en) | Unmanned equipment control method and device, storage medium and electronic equipment | |
| CN113340311B (en) | Path planning method and device for unmanned equipment | |
| CN112925210B (en) | Method and device for model training and unmanned equipment control | |
| CN114721290A (en) | Simulation test scene generation method and device, storage medium and electronic equipment | |
| CN112684720A (en) | Simulation test method and device | |
| CN114194213A (en) | Target object trajectory prediction method and device, storage medium and electronic equipment |
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 |