Simulation device and method based on external trigger information

Abstract

To provide a device and method for executing a simulation by controlling the operation algorithm of an external object in the simulation aiming at verifying an autonomous driving algorithm.SOLUTION: One embodiment of the present disclosure provides a method for executing a simulation includes the step of: (110) obtaining external trigger information regarding operation of a peripheral object; (130) determining a first input of a peripheral object control algorithm that corresponds to the external trigger information regarding the operation of the peripheral object; (150) determining a first output of the peripheral object control algorithm on the basis of the first input; and (170) providing the first output to a peripheral object management device.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an apparatus and method for performing a simulation, and more particularly to an apparatus and method for performing a simulation by controlling the operation algorithm of an external object in a simulation for the purpose of verifying an autonomous driving algorithm. [Background technology]

[0002] An autonomous vehicle is a vehicle that can navigate independently without driver input. It uses radar, LiDAR, GPS, cameras, and other technologies to recognize its surroundings and navigate autonomously by simply specifying a destination. For such autonomous vehicles to be commercialized, their safety must be guaranteed. Testing the safety of autonomous vehicles by conducting test drives on real roads using actual vehicles is somewhat challenging due to the high time and financial costs and high risk of accidents. To overcome these challenges, ongoing autonomous driving technology research is being conducted by implementing various road conditions in virtual environment simulators. However, since simulations are typically based on rule-based judgments, driving patterns are predetermined, limiting the ability to directly reproduce irregular human driving behaviors, such as restarting after a stop or returning to a lane after a lane change, in a simulated environment. Nevertheless, for the commercialization of autonomous driving, it is necessary to proactively address irregular human driving behaviors, and this disclosure aims to achieve this. Summary of the Invention [Problem to be solved by the invention]

[0003] An embodiment of the present disclosure aims to provide a simulation device and method based on external trigger information.

[0004] Another object of one embodiment of the present disclosure is to provide an automatic driving simulation device and method that can also handle irregular driving situations. [Means for solving the problem]

[0005] An embodiment of the present disclosure aims to provide a simulation device and method based on external trigger information.

[0006] In one embodiment of the present disclosure, an object is to provide a peripheral object control algorithm management device that includes a memory that stores one or more instructions and at least one processor that executes the one or more instructions stored in the memory, wherein the at least one processor, by executing the one or more instructions, acquires external trigger information regarding the operation of a peripheral object, determines a first input of a peripheral object control algorithm that corresponds to the external trigger information regarding the operation of the peripheral object, determines a first output of the peripheral object control algorithm based on the first input, and provides the first output to the peripheral object management device.

[0007] In one embodiment, the external trigger information regarding the behavior of the peripheral object may include a user input for changing the behavior of the peripheral object, trigger information regarding the behavior of the peripheral object determined by an artificial intelligence learning model, and at least one specific value determined by a random function.

[0008] In one embodiment, the at least one processor, by executing the one or more instructions, can obtain scenario information regarding a driving pattern including at least one of a target speed, acceleration, a driving lane, and a destination, determine a second output of the peripheral object control algorithm based on the scenario information, send the second output to the peripheral object management device, receive operation information of the peripheral object from the peripheral object management device, and receive operation information of the autonomous driving target from the autonomous driving target management device.

[0009] In one embodiment, the at least one processor, by executing the one or more instructions, can receive scenario information including condition information for changing an operation pattern, identify a trigger event for changing the operation pattern based on the condition information for changing the operation pattern, determine a third output of the peripheral object control algorithm based on the operation pattern corresponding to the trigger event for changing the operation pattern, and send the third output to the peripheral object management device.

[0010] One embodiment of the present disclosure aims to provide a simulation device that includes a peripheral object management device that receives scenario information and a peripheral object control algorithm to control peripheral objects, and an autonomous driving target management device that receives the scenario information and the autonomous driving target control algorithm to control autonomous driving targets, wherein the peripheral object management device receives external trigger information as input, receives a first output determined by the peripheral object control algorithm from the peripheral object control algorithm management device, and controls the peripheral objects based on the first output.

[0011] In one embodiment, the external trigger information may include a user input for modifying the behavior of a peripheral object, trigger information regarding the behavior of a peripheral object determined by an artificial intelligence learning model, and at least one input determined by a random function.

[0012] In one embodiment, the simulation device may further include a peripheral object control algorithm management device for acquiring the external trigger information, determining the first output of the peripheral object control algorithm based on the external trigger information, and providing the first output to the peripheral object management device.

[0013] In one embodiment, the peripheral object control algorithm management device may be a device separate from the simulation device.

[0014] In one embodiment, the peripheral object management device can determine the state of the peripheral object based on the output of the peripheral object control algorithm and provide the state of the peripheral object to the peripheral object control algorithm management device and the autonomous driving target control algorithm management device.

[0015] In one embodiment, the autonomous driving object management device can determine the state of the autonomous driving object based on the output of the autonomous driving object control algorithm, and provide the state of the autonomous driving object to the surrounding object control algorithm management device and the autonomous driving object control algorithm management device.

[0016] One embodiment of the present disclosure aims to provide an operating method of a peripheral object control algorithm management device, including the operations of acquiring external trigger information related to the operation of a peripheral object, identifying a first input of a peripheral object control algorithm in accordance with the external trigger information related to the operation of the peripheral object, determining a first output of the peripheral object control algorithm based on the first input, and providing the first output to a peripheral object management device.

[0017] In one embodiment, the external trigger information regarding the behavior of the peripheral object may include a user input for modifying the behavior of the peripheral object, trigger information regarding the behavior of the peripheral object determined by an artificial intelligence learning model, and at least one input determined by a random function.

[0018] In one embodiment, the method may further include an operation of acquiring scenario information regarding a driving pattern including at least one of a target speed, acceleration, a driving lane, and a destination; an operation of determining a second output of the peripheral object control algorithm based on the scenario information; an operation of transmitting the second output to the peripheral object management device; an operation of receiving operation information of the peripheral object from the peripheral object management device; and an operation of receiving operation information of the autonomous driving target from the autonomous driving target management device.

[0019] In one embodiment, the method may further include an operation of receiving scenario information including condition information under which an operation pattern is changed, an operation of identifying a trigger event for changing the operation pattern based on the condition information under which the operation pattern is changed, an operation of determining a third output of the peripheral object control algorithm based on the operation pattern corresponding to the trigger event for changing the operation pattern, and an operation of transmitting the third output to the peripheral object management device.

[0020] One embodiment of the present disclosure aims to provide a method for operating a simulation device, which includes the operations of receiving scenario information, acquiring a peripheral object control algorithm, receiving an autonomous driving target control algorithm, controlling peripheral objects based on the scenario information and the peripheral object control algorithm, and controlling the autonomous driving target based on the scenario information and the autonomous driving target control algorithm, wherein the method additionally includes the operations of receiving a first output determined by the peripheral object control algorithm using external trigger information as input, and controlling the peripheral objects based on the first output.

[0021] In one embodiment, the external trigger information may include information for changing the behavior of peripheral objects through user input, information regarding the behavior of peripheral objects determined by an artificial intelligence learning model, and input determined by at least one random function.

[0022] In one embodiment, the method may include an operation of obtaining external trigger information, an operation of determining a first output of a peripheral object control algorithm based on the external trigger information, and an operation of providing the first output to a peripheral object management device.

[0023] In one embodiment, the peripheral object control algorithm is transmitted from a peripheral object control algorithm manager, which may be a device separate from the simulation device.

[0024] In one embodiment, the operation of controlling a peripheral object may include an operation of determining the state of the peripheral object based on a peripheral object control algorithm, and an operation of providing the state of the peripheral object to a peripheral object control algorithm management device and an automatic driving target control algorithm management device.

[0025] In one embodiment, the operation of controlling the autonomous driving object may include an operation of determining the state of the autonomous driving object based on an autonomous driving object control algorithm, and an operation of providing the state of the autonomous driving object to a surrounding object control algorithm management device and an autonomous driving object control algorithm management device.

[0026] One embodiment of the present disclosure includes a recording medium having a program recorded thereon that enables a computer to execute a method according to one embodiment of the present disclosure.

[0027] One embodiment of the present disclosure includes a computer-readable recording medium having a program recorded thereon for causing a computer to execute a method according to one embodiment of the present disclosure.

[0028] One embodiment of the present disclosure includes a computer-readable recording medium on which a database used in one embodiment of the present disclosure is recorded. [Effects of the Invention]

[0029] According to one embodiment of the present disclosure, an autonomous driving simulation for commercialization of autonomous driving can be provided. [Brief explanation of the drawings]

[0030] [Figure 1] FIG. 1 is a flowchart illustrating an operation method of a peripheral object control algorithm management device according to an embodiment of the present disclosure. [Figure 2] FIG. 2 is a flowchart of a method of operating a simulation device according to one embodiment of the present disclosure. [Figure 3] FIG. 3 is a diagram illustrating a simulation method using a peripheral object control algorithm management device specific to a simulation device according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating a simulation method based on external trigger information according to one embodiment of the present disclosure. [Figure 5] FIG. 5 is a block diagram of a peripheral object control algorithm management device according to one embodiment of the present disclosure. [Figure 6] FIG. 6 is a block diagram of a simulation device according to one embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0031] To clarify the technical concept of the present disclosure, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. When describing the present disclosure, detailed descriptions of related notification functions or components will be omitted if such descriptions may unnecessarily obscure the gist of the present disclosure. In the drawings, components having substantially the same functions will be assigned the same reference numerals and symbols whenever possible, even if they are shown in different drawings. For convenience of description, devices and methods will be described together where necessary. The operations of the present disclosure do not necessarily have to be performed in the order described, and may be performed in parallel, selectively, or individually.

[0032] The terms used in the embodiments of the present disclosure are currently commonly used and generally selected as much as possible while taking into consideration the functionality of the present disclosure, but these may vary depending on the intentions of engineers in the field, legal precedents, the emergence of new technologies, etc. In addition, in certain cases, the applicant may have arbitrarily selected terms, and in such cases, the meanings thereof will be described in detail in the description of the relevant embodiments. Therefore, the terms used in this specification should be defined based on the meanings of the terms and the content throughout the present disclosure, rather than simply the names of the terms.

[0033] Throughout this disclosure, singular expressions can include plural expressions unless the context clearly indicates otherwise. Terms such as "comprise" and "have" specify the presence of a feature, number, step, operation, component, part, or combination thereof, but do not preclude the possible presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. In other words, throughout this disclosure, when a part is said to "comprise" a component, this does not exclude other components, but means that other components may be added, unless specifically stated to the contrary.

[0034] The phrase "at least one" means formulating the entire list of components, and not formulating the components of the list individually. For example, "at least one of A, B, and C" and "at least one of A, B, or C" refer to A only, B only, C only, both A and B, both B and C, both A and C, all of A, B, and C, or any combination thereof.

[0035] Furthermore, terms such as "unit" and "module" used in this disclosure refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software.

[0036] Throughout this disclosure, when a part is said to be "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another component therebetween. Furthermore, when a part is said to "include" a certain component, this does not exclude other components, but means that other components may be added, unless otherwise specified to the contrary.

[0037] As used throughout this disclosure, the phrase “configured (or set) to” can be used interchangeably with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of,” depending on the context. The term “configured (or set) to” does not necessarily mean “specially designed” in terms of hardware. Instead, in some contexts, the phrase “a system configured to” can mean that the system, together with other devices or components, is “capable of.” For example, the phrase “a processor configured (or set) to perform A, B, and C” can refer to a dedicated processor for performing the corresponding operations (e.g., an embedded processor) or a general-purpose processor (e.g., a CPU or application processor) that can perform the operations by executing one or more software programs stored in memory.

[0038] An embodiment of the present disclosure aims to provide a simulation device, a peripheral object control algorithm management device, a peripheral object management device, an autonomous driving target control algorithm management device, an autonomous driving target management device, and methods of operating the same. Throughout this disclosure, a device may include a server, and the server may be referred to as a device, or a device may be referred to as a server. Throughout this disclosure, some or all of the devices may be included in a single device. Alternatively, each device may be included in a different device.

[0039] Throughout this disclosure, the peripheral objects may include non-player characters (NPCs) such as other vehicles, trains, ships, aircraft, pedestrians, animals, etc. that are the subject of the automatic driving simulation. Therefore, the peripheral object control algorithm may include an NPC control algorithm.

[0040] Throughout this disclosure, updating an algorithm may include inputting inputs into the corresponding algorithm to derive outputs, as well as modifying or supplementing the algorithm itself.

[0041] Throughout this disclosure, external trigger information refers to information received from outside the simulation device to change the behavior of a peripheral object, and may include user input to change the behavior of a peripheral object, information determined for an artificial intelligence learning model to change the behavior of a peripheral object, information about the behavior of a peripheral object mapped to a specific value determined by a random function, etc. For example, information about the behavior of a peripheral object mapped to a specific value is as shown in Table 1 below.

[0042] [Table 1]

[0043] Furthermore, throughout this disclosure, the term "autonomous driving subject" may include a variety of autonomous driving subjects, such as an autonomous driving vehicle, an autonomous driving ship, an autonomous driving airplane, an autonomous driving train, an autonomous driving electric train, and an autonomous driving drone.

[0044] Generally, an autonomous driving simulation is performed along a driving pattern determined by considering the results of processes such as collision risk identification with other vehicles, traffic signal identification, stop line identification, and speed limit confirmation on a route from a current location on a map to a random destination. In this case, the driving pattern is selected based on rules such as the presence or absence of traffic signals, speed limits, and the order in which intersections are passed. This general autonomous driving simulation determines the driving pattern through simple rule-based judgments and is limited in its ability to directly reproduce the driving behavior of an ordinary human being, which is not based on rules. The present disclosure proposes an autonomous driving simulation method that can reproduce the driving behavior of an ordinary human being, which is not based on rules.

[0045] According to one embodiment of the present disclosure, by utilizing the HITL (Human-In-The-Loop) method, which allows humans to intervene in the "judgment" part of a vehicle's driving process of recognition, judgment, and driving, it is possible to generate driving patterns similar to those of a human, who can frequently change his or her judgment, such as restarting or stopping again after stopping.

[0046] Furthermore, according to one embodiment of the present disclosure, during a simulation operation for verifying an autonomous driving algorithm, external information received through an input device in real time can intervene in the movement of surrounding objects to generate interactions with the autonomous driving vehicle.

[0047] Furthermore, according to an embodiment of the present disclosure, a simulation method can be provided that can safely test imperfect algorithms while saving time, cost, and effort.

[0048] Furthermore, according to an embodiment of the present disclosure, it is possible to emulate a realistic driving environment regarding the interaction between an autonomous vehicle and surrounding objects.

[0049] Furthermore, according to one embodiment of the present disclosure, the reliability of the autonomous driving algorithm can be improved by implementing complex interactions such as those of a real driving environment in a simulation.

[0050] FIG. 1 is a flowchart of a method for operating a peripheral object control algorithm management device according to one embodiment of the present disclosure.

[0051] Referring to FIG. 1 , in operation 110, the peripheral object control algorithm management device may acquire external trigger information related to the peripheral object's behavior. In one embodiment, the external trigger information related to the peripheral object's behavior may include at least one of a user input for changing the peripheral object's behavior, trigger information related to the peripheral object's behavior determined by an AI learning model, and a specific value determined by a random function. Here, the user input for changing the peripheral object's behavior may be an input device that can be used by a person to input one or more independent pieces of information, such as input via a keyboard, input via a touch screen, or voice input via a microphone. The AI ​​learning model may also be a learning model that has learned human behavior. In this way, the AI ​​learning model can learn about unexpected human behavior, behaviors that frequently change judgment, and the like, to determine trigger information related to the behavior, and provide the determined trigger information to the peripheral object control algorithm management device.

[0052] In operation (130), the peripheral object control algorithm management device can determine a first input of the peripheral object control algorithm corresponding to external trigger information related to the behavior of the peripheral object. In one embodiment, the peripheral object control algorithm management device can determine a first input for generating a behavior pattern similar to a person's running, whose decisions can change frequently, based on the external trigger information. Here, the behavior pattern can include a running pattern. In one embodiment, if the external trigger information is a specific value determined by a random function, the peripheral object control algorithm management device can identify a behavior of the peripheral object corresponding to the specific value based on a predetermined mapping table. Furthermore, the peripheral object control algorithm management device can determine a first input of the peripheral object control algorithm corresponding to the identified behavior. For example, the first input can include an input value of the peripheral object control algorithm.

[0053] According to one embodiment, during a simulation operation for verifying an autonomous driving algorithm, external trigger information is reflected in real time on the behavior of a surrounding object via an input device, thereby generating an interaction between the external trigger information and the autonomous driving target, thereby enabling simulation in irregular situations.

[0054] In operation 150, the peripheral object control algorithm manager can determine a first output of the peripheral object algorithm based on the first input. For example, the first output can be an input value required for the peripheral object manager to control the peripheral object according to the motion pattern. That is, the first output of the peripheral object control algorithm can be an input value required for the peripheral object manager. In one embodiment, the peripheral object control algorithm manager can calculate the input value required for the peripheral object manager so that the peripheral object manager can change to the identified motion pattern. Furthermore, the peripheral object control algorithm manager can provide the corresponding input value to the peripheral object manager.

[0055] In one embodiment, the peripheral object control algorithm manager can determine and provide output values ​​to the peripheral object manager to allow for modification of the identified behavior pattern.

[0056] In operation 170, the first output may be provided to a peripheral object manager. The peripheral object manager may control the peripheral object based on the first output. In one embodiment, the peripheral object manager may calculate a state of the peripheral object based on the first output received from the peripheral object control algorithm manager. The peripheral object manager may also provide the calculated state of the peripheral object to the peripheral object control algorithm manager and the autonomous driving object control algorithm manager.

[0057] According to one embodiment, status information of the surrounding objects is sent to each algorithm management device, and the status information of the surrounding objects is input into each algorithm, so that interactions between the surrounding objects and the autonomous driving object can be generated.

[0058] According to one embodiment, driving patterns can be changed in real time based on external trigger information received while a scenario is in progress, and the automated driving algorithm can be verified based on the results of interactions with the driving patterns changed in real time.

[0059] FIG. 2 is a flowchart of a method of operating a simulation device according to one embodiment of the present disclosure.

[0060] 2, in operation 210, the simulation device may acquire scenario information, a peripheral object control algorithm, and an autonomous driving object control algorithm. In one embodiment, a peripheral object management device included in the simulation device may receive the scenario information and the peripheral object algorithm, and an autonomous driving object management device included in the simulation device may receive the scenario information and the autonomous driving object control algorithm.

[0061] In one embodiment, the scenario information may include initial state information of the autonomous driving object and the peripheral objects. The peripheral object management device and the autonomous driving target management device may acquire the initial state information described in the scenario and determine the initial states of the peripheral objects and the autonomous driving target, respectively. For example, the scenario information may include input values ​​required for each algorithm or values ​​output from each algorithm, such as the initial position, initial acceleration, initial speed, initial direction, and destination of the autonomous driving target and the peripheral objects. The scenario information may also include motion patterns of the peripheral objects and trigger condition information for the occurrence of the motion patterns. The trigger condition information for the occurrence of the motion patterns may include information regarding the conditions for the occurrence of specific motions. For example, the scenario information may include driving patterns such as acceleration, deceleration, lane change, and destination change. In one embodiment, the time at which the driving pattern is changed based on the scenario information may be determined using the state of the autonomous driving target or the state of the peripheral objects. For example, the absolute position, driving speed, etc. of the autonomous driving target or the peripheral objects may be determined based on the absolute state of the peripheral objects or the absolute state of the autonomous driving target. Alternatively, the relative position, relative speed, etc. between the autonomous driving target and the peripheral objects may be determined based on the relative state between the autonomous driving target and the peripheral objects.

[0062] In one embodiment, the peripheral object control algorithm management device can obtain information about a driving pattern, such as a target speed, a target acceleration, a driving lane, and a destination, from the scenario information and calculate input values ​​required for the moving object management device to enable the described driving. Here, the input values ​​required for the moving object management device may be output values ​​of a peripheral object control algorithm that are determined to enable the described driving.

[0063] In one embodiment, the peripheral object control algorithm management device can obtain condition information for changing the motion pattern from the scenario information, and calculate input values ​​required for the peripheral object management device so that the motion pattern can be changed when the condition is met. Here, the input values ​​for the peripheral object management device to change the motion pattern may be output values ​​of the peripheral object control algorithm determined to change the motion pattern.

[0064] In one embodiment, the autonomous driving target control algorithm management device can calculate and output input values ​​required for the autonomous driving target management device so that the autonomous driving target management device can perform the operations described in the autonomous driving target control algorithm. That is, the input values ​​required for the autonomous driving target management device may be output values ​​determined by the autonomous driving target control algorithm, and the autonomous driving target control algorithm may be an object to be verified using a simulation.

[0065] In operation (230), the simulation device can control peripheral objects based on the scenario information and a peripheral object control algorithm. In one embodiment, a peripheral object management device included in the simulation device can control peripheral objects based on the scenario information and a peripheral object control algorithm. For example, the peripheral object management device may determine the states of peripheral objects by specifying the states of the peripheral objects, such as the position, direction, speed, and acceleration of the peripheral objects, as specific values ​​or by calculating them using a predetermined method. The peripheral object management device may also obtain initial state information of the peripheral objects described in the scenario information and determine the states of the peripheral objects so that they correspond to the values ​​corresponding to the start of the scenario. The peripheral object management device may also obtain input values ​​necessary to calculate the states of the peripheral objects from the peripheral object control algorithm and calculate the states of the peripheral objects based on the obtained input values. The peripheral object management device may also provide the calculated states of the peripheral objects as input values ​​for the peripheral object control algorithm and the automatic driving target algorithm.

[0066] In operation (250), the simulation device can control the autonomous driving object based on the scenario information and the autonomous driving object control algorithm. In one embodiment, an autonomous driving object management device included in the simulation device can control the autonomous driving object based on the scenario information and the autonomous driving object control algorithm. For example, the autonomous driving object management device can specify specific values ​​for the state of the autonomous driving object, such as the position, direction, speed, and acceleration of the autonomous driving object, or calculate and specify them using the method described above. The autonomous driving object management device can also acquire initial state information for the autonomous driving object described in the scenario information and determine the initial state of the autonomous driving object at the start of scenario progression based on the initial state information. The autonomous driving object management device can also acquire input values ​​necessary for calculating the state of the autonomous driving object from the autonomous driving object control algorithm and calculate the state of the autonomous driving object using the input values. The autonomous driving object management device can also provide the calculated state of the autonomous driving object as input values ​​for the surrounding object control algorithm and the autonomous driving object control algorithm.

[0067] In operation 270, the simulation device may receive a first output from the peripheral object control algorithm manager. In one embodiment, the first output may be an output value determined by the peripheral object control algorithm manager using external trigger information as input.

[0068] In operation 290, the simulation device may control the peripheral objects based on the first output. In one embodiment, a peripheral object manager included in the simulation device may control the peripheral objects based on the received first output. Controlling the peripheral objects may include determining a driving pattern of the peripheral objects, including a driving direction, a driving speed, a driving acceleration, etc.

[0069] FIG. 3 is a diagram illustrating a simulation method using a peripheral object control algorithm management device specific to a simulation device according to an embodiment of the present disclosure.

[0070] 3, an NPC driving algorithm (350) is shown as an example of a peripheral object control algorithm, an NPC management device (360) is shown as an example of a peripheral object management device, an automatic driving algorithm (380) is shown as an example of an automatic driving object control algorithm, and an automatic driving vehicle management device (370) is shown as an example of an automatic driving object management device. The following description will be given using the above example, but is not limited to this. The NPC driving algorithm (350), NPC management device (360), automatic driving algorithm (380), and automatic driving vehicle management device (370) are equivalent, respectively. Alternatively, they can be replaced with a peripheral object control algorithm, a peripheral object management device, an automatic driving object control algorithm, and an automatic driving object management device.

[0071] In one embodiment, the simulator may include an NPC driving algorithm (350) management device, an NPC management device (360), and an automated vehicle management device (370). The NPC driving algorithm (350) management device may be a device that inputs input values ​​into the NPC driving algorithm (350) and derives output values.

[0072] In one embodiment, the scenario information (310) may be used as input to determine the output of the NPC driving algorithm (350). In one embodiment, if there are multiple NPCs, there may also be multiple NPC driving algorithms (350). For example, if there are opposing vehicles, pedestrians, and animals in the simulation situation, there may be separate driving algorithms for opposing vehicles, movement algorithms for pedestrians, and movement algorithms for animals. Furthermore, when an NPC driving algorithm management device included in the simulator (340) receives external trigger information from the input device (320), it may derive a new output using the NPC driving algorithm (350). For example, the NPC driving algorithm management device included in the simulator (340) may receive the scenario information (310) and the external trigger information received from the input device (320) as input to determine the output of the NPC driving algorithm (350).

[0073] In one embodiment, the NPC management device (360) can acquire scenario information (310). The scenario information (310) can include scenario information for the NPC. The NPC management device (360) can also acquire an output determined based on the NPC driving algorithm (350). The NPC management device (360) can control the behavior of the NPC based on the NPC driving algorithm (350) and the scenario information (310) and transmit NPC status information corresponding to the control results to the peripheral object control algorithm management device and the automatic driving object control algorithm management device. The peripheral object control algorithm management device can derive a new output value according to the NPC driving algorithm (350) based on the received NPC status information. The automatic driving object control algorithm management device can also determine an output value according to the automatic driving algorithm (380) based on the received NPC status information. That is, the output based on the NPC driving algorithm (350) and the output based on the automatic driving algorithm (380) can be determined based on the NPC status information.

[0074] In one embodiment, the autonomous vehicle management device (370) may acquire scenario information (310). The scenario information (310) may include scenario information for the autonomous vehicle. The autonomous vehicle management device (370) may also determine state information for the autonomous vehicle based on the scenario information (310). For example, the autonomous vehicle management device (370) may determine output values ​​through the autonomous driving algorithm (380) using the scenario information (310) as input. The autonomous vehicle management device (370) may determine state information for the autonomous vehicle based on the corresponding output values. The autonomous vehicle management device (370) may also transmit state information for the autonomous vehicle to the NPC driving algorithm management device and the autonomous driving algorithm management device. This allows the output values ​​through the NPC driving algorithm (350) to be determined taking into account both the scenario information (310), external trigger information from the input device (320), autonomous vehicle state information, and NPC state information. In addition, the autonomous driving algorithm management device can derive new output values ​​based on the autonomous driving algorithm, taking into account the state information of the autonomous driving vehicle and the state information of the NPC.

[0075] According to one embodiment, the state of the NPC is determined by the interaction of the NPC driving algorithm (350), the NPC management device (360), the autonomous vehicle management device (370), etc., and the driving pattern of the autonomous vehicle can be determined based on the state of the NPC and the autonomous driving algorithm (380).

[0076] Furthermore, according to one embodiment, by further considering external trigger information from the input device (320), it is possible to generate a running pattern similar to that of a person whose decisions can be changed frequently.

[0077] FIG. 4 is a diagram illustrating a simulation method based on external trigger information according to one embodiment of the present disclosure.

[0078] Referring to Figure 4, the transmission and reception of information is the same as in Figure 3, but the NPC driving algorithm (410) determination device is a separate device from the simulator (420), and the NPC driving algorithm (410) determination device is the simulator (420). The automatic driving simulation operation can be performed by exchanging information with the simulator (420). In other words, the NPC driving algorithm (410) may be stored and executed in a memory external to the simulator (420).

[0079] That is, the simulator (340) of FIG. 3 includes a peripheral object control algorithm management device that acquires external trigger information, determines a first output of a peripheral object control algorithm based on the external trigger information, and provides the first output to a peripheral object management device, while the peripheral object control algorithm management device of FIG. 4 may be a device separate from the simulator (420).

[0080] FIG. 5 is a block diagram of a peripheral object control algorithm management device according to one embodiment of the present disclosure.

[0081] Referring to Figure 5, the peripheral object control algorithm management device 500 may include a transceiver 510, a memory 520, and a processor 530. However, not all of the components shown in Figure 5 are essential components of the peripheral object control algorithm management device 500. The peripheral object control algorithm management device 500 may be realized with more components than those shown in Figure 5, or may be realized with fewer components than those shown in Figure 5. The transceiver 510, the processor 530, and the memory 520 may also be embodied in the form of a single chip.

[0082] In one embodiment, the transceiver 510 can communicate with a terminal, server, or other electronic device connected to the peripheral object control algorithm management device 500 via a wired or wireless connection. Various types of data, such as programs and files, including applications, can be installed and stored in the memory 520. The processor 530 can access and use the data stored in the memory 520 or store new data in the memory 520.

[0083] The processor 530 controls the overall operation of the peripheral object control algorithm management device 500 and may include at least one processor, such as a CPU or GPU. The processor 530 may control other components included in the peripheral object control algorithm management device 500 to execute operations for operating the peripheral object control algorithm management device 500. For example, the processor 530 may execute programs stored in the memory 520, read stored files, or save new files. In one embodiment, the processor 530 may execute programs stored in the memory 520 to execute operations for operating the peripheral object control algorithm management device 500.

[0084] In one embodiment, the processor (530) can acquire external trigger information related to the operation of a peripheral object. For example, the external trigger information can include a user input value that allows a user to change the driving pattern in real time at a desired time. The processor (530) can determine a first input of a peripheral object control algorithm corresponding to the external trigger information based on the user input value. Furthermore, the processor (530) can determine a first output via the peripheral object control algorithm based on the first input. That is, the first output can be an output value derived when the first input is input to the peripheral object control algorithm. For example, the processor (530) can calculate an input value required for the peripheral object management device to change to a predetermined operation pattern and control the transceiver unit (510) to transmit the input value to the peripheral object management device. Here, the input value required for the peripheral object management device can be a first output derived via the peripheral object control algorithm.

[0085] Furthermore, in one embodiment, the processor (530) can acquire scenario information regarding a driving pattern, including at least one of a target speed, acceleration, a driving lane, and a destination, and determine a second output of the peripheral object control algorithm based on the scenario information. Here, the second output may be an output value determined by the peripheral object control algorithm when the scenario information is used as input. That is, the processor (530) can acquire information regarding the driving pattern and calculate and output necessary input values ​​to the peripheral object management device so as to perform the described driving. The processor (530) can also control the transceiver (510) to transmit the second output to the peripheral object management device, control the transceiver (510) to receive operation information of the peripheral object from the peripheral object management device, and control the transceiver (510) to receive operation information of the autonomous driving target from the autonomous driving target management device. Here, the operation information of the peripheral object may include operation information of the peripheral object determined based on the second output, and the operation information of the autonomous driving target may include operation information of the autonomous driving target determined based on the operation information of the peripheral object determined based on the second output.

[0086] Furthermore, in one embodiment, the processor (530) may control the transceiver (510) to receive scenario information including condition information for changing a motion pattern. The processor (530) may also identify a trigger event for changing a motion pattern based on the condition information for changing a motion pattern. The processor (530) may also control the transceiver (510) to determine a third output of the peripheral object algorithm based on the motion pattern corresponding to the trigger event for changing the motion pattern and transmit the third output to the peripheral object management device. That is, the processor (530) may obtain condition information for changing a driving pattern from the scenario information, and calculate and output input values ​​required for the peripheral object management device so that the driving pattern can be changed when the corresponding condition is met.

[0087] According to one embodiment of the present disclosure, the peripheral object control algorithm management device (500) receives external trigger information from an input device, and provides necessary input values ​​to the peripheral object management device so that the driving pattern can be changed to one corresponding to the external trigger information.

[0088] FIG. 6 is a block diagram of a simulation device according to one embodiment of the present disclosure.

[0089] Referring to Figure 6, the simulation device 600 may include a transceiver 610, a memory 620, and a processor 630. However, not all of the components shown in Figure 6 are essential components of the simulation device 600. The simulation device 600 may be implemented with more components than those shown in Figure 6, or may be implemented with fewer components than those shown in Figure 6. The transceiver 610, the processor 630, and the memory 620 may also be implemented in the form of a single chip.

[0090] In one embodiment, the simulation device 600 may further include at least one of a peripheral object control algorithm management device 500, a peripheral object management device, and an autonomous driving target management device. For example, the simulation device 600 may include a peripheral object management device that controls peripheral objects based on scenario information and a peripheral object control algorithm, and an autonomous driving target management device that receives scenario information and an autonomous driving target control algorithm and controls the autonomous driving target.

[0091] The processor 630 controls the overall operation of the simulation device 600 and may include at least one processor, such as a CPU or GPU. The processor 630 may control other components included in the simulation device 600 to perform operations to operate the simulation device 600. For example, the processor 630 may execute a program stored in the memory 620, read a saved file, or save a new file. In one embodiment, the processor 630 may perform operations to operate the simulation device 600 by executing a program stored in the memory 620.

[0092] In one embodiment, the processor (630) can control the transceiver unit (610) to receive a first output from the peripheral object control algorithm management device and control the peripheral object based on the received first output, where the first output can be an output value determined by the peripheral object control algorithm using external trigger information as input.

[0093] In one embodiment, the processor that controls the operation of the peripheral object management device can determine the state of the peripheral object based on the output of the peripheral object control algorithm and provide information about the determined state of the peripheral object to the peripheral object control algorithm management device and the automatic driving target control algorithm management device.

[0094] In one embodiment, the processor that controls the operation of the autonomous driving object management device determines the state of the autonomous driving object based on the output of the autonomous driving object control algorithm, and can provide information about the determined state of the autonomous driving object to the algorithm management device that controls the surrounding objects and the autonomous driving object control algorithm management device.

[0095] An embodiment of the present disclosure may also be implemented in the form of a recording medium containing computer-executable instructions, such as a program module executed by a computer. Computer-readable media are any available media that can be accessed by a computer, including both volatile and nonvolatile media, removable and non-separate media. Furthermore, computer-readable media may include both computer storage media and communication media. Computer storage media includes both volatile and non-volatile, removable and non-separate media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Communication media typically contain computer-readable instructions, data structures, or program modules and include any information delivery media.

[0096] The above description of the present disclosure is for illustrative purposes only, and those skilled in the art will understand that the present disclosure can be easily modified into other specific forms without changing the technical idea or essential characteristics of the present invention. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and are not limiting. For example, each component described in a single form can be implemented in a distributed form, and similarly, components described as distributed can be implemented in a combined form.

[0097] The scope of the present disclosure is indicated by the claims that follow, rather than by the above detailed description, and all modifications and variations that fall within the meaning and scope of the claims and their equivalents should be construed as being within the scope of the present disclosure.

Claims

1. In a peripheral object control algorithm management device, a memory storing one or more instructions; at least one processor that executes the one or more instructions stored in the memory; The at least one processor executes the one or more instructions to: Obtaining external trigger information about the behavior of surrounding objects; determining a first input for a peripheral object control algorithm corresponding to external trigger information relating to the movement of the peripheral object; determining a first output of the peripheral object control algorithm based on the first input; a peripheral object control algorithm manager that provides the first output to a peripheral object manager;

2. external trigger information regarding the operation of the peripheral object, 2. The peripheral object control algorithm management device of claim 1, comprising at least one of a user input for changing the behavior of the peripheral object, trigger information regarding the behavior of the peripheral object determined by an artificial intelligence learning model, and a specific value determined by a random function.

3. The at least one processor executes the one or more instructions to: acquiring scenario information regarding a driving pattern including at least one of a target speed, an acceleration, a driving lane, and a destination; determining a second output of the peripheral object control algorithm based on the scenario information; sending the second output to the peripheral object manager; receiving operation information of the peripheral object from the peripheral object management device; The peripheral object control algorithm management device according to claim 1 , which receives operation information of the autonomous driving object from the autonomous driving object management device.

4. The at least one processor executes the one or more instructions to: receiving scenario information including condition information for changing an operation pattern; Identifying a trigger event for changing the operation pattern based on condition information for changing the operation pattern; determining a third output of the peripheral object control algorithm based on the movement pattern corresponding to the movement pattern change trigger event; The peripheral object control algorithm manager of claim 1 , wherein the third output is sent to the peripheral object manager.

5. In the simulation device, a peripheral object management device that receives the scenario information and the peripheral object control algorithm and controls the peripheral objects; an autonomous driving object management device that receives the scenario information and the autonomous driving object control algorithm and controls the autonomous driving object; the peripheral object management device, A simulation device that receives from a peripheral object control algorithm management device a first output determined by the peripheral object control algorithm using external trigger information as input, and controls the peripheral object based on the first output.

6. The external trigger information is The simulation device of claim 5, comprising at least one of a user input for changing the behavior of the peripheral object, trigger information regarding the behavior of the peripheral object determined by an artificial intelligence learning model, and an input determined by a random function.

7. 6. The simulation device according to claim 5, further comprising the peripheral object control algorithm management device that acquires the external trigger information, determines the first output of the peripheral object control algorithm based on the external trigger information, and provides the first output to the peripheral object management device.

8. The simulation device according to claim 5 , wherein the peripheral object control algorithm management device is a device separate from the simulation device.

9. the peripheral object management device, determining a state of the peripheral object based on an output of the peripheral object control algorithm; The simulation device according to claim 5 , wherein the state of the peripheral object is provided to the peripheral object control algorithm management device and the automatic driving target control algorithm management device.

10. The autonomous driving target management device determining a state of the autonomous driving object based on an output of the autonomous driving object control algorithm; The simulation device according to claim 5 , wherein the state of the autonomous driving object is provided to the surrounding object control algorithm management device and the autonomous driving object control algorithm management device.

11. A method for operating a peripheral object control algorithm management device, comprising: obtaining external trigger information regarding the behavior of surrounding objects; identifying a first input of a peripheral object control algorithm corresponding to external trigger information relating to the movement of the peripheral object; determining a first output of the peripheral object control algorithm based on the first input; providing the first output to a peripheral object manager.

12. external trigger information regarding the operation of the peripheral object, The method of claim 11 , comprising at least one of a user input for modifying the behavior of the peripheral object, trigger information regarding the behavior of the peripheral object determined by an artificial intelligence learning model, and an input determined by a random function.

13. The method comprises: An operation of acquiring scenario information regarding a driving pattern including at least one of a target speed, an acceleration, a driving lane, and a destination; determining a second output of the peripheral object control algorithm based on the scenario information; transmitting the second output to the peripheral object manager; receiving operation information of the peripheral object from the peripheral object management device; The method of claim 11 , further comprising: receiving operation information of the autonomous driving object from the autonomous driving object management device.

14. The method comprises: receiving scenario information including condition information for changing an operation pattern; an operation of identifying a trigger event for changing the behavior pattern based on condition information for changing the behavior pattern; determining a third output of the peripheral object control algorithm based on a movement pattern corresponding to a trigger event for changing the movement pattern; The method of claim 11 , further comprising the act of transmitting the third output to the peripheral object manager.

15. A method of operating a simulation device, comprising: receiving scenario information; obtaining a peripheral object control algorithm; receiving an automated driving target control algorithm; an operation of controlling peripheral objects based on the scenario information and the peripheral object control algorithm; and an operation of controlling the autonomous driving object based on the scenario information and the autonomous driving object control algorithm, The method comprises: receiving a first output determined by the peripheral object control algorithm using external trigger information as an input; and controlling the peripheral object based on the first output.

16. The external trigger information is 16. The method of claim 15, comprising at least one of a user input for modifying the behavior of the peripheral object, trigger information regarding the behavior of the peripheral object determined by an artificial intelligence learning model, and an input determined by a random function.

17. The method comprises: an operation of acquiring the external trigger information; determining the first output of the peripheral object control algorithm based on the external trigger information; The method of claim 15 , further comprising the act of providing the first output to a peripheral object manager.

18. The peripheral object control algorithm is transmitted from a peripheral object control algorithm management device; The method of claim 15 , wherein the peripheral object control algorithm manager is a separate device from the simulation device.

19. The operation of controlling the peripheral object includes: determining a state of the peripheral object based on the peripheral object control algorithm; and providing the state of the peripheral objects to a peripheral object control algorithm manager and an autonomous vehicle control algorithm manager.

20. The operation of controlling the autonomous driving object includes: determining a state of the autonomous driving object based on the autonomous driving object control algorithm; and providing the state of the autonomous vehicle to a surrounding object control algorithm manager and an autonomous vehicle control algorithm manager.

21. A program stored on a computer-readable recording medium for causing a computer to execute the method according to any one of claims 11 to 20.

Images