KR20220058741A - System and Method for driving of robot - Google Patents

Abstract

The present invention relates to a robot driving method to increase performance of self-driving robots in dense crowds and a system for supporting the same. According to the present invention, the robot driving method comprises the following steps by a robot device: receiving time information including a congestion change time for a designated area from a control device; operating an autonomous driving algorithm on the basis of the time information, sensor data collected by a sensor unit, and a stored target position to generate a driving model; and performing driving on the basis of the generated driving model. The generating step includes a step of generating a driving model including a route avoiding a designated specific area while driving at a relatively low speed at a time when a congestion level increases and a step of generating a driving model traveling at a relatively high speed at a time when the congestion level decreases.

Description

A method for driving a robot and a system supporting the same

The present invention relates to a driving method of a robot, and more particularly, to a dense crowd autonomous driving.

A conventional robot driving system is designed to perform a task by a robot device alone, or is operated in a form in which a task is assigned from a control server and processed. Such a conventional robot driving system collects sensor data, calculates the collected sensor data and a predefined target position or a target position received from a control server based on a pre-stored autonomous driving algorithm, and a robot control command based on the calculated data is creating The above-described conventional robot device is designed to search for a traveling route of a robot by a crowd by more actively utilizing the mounted sensor in a dense crowd environment.

In addition, in relation to the driving of the conventional robot device, a zone-based access prohibited area is set to prevent the robot device from approaching a specific area, or map information for driving the robot is transmitted, so that the robot device simply follows the map information. It is designed to drive.

As described above, since the driving of the conventional robot device is limited to the extent of actively utilizing sensors or receiving and operating map information for a target location, it is difficult to perform normal driving in a dense crowd environment, and consequently, it is appropriate in a dense crowd environment. There is a problem in which work cannot be performed.

An object of the present invention is to provide a robot driving method that supports more efficient driving and work by diversifying the accumulation of experience of an autonomous driving robot device in a dense crowd based on time, and a system supporting the same.

The robot driving method according to an embodiment of the present invention comprises the steps of: receiving, by the robot device, congestion level information for a designated area from a control device; generating a driving model by operating an autonomous driving algorithm based on Generating a driving model including a route avoiding a specified specific area while driving with a road, and generating a driving model traveling at a relatively high speed when the congestion level is less than a specified value.

The robot device according to an embodiment of the present invention includes a driving module for driving and a processor for controlling the driving module, wherein the processor receives the congestion level information that is received from the control device and includes a change in crowd density, the congestion level A driving model including at least one of a driving speed and a path of the driving module is updated based on the information, and driving is performed based on the updated driving model.

Here, the processor is characterized in that the driving speed and the route are determined so as to check the congestion level information, and to process a predefined amount of work before the density change.

In addition, the processor sets the driving speed to be lower than before when the density of the crowd increases, or operates a driving model including a route avoiding a specific area, and the driving speed when the density of the crowd decreases It is characterized in that it is set to be higher than before, or is set to operate a driving model including the specific area.

The robot device according to an embodiment of the present invention includes a driving module for driving, a memory for storing a plurality of driving models having different at least one of a driving speed and a route of the driving module, and a processor for controlling the driving module, When the processor receives congestion information received from the control device and includes a change in crowd density, a driving model corresponding to the change in crowd density included in the congestion information is selected from the plurality of driving models, and the selected driving model It is characterized in that the driving is performed based on the

In particular, the processor selects a driving model with a lower driving speed than before when the density of the crowd increases, and selects a driving model with a higher driving speed than before when the density of the crowd decreases. .

In addition, the robot device according to an embodiment of the present invention includes a driving module for driving and a processor for controlling the driving module, wherein the processor receives congestion information corresponding to the density of the crowd by time from the control device, and the It is characterized in that a driving model suitable for each congestion level is generated based on the received congestion level information for each hour, or a driving model is selected from previously stored driving models, and driving is performed based on the selected driving model for each time.

Here, the processor generates or selects a driving model in which the driving speed is relatively low and the safety distance to an obstacle is relatively short at a time when the congestion is high, and when the driving speed is relatively high in a time when the congestion is low It is characterized by creating or selecting a driving model that has a relatively long safety distance.

Additionally, the processor generates or selects a driving model set to stop driving when the congestion level is greater than or equal to a specified maximum value, and generates or selects a driving model that travels at the maximum speed of the driving model when the congestion level is less than a specified minimum value, or characterized by selection.

The system and method according to the present invention can receive information or intelligence from a control device and, at the same time, receive time information on crowd density to diversify intelligence, and based on this, can increase the performance of an autonomous driving robot in a dense crowd.

1 is a diagram schematically illustrating a robot driving environment according to an embodiment of the present invention.
2 is a diagram showing in more detail an example of a configuration of a robot device according to an embodiment of the present invention.
3 is a diagram illustrating an example of a processor configuration of a robot device according to an embodiment of the present invention.
4 is a view showing another example of the configuration of the processor of the robot device according to an embodiment of the present invention.
5 is a view showing an example of a robot driving method of a robot device according to an embodiment of the present invention.
6 is a view showing another example of a robot driving method of a robot device according to an embodiment of the present invention.
7 is a view showing another example of a robot driving method of a robot device according to an embodiment of the present invention.

It should be noted that, in the following description, only the parts necessary for understanding the embodiment of the present invention will be described, and descriptions of other parts will be omitted in the scope not disturbing the gist of the present invention.

The terms or words used in the present specification and claims described below should not be construed as being limited to their ordinary or dictionary meanings, and the inventors have appropriate concepts of terms to describe their invention in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention based on the principle that it can be defined in Therefore, the embodiments described in this specification and the configurations shown in the drawings are only preferred embodiments of the present invention, and do not represent all of the technical spirit of the present invention, so various equivalents that can be substituted for them at the time of the present application It should be understood that there may be variations and variations.

Hereinafter, embodiments of the present invention will be described in more detail with reference to the accompanying drawings.

1 is a diagram schematically showing a robot driving environment according to an embodiment of the present invention, and FIG. 2 is a diagram showing an example of a configuration of a robot device according to an embodiment of the present invention in more detail.

Referring to FIG. 1 , a robot driving environment 10 according to an embodiment of the present invention may include a robot device 100 and a control device 200 .

The control device 200 may store and manage a policy related to operation of the robot device 100 , and may operate at least one robot device 100 according to the stored policy. The control device 200 may, for example, transmit a task related to the driving and operation of the at least one robot device 100 for each region or region. In particular, the control device 200 of the present invention includes time information (eg, a time when crowd density or congestion is expected to be above or below a specified value) and congestion information (eg, at least one robot device 100 ) Calculate at least one of the congestion level for each time period or the work efficiency of the robot device 100 according to the congestion level for each time period of the zone arranged to work, and display at least one of the calculated time information and the congestion level information in real time or by the fixed time ( 100) can be forwarded. For example, the control device 200 may transmit at least one of the time information and the congestion level information to the robot device 100 before the robot device 100 starts traveling or moves to a target location. Alternatively, the control device 200 may transmit the time information to the robot device 100 in a designated time unit (eg, per day, per week, etc.). Alternatively, the control device 200 may collect information on a change in density (or change in congestion) of a crowd due to the occurrence of a specific event, and transmit time information corresponding thereto to the robot device 100 . In this regard, the control device 200 may include a server device capable of collecting information on changes in crowd density in the corresponding area or may be configured to receive information on changes in crowd density over time from the server device. . The control device 200 may establish a communication channel with the server device, a communication circuit capable of transmitting at least one of the time information and the congestion level information to the robot device 100, and the collected crowd density change congestion information and a control processor configured to transmit time information to the robot device 100 , and a storage unit configured to store at least one of the congestion level information and time information.

The robot device 100 is disposed in a designated area, and based on information received from the control device 200 (eg, map information or area information, time information, and congestion level information), it is possible to drive and work in the corresponding area. can In particular, the robot device 100 updates the driving model based on at least one of the time information and the congestion level information received from the control device 200, or selects a driving model corresponding to the corresponding time information from among a plurality of driving models. driving can be performed. Such a robot device 100 may include the configuration shown in FIG. 2 .

Referring to FIG. 2 , the robot device 100 may include a communication circuit 110 , a memory 120 , a sensor unit 130 , a driving module 140 , a work module 160 , and a processor 150 . there is.

The communication circuit 110 may form a communication channel of the robot device 100 . For example, the communication circuit 220 forms a communication channel with the control device 200 , and from the control device 200 , among the basic model related to the driving route, the extended driving model in which the route varies according to time, time information, and congestion level information, At least one, at least one of area information (or map information) may be received. The communication circuit 110 may transmit the received models and information to the processor 150 , and may transmit the received models and information to the memory 120 in response to the control of the processor 150 .

The memory 120 may store at least one program related to operation of the robot device 100 , a plurality of driving models 121 including a basic model, at least one of time information and congestion information, area information, and the like. The memory 170 may temporarily store data collected by the sensor unit 130 (eg, a photographed image acquired by a camera, an ultrasound signal, a signal for proximity detection, an illuminance detection signal, a temperature detection signal, etc.). Also, the memory 120 may store an autonomous driving algorithm for calculating a driving model. The autonomous driving algorithm may include, for example, an algorithm that receives at least one of time information and congestion information, sensor data, and a target location as inputs, and calculates a driving model to the target location based on the input information. The plurality of driving models 121 are received from the control device 200 and stored, or the processor 150 of the robot device 100 applies the basic model, time information, target position, and sensor data to the autonomous driving algorithm. It may include a plurality of driving models generated by The memory 120 may further store a deep learning model and a map (or area information).

The sensor unit 130 may include at least one sensor capable of collecting various signals related to the surroundings of the robot device 100 . For example, the sensor unit 130 may include a camera. The camera may be disposed at a specific position of the body of the robot device 100 (eg, a position at a predetermined height from the floor surface, such as a chest or a chest of the robot device 100 ). The data collected by the camera is transmitted to the processor 150, and the processor 150 determines the location and distance of an obstacle (eg, a person, a fixed structure, a movable structure, etc.) in the vicinity through an image analysis collected by the camera. can The sensor unit 130 includes an ultrasonic sensor, and based on this, a distance between the surrounding obstacle and the robot device 100 may be calculated.

The driving module 140 may include an exercise module and a power unit. The motion module may be disposed at the end of the robot device 100 or on the bottom surface of the robot device 100 . For example, the motion module may include a track disposed on the bottom surface of the robot device 100 , a wheel, at least one shaft connected to the wheel, and at least one gear for rotating the at least one shaft. The power device may generate power for the motion of the exercise module, and transmit the generated power to the exercise module under the control of the processor 150 . For example, the power device may include at least one motor or at least one hydraulic device to generate power, and may include a power transmission means capable of transmitting the generated power to a gear or shaft of the exercise module. The degree of power generation and power transmission of the power unit may be controlled by the processor 150 . For example, the power device may generate power for an operation such as acceleration, deceleration, direction change, and stop of the robot device 100 and transmit it to the exercise module.

The work module 160 may include various structures according to the work purpose of the robot device 100 . For example, when the robot device 100 is a cleaning robot, the work module 160 may include a cleaning tool. Alternatively, the work module 160 may include a structure capable of loading and unloading loads when the robot device 100 is a transport device. Alternatively, when the robot device 100 is a guide robot, the work module 160 may include a display capable of displaying information or an audio device outputting information as audio. In addition, the work module 160 may include a thermometer or a thermal imaging camera for checking a person's fever in the case of a device for checking a person's fever. The above-described work module 160 may perform a work at a specific location in a zone in response to the control of the processor 150 or perform a specific work during a driving process.

The processor 150 processes information related to the operation of the robot device 100 and travels and work can be done. When at least one of a target position, time information, and congestion level information is received from the control device 200 for the driving of the driving robot device 100 , the processor 150 determines a target in relation to at least one of the time information and the congestion level information. For driving to a location, any one of the plurality of driving models 121 stored in the memory 120 may be selected, and driving according to the selected driving model may be performed. Alternatively, when at least one of the target location, time information, and congestion information is received from the control device 200, the processor 150 generates a driving model to the target location based on the sensor data or updates the basic model, It can be controlled to drive based on the updated driving model.

For example, when the robot device 100 is disposed in a shopping mall area with a theater, the processor 150 receives movie screening time information from the control device 200 and avoids the theater entrance area for a predetermined time before and after the corresponding screening start time. A driving model that travels to a target position can be created. Alternatively, the processor 150 may update the basic model by using the autonomous driving algorithm so as not to drive the theater entrance area for a specified period of time (eg, a predetermined time before and after the movie start time or a predetermined time immediately after the movie ending time).

Alternatively, when the robot device 100 is disposed in a specific school area, the processor 150 receives time information about school class time and break time from the control device 200, and the density of the crowd is changed in the time information Accordingly, the driving model can be created or the basic model can be modified so that the driving and work can be performed while avoiding the area around the classroom during the corresponding time. When the area in which the robot device 100 is located is a shopping mall area including a complex shopping mall, the processor 150 receives information on breakfast, lunch, and dinner times from the control device 200, and at the corresponding time in the shopping mall area It is possible to create a driving model or update the basic model to avoid the middle restaurant area, and to drive and work in the restaurant area outside of the time period. If the area in which the robot device 100 is located is a transportation area such as an airport or a train station, the processor 150 receives information about the arrival time and departure time of the transportation means from the control apparatus 200, and based on the received time You can create a driving model for the corresponding area or update the basic model. In addition, when the processor 150 receives time information including a change in the degree of congestion in a specific area from the control device 200 , the task is completed before the time when the degree of congestion increases or during the time when the time when the degree of congestion increases is avoided. It is possible to create a work load distribution and a driving model accordingly.

3 is a diagram illustrating an example of a processor configuration of a robot device according to an embodiment of the present invention.

Referring to FIG. 3 , the processor 150 according to an embodiment of the present invention may include a sensor data collecting unit 151 , a time information receiving unit 153 , and a model selecting unit 155 .

The sensor data collection unit 151 may collect sensor data by controlling the sensor unit 130 of the robot device 100 . For example, when the sensor data collection unit 151 receives information on the target location from the control device 200 or when a specific time arrives according to specified scheduling information, at least one of time information and congestion information from the control device 200 . When one is received or when a user input is received, the sensor unit 130 may be activated and sensor data may be collected. The sensor data collection unit 151 may transmit the collected sensor data to the model selection unit 155 .

The time information receiving unit 153 may establish a communication channel with the control device 200 at a predetermined period and receive time information from the control device 200 . The time information may be received according to a decision of the control device 200 or according to a designated scheduling. The time information receiving unit 153 is a control device at a specified time (eg, 07 am and 08 pm, 10 minutes before work starts, 1 hour before the start of movie screening, 10 minutes before the end of class, 10 minutes before arrival of the transportation means, etc.) Time information may be received from 200 . The time information receiver 153 may transmit the received time information to the model selector 155 .

The model selection unit 155 may receive sensor data from the sensor data collection unit 151 and, when receiving time information from the time information receiving unit 153 , receive a target position from the control device 200 . . Alternatively, the target position may be pre-stored in the memory 120 of the robot device 100 . The model selector 155 may determine the received sensor data, time information, and the target position as parameters, and may select an optimal path suitable for the corresponding time information from the plurality of driving models 121 by driving an autonomous driving algorithm. The model selection unit 155 generates a control signal related to the driving of the robot device 100 based on the selected driving model, and transmits the control signal to the driving module 140 and the operation module 160 to the robot device It is possible to carry out the driving and work of (100).

As described above, the processor 150 of the robot device 100 pre-stores a plurality of driving models 121 related to the amount of work and driving of the robot device 100 in the memory 120, and according to the time information, The robot apparatus 100 may be driven by selecting a specific driving model. Meanwhile, the plurality of driving models 121 may be respectively received and stored from the control device 200 .

4 is a view showing another example of the configuration of the processor of the robot device according to an embodiment of the present invention.

Referring to FIG. 4 , the processor 150 according to an embodiment of the present invention may include a sensor data collection unit 151 , an information reception unit 154 , and a model management unit 156 .

The sensor data collection unit 151 may collect sensor data by controlling the sensor unit 130 of the robot device 100 . The sensor data collection unit 151 may have substantially the same or similar configuration to the sensor data collection unit 151 described with reference to FIG. 3 .

The information receiving unit 154 receives specific time information from the control device 200 (eg, a time when congestion or crowd density is expected to show a change over a specified value, movie start time, class end time, transportation means arrival time information) ), congestion level information (eg, movie screening start time, class end time, transportation means arrival time, congestion level information expected in information on the expected number of people to be crowded according to a specific event) may be received. The congestion degree may be calculated based on the number of moviegoers, the expected number of people to be clustered according to the type of movie, the number of people going to school, the number of people using the transportation means, and the like, and the size of the area of the corresponding workplace. The congestion level may be calculated and transmitted by the control device 200 or may be calculated by the information receiving unit 154 . The information receiver 154 may transmit at least one of the received time information and the congestion level information to the model manager 156 .

The model manager 156 may include at least one of a model generator 156a and a model updater 156b. The model generator 156a may generate a driving model for each time information or each congestion level information using an autonomous driving algorithm, and store and manage the generated driving models in the memory 120 . As an example, the model generating unit 156a may calculate the congestion level by time, generate driving models for each congestion level, and store and manage the map with time information. In this operation, when the specified number of driving models are generated, the model generating unit 156a stops generating the driving model, and when at least one of time information and congestion information is received later, the degree of similarity with the received information (eg: The driving model may be selected based on the similarity with the time information used for generating the driving model or the similarity with the congestion level). The model update unit 156b updates the basic model according to time information or congestion level information based on the basic model pre-stored in the memory 120 , for example, and stores the updated driving model in the memory 120 . can manage

5 is a view showing an example of a robot driving method of a robot device according to an embodiment of the present invention.

Referring to FIG. 5 , in relation to the robot driving method according to an embodiment of the present invention, in step 501 , the robot device 100 may check whether time information is received from the control device 200 . In this regard, the robot device 100 may activate a communication function and maintain a state in which a communication channel is established with the control device 200 . According to an embodiment, the robot device 100 may form a short-range wireless communication channel (eg, a Bluetooth communication channel) or a Wi-Fi communication channel with the control device 200 .

When there is no reception of time information from the control device 200 , the robot device 100 may perform driving and work based on the basic model and sensor data in step 503 . In this regard, the memory 120 of the robot device 100 may store a basic model. The robot device 100 may drive to a target position using the basic model stored in the memory 120 . Alternatively, the robot device 100 may activate the sensor unit 130 to collect sensor data and operate an autonomous driving algorithm to move to a target position transmitted by the control device 200 or a pre-stored target position.

Meanwhile, when receiving time information in step 501 , the robot device 100 may perform time information-based model selection in step 505 . In this regard, the robot device 100 may store and manage the plurality of driving models 121 for each time in the memory 120 . The robot device 100 may select a driving model corresponding to the received time information from a plurality of driving models 121 stored in the memory 120 .

In step 507 , the robot device 100 may perform driving and operation based on the selection model and sensor data. In this operation, the robot device 100 may activate the sensor unit 130 and perform obstacle avoidance while driving based on the sensor data received through the sensor unit 130 .

Next, in step 509 , the robot device 100 may check whether an event related to the end of driving occurs. When an event related to the end of driving occurs, the robot device 100 may end the driving and process execution of a specified function. for example,

If there is no event related to the end of driving, the robot device 100 maintains the previous operation (eg, driving and performing tasks based on the basic model or the selected model and sensor data) or branches to step 501 and performs the following operations can be redone.

Meanwhile, in the robot driving method, the robot device 100 may receive driving models for each time information from the control device 200 . Alternatively, when the robot device 100 receives time information (eg, time information when the crowd density is changed) from the control device 200 , the robot device 100 operates an autonomous driving algorithm using the received time information, sensor data, and target location as parameters. to create, store, and operate new driving models.

6 is a view showing another example of a robot driving method of a robot device according to an embodiment of the present invention.

Referring to FIG. 6 , in relation to the robot driving method according to an embodiment of the present invention, the robot device 100 may collect sensor data for driving in step 601 . While the robot device 100 starts collecting sensor data, in step 603 , it may be confirmed whether there is a congestion level reception from the control device 200 . The congestion degree is a crowd density, and may include information on changes in the density of the crowd over time in a designated area (eg, an area in which the robot device 100 will perform a task). When the degree of congestion is greater than or equal to a specified value, the control device 200 may transmit it to the robot device 100 . Alternatively, when the congestion level is expected to change (eg, by identifying the number of people entering and leaving a building or a specific area, the control device 200 detects or expects a change in the congestion level based on the increase or decrease of the number of people), the expected The degree of congestion may be transmitted to the robot device 100 .

When the congestion level is received from the control device 200 , in step 605 , the robot device 100 may update the driving model. For example, when the congestion level is a relatively low congestion level, the robot device 100 may generate a driving model that works while moving to a target location at a first speed, or may update an existing basic model. The robot device 100 may generate a driving model that works while moving to a target location at a second speed (eg, a speed slower than the first speed) to a target location, or may update an existing basic model when the congestion level is a medium congestion level . The robot device 100 generates a driving model that works while moving to a third speed (eg, slower than the second speed) to a target location when the degree of congestion is a relatively high degree of congestion, or updates an existing basic model. can Alternatively, when the degree of congestion is high, the robot device 100 travels at a specified speed (eg, the second speed or the third speed) while avoiding a specified area (eg, a predetermined area including an entrance or exit of a building). and creating a working driving model, or updating the basic model.

In operation 607, the robot device 100 may perform driving based on the updated driving model. In this operation, the robot device 100 may perform a specified task while driving based on the updated model.

Meanwhile, if there is no congestion level reception in step 603 , the robot device 100 may perform basic model-based driving in step 609 . In this operation, the robot device 100 may perform a specified task while driving based on the basic model.

Next, in step 611 , the robot device 100 may determine whether an event related to the end of driving occurs. When an event related to the end of driving occurs, the robot device 100 may end the driving and process execution of a specified function. for example,

If there is no event related to the end of driving, the robot device 100 may maintain the previous operation (eg, perform driving based on the updated driving model or basic model) or branch to step 601 and perform the following operations again. .

7 is a view showing another example of a robot driving method of a robot device according to an embodiment of the present invention.

Referring to FIG. 7 , in relation to the robot driving method according to the embodiment of the present invention, in step 701 , the robot device 100 may check whether time information or congestion information is received from the control device 200 .

When time information or congestion level information is received from the control device 200 , the robot device 100 may check the amount of work in step 703 . The amount of work may be a residual amount of work obtained by subtracting the amount of work performed up to the current time from among the amounts of work set by the manager or provided in advance from the control device 200 while the robot device 100 is disposed in the designated area.

The robot apparatus 100 may update at least one of a traveling speed and a route based on the confirmed amount of work in step 705 . For example, if it is determined that the time point at which the crowd density (or congestion level) increases to more than a specified reference value arrives within a first time from now (eg, determined by checking time information), the robot device 100 It is possible to increase the running speed and the working speed that can handle the remaining amount of work within one hour.

Alternatively, if the robot device 100 determines that the point in time when the crowd density (or congestion) increases below the specified reference value arrives within a second time from now (eg, determined by checking time information), the second time is After calculating the driving speed capable of processing the remaining amount of work from afterward until before the designated task completion time, the driving speed and the operation may be performed while waiting until the second time arrives or maintaining the current speed.

Alternatively, when the robot device 100 receives the congestion level information for each hour, it calculates a driving speed (eg, a speed that may not statistically cause a safety accident) according to the congestion level for each hour, and distributes the workload according to the calculated driving speed. , the driving model can be updated (eg driving speed and route updates) so that the task can be completed within a given time period. With respect to the traveling speed for each congestion level, the robot device 100 may lower the traveling speed in a relatively high congestion section and increase the traveling speed in a relatively low congestion level section. Alternatively, the robot device 100 may generate or update a driving model to stop traveling and work when the congestion level is equal to or greater than a specified maximum value, and to travel at a maximum speed when the congestion level is less than the minimum value. Additionally, the robot device 100 may set a different safety distance from an obstacle according to a change in traveling speed or a change in congestion. For example, when the degree of congestion is high, the robot device 100 lowers the traveling speed and sets a shorter safety distance with an obstacle (eg, a collision avoidance distance set based on sensor data obtained by the sensor unit 130) shorter, When the congestion level is low, the driving speed can be increased and the safe distance from obstacles can be set longer.

In step 707 , the robot device 100 may travel and perform a task based on at least one of the updated travel speed and route.

Meanwhile, when there is no reception of congestion information in step 709 , the robot device 100 may drive and perform a task according to the basic model in step 709 .

Next, in step 711 , the robot device 100 may determine whether an event related to the end of driving occurs. When an event related to the end of driving occurs, the robot device 100 may end the driving and process execution of a specified function. for example,

If there is no event related to the end of driving, the robot device 100 maintains the previous motion (eg, driving and performing a task based on the updated driving speed and route or the basic model) or branches to step 701 and performs the following motions can be redone.

As described above, the robot driving method and system according to an embodiment of the present invention is a technology for performing autonomous driving tasks based on movement in a dense crowd environment over time when a mobile robot autonomously drives in a dense crowd environment is about The method and system of the present invention are time-related time information and intelligence (eg, driving model) received from a control device (eg, an IT system such as Internet of things (IoT)), in which a robot diversifies an autonomous driving plan in the same space. make it possible to perform In particular, the method and system of the present invention can diversify control parameter tuning such as the maximum speed of the robot device 100 in performing work, the level of securing a safe distance from obstacles, as well as efficient path creation or update according to time. , in addition to replacing the algorithm or model according to the conventional situation, it is also possible to add a time variable to the reinforcement learning model.

On the other hand, the embodiments disclosed in the present specification and drawings are merely presented as specific examples to aid understanding, and are not intended to limit the scope of the present invention. It will be apparent to those of ordinary skill in the art to which the present invention pertains that other modifications based on the technical spirit of the present invention can be implemented in addition to the embodiments disclosed herein.

10: Robot driving environment
100: robot device
110: communication circuit
120: memory
130: sensor unit
140: driving module
150: processor
160: work module
200: control device

Claims (9)

Receiving, by the robot device, time information including a congestion degree change time for a designated area from the control device;
generating, by the robot device, a driving model by operating an autonomous driving algorithm based on the time congestion information, sensor data collected by a sensor unit, and a pre-stored target position;
Including, by the robot device, driving based on the generated driving model;
The generating step is
generating a driving model including a path that avoids a specified specific area while driving at a relatively low speed for an increasing time when the congestion level is greater than or equal to a specified value;
and generating a driving model that travels at a relatively high speed in a decreasing time when the congestion level is less than a specified value. driving module for driving;
Including; a processor for controlling the driving module;
the processor is
When receiving time congestion information received from the control device and including a time including a change in crowd density, updating a driving model including at least one of a driving speed and a route of the driving module based on the time congestion information, A robot device, characterized in that the driving is performed based on the updated driving model. 3. The method of claim 2,
the processor is
The robot apparatus according to claim 1, wherein the traveling speed and the route are determined so as to check the time congestion information and process a predefined workload before the density change. 4. The method of claim 3,
the processor is
During the time when the density of the crowd increases, the driving speed is set to lower than before, or a driving model including a path to avoid a specific area is operated,
During the time when the density of the crowd decreases, the driving speed is set to be higher than before, or a driving model including the specific area is set to operate. driving module for driving;
a memory for storing a plurality of driving models in which at least one of a driving speed and a path of the driving module is different;
Including; a processor for controlling the driving module;
the processor is
Upon receiving the time congestion information received from the control device and including the time for the change in crowd density, a driving model corresponding to the change in crowd density included in the time congestion information is selected from the plurality of driving models, and the selected A robot device, characterized in that the driving is performed based on the driving model. 6. The method of claim 5,
the processor is
When the density of the crowd increases, select a driving model that lowers the driving speed than before during time,
When the density of the crowd decreases, during a time period, the robot device, characterized in that it selects a driving model with a higher driving speed than before. driving module for driving;
Including; a processor for controlling the driving module;
the processor is
Receives congestion level information corresponding to the density of the crowd by time from the control device, generates a driving model suitable for each congestion level based on the received congestion level information by time, or selects from pre-stored driving models, and selects the selected driving model for each time A robot device, characterized in that it performs driving based on it. 8. The method of claim 7,
the processor is
generating or selecting a driving model in which the driving speed is relatively low and the safety distance to an obstacle is relatively short in the time of high congestion,
In the time when the congestion level is low, the driving speed is relatively high and the safety distance to the obstacle is relatively long, and a driving model is generated or selected. 8. The method of claim 7,
the processor is
generating or selecting a driving model set to stop driving when the congestion level is greater than or equal to the specified maximum value;
When the congestion degree is less than a specified minimum value, the robot device, characterized in that generating or selecting a driving model that travels at the maximum speed of the driving model.

Images