Device for generating local path and trajectory

The described strategy for generating local paths and trajectories addresses the limitations of existing technologies by enabling robots to adapt to both service and industrial environments, ensuring precision and obstacle avoidance through optimal path selection and Complete Path Planning.

KR103047024B1Active Publication Date: 2026-11-11CLOBOT CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
KR1020240200924
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2024-12-30
Publication Date
2026-11-11
Estimated Expiration
2044-12-30

AI Technical Summary

Technical Problem

Existing local planning technologies for mobile robots are limited in their ability to adapt to both service and industrial environments, failing to provide a general-purpose solution that ensures obstacle avoidance and precision in path generation.

Method used

A strategy for generating local paths and trajectories using a processor to determine the closest point on a global path, analyze obstacles, and select optimal local paths based on obstacle avoidance mode, employing Complete Path Planning techniques to ensure collision-free navigation.

Benefits of technology

Enables robots to efficiently navigate dynamic environments, ensuring precision in industrial settings and obstacle avoidance in service settings, enhancing reliability and predictability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112024145997386-PAT00002_ABST
    Figure 112024145997386-PAT00002_ABST
Patent Text Reader

Abstract

The present invention relates to an apparatus for generating local paths and trajectories. More specifically, the apparatus for generating local paths and trajectories according to the present disclosure comprises: a sensor module for detecting the position of said apparatus; a memory storing at least one process related to the operation of generating said local paths and trajectories; and a processor for performing an operation according to said process. The processor may determine a first point closest to said apparatus among a plurality of points existing on a pre-stored global path, determine a second point among said points that is closer to a target point of said global path than the first point, generate a plurality of local paths using said first point and said second point, determine an optimal local path among said local paths based on whether a collision occurs and whether an obstacle avoidance mode is in place in said local paths, and generate said trajectories based on whether a collision occurs in said optimal local path and whether an obstacle avoidance mode is in place. Other embodiments are also possible.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present disclosure relates to an apparatus for generating local paths and orbits. More specifically, the present disclosure relates to an apparatus for generating local paths and orbits based on strategies that can be used in various scenarios. Background Technology

[0002] Mobile robot technology has recently been attracting significant attention in both service and industrial settings, and the advancement of autonomous driving technology is increasing its potential for application in various fields. One of the core technologies of these mobile robots is Local Planning, which can be considered a crucial element that helps robots plan movement paths in real-time within a given environment, avoid obstacles, and reach target destinations. While various attempts have been made regarding path generation and obstacle avoidance in existing Local Planning technologies, they still have several limitations.

[0003] For example, in industrial settings, it may be critical for robots to maintain a global path as much as possible without colliding with obstacles. This is necessary to maintain process precision and safety and can be effective in environments where interaction with obstacles is limited. On the other hand, in service environments, avoiding obstacles to quickly reach a target point can be a critical requirement. Due to these differing requirements in the two environments, existing local planning technologies may have limitations that make it difficult to apply them as a single, general-purpose solution.

[0004] Accordingly, there is a need for local planning problem-solving strategies applicable to various scenarios in service and industrial settings. Prior art literature

[0005] Patent Document: Korean Published Patent Application No. 10-2019-0111866 The problem to be solved

[0006] The present disclosure aims to provide a generalized local planning problem-solving strategy applicable to various scenarios in service and industrial settings.

[0007] The present disclosure provides a strategy for efficiently solving local planning problems and aims to enable a robot to determine the closest point among points on a global path and generate a local path based on that point.

[0008] The present disclosure aims to enable a robot to detect obstacles that may occur while moving in real time and to select an optimal local path depending on whether an obstacle avoidance mode is activated.

[0009] The present disclosure aims to provide a Local Planning strategy that enables a robot to reach a destination while avoiding obstacles in a service environment and to move safely while minimizing the error with the global path in an industrial environment.

[0010] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0011] An apparatus for generating a local path and a trajectory according to the present disclosure for achieving the above-described technical problem comprises: a sensor module for detecting the position of the apparatus; a memory in which at least one process related to the operation of generating the local path and the trajectory is stored; and a processor for performing an operation according to the process, wherein the processor determines a first point closest to the apparatus among a plurality of points existing on a pre-stored global path, determines a second point among the plurality of points that is closer to a target point of the global path than the first point, generates a plurality of local paths using the first point and the second point, determines an optimal local path among the plurality of local paths based on whether a collision occurs and whether an obstacle avoidance mode is in place in the plurality of local paths, and generates the trajectory based on whether a collision occurs in the optimal area and whether an obstacle avoidance mode is in place.

[0012] Additionally, the processor determines whether the device is on the global path by comparing the first point and the current location of the device, and if the device is on the global path, creates a first local path that connects the first point and the second point and constitutes a part of the global path, and if the device is not on the global path, creates a first local path that connects the current location of the device and the second point, and can store the first local path in the plurality of local paths.

[0013] Additionally, the processor can determine the direction of movement of the device on the global path based on the second point, generate a plurality of second sub-points that are moved in a direction perpendicular to the direction of movement, and store paths connecting the current location of the device and each of the plurality of second sub-points in the plurality of local paths.

[0014] In addition, the processor analyzes the plurality of local paths to determine whether there is a collision with an obstacle, and if the device is in the obstacle avoidance mode, it can set a local path among the plurality of local paths that is capable of entering the global path or constitutes a part of the global path as the optimal local path.

[0015] Additionally, when the device is not in the obstacle avoidance mode, the processor may evaluate the plurality of local paths based on non-collision conditions and set the optimal local path based on whether there is a collision with the obstacle and the non-collision conditions.

[0016] In addition, the processor may determine whether a collision actually occurs in the optimal local path set above, and if it determines that no collision occurs, set one of the points existing in the optimal local path as a local trajectory target point, perform velocity profiling from the current position of the device to the local trajectory target point, and generate the trajectory based on the result of the profiling.

[0017] Additionally, when the processor determines that the collision has occurred, it checks whether the device is in the obstacle avoidance mode, and if the device is not in the obstacle avoidance mode, it sets the local trajectory target point by considering the movement margin of the device at the point where the first collision occurs among the optimal local paths, performs speed profiling from the current position of the device to the local trajectory target point, and can generate the trajectory based on the result of the profiling.

[0018] Additionally, when the device is in the obstacle avoidance mode, the processor sets a region of interest including the current location of the device based on the global path based on the SO2 space, performs a Complete Path Planning technique on a path connecting the current location of the device to the second point based on the SO2 space and the region of interest, and the SO2 space may be a space representing a state including the location and orientation of the device in a two-dimensional plane.

[0019] In addition, the processor determines whether the result of the execution according to the Complete Path Planning technique is successful, and if the result of the execution according to the Complete Path Planning technique is unsuccessful, sets the local trajectory target point by considering the movement margin of the device at the point where the first collision occurs among the optimal local paths, performs velocity profiling from the current position of the device to the local trajectory target point, and can generate the trajectory based on the result of the execution.

[0020] In addition, if the result of the execution according to the Complete Path Planning technique is successful, the processor may perform trajectory planning using the local path generated according to the Complete Path Planning technique as a reference path, and if the trajectory planning is successful, may store the trajectory generated according to the trajectory planning and the reference path.

[0021] In addition to this, a computer-readable recording medium for recording a computer program for implementing the present disclosure may be further provided. Effects of the invention

[0022] According to the aforementioned means for solving the problem of the present disclosure, a general-purpose local planning strategy capable of satisfying all diverse requirements of service and industrial sites can be provided. Through this, a robot can stably generate a trajectory even in a dynamic environment and reach a target point.

[0023] According to the aforementioned means for solving the problem of the present disclosure, an optimal local path can be selected by generating a plurality of local path candidates and evaluating them. Through this, the possibility of collision can be minimized and safety improved compared to existing path generation algorithms.

[0024] According to the aforementioned means for solving the problem of the present disclosure, flexible path selection is possible depending on whether the obstacle avoidance mode is activated. In a service environment, a target point can be reached while avoiding obstacles, and in an industrial environment, the precision of the operation can be ensured by maintaining the global path as much as possible.

[0025] According to the aforementioned means for solving the problem of the present disclosure, a robot can implement a human-intuitive movement pattern by generating an optimal local trajectory based on a global path. This can increase reliability and predictability in interaction with a user.

[0026] According to the aforementioned means for solving the problem of the present disclosure, by performing path planning using the Complete Path Planning technique and SO2 space, it is possible to enable stable path search and trajectory generation even in complex environments. Through this, the efficiency of the planning algorithm can be improved compared to existing technologies.

[0027] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0028] FIG. 1 is a block diagram illustrating the detailed configuration of a device according to an example of the present invention. FIG. 2 is a flowchart illustrating a method for generating a local path and a trajectory according to an example of the present invention. FIG. 3 is a flowchart illustrating a local path generation method according to an example of the present invention. FIGS. 4 and FIGS. 5 are exemplary diagrams illustrating a local path method according to an example of the present invention. FIG. 6 is a flowchart illustrating a method for generating an optimal local path according to an example of the present invention. FIG. 7 is an exemplary diagram illustrating a method for generating an optimal local path according to an example of the present invention. FIG. 8 is a flowchart illustrating a method for generating a trajectory and an optimal local path according to an example of the present invention. Specific details for implementing the invention

[0029] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms 'part, module, component, block' as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of 'parts, modules, components, blocks' may be implemented as a single component, or a single 'part, module, component, block' may include a plurality of components.

[0030] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0031] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0032] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.

[0033] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0034] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0035] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0036] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.

[0037] In this specification, the term "device according to the present disclosure" includes all various devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include all of a computer, a mobile robot, a cleaning robot, a server device, and a portable terminal, or may be in the form of any one of these.

[0038] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0039] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0040] The above portable terminal may include, for example, all types of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smartphones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0041] FIG. 1 is a block diagram illustrating the detailed configuration of a device according to an example of the present invention.

[0042] Referring to FIG. 1, a local path and trajectory generating device (10) according to the present disclosure may include a processor (100), a sensor module (200), a communication module (300), a memory (400), and a driving module (500).

[0043] In one embodiment, the sensor module (200) is a component for detecting the current location of the device or the location of obstacles in the environment, and can contribute to increasing the operational stability of the device (10). This module may include various sensors such as LIDAR, camera sensors, and ultrasonic sensors, and can provide environmental data to the processor (100) in real time. Through this, the device (10) can efficiently generate local paths even in a dynamic environment.

[0044] For example, the sensor module (200) may include at least one of LiDAR (Light Detection and Ranging), proximity sensor, illumination sensor, touch sensor, acceleration sensor, magnetic sensor, gravity sensor (G-sensor), gyroscope sensor, motion sensor, RGB sensor, infrared sensor (IR sensor: infrared sensor), fingerprint sensor (finger scan sensor), ultrasonic sensor, optical sensor (e.g., camera), microphone, environmental sensor (e.g., including at least one of a barometer, hygrometer, thermometer, radiation detection sensor, heat detection sensor, gas detection sensor), and chemical sensor (e.g., healthcare sensor, biometric sensor, etc.). Meanwhile, the device may combine and utilize information sensed from at least two of these sensors.

[0045] In one embodiment, the communication module (300) is a component that performs data exchange between the local path and trajectory generating device (10) and an external system, and can provide status information of the device (10) to an external monitoring system or receive global path and environment information from the outside. This module can enable stable communication by utilizing Wi-Fi, Bluetooth, cellular networks, etc.

[0046] For example, the communication module (300) may include one or more components that enable communication with an external device, and may include, for example, at least one of a wireless communication module, a short-range communication module, and a location information module.

[0047] In one embodiment, the wireless communication module may include a wireless communication module that supports various wireless communication methods, such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a Wi-Fi module and a WiBro (Wireless broadband) module.

[0048] The wireless communication module may include a wireless communication interface comprising an antenna and a receiver for receiving a signal from a server. Additionally, the wireless communication module may further include a signal conversion module for demodulating an analog wireless signal received through the wireless communication interface into a digital control signal.

[0049] In one embodiment, the short-range communication module is for short-range communication and can support short-range communication by using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0050] In one embodiment, the memory (400) is a device for storing data necessary for the processor (100) to perform operations, and may include global path data, local path candidates, obstacle data, and completed trajectory data. Additionally, the processor may perform real-time calculations based on the data stored in the memory and continuously update the generated path data.

[0051] For example, the memory (400) can store data supporting various functions of the device and programs for the operation of the processor, and can store input / output data (e.g., music files, still images, videos, etc.), and can store a number of application programs (or applications) running on the device, data for the operation of the device, and instructions. At least some of these application programs can be downloaded from an external server via wireless communication.

[0052] Such memory (400) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (140) may be a database that is separated from the device but connected via wired or wireless connection.

[0053] In one embodiment, the drive module (500) is a component that physically moves the device based on the optimal local path and trajectory generated by the processor (100), and may include various moving mechanisms such as wheel-type or leg-type. The drive module precisely controls the speed and direction so that the device (10) can move along the generated path.

[0054] In one embodiment, the processor (100) serves as a central control unit of the local path and trajectory generation device (10) and can perform major operations and control operations of the device. The processor can determine the closest point (first point) and the target point (second point) among a plurality of points based on pre-stored global path data. Additionally, it can generate a plurality of local path candidates and determine the optimal local path by analyzing whether there is a collision and the obstacle avoidance mode state. The processor generates a trajectory based on the optimal local path and, if necessary, uses a Complete Path Planning technique to enable stable path search even in complex environments.

[0055] For example, the processor (100) may be implemented with a memory that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the device, and at least one processor (not shown) that performs the aforementioned operation using the data stored in the memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0056] At least one component may be added or removed in response to the performance of the components illustrated in FIG. 1. Additionally, it will be readily understood by those skilled in the art that the relative positions of the components may be changed in response to the performance or structure of the system.

[0057] Meanwhile, each component illustrated in Fig. 1 refers to a software and / or hardware component such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0058] FIG. 2 is a flowchart illustrating a method for generating a local path and a trajectory according to an example of the present invention. The operations disclosed in FIG. 2 can be performed by the device (10) of FIG. 1.

[0059] Referring to FIG. 2, in one embodiment, in operation 21, the processor (400) can determine a first point closest to the device among a plurality of points existing on a global path that is previously stored in memory (300). For example, the processor (400) can analyze the stored global path data to determine the point (first point) closest to the location of the device (10) detected through the current sensor module (200). In this process, the current location of the device (10) can be updated in real time through data input such as a LIDAR, ultrasonic, or camera sensor.

[0060] For example, assuming that a device (10) in a warehouse is located in front of shelf 1, the first point can be set as a coordinate on a global path near the shelf. This allows the device (10) to accurately determine where it is currently located on the global path.

[0061] In one embodiment, in operation 22, the processor (400) can determine a second point as a goal required for a local plan using the first point. For example, the processor (400) can select a second point from among points that exist on the global path relative to the first point and are ahead of the first point, using the state of the device (speed, angle of travel information, etc.). This is an important step for the device (10) to set a short-term goal and determine the next area to move to. For example, if the global path consists of A, B1, and C, and the first point is A, the second point is set to B1. In this process, the device (10) can be designed to move naturally in the direction where the target point C is located.

[0062] In one embodiment, in operation 23, the processor (400) can generate a plurality of local paths using a first point and the second point. For example, the processor (400) can generate an initial local path by connecting the first point and the second point, and additionally set a plurality of sub-points that are vertically parallel to the second point. Each sub-point can be used as a local planning target point to generate an alternative path to minimize the possibility of collision and avoid obstacles.

[0063] For example, multiple local paths are generated by creating curves that are compatible with human intuition and can be quickly generated, starting from the robot's current position as the starting point and reaching the second point and sub-points. These multiple local paths generated in this way are named intuitive local paths.

[0064] In one embodiment, in operation 24, the processor (400) can determine the optimal local path among the plurality of intuitive local paths based on whether a collision occurs and whether obstacle avoidance is involved. For example, if an obstacle such as a box is present on the passageway, and the obstacle avoidance mode is disabled, the device can select a path that can precisely pass through the box or stop.

[0065] For example, in the case of an industrial site, the main requirement of Local Planning is to follow the global path as accurately as possible. In such an environment, lateral error must be minimized, and if an obstacle appears, the device can be designed to stop at a point where it does not collide. Accordingly, the processor (400) analyzes the possibility of collision for multiple local paths and, when the obstacle avoidance mode is disabled, prioritizes selecting a path with high similarity to the global path and can utilize it even when an obstacle is present. For example, if an obstacle such as a box is present on a passageway and the obstacle avoidance mode is disabled, the device performs a collision check on the path with the highest similarity, and if no collision occurs, it passes through the box precisely, or if a collision occurs, it stops using a point on that path where no collision with the obstacle does not occur as a target point.

[0066] On the other hand, in the case of a service site, reaching a specific target point is prioritized. In this environment, the lateral error with respect to the global path is not very important, and it is necessary to reach the target point while effectively avoiding obstacles. Therefore, when the obstacle avoidance mode is activated, the processor (400) can select a local path that can bypass obstacles relative to the global path. For example, if it is necessary to reach a target point by bypassing a box on a passageway, a path that can safely bypass the box can be selected.

[0067] At this stage, the processor (400) can determine whether the operating mode of the current device (10) is active or inactive by referring to the obstacle avoidance mode setting value stored in memory (500). If the obstacle avoidance mode is active, the processor (400) can generate a path that has a low probability of collision with obstacles and meets the requirements of the service site, and select this as the optimal path. On the other hand, if the obstacle avoidance mode is inactive, it can select a path that follows the global path as precisely as possible to meet the requirements of the industrial site, or stop at a point where collision with obstacles can be avoided.

[0068] In conclusion, operation 24 can serve as an important branching point for determining the optimal path according to the driving environment of the device (10). This allows the device to meet the requirements of both service sites and industrial sites, and to drive effectively and safely in various environments.

[0069] In one embodiment, in operation 25, the processor (400) can generate the trajectory based on whether a collision occurs in the optimal area and whether the obstacle avoidance mode is active. For example, the processor (400) can generate the trajectory of the device (10) based on the optimal area path.

[0070] In one embodiment, trajectory generation is achieved through a process of profiling the speed and direction from the current position of the device (10) to the target point, and since the trajectory is generated using an intuitive path, the trajectory can also be generated in accordance with intuition.

[0071] However, while the optimal path obtained from intuitive local paths has the advantages of fast generation speed and intuitiveness, it has the disadvantage of not guaranteeing collision-free status. It works well in situations with relatively few obstacles, but a collision-free path may not be generated in situations where obstacles are numerous and irregularly placed.

[0072] Therefore, to compensate for these shortcomings, complete path planning techniques can be utilized, enabling the generation of collision-free paths even in complex environments.

[0073] The Complete Path Planning technique is a technology that analyzes the entire environment based on global and local paths and generates an optimal trajectory by considering obstacles and limitations. This technique can represent a state including position and orientation information of the device (10) by utilizing a two-dimensional plane (SO2 space). Through this, the device (10) can efficiently explore a drivable area and maximize safety and mobility.

[0074] For example, the processor (400) can obtain a collision-free local path by considering only the kinematics of the device or, if time permits, also considering the dynamics, with the last point of the optimal intuitive local path as the target point. The local path obtained in this way may differ from human intuition, but it can guarantee collision-freeness. The processor (400) can set the obtained local path as the optimal local path and generate a trajectory that can stably pass between shelves while avoiding obstacles through velocity profiling on the optimal local path.

[0075] Meanwhile, if an attempt to generate an intuitive local path fails, local path generation through complete path planning can be performed repeatedly at every moment, and once the situation where there are irregularly placed obstacles is resolved, an intuitive trajectory can be generated again.

[0076] In one embodiment, in operation 26, the processor (400) can transmit a control command to the driving module (500) to move the device (10) according to the optimal local path and trajectory. For example, the processor (400) can transmit a control command to the driving module (500) based on the optimal local path and trajectory data generated in operation 25. This command includes the movement direction, speed, rotation angle, etc. of the device (10), and the driving module (500) can execute it in real time to move the device (10).

[0077] For example, if the device (10) needs to move to a target point by bypassing an obstacle, the processor (400) calculates speed and direction data for the bypass path and transmits it to the drive module (500). The drive module (500) can then control the wheels or moving device of the device (10) to perform smooth and accurate movement.

[0078] Specifically, the processor (400) can subdivide the trajectory data to sequentially generate movement commands that the device (10) must perform at each point on the path. These commands are designed to allow the device (10) to move stably to a target point without deviating from the trajectory. For example, if it must pass through a narrow passage, the processor (400) can send a command to the drive module (500) to reduce speed and fine-tune the steering angle.

[0079] In addition, to respond to unexpected situations that may occur during operation (e.g., the appearance of a new obstacle), the processor (400) receives real-time data from the sensor module (200) and can dynamically adjust the drive command. This allows the device (10) to immediately reflect changes in the surrounding environment and maintain optimal movement.

[0080] FIG. 3 is a flowchart illustrating a local path generation method according to an example of the present invention, and FIG. 4 and FIG. 5 are illustrative diagrams illustrating a local path method according to an example of the present invention. The operations disclosed in FIG. 3 can be performed by the device (10) of FIG. 1.

[0081] Referring to FIGS. 3 to 5, in one embodiment, in operation 31, the processor (400) can determine a first point closest to the device among a plurality of points existing on a previously stored global path. For example, as shown in FIG. 4, the processor (400) can analyze global path data stored in memory (300) to determine a point (first point (A)) closest to the current location of the device (10) detected by the sensor module (200).

[0082] In this process, the sensor module (200) measures the current location of the device (10) through a LIDAR, camera, or ultrasonic sensor and provides this to the processor (400). For example, if the device (10) in the warehouse is located in front of a specific shelf, the first point can be set as the point on the global path closest to the shelf. This is designed so that the device (10) can check its current location on the global path and not deviate from the path.

[0083] In one embodiment, in operation 32, the processor (400) can determine a second point as a goal required for local planning using the first point. For example, the processor (400) can select a second point from among points that exist on the global path relative to the first point and are ahead of the first point, using the state of the device (speed, angle of travel information, etc.). For example, as shown in FIG. 4, B1, which is closer to the goal point than the first point (A), is set as the second point. Through this, the device (10) can move efficiently in the direction of the goal.

[0084] In one embodiment, in operations 33 and 34, the processor (400) can determine whether the device is on the global path by comparing the first point with the current location of the device. For example, the processor (400) can determine whether the device (10) is on the global path by comparing the first point with the current location of the device (10) detected through the sensor module (200).

[0085] If the device (10) is on a global path, the device (10) can move along the given path, and if it deviates from the global path, a new path must be created. For example, if the device (10) deviates from the path due to an obstacle, the processor (400) can recognize this and start a new path creation process.

[0086] In one embodiment, if the device is on the global path as a result of the determination, in operation 35, the processor (400) may create a first local path that connects the first point and the second point and constitutes a part of the global path.

[0087] For example, if it is determined that the device (10) is on a global path, the processor (400) may create a first local path that connects a first point and a second point and constitutes part of the global path. For example, if the device (10) needs to move from A to B1 as shown in FIG. 5, the first local path may be set to A1 as shown in (a).

[0088] In one embodiment, if the determination result shows that the device is not on the global path, in operation 36, the processor (400) can create a path connecting the current location of the device and the second point as the first local path.

[0089] For example, if the device (10) is not on the global path, the processor (400) can generate a first local path connecting the current location of the device (10), detected through the sensor module (200), and a second point. In this case, the processor (400) can calculate a path that allows the device (10) to move to a target point even in a complex environment or bypassing obstacles. For example, as shown in FIG. 5, if the device (10) needs to move from its current location to B1, the first local path can be set to A1 as shown in (b). This path enables efficient movement while minimizing the error with the global path.

[0090] In one embodiment, in operation 37, the processor (400) may store the first local path in the plurality of local paths. For example, the processor (400) may store the first local path generated in operation 35 or operation 36 in the plurality of local paths. This is to allow storing multiple alternative paths and selecting the optimal path through comparative evaluation when necessary. For example, if multiple paths capable of bypassing an obstacle are generated, all paths may be stored in the plurality of local paths, and then the optimal path may be selected based on collision probability, movement efficiency, etc.

[0091] FIG. 6 is a flowchart illustrating a method for generating an optimal local path according to an example of the present invention, FIG. 7 is an illustrative diagram illustrating a method for generating an optimal local path according to an example of the present invention, and the operations disclosed in FIG. 6 can be performed by the device (10) of FIG. 1.

[0092] Referring to FIG. 6, in one embodiment, in operation 71, the processor (400) can determine the direction of travel of the device on the global path based on a second point and generate a plurality of second sub-points that are parallel to the direction of travel. Each sub-point can be used as a local planning target point to generate an alternative path to minimize the possibility of collision and avoid obstacles. For example, as shown in FIG. 7, B2, B3, and B4 can be generated as second sub-points.

[0093] For example, when the device (10) moves between shelves in a warehouse, the second point can be set as the end point of the shelf. At this time, the processor (400) can prepare basic data for local path generation by generating multiple points (second sub-points) that are moved left and right at regular intervals based on the direction of travel. This provides the possibility of various path selections considering obstacle avoidance.

[0094] In one embodiment, in operation 72, the processor (400) may store paths connecting the current location of the device and each of the plurality of second sub-points in the plurality of local paths. For example, starting from the robot's current location as a starting point, a plurality of local paths are generated as curves that can be quickly generated in accordance with human intuition to reach the second point and the second sub-points. The plurality of local paths generated in this way are named intuitive local paths. Among the intuitive local paths, the optimal local path can be determined based on whether a collision occurs and whether obstacle avoidance is involved.

[0095] In one embodiment, in operation 73, the processor (400) can analyze a plurality of intuitive local paths to determine whether there is a collision with an obstacle. For example, the sensor module (200) collects surrounding obstacle data through LIDAR, ultrasound, or a camera and provides it to the processor (400). For example, if an obstacle in a hallway is located on the right, the right detour path is evaluated as having a high probability of collision, while the straight path and the left detour path are evaluated as having a low risk of collision.

[0096] In one embodiment, in operation 74, the processor (400) can determine whether the device (10) is in obstacle avoidance mode. This operation can serve as a critical turning point in meeting different requirements depending on whether the environment in which the device (10) is currently operating is an industrial site or a service site.

[0097] In the case of an industrial site, the most important aspect of Local Planning is that the device travels along a global path designated in advance by a person with minimal lateral error. If an obstacle is present during this process, the device (10) may be required to stop without colliding with the obstacle. Therefore, the processor (400) can determine whether the device is set to follow the global path as accurately as possible by checking whether the obstacle avoidance mode is disabled.

[0098] On the other hand, in a service field, the goal is to reach a specific point along a global path, and the occurrence of lateral error with respect to the global path is relatively insignificant. An important factor required in a service field is to reach the target point by effectively avoiding obstacles. Therefore, the processor (400) can determine whether the device is configured to generate an appropriate path and drive in a service environment by checking whether the obstacle avoidance mode is activated.

[0099] This operation serves as an initial judgment step to distinguish between the requirements of industrial sites and service sites, and can influence local path generation and optimal path setting in subsequent operation stages. When obstacle avoidance mode is activated, the device moves according to the path generation method required by the service site, and when deactivated, it operates using a path generation method suitable for the requirements of the industrial site.

[0100] In one embodiment, if the device is in the obstacle avoidance mode as a result of verification, in operation 75, the processor (400) can set the local path that is capable of entering the global path or constitutes a part of the global path among the plurality of intuitive local paths as the optimal local path.

[0101] In one embodiment, if the device is not in the obstacle avoidance mode as a result of verification, in operation 76, the processor (400) may evaluate the plurality of intuitive local paths based on non-collision conditions. For example, non-collision conditions may include proximity to an obstacle, right-hand traffic, similarity to a global path, etc. For example, if a left path is more similar to a global path and conforms to the right-hand traffic rule, this path may receive a high score.

[0102] In one embodiment, in operation 77, the processor (400) may set the optimal local path based on whether there is a collision with an obstacle and the conditions other than the collision. For example, if a straight path is evaluated as having the lowest probability of collision and being similar to the global path, the processor (400) may set it as the optimal path and prepare a command for the device to move along the path.

[0103] FIG. 8 is a flowchart illustrating a method for generating a trajectory and an optimal local path according to an example of the present invention. The operations disclosed in FIG. 8 can be performed by the device (10) of FIG. 1.

[0104] Referring to FIG. 8, in one embodiment, in operation 81, the processor (400) can determine whether a collision actually occurs in the set optimal local path. This can be done by the processor (400) analyzing obstacle information collected through a sensor module and examining each point on the current path to check for the possibility of a collision. For example, the processor can calculate the location of obstacles and whether the path overlaps while moving along the current optimal local path, and if it determines that a risk of collision exists, it can record this.

[0105] In one embodiment, if it is determined that no collision occurs, in operation 82, the processor (400) may set any one of the points existing in the optimal local path as the local trajectory target point. In this process, the processor may select the most efficient point based on the distance from the target point of the global path, or set a point where the change in speed is minimized by considering the movement stability of the device (10).

[0106] In one embodiment, in operation 83, the processor (400) can perform speed profiling from the current location of the device to a local trajectory target point. Speed ​​profiling is the task of establishing a speed plan that ensures smooth and efficient movement by considering the acceleration, deceleration, and maximum speed of the device (10). Subsequently, the processor can generate a trajectory according to the speed profile and store it in memory (400). When this step is completed, the processor can proceed to operation 91 to store the optimal local path and the generated trajectory and terminate the operation.

[0107] In one embodiment, if it is determined that a collision has occurred, in operation 84, the processor (400) can check whether the device is in the obstacle avoidance mode. Whether the obstacle avoidance mode is active can be determined through the current setting value stored in memory (400). This step plays an important role in distinguishing whether the environment in which the device (10) is operating is a service site or an industrial site. Whether the obstacle avoidance mode is active can be determined through the current setting value stored in memory (500).

[0108] In an industrial setting, it is important for the device to follow a pre-designated global path as accurately as possible and to drive without lateral errors. At this time, if an obstacle appears, it is a basic requirement for the device to stop without colliding with the obstacle. Accordingly, the processor (400) can check whether the mode is disabled by referring to the obstacle avoidance mode setting value stored in memory (500). If it is disabled, the device can operate to follow the global path according to the requirements of the industrial setting and stop moving when an obstacle occurs.

[0109] On the other hand, in a service field, the goal is to reach a specific point along a global path, and lateral error is not very important. An important factor in a service field is to reach the target point while effectively avoiding obstacles. In this case, the processor (400) checks whether the obstacle avoidance mode is activated, and if it is activated, the device can move to the target point by creating an appropriate path while avoiding obstacles.

[0110] Therefore, the obstacle avoidance mode check step in operation 84 can serve as a branching point for the device to perform appropriate operations according to the characteristics of the driving environment. When the obstacle avoidance mode is activated, the device operates according to the requirements of the service site, and when it is deactivated, it can perform operations that meet the requirements of the industrial site. As a result, the device can be designed to enable efficient and safe driving in various environments.

[0111] In one embodiment, when the device is not in the obstacle avoidance mode, in operation 85, the processor (400) may set the local trajectory target point by considering the movement margin of the device at the point where the first collision occurs in the optimal local path. This is a step that ensures the device (10) maintains a safe distance to avoid a collision. Then, the processor (400) may proceed to operation 83 to perform speed profiling from the device's current position to the local trajectory target point, generate the trajectory based on the result of the profiling, and proceed to operation 91 to store the optimal local path and trajectory.

[0112] In one embodiment, when the device is in the obstacle avoidance mode, in operation 86, the processor (400) may set a region of interest including the current location of the device based on the global path based on the SO2 space. The SO2 space is a state space including the location and orientation of the device (10) in a two-dimensional plane, and the region of interest may limit the range of path search by considering obstacle information.

[0113] In one embodiment, in operation 87, the processor (400) may perform a Complete Path Planning technique on a path connecting the current location of the device to the second point based on the SO2 space and the region of interest. This technique may include an algorithm that evaluates possible paths, prevents collisions, and ensures efficient movement to a target point. This technique aims to evaluate possible paths, prevent collisions, and ensure efficient movement to a target point.

[0114] In one embodiment, the Complete Path Planning technique can first generate a state space representing the position and orientation information of the device (10) by utilizing the SO2 space. The SO2 space is composed of information including the physical position of the device in a two-dimensional plane as well as the direction of movement and the direction of rotation. Through this, the device can clearly distinguish between areas where it can move and areas where it cannot move. For example, a space blocked by obstacles or walls can be defined as an area where movement is impossible, and the device must avoid such a space.

[0115] In one embodiment, the processor (400) can set a region of interest within the SO2 space and explore possible paths within this region. The region of interest is defined as a limited space related to movement from the device's current location to a target point, thereby increasing computational efficiency. A Complete Path Planning technique generates a path within this region, and the path can be designed to minimize the possibility of collision and maximize movement efficiency.

[0116] In the path generation process, the processor (400) can evaluate all possible paths and analyze the safety, efficiency, and feasibility of each path.

[0117] For example, multiple paths are generated within the region of interest for the device to reach a target point. In this case, each path is generated considering the possibility of collision with obstacles.

[0118] For example, generated path candidates are evaluated and ranked based on safety (distance from obstacles), movement efficiency (path length and curvature), and stability (smoothness of speed and acceleration).

[0119] For example, based on the evaluation results, the route with the highest score is selected as the optimal route. This route becomes the safest and most efficient way to reach the target destination.

[0120] For example, if the device (10) needs to pass through a narrow passage or bypass an obstacle, the Complete Path Planning technique can generate a smooth curved path to reduce the risk of collision in the narrow space. In this process, the path is designed by taking into account the device's dynamic constraints (e.g., maximum speed, maximum turning radius).

[0121] Additionally, the Complete Path Planning technique can be designed to incorporate a predictive control technique so that the device can immediately respond to potential collisions or changed environmental conditions that may occur while moving. For example, if the device detects a new obstacle while moving, the processor (400) can adjust the existing path in real time to prevent a collision.

[0122] In one embodiment, in operation 88, the processor (400) can determine whether the result of execution according to the Complete Path Planning technique is successful.

[0123] In one embodiment, if the result of the above execution according to the Complete Path Planning technique fails, the processor (400) may proceed to operation 85 to set the local trajectory target point by considering the movement margin of the device at the point where the first collision occurs among the optimal local paths, proceed to operation 83 to perform speed profiling from the current position of the device to the local trajectory target point, generate the trajectory based on the result of the above execution, and proceed to operation 91 to save the optimal local path and trajectory.

[0124] In one embodiment, if the result of the execution according to the Complete Path Planning technique is successful, in operation 89, the processor (400) can perform trajectory planning using the local path generated according to the Complete Path Planning technique as a reference path. Trajectory planning is an additional planning task that ensures the device (10) moves along the reference path and operates stably and efficiently.

[0125] In one embodiment, in operation 90, the processor (400) can determine whether trajectory planning is successful.

[0126] In one embodiment, if trajectory planning is successful, in operation 91, the processor (400) can store the trajectory generated according to the trajectory planning and the reference path (optimal local path).

[0127] In one embodiment, on the other hand, if trajectory planning fails, the processor (400) may proceed to operation 85 to set the local trajectory target point by considering the movement margin of the device at the point where the first collision occurs in the optimal local path, proceed to operation 83 to perform speed profiling from the current position of the device to the local trajectory target point, generate the trajectory based on the result of the operation, and proceed to operation 91 to save the optimal local path and trajectory.

[0128] The present invention has technical features that enable a robot to reach a target point stably and efficiently while effectively avoiding obstacles on a global path in a device for generating local paths and trajectories. The present invention can systematically and organically perform complex path planning and trajectory generation tasks by combining various components such as a sensor module (200), a processor (400), a memory (400), and a driving module (500).

[0129] In particular, the present invention can provide the following technical features and effects. First, it can efficiently provide core basic data for generating local paths by determining a first point closest to the robot on a pre-stored global path and a second point as a goal required for local planning. Second, it can ensure stable and safe movement of the robot by generating multiple local paths and selecting an optimal path by considering the possibility of collision and obstacle avoidance modes in each path. Third, it provides an appropriate alternative path depending on whether a collision occurs and the obstacle avoidance mode, and enables path search and trajectory planning even in complex environments by utilizing additional spatial information, such as SO2 space, when necessary.

[0130] In addition, through velocity profiling and trajectory planning techniques, the robot can perform smooth and efficient movement to a target point, and the trajectory generation results can be stored in memory to maintain continuity in the next movement. This technical configuration can effectively solve problems such as path collisions, inefficient path search, and movement instability that may occur in existing path planning and trajectory generation systems.

[0131] Through the application of the present invention, robots can move to target points while avoiding obstacles in various application fields, such as industrial sites or service environments, thereby significantly improving the practicality and stability of autonomous robots. This can ultimately contribute to increasing work efficiency, ensuring the reliability of robot-based automation systems, and enhancing user satisfaction.

[0132] Therefore, the present invention provides a groundbreaking solution capable of effectively performing path planning and trajectory generation for autonomous robots even in complex environments, and presents a new technical approach that can overcome the limitations of existing technologies.

[0133] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0134] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0135] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively. Explanation of the symbols

[0136] 10: Local path and trajectory generator 100 : Processor 200 : Sensor module 300: Communication module 400 : Memory 500 : Drive module

Claims

Claim 1 A device for generating a local path and an orbit, comprising: a sensor module for detecting the position of said device; and a memory in which at least one process related to the operation of generating said local path and said orbit is stored. The system includes a processor that performs operations according to the above process, wherein the processor determines a first point closest to the device among a plurality of points existing on a pre-stored global path, determines a second point on the global path that is closer to a target point than the first point based on the first point, generates a plurality of local paths using the first point and the second point, generates a plurality of sub-points in a direction perpendicular to the direction of travel based on the second point, generates a plurality of local paths connecting the current position of the device with the second point and the plurality of sub-points, respectively, determines an optimal local path for the plurality of local paths based on whether there is a collision with an obstacle and whether there is an obstacle avoidance mode, and if the optimal local path is determined to include a collision, if the device is not in obstacle avoidance mode, sets a local trajectory target point considering the movement margin of the device based on the point where the first collision occurs on the optimal local path, performs velocity profiling from the current position of the device to the local trajectory target point, and if the device is in obstacle avoidance mode, sets a region of interest including the current position of the device based on the global path based on SO2 space. Sets, and performs a Complete Path Planning technique on a path connecting the current location of the device to the second point based on the SO2 space and the region of interest; if the result of performing the Complete Path Planning technique is successful, generates a trajectory based on the generated path; if the result of performing the Complete Path Planning technique fails, sets the local trajectory target point and performs velocity profiling.A device characterized by generating a trajectory including position and velocity over time from the current position of the device to a target point based on the result of the above-described velocity profiling, and, if it is determined that the optimal local path does not include a collision, setting a point on the optimal local path as a local trajectory target point and generating the trajectory. Claim 2 A device according to claim 1, wherein the processor determines whether the device is on the global path by comparing the first point and the current location of the device, and if the device is on the global path, creates a first local path that connects the first point and the second point and constitutes a part of the global path, and if the device is not on the global path, creates a first local path that connects the current location of the device and the second point, and stores the first local path in the plurality of local paths. Claim 3 delete Claim 4 The device according to claim 1, wherein the processor analyzes the plurality of local paths to determine whether there is a collision with an obstacle, and when the device is in the obstacle avoidance mode, sets a local path among the plurality of local paths that is capable of entering the global path or constitutes a part of the global path as the optimal local path. Claim 5 A device according to claim 4, wherein the processor evaluates the plurality of local paths based on non-collision conditions when the device is not in the obstacle avoidance mode, and sets the optimal local path based on whether there is a collision with the obstacle and the non-collision conditions. Claim 6 delete Claim 7 delete Claim 8 delete Claim 9 delete Claim 10 delete

Citation Information

Patent Citations

  • Path planning apparatus and method for autonomous vehicle

    KR101795250B1

  • Apparatus and method for generating path of mobile robot or grond vehicle

    KR1020130065126A

  • Apparatus for planning dual path and determining road judgement area for autonomous driving and method using thereof

    KR1020200063039A