Mother-son type intelligent traffic robot scheduling system

Abstract

The invention belongs to the technical field of traffic robots, and discloses a child-mother type intelligent traffic robot scheduling system, which comprises a mother ship, child action units and a body sensing unit, and is characterized in that the mother ship comprises an edge calculation module arranged in the mother ship and a power unit arranged at the bottom of the mother ship, and each child action unit comprises a lightweight ROS chassis; a traffic cone and an RTK module are arranged at the top of the light-weight ROS chassis, the RTK module is connected with an edge calculation module, a power module is arranged in the light-weight ROS chassis, the power module is connected with the edge calculation module and the RTK module, and a body sensing unit is arranged at the front top of a mother ship and connected with the edge calculation module; according to the invention, the formation of the sub-action units can be realized, the operation efficiency is obviously improved, the path planning of the mother ship can be realized, the intelligentization, clustering and automatic upgrading of traffic management operation are realized, and the labor cost and the safety risk are effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of transportation robot technology, and specifically to a mother-daughter intelligent transportation robot scheduling system. Background Technology

[0002] Traffic robots are intelligent devices applied to transportation systems. By integrating perception, decision-making, and control technologies, they perform tasks in specific scenarios. Common forms include road inspection robots and tunnel monitoring robots. Traffic robots are driving the evolution of traffic management towards intelligence and automation, effectively improving road network efficiency and safety, and are a key component of smart city transportation systems.

[0003] Traditional traffic cones, as common temporary roadside facilities, primarily function limited to physical isolation, warning, and traffic guidance, making their functionality relatively simple. In practical applications, the placement and removal of traffic cones heavily rely on manual operation. Especially in high-speed environments such as highways, maintenance personnel must directly enter the driving area, facing not only extremely high safety risks but also generally low operational efficiency. Meanwhile, traditional engineering transport vehicles (carrying traffic cones) are often affected by real-time road conditions and traffic congestion on their way to the scene, making it difficult to reach the target section in a timely manner, further delaying the response time.

[0004] Therefore, the process of manually moving and placing traffic cones is labor-intensive and takes a long time to occupy the road, which not only affects the road's traffic capacity but also brings continuous exposure risks to the workers. In addition, there is a lack of route planning on the way, making it difficult to meet the development needs of modern traffic management for efficiency, safety and intelligence. Summary of the Invention

[0005] The purpose of this invention is to provide a mother-daughter intelligent transportation robot scheduling system to overcome the problems existing in the prior art. This invention can realize the formation of sub-action units, significantly improve the operation efficiency, and also realize the path planning of engineering transport vehicles (mother ships), realizing the intelligent, clustered and automated upgrade of traffic management operations, effectively reducing labor costs and safety risks.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: This invention provides a mother-daughter intelligent transportation robot scheduling system, comprising: The mothership includes an edge computing module located inside the mothership and a power unit located at the bottom of the mothership. Several sub-action units, each of the sub-action units includes a lightweight ROS chassis, a traffic cone and an RTK module are arranged on the top of the lightweight ROS chassis, the RTK module is located on the side of the traffic cone, the RTK module is connected to the edge computing module, and a power module is arranged inside the lightweight ROS chassis, the power module is connected to the edge computing module and the RTK module respectively; The embodied perception unit is located on the front top of the mothership and is connected to the edge computing module.

[0007] According to one embodiment of the present invention, the mothership further includes a plurality of wheels disposed at its bottom, and the power unit is disposed on the wheels.

[0008] According to one embodiment of the present invention, a baffle is rotatably provided at the rear of the mothership.

[0009] According to one embodiment of the present invention, the mothership is an AGV intelligent mothership.

[0010] According to one embodiment of the present invention, the bottom of the lightweight ROS chassis is provided with a plurality of rollers, and the interior of the lightweight ROS chassis is also provided with a motor drive controller, a signal transmission module and a motor; The motor drive controller is connected to the RTK module, the signal transmission module, and the motor respectively; the signal transmission module is connected to the mothership; and the motor is connected to the power supply module.

[0011] According to one embodiment of the present invention, the embodied sensing unit includes a radar sensing device and a visual sensing device; The edge computing module is connected to the radar sensing device and the visual sensing device, respectively.

[0012] According to one embodiment of the present invention, the radar sensing device includes a lidar, which is connected to the edge computing module; The visual sensing device includes an industrial camera, which is connected to the edge computing module.

[0013] According to one embodiment of the present invention, the visual sensing device further includes a camera, which is connected to the edge computing module.

[0014] According to one embodiment of the present invention, an alarm unit is provided on the front top of the mothership.

[0015] According to one embodiment of the present invention, the radar sensing device further includes a millimeter-wave radar, which is connected to the edge computing module and the alarm unit respectively.

[0016] The above technical solution has the following advantages or beneficial effects: This invention provides a mother-daughter intelligent traffic robot scheduling system. First, through a collaborative architecture of mothership and sub-action units, it achieves large-scale, high-efficiency traffic warning and diversion operations. Using the mothership as a mobile command and charging center, it can quickly deploy and retrieve multiple sub-action units, greatly improving operational coverage and maneuverability. Second, the system deeply integrates edge computing, RTK high-precision positioning, and embodied perception technologies. The edge computing module ensures low latency for real-time decision-making and collaborative control of multiple sub-action units under complex road conditions, enabling the scheduling of the mothership's movement and the formation of sub-action units, significantly improving operational efficiency. The RTK module ensures centimeter-level precise positioning and formation maintenance for the action units. The embodied perception unit endows the system with real-time perception of the dynamic environment and intelligent obstacle avoidance capabilities, greatly improving operational safety and adaptability. Furthermore, the sub-action units adopt a lightweight ROS chassis and integrate traffic cones, combining flexible movement with standardized warning functions. The power module provides unified power supply management, enhancing system endurance and reliability. The overall system achieves intelligent, clustered, and automated upgrades to traffic management operations, effectively reducing labor costs and safety risks.

[0017] In some embodiments, by equipping the mothership with several wheels, the mothership is given autonomous mobility, enabling it to directly transport and coordinate with sub-action units to reach the work area; the power unit is integrated with the wheels, resulting in a compact structure that enhances the mothership's mobility, allowing it to adapt to complex road environments, thereby supporting the rapid deployment and flexible scheduling of the entire system.

[0018] In some embodiments, a rotatable baffle at the rear of the mothership forms a ramp passage that facilitates the autonomous entry and exit of sub-operation units, enabling rapid deployment and efficient recovery of sub-units, simplifying loading and unloading processes, significantly improving the system's mobility and operational cycle efficiency, and reducing reliance on external auxiliary equipment or personnel.

[0019] In some embodiments, the mothership is specifically defined as an AGV intelligent mothership, which enables it to have core capabilities of autonomous navigation, path planning and automatic driving, realizing full automation of the entire system from deployment and movement to recovery, greatly improving operational efficiency and intelligence level, and is a key foundation for the system to achieve unmanned and clustered traffic control.

[0020] In some embodiments, a motor drive controller and a signal transmission module are integrated inside the lightweight ROS chassis to achieve precise closed-loop motion control of the sub-units. By receiving RTK positioning commands and mothership coordination signals, the motor drive controller can control the power unit in real time and accurately, ensuring that each sub-action unit can stably and reliably perform autonomous movement and formation tasks in complex traffic environments.

[0021] In some embodiments, a multi-dimensional redundant embodied perception system is constructed by integrating radar sensing devices and visual sensing devices. The radar provides stable and reliable distance and speed detection, while the vision provides rich texture and semantic information. The two complement each other and are processed in real time by an edge computing module, which significantly improves the mothership's overall perception accuracy, reliability, and real-time response capability to complex and dynamic traffic environments.

[0022] In some embodiments, a core sensing combination of LiDAR and industrial camera is used to achieve simultaneous acquisition of long-distance, high-precision 3D ranging and high-definition visual information. LiDAR provides accurate point cloud data for environmental modeling and obstacle localization, while industrial camera captures rich color and texture information for target recognition and semantic understanding. The data from both are fused and processed in the edge computing module, which greatly improves the system's environmental perception robustness and decision-making accuracy under complex lighting and weather conditions.

[0023] In some embodiments, adding a camera in addition to an industrial camera effectively expands the dimensions and functions of visual perception; the camera can continuously record wide-angle or close-up videos of the work area, which not only provides dynamic scene monitoring data for the edge computing module to optimize decision-making, but also records the on-site situation for post-event review and analysis, thereby enhancing the system's full-process monitoring and evidence collection capabilities in traffic management and safety management tasks.

[0024] In some embodiments, an alarm unit is installed on the front top of the mothership to realize active audible and visual early warning functions. During operation or movement, it promptly issues warning signals to surrounding vehicles and pedestrians, significantly improving the active safety of the entire system and the effectiveness of on-site command in complex traffic environments. By adding a millimeter-wave radar and directly connecting it to the alarm unit, the active safety performance of the system is significantly enhanced. The millimeter-wave radar has excellent speed measurement capabilities and all-weather operating characteristics, and can accurately detect rapidly approaching moving targets. Once a potential collision risk is detected, the system can issue an immediate warning through the edge computing module or by directly triggering the alarm unit, achieving an extremely low-latency response to dynamic threats and further ensuring operational safety.

[0025] Secondly, this invention provides a mother-daughter intelligent transportation robot scheduling method. By constructing a collaborative mode of "centralized transportation and decision-making by the mother ship and distributed precise execution by the sub-units," a high degree of automation and intelligence in traffic control operations is achieved. The system utilizes fusion perception technology to construct a precise environmental model in real time, and the edge computing module performs dual path planning for both global and individual scenarios, significantly improving the accuracy and efficiency of deployment. The sub-action units adopt a lightweight and low-cost design and achieve centimeter-level positioning with the help of RTK, ensuring the accuracy and reliability of the formation while reducing deployment and maintenance costs. The overall system can respond quickly and adapt to complex road environments, significantly improving the safety and operational efficiency in scenarios such as road construction and temporary traffic control. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of a mother-daughter intelligent transportation robot scheduling system according to some embodiments of this specification; Figure 2 This is a schematic diagram of the action unit structure according to some embodiments of this specification; Figure 3 This is a schematic diagram of the embodied sensing unit structure according to some embodiments of this specification; In all the accompanying drawings, the same reference numerals denote the same technical features, specifically: 100. Mothership; 101. Body; 102. Direct-drive hub motor; 103. Edge computing module; 104. Baffle; 105. Alarm unit; 200. Sub-action unit; 201. Lightweight ROS chassis; 202. Traffic cone; 203. RTK module; 204. Power module; 300. Embodied perception unit; 301. LiDAR; 302. Millimeter-wave radar; 303. Industrial camera; 304. Camera. Detailed Implementation

[0027] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0028] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0029] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0030] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a communication connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0031] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Example: This embodiment provides a mother-daughter intelligent transportation robot scheduling system, see [link / reference] Figure 1 It includes: a mothership 100, several sub-operation units 200, and an embodied perception unit 300; The mothership 100 includes an edge computing module 103 disposed inside the mothership 100 and a power unit disposed at the bottom of the mothership 100; each sub-action unit 200 includes a lightweight ROS chassis 201, on the top of the lightweight ROS chassis 201 are a traffic cone 202 and an RTK module 203, the RTK module 203 is located on the side of the traffic cone 202 and is connected to the edge computing module 103; a power module 204 is disposed inside the lightweight ROS chassis 201 and is connected to the edge computing module 103 and the RTK module 203 respectively; an embodied perception unit 300 is disposed at the front top of the mothership 100 and is connected to the edge computing module 103.

[0034] In some embodiments, the shape of the mothership 100 is not limited to... Figure 1 As shown, it can be changed according to different occasions and carrying capacity requirements. Depending on the mission being performed, the mothership 100 can carry different numbers of sub-action units 200.

[0035] In some embodiments, the mothership 100 further includes a body 101, the edge computing module 103 is disposed inside the body 101, and the body perception unit 300 is disposed on the front top of the body 101.

[0036] In some embodiments, the bottom of the vehicle body 101 is provided with a plurality of wheels, and the power unit is disposed on the wheels for transporting the sub-action unit 200 to a designated location.

[0037] In some embodiments, the number of wheels can be 4, 6, or other achievable numbers.

[0038] In some embodiments, the power unit is a direct-drive hub motor 102.

[0039] In some embodiments, the edge computing module 103 is a Jetson Orin Nano Super or Rockchip RK3588, which is used to automatically plan the movement path of the mothership 100 and the formation of the sub-action units 200 according to environmental conditions and mission requirements through a built-in path planning algorithm, generate the forward path of each sub-action unit 200, and then issue instructions to each sub-action unit 200.

[0040] In some embodiments, a baffle 104 is rotatably provided at the rear of the mothership 100. When the mothership 100 moves to a safe area near the target location, such as the shoulder of the emergency vehicle lane on a highway, by means of automatic navigation, the baffle 104 is rotated to form a downhill slope. The sub-action units 200 carried by the mothership 100 receive instructions from the mothership 100 to disembark in sequence and line up on the shoulder.

[0041] In some embodiments, an alarm unit 105 is provided on the front top of the vehicle body 101.

[0042] In some embodiments, the alarm unit 105 includes a warning light and an alarm, which are also integrated into the front of the vehicle body 101 as standard equipment for traffic devices, to provide audible and visual warnings to oncoming vehicles.

[0043] In some embodiments, the mothership 100 is an AGV intelligent mothership.

[0044] In some embodiments, the vehicle body 101 is a narrow body, which can pass through narrow road sections. By applying a mature AGV chassis architecture, it is particularly suitable for use on outdoor paved roads. The battery is integrated into the chassis to meet the requirements of long-term use.

[0045] In some embodiments, the command and dispatch system of this embodiment is implemented entirely by the mothership 100. Specifically, it uses common industry standards such as traffic cones 202 to implement management methods, combined with a large number of application cases to form a local big data model. The edge computing module 103 learns relevant data to form a correspondence between tasks and the number and formation of sub-action units 200, and then allocates an appropriate number of sub-action units 200 and formation method to each task.

[0046] In some embodiments, see Figure 2 The lightweight ROS chassis 201 is equipped with several rollers at its bottom. The lightweight ROS chassis 201 also houses a motor drive controller, a signal transmission module, and a motor. Simplifying the functions of the ROS chassis can significantly reduce procurement costs. Since traffic cones 202 are easily scratched by passing vehicles on the road or tilted and damaged by special weather conditions, the economic loss when a low-cost traffic cone 202 is damaged is relatively small. At the same time, the damage to a single traffic cone 202 will not affect the overall mission. In this case, the mothership 100 will compensate by deploying a spare sub-action unit 200 or adjusting the formation.

[0047] The RTK module 203 is connected to the USB port of the motor drive controller; the signal transmission module is connected to the motor drive controller via a TTL serial port module; the motor drive controller is connected to the motor; the motor is connected to the power supply module 204; and the signal transmission module is connected to the mothership 100 via a LoRa IoT or Wi-Fi network.

[0048] In some embodiments, the traffic cone 202 is a 900 mm highway traffic cone.

[0049] In some embodiments, the power module 204 includes a switch, a lithium-ion battery, an embedded battery control board, charging contacts, connectors, etc.; wherein, the switch, charging contacts, and lithium-ion battery are all electrically connected to the embedded battery control board, which is connected to the edge computing module 103 and the RTK module 203 respectively, and supplies power to other modules through the embedded battery control board; the power module 204 can provide feedback on power information, and can be charged by plugging or magnetic attraction. Specifically, after the sub-action unit 200 returns to the mothership 100, a contact charging head is provided at the bottom of the corresponding position, which contacts the charging contacts at the bottom of the power module 204 to achieve charging.

[0050] In some embodiments, see Figure 3 The embodied perception unit includes a radar sensing device and a visual sensing device. The edge computing module 103 is connected to the radar sensing device and the visual sensing device respectively, and is used to analyze the surrounding environment information and provide important parameters for the system.

[0051] In some embodiments, the radar sensing device includes a lidar 301 and a millimeter-wave radar 302; the edge computing module 103 is connected to the lidar 301 and the millimeter-wave radar 302 respectively; the millimeter-wave radar 302 is connected to the alarm unit 105; the millimeter-wave radar 302 can identify moving objects within a range of 200 meters in front, serving as a supplement to the embodied sensing unit 300, and is used to promptly detect whether a high-speed vehicle has entered the road from a distance, and to take corresponding strategies, such as emergency alarms, suspension of execution, or advance avoidance.

[0052] In some embodiments, the lidar 301 is a 360° lidar.

[0053] In some embodiments, the visual sensing device includes an industrial camera 303 and a video camera 304; the edge computing module 103 is connected to the industrial camera 303 and the video camera 304 respectively.

[0054] In some embodiments, the camera 304 is spherical and is used to continuously monitor the area around the current location of the mothership 100. As a monitoring device, it observes the situation within the mission area, and the data stream can be transmitted to a nearby engineering command vehicle, which facilitates remote observation by the command personnel and helps to avoid risks and obstacles during the journey. The real-time video recording of the surrounding environment plays a role in monitoring and patrolling.

[0055] In some embodiments, during operation, the lidar 301 continuously scans the surrounding environment to generate an environmental digital model (3D digital model) in the form of point clouds, while the industrial camera 303 acquires clear images within its field of view directly in front. The images and the environmental digital model are superimposed to obtain real-time 3D images within a certain range in the forward direction. The mothership 100 will then plan a reasonable operating trajectory based on the real-time 3D images. In particular, the lidar 301 and the industrial camera 303 are relatively fixed in position, and a unified coordinate system is established in advance so that the two have the same reference, so that the two sets of data can be aligned.

[0056] In some embodiments, the running trajectory includes not only the movement of the mothership 100 itself, but also the movement trajectory of the sub-action units 200 within the mission range.

[0057] In some embodiments, radar sensing devices and visual sensing devices can transmit collected environmental information, including images and data, to a remote terminal in real time. This embodiment provides an information interaction method in which the mothership 100 acts as a relay station for information interaction. Through the command and dispatch system and the embodied sensing unit 300, the collected information is transmitted to nearby engineering command vehicles or to the traffic command center via wireless transmission methods such as 5G and WIFI. This allows for comprehensive monitoring of traffic conditions at various nodes on the highway and timely detection of potential hazards. Similarly, the mothership 100 can also remotely receive and execute instructions issued by the command center.

[0058] This embodiment also provides a method for scheduling mother-daughter intelligent transportation robots, including the following steps: Step 1: Based on the task information, the embodied perception unit 300 is activated to scan the surrounding environment. The embodied perception unit 300 obtains real-time 3D images and generates an environmental digital model in the form of point clouds. The real-time 3D images and environmental digital model are then transmitted to the edge computing module 103.

[0059] In some embodiments, this step can also combine SLAM (Simultaneous Localization and Mapping) with 3D dynamic environment modeling algorithms to provide a high-precision environmental map for the mothership 100's own navigation and the deployment of sub-action units 200. Specifically, this includes: combining the wheel encoder of the direct-drive hub motor 102 with the point cloud / visual features of the LiDAR 301, using an iterative nearest-point algorithm or visual odometry to calculate the real-time pose changes of the mothership 100, reducing the error of pure RTK under occlusion; adopting a graph-optimized SLAM framework, using keyframe poses and landmark points (from LiDAR point clouds or visual features) as nodes to construct a constraint graph, perform global optimization, and generate a globally consistent 3D occupancy grid map or point cloud map, which contains static obstacle (guardrail, shoulder) information; in the point cloud or image sequence, using clustering and tracking algorithms (such as DBSCAN clustering, multi-object tracking) to identify and remove dynamic objects (vehicles, pedestrians) to ensure that the constructed map is a static environment for long-term path planning.

[0060] Step 2: The edge computing module 103 receives and obtains the forward path of the mothership 100, the formation mode and forward path of the sub-action units 200 based on the real-time 3D image and the environmental digital model. It then transmits the forward path of the mothership 100 to the mothership 100 and transmits the formation mode and forward path of the sub-action units 200 to the lightweight ROS chassis 201.

[0061] In some embodiments, the algorithm for this step can be: an input environment digital model (static structure), real-time 3D imagery (fused with dynamic targets), and high-level task instructions (such as "close the right lane for 500 meters"). Processing flow: Using a built-in traffic rule knowledge base, the task is decomposed into geometric constraints (such as deployment length, number of isolated lanes, and cone spacing specifications); based on a map search algorithm (such as A*), with distance from the main traffic flow as the key cost factor, the optimal path for the mothership 100 to reach a safe assembly area near the target area (such as the widest part of the emergency lane) from its current position is calculated, ensuring the stability of the mothership 100 and the safety of the sub-action units 200 disembarking; then, combining environmental constraints (road width, curve curvature) and task constraints, matching or fine-tuning from a formation template library (such as linear, arc, and stepped shapes) generates a formation that meets safety standards. The algorithm calculates the target pose matrix of sub-action units 200 and the mission objective. In a dynamic environment, it predicts and avoids perceived moving obstacles. Then, taking the expected formation of sub-action units 200 from their disembarkation points to their respective target points as the endpoint, it adopts a centralized planning and distributed execution strategy. The algorithm calculates a collision-free smooth path for each sub-action unit 200 and plans the precise disembarkation timing and initial movement order to avoid congestion and collisions when leaving the mothership 100. Finally, it outputs the mothership navigation path point sequence, the independent target coordinate sequence (forward path) of each sub-unit, and the global formation shape command.

[0062] Step 3: The mothership 100 receives and moves to the target area according to its forward path. The lightweight ROS chassis 201 receives and controls several sub-action units 200 to move to their respective target positions according to the formation and forward path of the sub-action units 200, forming a target formation and completing the scheduling.

[0063] In some embodiments, this step can be physically implemented through hierarchical control and collaborative execution. The mothership 100 adopts hierarchical motion control. The upper layer (controller receives) receives the path point sequence and, combined with its own positioning (fusion of RTK and odometer), generates real-time speed and steering commands through model predictive control or pure tracking algorithms. The lower layer direct-drive hub motors 102 execute the commands, driving the vehicle body to smoothly travel along the planned path to the target area and maintaining a precise docking posture so that the sub-action unit 200 can disembark. In the sub-action unit 200, each lightweight ROS chassis 201 runs a distributed trajectory tracking and formation keeping algorithm. It receives its own target point sequence, first uses RTK to provide centimeter-level absolute positioning, calculates the motor differential speed through proportional-integral-derivative control or a more advanced linear quadratic regulator, and drives the rollers to accurately reach each path point. During movement, each unit only needs to focus on its own path. The central system performs macro-level formation fine-tuning by monitoring all RTK feedback positions to form the final target formation.

[0064] Traditional traffic cones are mainly used for temporary isolation, warning, or traffic flow guidance. Their function is limited, and deployment and retrieval rely on manual operation, resulting in low efficiency and safety risks. With the development of intelligent transportation systems, some intelligent traffic cones with autonomous walking capabilities have emerged. However, they are still limited by the concept of a traffic cone, and their functions can only partially replace traditional traffic cone applications. This invention aims to overcome this limitation by applying the concept of a mothership + carrier-based aircraft. It expands the capabilities of the AGV-based mothership 100, along with its embodied perception and command and dispatch capabilities, enabling it to adapt to a wider range of application scenarios. Furthermore, the carrier-based aircraft approach can reduce the procurement cost of intelligent traffic cones and avoid significant economic losses caused by collisions on roads.

[0065] This invention aims to break through the traditional concept of traffic cones by applying a combination of a mothership 100 and sub-action units 200. The mothership system, with intelligent AGVs as the main carrier, expands the embodied perception and command and dispatch capabilities, enabling it to adapt to a wider range of application scenarios and endowing it with more efficient command and dispatch capabilities. At the same time, the functions of the sub-action units 200 are correspondingly simplified, reducing the economic losses caused by collisions and damage on the road. In addition, the use of the mothership 100 system solves the limitations of traditional engineering vehicles in transporting traffic cones, realizing unmanned operation of the entire process of transportation, deployment, monitoring, and retrieval.

[0066] This invention combines intelligent transportation with the rapidly developing AI technology, completely breaking away from the traditional concept of traffic cones and expanding their application scenarios. It allows personnel to completely escape dangerous working environments. The system has broad application prospects in lane control, inspection of key nodes such as bridges and culverts, traffic management at traffic nodes, and rapid response to emergencies.

[0067] The structure and working principle of the present invention will be further explained below: The purpose of this invention is to provide a mother-daughter intelligent transportation robot scheduling system. When using this device, such as for lane blocking and control tasks, the mother ship 100 is carried by an engineering command vehicle and towed to the vicinity of the task location. The mother ship 100 is placed on the road by the engineering vehicle, and then the mother ship 100 receives task information via Wi-Fi through electronic devices on the hands of on-site personnel. Based on the task information, the embodied perception unit 300 is activated to scan the surrounding environment. Specifically, the LiDAR 301 continuously scans the surrounding environment, generating an environmental digital model in the form of point clouds, while the industrial camera 303 captures clear images within its forward field of view. By overlaying the images and the environmental digital model, a real-time three-dimensional image of a certain range in the direction of travel can be obtained. The mothership 100 navigates to a safe location near the target area based on the environmental digital model and real-time 3D image navigation, such as next to the emergency vehicle shoulder on a highway. The edge computing module 103 plans the formation of the sub-action units 200 according to the environmental digital model and task information through the built-in path planning algorithm, generates the target point and travel path of each sub-action unit 200, and then issues a movement command containing the target point and travel path to each sub-action unit 200. The sub-action unit 200 receives the movement command containing the target point and travel path, opens the rotatable baffle 104, and several sub-action units 200 disembark in sequence. Each sub-action unit 200 moves to its respective target point according to the movement command to form a target formation to complete the deployment task.

[0068] Specifically, the movement of the sub-action unit 200 is not autonomous navigation, but rather movement along the X and Y coordinates on the road surface under the command of the edge computing module 103, and feedback of its current position to the edge computing module 103 through its own loaded RTK module 203.

[0069] This mother-daughter intelligent transportation robot scheduling system is a highly collaborative intelligent mobile deployment system. Its core working principle revolves around a closed-loop process of "perception-decision-scheduling-execution," with each component having a clear division of labor and working collaboratively. The specific working principle of this invention is as follows: Step 1, Environmental Perception and Data Acquisition: After the system starts, the Embodied Perception Unit 300 works. The Embodied Perception Unit 300 integrates devices such as LiDAR 301 and industrial camera 303. LiDAR 301 rotates 360° to scan and generate a high-precision point cloud digital model (environmental digital model) of the surrounding environment. The industrial camera 303 simultaneously captures visual images in front. The environmental digital model and images are fused in the edge computing module 103 to provide the system with comprehensive and accurate perception of the working environment.

[0070] Step 2, Central Computing and Path Planning: The edge computing module 103 acts as the brain of the system, receiving and processing the perceived data. The edge computing module 103 has built-in intelligent algorithms and performs dual path planning based on task requirements (such as lane closure range and formation shape) and real-time environmental models (such as road width and obstacle positions): First, it plans the optimal travel path for the mothership 100 to move safely from the starting point to the vicinity of the target area (such as the shoulder of a highway); second, it calculates the target points and movement paths of all sub-action units 200 within the target area and determines the overall formation (such as a straight line or an arc).

[0071] Step 3, Mothership 100 Maneuver and Command Issuance: Edge computing module 103 issues the travel path command of mothership 100 to the power unit (direct drive hub motor 102) at the bottom of mothership 100, driving mothership 100 to drive autonomously along the planned path. After arriving at the predetermined safe zone, the rotatable baffle 104 at the rear of mothership 100 is lowered, serving as a disembarkation ramp for sub-action units 200. At the same time, mothership 100 wirelessly issues formation commands, target locations, and individual paths to each sub-action unit 200 through a signal transmission module (such as LoRa / WiFi).

[0072] Step 4, Sub-unit Coordinated Deployment and Precise Positioning: After receiving instructions, each sub-action unit 200's lightweight ROS chassis 201 begins operation. The motor drive controller integrated in the ROS chassis 201 controls the motor movement according to the received path coordinates. The motor charges the lithium-ion battery during operation, enabling each sub-action unit 200 to move via rollers. The RTK module 203 on top of each sub-unit receives high-precision satellite differential positioning signals in real time and continuously feeds back its centimeter-level position information to the edge computing module 103 of the mothership 100, forming a closed-loop control to ensure that it can move precisely to the designated point. Upon arrival, the traffic cones 202 serve as physical markers to form a target formation (such as the boundary of the construction area).

[0073] Step 5, Full-process monitoring and safety early warning: Throughout the process, the camera 304 on top of the mothership 100 provides 360° video monitoring, and the images can be transmitted back to the command center; the millimeter-wave radar 302 continuously detects long-distance moving targets (such as high-speed vehicles) ahead. Once a potential collision risk is identified, it will immediately trigger the alarm unit 105 to issue an audible and visual alarm, and can also link with the edge computing module 103 to urgently adjust the action strategy of the sub-action unit 200 or the mothership 100 to ensure system safety.

[0074] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the scope of the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0075] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A parent-child intelligent traffic robot dispatching system, characterized in that, include: The mothership (100) includes an edge computing module (103) disposed inside the mothership (100) and a power unit disposed at the bottom of the mothership (100); Several sub-action units (200) are provided, each of which includes a lightweight ROS chassis (201). A traffic cone (202) and an RTK module (203) are provided on the top of the lightweight ROS chassis (201). The RTK module (203) is located on the side of the traffic cone (202) and is connected to the edge computing module (103). A power module (204) is provided inside the lightweight ROS chassis (201). The power module (204) is connected to the edge computing module (103) and the RTK module (203) respectively. The embodied perception unit (300) is located on the front top of the mothership (100) and is connected to the edge computing module (103).

2. The mother-daughter intelligent traffic robot dispatching system of claim 1, wherein, The mothership (100) also includes several wheels located at its bottom, and the power unit is mounted on the wheels.

3. The mother-daughter intelligent traffic robot dispatching system of claim 1, wherein, The rear of the mothership (100) is rotatably equipped with a baffle (104).

4. The mother-daughter intelligent transportation robot scheduling system according to claim 1, characterized in that, The mothership (100) is an AGV intelligent mothership.

5. The mother-daughter intelligent transportation robot scheduling system according to claim 1, characterized in that, The lightweight ROS chassis (201) is provided with several rollers at the bottom, and the interior of the lightweight ROS chassis (201) is also provided with a motor drive controller, a signal transmission module and a motor; The motor drive controller is connected to the RTK module (203), the signal transmission module, and the motor respectively; the signal transmission module is connected to the mothership (100); and the motor is connected to the power supply module (204).

6. The mother-daughter intelligent transportation robot scheduling system according to claim 1, characterized in that, The embodied perception unit includes radar sensing equipment and visual sensing equipment. The edge computing module (103) is connected to the radar sensing device and the visual sensing device respectively.

7. A mother-daughter intelligent transportation robot scheduling system according to claim 6, characterized in that, The radar sensing device includes a lidar (301), which is connected to the edge computing module (103); The visual sensing device includes an industrial camera (303), which is connected to the edge computing module (103).

8. A mother-daughter intelligent transportation robot scheduling system according to claim 7, characterized in that, The visual sensing device also includes a camera (304), which is connected to the edge computing module (103).

9. A mother-daughter intelligent transportation robot scheduling system according to claim 6, characterized in that, An alarm unit (105) is provided on the front top of the mothership (100). The radar sensing device also includes a millimeter-wave radar (302), which is connected to the edge computing module (103) and the alarm unit (105) respectively.

10. A method for scheduling mother-daughter intelligent transportation robots, characterized in that, A mother-daughter intelligent transportation robot scheduling system according to any one of claims 1-9 includes the following steps: Based on the task information, the embodied perception unit (300) is activated to scan the surrounding environment. The embodied perception unit (300) obtains real-time three-dimensional images and generates an environmental digital model in the form of point clouds. The real-time three-dimensional images and environmental digital model are then transmitted to the edge computing module (103). The edge computing module (103) receives and obtains the forward path of the mothership (100), the formation mode and forward path of the sub-action units (200) based on the real-time three-dimensional image and the environmental digital model. It transmits the forward path of the mothership (100) to the mothership (100) and transmits the formation mode and forward path of the sub-action units (200) to the lightweight ROS chassis (201). The mothership (100) receives and moves to the target area according to the forward path of the mothership (100). The lightweight ROS chassis (201) receives and controls several sub-action units (200) to move to their respective target positions according to the formation and forward path of the sub-action units (200), forming a target formation and completing the scheduling.

Images