Inspection robot system integrating autonomous navigation and real-time monitoring

Abstract

The invention provides an autonomous navigation and real-time monitoring integrated inspection robot system. The autonomous navigation and real-time monitoring integrated inspection robot system comprises a mobile platform used for providing the motion ability of a robot in a two-dimensional plane, and a multi-sensor fusion module which comprises a laser radar, a visual camera, an inertial measurement unit and an ultrasonic sensor and is used for collecting environment data, generating a high-precision two-dimensional map, and transmitting the environment data to the mobile platform. And perception of a dynamic environment is realized. According to the autonomous navigation and real-time monitoring integrated inspection robot system, by integrating autonomous navigation and real-time monitoring functions, the adaptive capacity and task execution efficiency of an inspection robot in a complex dynamic environment are remarkably improved, a multi-sensor fusion module is adopted, and a laser radar, a visual camera, an inertial measurement unit and an ultrasonic sensor are combined, so that the inspection robot system is more accurate and reliable. Accurate acquisition of environmental data and high-precision two-dimensional map generation are realized, and the positioning and navigation capabilities of the robot under various environmental conditions are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of inspection robot systems, and in particular to an inspection robot system integrating autonomous navigation and real-time monitoring. Background Art

[0002] A patrol robot system integrating autonomous navigation and real-time monitoring, mainly composed of a mobile platform, a sensor module, an autonomous navigation system, a real-time monitoring system, and a control and communication module. The mobile platform provides basic walking capabilities and usually adopts an omnidirectional wheel design to achieve flexible mobility. The sensor module includes a laser radar, a camera, and an infrared sensor for environmental perception and data collection. The autonomous navigation system based on the SLAM (Simultaneous Localization and Mapping) algorithm builds an environmental map in real time through sensor data and plans the optimal path, enabling the robot to avoid obstacles and patrol autonomously. The real-time monitoring system is responsible for collecting environmental data such as temperature, humidity, and gas concentration, and uploading the information to the central control unit or cloud platform through the wireless communication module. Each module works together through an embedded control system to achieve the functional integration of precise patrol and data monitoring.

[0003] In two-dimensional position or channel control, when environmental factors such as wind, terrain complexity or water flow disturbance change dramatically, the dynamic response speed of the existing system may be insufficient, resulting in increased errors in positioning and channel control. For complex scenarios, there are certain deficiencies in the data acquisition capabilities of sensors and the real-time performance of algorithms, making it difficult to ensure the stability and reliability of the system under extreme conditions. The algorithm optimization of current control systems is mostly based on specific application scenarios, lacking the ability to adapt to multiple types of transportation tools or multiple scenarios, which limits the scalability of the technology. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an inspection robot system integrating autonomous navigation and real-time monitoring, which solves the problems of insufficient accuracy and dynamic response, limited adaptability in complex environments, and the versatility of control algorithms.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an inspection robot system integrating autonomous navigation and real-time monitoring, comprising:

[0006] A mobile platform is used to provide the robot with the ability to move in a two-dimensional plane;

[0007] Multi-sensor fusion module, including lidar, visual camera, inertial measurement unit and ultrasonic sensor, is used to collect environmental data, generate high-precision two-dimensional maps, and realize the perception of dynamic environment;

[0008] A dynamic adaptive autonomous navigation system, wherein the dynamic adaptive autonomous navigation system comprises a path planning and optimization module;

[0009] The control system includes a real-time monitoring module, which is used to coordinate the operation of the multi-sensor fusion module, the navigation system and the real-time monitoring module, and transmit the data to the cloud or local terminal;

[0010] Communication module, which realizes remote control and data transmission through wireless communication technology;

[0011] A power management module is used to optimize the energy consumption of the system and provide backup power to ensure long-term autonomous operation of the robot.

[0012] Preferably, the dynamic adaptive autonomous navigation system adaptively adjusts the sensor weight distribution in the SLAM positioning module through real-time calculation of environmental interference parameters, and the calculation formula is:

[0013]

[0014] Among them, W i is the weight of sensor i, σ i is the error variance of sensor data, ensuring accurate fusion of sensor data in complex environments.

[0015] Preferably, the path planning and optimization module adopts a multi-scenario adaptive learning mechanism based on the following update formula:

[0016]

[0017] Among them, Q(s,a) is the value function of selecting action a in state s, α is the learning rate, γ is the discount factor, and the path is dynamically optimized through the reinforcement learning algorithm.

[0018] Preferably, the real-time monitoring module is based on a multimodal data fusion algorithm and uses a Kalman filter model to improve the stability of monitoring data in harsh environments. Its state update formula is:

[0019]

[0020] in, is the current estimated state, K t is the Kalman gain, z t is the observed value, and H is the measurement matrix.

[0021] Preferably, the power management module integrates a dynamic energy consumption prediction model to evaluate the remaining power of the robot task in real time based on the following formula:

[0022]

[0023] Among them, E r is the remaining power, E tis the initial power, and P(t) is the instantaneous power consumption.

[0024] Preferably, the path planning and optimization module supports multi-objective task scheduling, can dynamically adjust weights according to task importance, and optimize inspection efficiency. After the inspection is completed, the inspection robot can generate a visual report based on cloud computing and realize simultaneous sharing on multiple platforms.

[0025] Preferably, the dynamic adaptive autonomous navigation system includes a SLAM positioning module, which constructs a two-dimensional environment map in real time and performs precise positioning based on multi-sensor data;

[0026] The path planning and optimization module generates an optimal navigation path that is adaptive to environmental interference based on a dynamic Bayesian network and a reinforcement learning algorithm, wherein the path planning optimization uses the following formula:

[0027]

[0028] Among them, E d (t) is the path deviation, E o (t) is the obstacle distance cost, E v (t) is the speed control cost, w1, w2, w3 are weight factors, which ensure the optimal adaptability of path planning in a dynamic environment.

[0029] Preferably, the dynamic adaptive autonomous navigation system further includes:

[0030] Real-time monitoring module, used to obtain temperature, humidity, gas concentration and vibration signals in the inspection environment, and generate comprehensive monitoring reports through multi-dimensional data fusion technology;

[0031] The dynamic response enhancement module includes a feedback controller based on model predictive control, which is used to adjust the robot position and posture in real time. Its dynamic response algorithm uses the following formula:

[0032] x t+1 =Ax t +Bu t +G w w t ;

[0033] Among them, x t is the state vector, u t is the control input, w t A, B, G are environmental interferences. w It is the system matrix to improve the robustness and real-time performance under complex environmental interference.

[0034] Preferably, the dynamic response enhancement module is combined with an extended Kalman filter and a predictive control algorithm to dynamically adjust the priority of the robot's navigation and monitoring tasks. The communication module supports 5G network and edge computing collaboration to ensure real-time processing of high-capacity data and low-latency remote control. The robot has real-time feedback and self-learning capabilities, and optimizes navigation and monitoring algorithms through inspection data. The multi-sensor fusion module uses an adaptive signal noise reduction algorithm to enhance the effectiveness of low signal-to-noise ratio sensor data in the environment. The control system adopts a distributed fault-tolerant design to ensure high-reliability operation of key modules.

[0035] The present invention provides an inspection robot system integrating autonomous navigation and real-time monitoring. It has the following beneficial effects:

[0036] The patrol robot system with integrated autonomous navigation and real-time monitoring has significantly improved the patrol robot's adaptability and task execution efficiency in complex dynamic environments by integrating autonomous navigation and real-time monitoring functions. It uses a multi-sensor fusion module, combined with lidar, visual camera, inertial measurement unit and ultrasonic sensor, to achieve accurate collection of environmental data and high-precision two-dimensional map generation, enhancing the robot's positioning and navigation capabilities under various environmental conditions. Through the dynamic adaptive autonomous navigation system, the robot can adjust the sensor weight in real time and optimize the path planning through reinforcement learning to ensure accurate positioning and path optimization in complex environments. At the same time, the system can make adaptive adjustments according to the priority of the task and environmental changes to optimize the inspection efficiency, and provide more robust navigation and task scheduling functions through the SLAM positioning module and multi-scenario adaptive learning mechanism to ensure effective operation in a variety of complex task scenarios.

[0037] This technical solution also introduces advanced dynamic response enhancement modules and power management modules in robot control and energy management. The dynamic response enhancement module combines model predictive control and extended Kalman filter algorithm to adjust the robot's position and posture in real time under complex environmental interference, improving its robustness and real-time response capabilities in dynamic changes. The power management module integrates a dynamic energy consumption prediction model to ensure that the robot continues to operate stably during long-term tasks, optimizes energy use by real-time evaluation of remaining power, and reduces energy waste. The solution also supports the collaboration of 5G networks and edge computing to achieve real-time transmission of high-capacity data and low-latency remote control, enabling the robot to have self-learning and real-time feedback capabilities, and continuously optimize navigation and monitoring algorithms in actual inspection tasks. In summary, this technical solution effectively improves the stability, reliability and efficiency of inspection robots in complex and changing environments by comprehensively using advanced sensor fusion, path planning, dynamic response and energy management technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic diagram comparing the multi-sensor data fusion and optimization effects of the present invention;

[0039] Figure 2 It is a schematic diagram of the path planning and optimization process of the present invention;

[0040] Figure 3 It is a schematic diagram of the control effect of the dynamic response enhancement module of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Embodiment 1

[0043] like Figure 1-3 As shown, an embodiment of the present invention provides an inspection robot system integrating autonomous navigation and real-time monitoring, including a mobile platform for providing the robot with movement capability in a two-dimensional plane.

[0044] The multi-sensor fusion module, including lidar, visual camera, inertial measurement unit and ultrasonic sensor, is used to collect environmental data, generate high-precision two-dimensional maps, and realize the perception of dynamic environment.

[0045] Dynamic adaptive autonomous navigation system, the dynamic adaptive autonomous navigation system includes a path planning and optimization module. The dynamic adaptive autonomous navigation system adaptively adjusts the sensor weight distribution in the SLAM positioning module through real-time calculation of environmental interference parameters. The calculation formula is:

[0046]

[0047] Among them, W i is the weight of sensor i, σ i To reduce the error variance of sensor data and ensure accurate fusion of sensor data in complex environments, the path planning and optimization module adopts a multi-scenario adaptive learning mechanism based on the following update formula:

[0048]

[0049] Among them, Q(s,a) is the value function of selecting action a under state s, α is the learning rate, and γ is the discount factor. The path is dynamically optimized through the reinforcement learning algorithm. The path planning and optimization module supports multi-objective task scheduling, and can dynamically adjust the weight according to the importance of the task to optimize the inspection efficiency. After the inspection is completed, the inspection robot can generate a visual report based on cloud computing and realize multi-platform synchronous sharing. The dynamic adaptive autonomous navigation system includes a SLAM positioning module, which builds a two-dimensional environment map in real time and synchronously based on multi-sensor data and performs precise positioning.

[0050] The path planning and optimization module generates the optimal navigation path that is adaptive to environmental interference based on the dynamic Bayesian network and reinforcement learning algorithm. The path planning optimization uses the following formula:

[0051]

[0052] Among them, E d (t) is the path deviation, E o (t) is the obstacle distance cost, E v (t) is the speed control cost, w1, w2, w3 are weight factors to ensure the optimal adaptability of path planning in a dynamic environment. The dynamic adaptive autonomous navigation system also includes:

[0053] The real-time monitoring module is used to obtain temperature and humidity, gas concentration and vibration signals in the inspection environment, and generate a comprehensive monitoring report through multi-dimensional data fusion technology.

[0054] The dynamic response enhancement module includes a feedback controller based on model predictive control, which is used to adjust the robot position and posture in real time. Its dynamic response algorithm uses the following formula:

[0055] x t+1 =Ax t +Bu t +G w w t ;

[0056] Among them, x t is the state vector, u t is the control input, w t A, B, G are environmental interferences. wIt is a system matrix to improve the robustness and real-time performance under complex environmental interference. The dynamic response enhancement module combines the extended Kalman filter and predictive control algorithm to dynamically adjust the priority of the robot's navigation and monitoring tasks. The communication module supports 5G network and edge computing collaboration to ensure real-time processing of high-capacity data and low-latency remote control. The robot has real-time feedback and self-learning capabilities, and optimizes navigation and monitoring algorithms through inspection data. The multi-sensor fusion module uses an adaptive signal noise reduction algorithm to enhance the effectiveness of low signal-to-noise ratio sensor data in the environment. The control system adopts a distributed fault-tolerant design to ensure high-reliability operation of key modules.

[0057] The control system includes a real-time monitoring module, which is used to coordinate the operation of the multi-sensor fusion module, the navigation system and the real-time monitoring module, and transmit the data to the cloud or the local terminal. The real-time monitoring module is based on a multimodal data fusion algorithm and uses a Kalman filter model to improve the stability of monitoring data in harsh environments. Its state update formula is:

[0058]

[0059] in, is the current estimated state, K t is the Kalman gain, z t is the observed value, and H is the measurement matrix.

[0060] Communication module, realizes remote control and data transmission through wireless communication technology.

[0061] The power management module is used to optimize the energy consumption of the system and provide backup power to ensure that the robot can operate autonomously for a long time. The power management module integrates a dynamic energy consumption prediction model to evaluate the remaining power of the robot task in real time based on the following formula:

[0062]

[0063] Among them, E r is the remaining power, E t is the initial power, and P(t) is the instantaneous power consumption.

[0064] Embodiment 2

[0065] like Figure 1-3 As shown, an embodiment of the present invention provides an inspection robot system integrating autonomous navigation and real-time monitoring, including a mobile platform for providing the robot with movement capability in a two-dimensional plane.

[0066] The multi-sensor fusion module, including lidar, visual camera, inertial measurement unit and ultrasonic sensor, is used to collect environmental data, generate high-precision two-dimensional maps, and realize the perception of dynamic environment.

[0067] Dynamic adaptive autonomous navigation system, the dynamic adaptive autonomous navigation system includes a path planning and optimization module. The dynamic adaptive autonomous navigation system adaptively adjusts the sensor weight distribution in the SLAM positioning module through real-time calculation of environmental interference parameters. The calculation formula is:

[0068]

[0069] Among them, W i is the weight of sensor i, σ i To reduce the error variance of sensor data and ensure accurate fusion of sensor data in complex environments, the path planning and optimization module adopts a multi-scenario adaptive learning mechanism based on the following update formula:

[0070]

[0071] Among them, Q(s,a) is the value function of selecting action a under state s, α is the learning rate, and γ is the discount factor. The path is dynamically optimized through the reinforcement learning algorithm. The path planning and optimization module supports multi-objective task scheduling, and can dynamically adjust the weight according to the importance of the task to optimize the inspection efficiency. After the inspection is completed, the inspection robot can generate a visual report based on cloud computing and realize multi-platform synchronous sharing. The dynamic adaptive autonomous navigation system includes a SLAM positioning module, which builds a two-dimensional environment map in real time and synchronously based on multi-sensor data and performs precise positioning.

[0072] The path planning and optimization module generates the optimal navigation path that is adaptive to environmental interference based on the dynamic Bayesian network and reinforcement learning algorithm. The path planning optimization uses the following formula:

[0073]

[0074] Among them, E d (t) is the path deviation, E o (t) is the obstacle distance cost, E v (t) is the speed control cost, w1, w2, w3 are weight factors to ensure the optimal adaptability of path planning in a dynamic environment. The dynamic adaptive autonomous navigation system also includes:

[0075] The real-time monitoring module is used to obtain temperature and humidity, gas concentration and vibration signals in the inspection environment, and generate a comprehensive monitoring report through multi-dimensional data fusion technology.

[0076] The dynamic response enhancement module includes a feedback controller based on model predictive control, which is used to adjust the robot position and posture in real time. Its dynamic response algorithm uses the following formula:

[0077] x t+1 =Ax t +But +G w w t ;

[0078] Among them, x t is the state vector, u t is the control input, w t A, B, G are environmental interferences. w It is a system matrix to improve the robustness and real-time performance under complex environmental interference. The dynamic response enhancement module combines the extended Kalman filter and predictive control algorithm to dynamically adjust the priority of the robot's navigation and monitoring tasks. The communication module supports 5G network and edge computing collaboration to ensure real-time processing of high-capacity data and low-latency remote control. The robot has real-time feedback and self-learning capabilities, and optimizes navigation and monitoring algorithms through inspection data. The multi-sensor fusion module uses an adaptive signal noise reduction algorithm to enhance the effectiveness of low signal-to-noise ratio sensor data in the environment. The control system adopts a distributed fault-tolerant design to ensure high-reliability operation of key modules.

[0079] The control system includes a real-time monitoring module, which is used to coordinate the operation of the multi-sensor fusion module, the navigation system and the real-time monitoring module, and transmit the data to the cloud or the local terminal. The real-time monitoring module is based on a multimodal data fusion algorithm and uses a Kalman filter model to improve the stability of monitoring data in harsh environments. Its state update formula is:

[0080]

[0081] in, is the current estimated state, K t is the Kalman gain, z t is the observed value, and H is the measurement matrix.

[0082] Communication module, realizes remote control and data transmission through wireless communication technology.

[0083] The power management module is used to optimize the energy consumption of the system and provide backup power to ensure that the robot can operate autonomously for a long time. The power management module integrates a dynamic energy consumption prediction model to evaluate the remaining power of the robot task in real time based on the following formula:

[0084]

[0085] Among them, E r is the remaining power, E t is the initial power, and P(t) is the instantaneous power consumption.

[0086] Intelligent environmental perception and adaptive decision-making module

[0087] The intelligent environmental perception and adaptive decision-making module combines deep learning and reinforcement learning methods to enhance the robot's ability to perceive environmental changes and make autonomous adaptive decisions based on real-time changes in the environment. Environmental perception not only relies on the fusion of multi-sensor data, but can also adjust inspection strategies in advance by predicting dynamic changes in the environment, ensuring that the robot can flexibly perform tasks in complex and uncertain environments.

[0088] Deep environmental perception: Use convolutional neural networks to perform deep image recognition of the environment around the robot. The image data collected from the visual camera is used for feature extraction through the convolutional neural network model to identify objects, obstacles, structural changes and environmental features. The depth information provided by lidar and ultrasonic sensors is used to further enhance the robot's three-dimensional environmental perception capabilities.

[0089] Environmental prediction and adaptive adjustment: Combined with the long short-term memory network model, the robot can make time series predictions on changes in the dynamic environment, and understand possible changes in the environment in advance. Based on the predicted information, the robot can adjust the inspection path, task priority or working mode in advance. When encountering obstacles, the robot predicts the movement trajectory of the obstacle through the long short-term memory network, and plans an avoidance path in advance to avoid collision.

[0090] Adaptive decision-making: Reinforcement learning combined with environmental prediction enables the robot to make autonomous decisions through real-time perception and prediction information, and select the optimal task execution sequence and path. Through real-time environmental information updates and reward mechanisms, the robot can optimize its behavior, reduce resource waste, and improve inspection efficiency.

[0091] Value Update in Reinforcement Learning:

[0092]

[0093] Environmental Forecast:

[0094] h t =f(CNN t ,LSTM t );

[0095] Among them, h t is the predicted value of the current environmental state, CNN t is the deep feature of the environmental image data, LSTM t It is the time series prediction result based on historical environmental data.

[0096] Embodiment 3

[0097] like Figure 1-3As shown, an embodiment of the present invention provides an inspection robot system integrating autonomous navigation and real-time monitoring, including a mobile platform for providing the robot with movement capability in a two-dimensional plane.

[0098] The multi-sensor fusion module, including lidar, visual camera, inertial measurement unit and ultrasonic sensor, is used to collect environmental data, generate high-precision two-dimensional maps, and realize the perception of dynamic environment.

[0099] Dynamic adaptive autonomous navigation system, the dynamic adaptive autonomous navigation system includes a path planning and optimization module. The dynamic adaptive autonomous navigation system adaptively adjusts the sensor weight distribution in the SLAM positioning module through real-time calculation of environmental interference parameters. The calculation formula is:

[0100]

[0101] Among them, W i is the weight of sensor i, σ i To reduce the error variance of sensor data and ensure accurate fusion of sensor data in complex environments, the path planning and optimization module adopts a multi-scenario adaptive learning mechanism based on the following update formula:

[0102]

[0103] Among them, Q(s,a) is the value function of selecting action a under state s, α is the learning rate, and γ is the discount factor. The path is dynamically optimized through the reinforcement learning algorithm. The path planning and optimization module supports multi-objective task scheduling, and can dynamically adjust the weight according to the importance of the task to optimize the inspection efficiency. After the inspection is completed, the inspection robot can generate a visual report based on cloud computing and realize multi-platform synchronous sharing. The dynamic adaptive autonomous navigation system includes a SLAM positioning module, which builds a two-dimensional environment map in real time and synchronously based on multi-sensor data and performs precise positioning.

[0104] The path planning and optimization module generates the optimal navigation path that is adaptive to environmental interference based on the dynamic Bayesian network and reinforcement learning algorithm. The path planning optimization uses the following formula:

[0105]

[0106] Among them, E d (t) is the path deviation, E o (t) is the obstacle distance cost, E v (t) is the speed control cost, w1, w2, w3 are weight factors to ensure the optimal adaptability of path planning in a dynamic environment. The dynamic adaptive autonomous navigation system also includes:

[0107] The real-time monitoring module is used to obtain temperature and humidity, gas concentration and vibration signals in the inspection environment, and generate a comprehensive monitoring report through multi-dimensional data fusion technology.

[0108] The dynamic response enhancement module includes a feedback controller based on model predictive control, which is used to adjust the robot position and posture in real time. Its dynamic response algorithm uses the following formula:

[0109] x t+1 =Ax t +Bu t +G w w t ;

[0110] Among them, x t is the state vector, u t is the control input, w t A, B, G are environmental interferences. w It is a system matrix to improve the robustness and real-time performance under complex environmental interference. The dynamic response enhancement module combines the extended Kalman filter and predictive control algorithm to dynamically adjust the priority of the robot's navigation and monitoring tasks. The communication module supports 5G network and edge computing collaboration to ensure real-time processing of high-capacity data and low-latency remote control. The robot has real-time feedback and self-learning capabilities, and optimizes navigation and monitoring algorithms through inspection data. The multi-sensor fusion module uses an adaptive signal noise reduction algorithm to enhance the effectiveness of low signal-to-noise ratio sensor data in the environment. The control system adopts a distributed fault-tolerant design to ensure high-reliability operation of key modules.

[0111] The control system includes a real-time monitoring module, which is used to coordinate the operation of the multi-sensor fusion module, the navigation system and the real-time monitoring module, and transmit the data to the cloud or the local terminal. The real-time monitoring module is based on a multimodal data fusion algorithm and uses a Kalman filter model to improve the stability of monitoring data in harsh environments. Its state update formula is:

[0112]

[0113] in, is the current estimated state, K t is the Kalman gain, z t is the observed value, and H is the measurement matrix.

[0114] Communication module, realizes remote control and data transmission through wireless communication technology.

[0115] The power management module is used to optimize the energy consumption of the system and provide backup power to ensure that the robot can operate autonomously for a long time. The power management module integrates a dynamic energy consumption prediction model to evaluate the remaining power of the robot task in real time based on the following formula:

[0116]

[0117] Among them, E r is the remaining power, E t is the initial power, and P(t) is the instantaneous power consumption.

[0118] Collaborative task execution and resource sharing module: The collaborative task execution and resource sharing module allows multiple inspection robots to distribute tasks and work together, improving the inspection efficiency and flexibility of the entire system. Through resource sharing and task collaboration, multiple robots can jointly complete one or more complex tasks, avoiding excessive workload for a single robot, and can adjust the work distribution between robots in real time according to task requirements and environmental conditions.

[0119] Based on the task priority, workload and environmental changes of the robot system, a distributed algorithm is used to allocate tasks. Through cooperative game theory, the system can automatically calculate the dependencies and priorities between tasks and reasonably allocate tasks to different robots for execution. Robots synchronize task progress and resource requirements in real time through wireless communication to ensure that tasks are not repeated and redundant work is avoided.

[0120] When multiple robots perform tasks together, path planning needs to consider not only the individual path of each robot, but also the relative positions and collaborative work between robots. For example, when multiple robots perform inspection tasks in the same area, they need to avoid path intersections or collisions while ensuring coverage of the entire area. In this case, the robot uses distributed collaborative path planning algorithms, such as multi-agent reinforcement learning, to enable multiple robots to collaborate in a shared area and adjust paths in real time.

[0121] When a robot is overloaded with tasks or runs out of power, the system can intelligently dispatch other robots to share the task or replace it. The system dynamically allocates resources based on each robot's remaining power, task progress, and current status information to ensure load balancing for the entire team. The battery management system is also combined with the task scheduling system to optimize energy distribution and prevent the robot from stopping midway due to lack of power.

[0122] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An inspection robot system integrating autonomous navigation and real-time monitoring, characterized in that: include: A mobile platform is used to provide the robot with the ability to move in a two-dimensional plane; Multi-sensor fusion module, including lidar, visual camera, inertial measurement unit and ultrasonic sensor, is used to collect environmental data, generate high-precision two-dimensional maps, and realize the perception of dynamic environment; A dynamic adaptive autonomous navigation system, wherein the dynamic adaptive autonomous navigation system comprises a path planning and optimization module; The control system includes a real-time monitoring module, which is used to coordinate the operation of the multi-sensor fusion module, the navigation system and the real-time monitoring module, and transmit the data to the cloud or local terminal; Communication module, which realizes remote control and data transmission through wireless communication technology; A power management module is used to optimize the energy consumption of the system and provide backup power to ensure long-term autonomous operation of the robot.

2. The inspection robot system integrating autonomous navigation and real-time monitoring according to claim 1 is characterized in that: The dynamic adaptive autonomous navigation system adaptively adjusts the sensor weight distribution in the SLAM positioning module through real-time calculation of environmental interference parameters. The calculation formula is: Among them, W i is the weight of sensor i, σ i is the error variance of sensor data, ensuring accurate fusion of sensor data in complex environments.

3. The inspection robot system integrating autonomous navigation and real-time monitoring according to claim 1 is characterized in that: The path planning and optimization module adopts a multi-scenario adaptive learning mechanism based on the following update formula: Among them, Q(s,a) is the value function of selecting action a in state s, α is the learning rate, γ is the discount factor, and the path is dynamically optimized through the reinforcement learning algorithm.

4. The inspection robot system integrating autonomous navigation and real-time monitoring according to claim 1 is characterized in that: The real-time monitoring module is based on a multimodal data fusion algorithm and uses a Kalman filter model to improve the stability of monitoring data in harsh environments. Its state update formula is: in, is the current estimated state, K t is the Kalman gain, z t is the observed value, and H is the measurement matrix.

5. The inspection robot system integrating autonomous navigation and real-time monitoring according to claim 4 is characterized in that: The power management module integrates a dynamic energy consumption prediction model to evaluate the remaining power of the robot task in real time based on the following formula: Among them, E r is the remaining power, E t is the initial power, and P(t) is the instantaneous power consumption.

6. The inspection robot system integrating autonomous navigation and real-time monitoring according to claim 1 is characterized in that: The path planning and optimization module supports multi-objective task scheduling, can dynamically adjust weights according to task importance, and optimize inspection efficiency. After the inspection is completed, the inspection robot can generate a visual report based on cloud computing and realize multi-platform synchronous sharing.

7. The inspection robot system integrating autonomous navigation and real-time monitoring according to claim 1 is characterized in that: The dynamic adaptive autonomous navigation system includes a SLAM positioning module, which builds a two-dimensional environment map in real time and performs precise positioning based on multi-sensor data; The path planning and optimization module generates an optimal navigation path that is adaptive to environmental interference based on a dynamic Bayesian network and a reinforcement learning algorithm, wherein the path planning optimization uses the following formula: Among them, E d (t) is the path deviation, E o (t) is the obstacle distance cost, E v (t) is the speed control cost, w1, w2, w3 are weight factors, which ensure the optimal adaptability of path planning in a dynamic environment.

8. The inspection robot system integrating autonomous navigation and real-time monitoring according to claim 7 is characterized in that: The dynamic adaptive autonomous navigation system also includes: The real-time monitoring module is used to obtain temperature and humidity, gas concentration and vibration signals in the inspection environment, and generate a comprehensive monitoring report through multi-dimensional data fusion technology; The dynamic response enhancement module includes a feedback controller based on model predictive control, which is used to adjust the robot position and posture in real time. Its dynamic response algorithm uses the following formula: x t+1 =Ax t +Bu t +G w w t ; Among them, x t is the state vector, u t is the control input, w t is environmental interference, A, B, G w It is the system matrix to improve the robustness and real-time performance under complex environmental interference.

9. The inspection robot system integrating autonomous navigation and real-time monitoring according to claim 8, characterized in that: The dynamic response enhancement module combines extended Kalman filtering and predictive control algorithms to dynamically adjust the priorities of robot navigation and monitoring tasks. The communication module supports 5G network and edge computing collaboration to ensure real-time processing of high-capacity data and low-latency remote control. The robot has real-time feedback and self-learning capabilities, and optimizes navigation and monitoring algorithms through inspection data. The multi-sensor fusion module uses an adaptive signal noise reduction algorithm to enhance the effectiveness of low signal-to-noise ratio sensor data in the environment. The control system adopts a distributed fault-tolerant design to ensure high-reliability operation of key modules.

Images