Interference-free autonomous travel system for unmanned devices
By dynamically adjusting the gain coefficient through environmental perception and chaotic control modules, the problem of unstable movement of unmanned equipment in complex environments without external control signals is solved, enabling autonomous obstacle avoidance and path planning, and improving the equipment's adaptability in complex environments.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI UNIV OF ENG SCI
- Filing Date
- 2026-03-03
- Publication Date
- 2026-06-12
AI Technical Summary
Existing unmanned equipment struggles to operate stably in environments without external control signals and in complex, unstructured environments. In particular, its trajectory is easily predicted and intercepted under strong noise interference, and it lacks real-time adaptive capabilities.
It employs an environmental perception module, a global task planning module, a decision fusion and chaos control module, a chaos behavior generator, and a motion execution module, combined with LiDAR, depth camera, millimeter-wave radar, and IMU sensors. By dynamically adjusting the gain coefficient of the chaos behavior generator, it generates chaotic control signals to achieve autonomous obstacle avoidance and path planning.
In the absence of external control signals and under complex noise interference, the equipment's trajectory is complex and unpredictable. It has efficient autonomous obstacle avoidance capabilities, ensuring stable operation in unstructured environments, and is suitable for fields such as military reconnaissance and security patrol.
Smart Images
Figure CN122194985A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of autonomous control and intelligent cruise technology for unmanned equipment, and in particular to an interference-free autonomous movement system for unmanned equipment. Background Technology
[0002] With the rapid development of automation technology, unmanned equipment (such as drones, unmanned vehicles, and underwater robots) has been widely used in logistics, surveying and mapping, agriculture, security patrol, and military reconnaissance. One of its core technologies is the autonomous mobility system, which determines the intelligence level, adaptability, and reliability of the equipment in achieving its target tasks in complex environments.
[0003] In existing technologies, methods based on SLAM and deterministic path planning algorithms use simultaneous localization and mapping (SLAM) techniques, combined with algorithms such as A / D and fast randomized tree search, for real-time path planning. However, the trajectory of the unmanned equipment controlled in this technology is usually a smooth, predictable curve. Although it can handle static obstacles, it requires a connection to external satellite signals and cannot operate stably when it cannot connect to external control signals or is subjected to strong noise interference.
[0004] Therefore, there is an urgent need for an autonomous movement system for unmanned equipment to improve the real-time adaptive capability of unmanned equipment in complex unstructured environments without external control signals. Summary of the Invention
[0005] Therefore, it is necessary to provide an interference-free autonomous movement system for unmanned equipment to address the aforementioned technical problems.
[0006] The present invention adopts the following technical solution: This invention provides an interference-free autonomous movement system for unmanned equipment, comprising: The module consists of an environmental perception module, a global task planning module, a decision fusion and chaos control module, a chaotic behavior generator, and a motion execution module. The environmental perception module is used to collect real-time environmental data of the environment in which the unmanned equipment is located; The global task planning module is used to set the task objectives of unmanned equipment based on real-time environmental data and issue navigation commands based on the task objectives. The decision fusion and chaos control module is used to set the autonomous travel direction of the unmanned device in an interference-free state according to the navigation instructions; if the unmanned device travels in the autonomous travel direction, the gain coefficient of the chaos behavior generator is dynamically adjusted according to real-time environmental data, including: when the distance between the obstacle and the unmanned device in the real-time environmental data is greater than 3 times the size of the unmanned device in the autonomous travel direction, the gain coefficient is adjusted to between 0.5 and 0.8; when the distance between the obstacle and the unmanned device in the real-time environmental data is less than 3 times the size of the unmanned device in the autonomous travel direction, the gain coefficient is adjusted to below 0.5; if the unmanned device travels in a non-autonomous travel direction, the gain coefficient is adjusted to above 0.8. A chaotic behavior generator is used to generate chaotic control signals and obstacle avoidance commands for unmanned equipment based on the gain coefficient. The motion execution module is used to convert obstacle avoidance commands and chaotic control signals into mechanical control signals for unmanned equipment, so as to control the autonomous movement of the unmanned equipment.
[0007] Preferably, the environmental perception module includes: a lidar, a depth camera, a millimeter-wave radar, and an IMU sensor; The lidar generates dense point cloud data of the environment in which the unmanned equipment is located by emitting laser beams and measuring the return time. The depth camera, combined with 2D RGB image information, is used to identify and segment specific objects in the environment where the unmanned device is located, providing depth navigation information for the unmanned device in narrow or complex spaces. The millimeter-wave radar uses the Doppler effect to measure the relative radial velocity of a target; The IMU sensor is used to measure the device's triaxial angular velocity and triaxial acceleration in real time.
[0008] Preferably, the global task planning module integrates an embedded system with a microprocessor and DDR4 memory, as well as eMMC flash memory, and is externally connected to a GNSS / IMU integrated navigation module via a UART interface; The eMMC flash memory contains a digital map and geofence coordinates of the unmanned equipment's operating area; The microprocessor receives the task objective sent by the remote control center, loads the digital map and geofence coordinates of the unmanned equipment's operating area from the eMMC flash memory, calls the internally stored path planning algorithm based on the digital map and geofence coordinates of the operating area to generate a waypoint sequence for the operating area, and generates navigation instructions based on the waypoint sequence.
[0009] Preferably, the global task planning module further includes: a data storage unit and a positioning and attitude processing unit; The data storage unit is used to store real-time environmental data of the environment in which the unmanned equipment is located; the positioning and attitude processing unit is used to provide attitude estimation results of the unmanned equipment.
[0010] Preferably, the chaotic behavior generator includes: an FPGA processor, a digital-to-analog converter, high-speed RAM, and multiple built-in controllable chaotic systems.
[0011] Preferably, the chaotic behavior generator also includes a synchronization control system for real-time differential compensation of velocity and angular velocity when the unmanned equipment is subjected to external disturbances.
[0012] Preferably, the motion execution module includes an instruction fusion unit, a PID controller, and an electronic speed controller; The instruction fusion unit is used to fuse obstacle avoidance instructions and chaotic control signals to generate final control instructions. The PID controller is used to compare the final control command with the actual state of the unmanned equipment fed back by the sensor, and to obtain a mechanical control signal that eliminates the error between the final control command and the actual state of the unmanned equipment through PID calculation. The electronic speed controller is used to convert mechanical control signals into three-phase AC power to control the motor speed and torque, thereby controlling the autonomous movement of the unmanned equipment.
[0013] The above-mentioned at least one technical solution adopted in this invention can achieve the following beneficial effects: In the interference-free autonomous movement system for unmanned equipment provided by this invention, the decision fusion and chaos control module receives information from the environmental perception module and instructions from the global task planning module. When the environment is relaxed, the control parameters of the chaotic system are increased, enhancing the randomness of the output signal and making the equipment's trajectory more complex and unpredictable. The generated trajectory has quasi-random characteristics at the microscopic level, making it difficult for the enemy to predict or intercept, and is particularly suitable for military reconnaissance, security patrols, and other fields. When the unmanned equipment approaches obstacles or dangers, the chaos effect is reduced or even temporarily shut down. By introducing convergence control, the equipment's behavior tends to stabilize, and it prioritizes switching to obstacle avoidance mode to perform obstacle avoidance. The action requires the chaotic behavior generator to work continuously while moving covertly, ensuring that the trajectory cannot be predicted by an external observer using a simple model. The chaotic system of the chaotic behavior generator is extremely sensitive to initial conditions, enabling the device to generate rich behavioral changes with tiny control inputs internally, and to respond quickly to complex environmental disturbances. This allows the unmanned device to move stably along the expected path in unstructured environments without external control signals and complex noise interference, thereby effectively improving the real-time adaptive capability of the unmanned device in unstructured environments without external control signals, and enabling the unmanned device to operate stably in complex unstructured environments without external control signals. Attached Figure Description
[0014] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0015] Figure 1 This is a schematic diagram of the structure of an interference-free unmanned autonomous movement system provided by the present invention. Detailed Implementation
[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in the specification without creative effort are within the scope of protection of this application.
[0017] Currently, mainstream autonomous movement solutions for unmanned equipment mainly include: Methods based on pre-programmed paths and PID control: The equipment travels along a pre-defined fixed path. This method is simple to implement but extremely inflexible, unable to cope with any unmodeled environmental changes (such as sudden obstacles or wind disturbances), making it difficult to apply effectively in dynamic, unstructured real-world environments. Methods based on SLAM and deterministic path planning algorithms: Real-time path planning is performed using simultaneous localization and mapping (SLAM) techniques combined with algorithms such as A / D and fast randomized tree search. While this method can handle static obstacles, the generated paths are usually smooth curves with global or local optima, exhibiting significant limitations. Its trajectory is highly predictable and easily intercepted by interference systems, posing serious risks in military and security fields. In environments with dense dynamic obstacles, frequent global replanning is required, resulting in high computational load, a sharp drop in real-time performance, and a tendency to get trapped in local optima or cyclical calculations. When exploring unknown areas, systematic scanning coverage methods may generate numerous duplicate paths, leading to low efficiency and the potential to miss key features. Methods based on traditional artificial intelligence, such as deep learning and reinforcement learning. These methods train decision models on massive amounts of data, achieving excellent performance on certain specific tasks. However, they also have inherent drawbacks: model training requires massive, high-quality datasets, which is costly. When encountering critical situations outside the training set, their behavior becomes unpredictable, potentially leading to catastrophic consequences. Furthermore, efficient real-time learning and adaptation during task execution are difficult.
[0018] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.
[0019] Figure 1 This is a schematic diagram of the structure of an interference-free unmanned autonomous movement system according to the present invention, specifically including: The environmental perception module is used to collect real-time environmental data of the environment in which the unmanned equipment is located; The module consists of an environmental perception module, a global task planning module, a decision fusion and chaos control module, a chaotic behavior generator, and a motion execution module. The environmental perception module is used to collect real-time environmental data of the environment in which the unmanned equipment is located; The global task planning module is used to set the task objectives of unmanned equipment based on real-time environmental data and issue navigation commands based on the task objectives. The decision fusion and chaos control module is used to set the autonomous travel direction of the unmanned device in an interference-free state according to the navigation instructions; if the unmanned device travels in the autonomous travel direction, the gain coefficient of the chaos behavior generator is dynamically adjusted according to real-time environmental data, including: when the distance between the obstacle and the unmanned device in the real-time environmental data is greater than 3 times the size of the unmanned device in the autonomous travel direction, the gain coefficient is adjusted to between 0.5 and 0.8; when the distance between the obstacle and the unmanned device in the real-time environmental data is less than 3 times the size of the unmanned device in the autonomous travel direction, the gain coefficient is adjusted to below 0.5; if the unmanned device travels in a non-autonomous travel direction, the gain coefficient is adjusted to above 0.8. A chaotic behavior generator is used to generate chaotic control signals and obstacle avoidance commands for unmanned equipment based on the gain coefficient. The motion execution module is used to convert obstacle avoidance commands and chaotic control signals into mechanical control signals for unmanned equipment, so as to control the autonomous movement of the unmanned equipment.
[0020] Optionally, the environmental perception module includes: LiDAR, depth camera, millimeter-wave radar, and IMU sensor; The lidar generates dense point cloud data of the environment in which the unmanned equipment is located by emitting laser beams and measuring the return time. The depth camera, combined with 2D RGB image information, is used to identify and segment specific objects in the environment where the unmanned device is located, providing the unmanned device with fine depth navigation information in narrow or complex spaces. The millimeter-wave radar uses the Doppler effect to measure the relative radial velocity of a target; The IMU sensor is used to measure the device's triaxial angular velocity and triaxial acceleration in real time.
[0021] Specifically, the IMU data is input to the underlying attitude PID controller to maintain the stability of the device when chaotic perturbations are introduced; on the other hand, the data is uploaded to the decision fusion and chaos controller as real physical state feedback to evaluate the actual performance of chaotic behavior, thereby realizing adaptive closed-loop adjustment of chaos intensity.
[0022] Optionally, the global task planning module integrates an embedded system with a microprocessor and DDR4 memory, as well as eMMC flash memory, and connects to the GNSS / IMU integrated navigation module via a UART interface; The eMMC flash memory contains a digital map and geofence coordinates of the unmanned equipment's operating area; The microprocessor receives the task objective sent by the remote control center, loads the digital map and geofence coordinates of the unmanned equipment's operating area from the eMMC flash memory, calls the internally stored path planning algorithm based on the digital map and geofence coordinates of the operating area to generate a waypoint sequence for the operating area, and generates navigation instructions based on the waypoint sequence.
[0023] Optionally, the global task planning module also includes: a data storage unit and a positioning and attitude processing unit; The data storage unit is used to store real-time environmental data of the environment in which the unmanned equipment is located; the positioning and attitude processing unit is used to provide attitude estimation results of the unmanned equipment.
[0024] Optionally, the chaotic behavior generator includes: an FPGA processor, a digital-to-analog converter, a high-speed RAM, and multiple built-in controllable chaotic systems; the chaotic behavior generator also includes a synchronization control system for real-time interpolation of velocity and angular velocity when the unmanned equipment receives external disturbances.
[0025] Optionally, the motion execution module includes an instruction fusion unit, a PID controller, and an electronic speed controller; The instruction fusion unit is used to fuse the baseline control instructions output by the decision fusion and chaos control module and the chaotic control signals output by the chaotic behavior generator to generate the final control instructions. The PID controller is used to compare the final control command with the actual state fed back by the sensor, and to obtain a mechanical control signal that eliminates the error between the final control command and the actual state through PID calculation. The electronic speed controller is used to convert mechanical control signals into three-phase AC power to control the motor speed and torque, thereby controlling the autonomous movement of the unmanned equipment.
[0026] Specifically, this embodiment provides an autonomous driving system for unmanned equipment based on chaotic control theory to further illustrate the technical solution of the present invention. This autonomous driving system includes: an environmental perception module, a chaotic behavior generator, a global task planning module, a decision fusion and chaotic control module, and a motion execution module. The environmental perception module is used to collect environmental information around the unmanned equipment in real time, including LiDAR, a depth camera, millimeter-wave radar, and an IMU sensor. The LiDAR generates dense point cloud data of the surrounding environment by emitting laser beams and measuring the return time, accurately depicting the contours of objects and terrain. It can identify and classify vehicles, pedestrians, trees, buildings, etc. Matching with pre-made high-precision maps enables high-precision positioning of the equipment. The depth camera, combined with 2D RGB image information, can accurately identify and segment specific objects, providing detailed depth navigation information for the unmanned equipment in narrow or complex spaces. The millimeter-wave radar directly and accurately measures the relative radial velocity of targets using the Doppler effect. LiDAR provides precise geometric contours of distant objects, while a depth camera offers rich color and texture details at close range, supplementing and enhancing the LiDAR point cloud. Millimeter-wave radar enables accurate determination of the device's movement speed and orientation. The environmental perception module collects data on the device's surrounding environment, processes this data, and provides a basis for decision-making regarding the device's movement control in the absence of external control signals. The environmental perception module is electrically connected to the global task planning module and the decision fusion and chaos control module.
[0027] The global task planning module includes a main processor, a data storage unit, a positioning and attitude processing unit, an external communication interface, and an internal communication bus. This module sets the macroscopic task objectives of the unmanned equipment, issues high-level navigation commands, defines physical and behavioral boundaries for the equipment's chaotic behavior, and can dynamically adjust the task objectives as needed. It enables tasks such as moving from point A to point B along the shortest path and conducting area patrols according to paths planned by the chaotic behavior generation module. The global task planning module is based on an embedded system integrating an ARM architecture microprocessor and DDR4 memory. This module connects to a high-precision GNSS / IMU integrated navigation module via its UART interface to acquire the global pose of the unmanned equipment in real time. The module integrates eMMC flash memory, which pre-stores digital maps and geofence coordinates of the operating area. The module receives patrol task commands from a remote control center via a 4G LTE communication module. During operation, the microprocessor loads map data from the eMMC into the DDR4 memory and parses the 'area coverage patrol' commands received via the 5G module. The microprocessor calls the path planning algorithm stored in its internal memory to generate a series of waypoint sequences covering the area based on the digital map, and continuously sends the next target waypoint and behavior pattern parameters to the decision fusion and chaos controller via the CAN bus.
[0028] The main processor is electrically connected to the data storage unit, the positioning and attitude processing unit, the external communication interface, and the internal communication bus. The data storage unit stores environmental information data collected and transmitted by the environmental perception module and is electrically connected to the internal communication bus.
[0029] The positioning and attitude processing unit includes a gyroscope and an accelerometer. The gyroscope and accelerometer provide the device attitude calculation results and are electrically connected to the external communication interface.
[0030] The chaotic behavior generator includes an FPGA processor, a digital-to-analog converter, high-speed RAM, and multiple built-in controllable chaotic systems, such as various chaotic systems based on Chen, Chai, and LV-like systems. By receiving control parameters from the decision fusion module, the generator outputs bounded random signals with chaotic characteristics. These signals serve as reference input parameters for the unmanned equipment's underlying control (such as speed, angular velocity, and attitude fine-tuning), enabling the unmanned equipment to autonomously travel along the generated chaotic path. The chaotic behavior generator includes a synchronous control system, enabling real-time interpolation to prevent uncontrollable behavior caused by the system's sensitivity to initial conditions due to external interference. The chaotic behavior generator is electrically connected to the decision fusion and chaotic controller, and also electrically connected to the motion execution module.
[0031] The decision fusion and chaos controller receives information from the environmental perception module and instructions from the global task planning module. It also records and stores data along the device's path and dynamically adjusts the parameters of the chaos behavior generator. Its core logic is to increase the control parameters of the chaotic system when the environment is relaxed, enhancing the randomness of the output signal and making the device's trajectory more complex and unpredictable, thus achieving an "exploration" mode. When approaching obstacles or dangers, the chaos effect is reduced or even temporarily shut down, introducing convergence control to stabilize the device's behavior. Pre-set control parameters are input to keep the device hovering or in a uniform linear motion at a speed less than 5 m / s, prioritizing switching to obstacle avoidance mode to perform obstacle avoidance actions. When covert movement is required, the chaos behavior generator continues to operate, ensuring that the trajectory cannot be predicted by an external observer using a simple model. This module uses fuzzy logic, neural networks, or rule-based systems to map environmental states to chaotic control parameters.
[0032] The decision fusion and chaos controller is electrically connected to the environmental perception module and the motion execution module.
[0033] The motion execution module includes an instruction fusion unit, a PID controller, and an electronic speed controller. The motion execution module converts the final control command (which integrates chaotic fine-tuning and deterministic obstacle avoidance commands) output by the decision fusion module into specific control signals for the motor, servo motor, or thruster.
[0034] The instruction fusion unit receives the baseline control instruction from the decision fusion unit and the chaotic control signal from the chaotic behavior generator, and generates the final control instruction after fusion and discrimination.
[0035] The PID controller receives the fused command and compares it with the actual state fed back by the sensor. Through proportional, integral, and derivative operations, it calculates the precise drive signal required to eliminate the error.
[0036] The electronic speed controller receives PWM signals from the PID controller and converts them into three-phase AC power to precisely control the motor's speed and torque, thereby controlling the movement of the equipment.
[0037] The electronic speed controller is electrically connected to the PID controller and to the motor controlled by the unmanned equipment. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this invention.
Claims
1. An interference-free autonomous movement system for unmanned equipment, characterized in that, include: The module consists of an environmental perception module, a global task planning module, a decision fusion and chaos control module, a chaotic behavior generator, and a motion execution module. The environmental perception module is used to collect real-time environmental data of the environment in which the unmanned equipment is located; The global task planning module is used to set the task objectives of unmanned equipment based on real-time environmental data and issue navigation commands based on the task objectives. The decision fusion and chaos control module is used to set the autonomous travel direction of the unmanned equipment in an interference-free state according to the navigation instructions; If the unmanned device travels in the autonomous travel direction, the gain coefficient of the chaotic behavior generator is dynamically adjusted according to real-time environmental data, including: when the distance between the obstacle and the unmanned device in the real-time environmental data is greater than 3 times the size of the unmanned device in the autonomous travel direction, the gain coefficient is adjusted to between 0.5 and 0.8; when the distance between the obstacle and the unmanned device in the real-time environmental data is less than 3 times the size of the unmanned device in the autonomous travel direction, the gain coefficient is adjusted to below 0.5; if the unmanned device travels in a non-autonomous travel direction, the gain coefficient is adjusted to above 0.
8. A chaotic behavior generator is used to generate chaotic control signals and obstacle avoidance commands for unmanned equipment based on the gain coefficient. The motion execution module is used to convert obstacle avoidance commands and chaotic control signals into mechanical control signals for unmanned equipment, so as to control the autonomous movement of the unmanned equipment.
2. The interference-free unmanned autonomous movement system as described in claim 1, characterized in that, The environmental perception module includes: lidar, depth camera, millimeter-wave radar, and IMU sensor; The lidar generates dense point cloud data of the environment in which the unmanned equipment is located by emitting laser beams and measuring the return time. The depth camera, combined with 2D RGB image information, is used to identify and segment specific objects in the environment where the unmanned device is located, providing depth navigation information for the unmanned device in narrow or complex spaces. The millimeter-wave radar uses the Doppler effect to measure the relative radial velocity of a target; The IMU sensor is used to measure the device's triaxial angular velocity and triaxial acceleration in real time.
3. The interference-free unmanned autonomous movement system as described in claim 1, characterized in that, The global task planning module integrates an embedded system with a microprocessor and DDR4 memory, as well as eMMC flash memory, and is externally connected to a GNSS / IMU integrated navigation module via a UART interface; The eMMC flash memory contains a digital map and geofence coordinates of the unmanned equipment's operating area; The microprocessor receives the task objective sent by the remote control center, loads the digital map and geofence coordinates of the unmanned equipment's operating area from the eMMC flash memory, calls the internally stored path planning algorithm based on the digital map and geofence coordinates of the operating area to generate a waypoint sequence for the operating area, and generates navigation instructions based on the waypoint sequence.
4. The interference-free unmanned equipment autonomous movement system as described in claim 1, characterized in that, The global task planning module also includes: a data storage unit and a positioning and attitude processing unit; The data storage unit is used to store real-time environmental data of the environment in which the unmanned equipment is located; the positioning and attitude processing unit is used to provide attitude estimation results of the unmanned equipment.
5. The interference-free unmanned equipment autonomous movement system as described in claim 1, characterized in that, The chaotic behavior generator includes an FPGA processor, a digital-to-analog converter, high-speed RAM, and multiple built-in controllable chaotic systems.
6. The interference-free unmanned autonomous movement system as described in claim 1, characterized in that, The chaotic behavior generator also includes a synchronization control system for real-time differential compensation of velocity and angular velocity when the unmanned equipment is subjected to external disturbances.
7. The interference-free unmanned autonomous movement system as described in claim 1, characterized in that, The motion execution module includes an instruction fusion unit, a PID controller, and an electronic speed controller; The instruction fusion unit is used to fuse obstacle avoidance instructions and chaotic control signals to generate final control instructions. The PID controller is used to compare the final control command with the actual state of the unmanned equipment fed back by the sensor, and to obtain a mechanical control signal that eliminates the error between the final control command and the actual state of the unmanned equipment through PID calculation. The electronic speed controller is used to convert mechanical control signals into three-phase AC power to control the motor speed and torque, thereby controlling the autonomous movement of the unmanned equipment.