Communication method and system applied to intelligent robot
Optimizing intelligent robot communication through multimodal communication and adaptive algorithms solves the problems of complex environments and diversified needs, realizes low-latency, high reliability and energy-saving communication, and improves the working efficiency and stability of intelligent robots.
Patent Information
- Application Number
- CN202410934519.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-07-12
AI Technical Summary
The existing intelligent robot communication methods are difficult to cope with the changes in complex environments and diversified communication needs, resulting in easy collisions between intelligent robots and affecting work efficiency.
The multimodal communication method is adopted to optimize communication strategies through environment perception and adaptive communication mode selection, combined with machine learning algorithms, and realize low-latency, high reliability, energy-saving and secure communication. Specific steps include multimodal communication initialization, environment perception, adaptive communication mode selection, communication quality monitoring, multimodal communication fusion, task-specific communication adjustment and collaborative communication.
It improves the flexibility and adaptability of intelligent robot communication, ensures the efficiency and stability of task execution, and can dynamically optimize communication strategies according to environment and task needs, avoid collisions and signal interference, and improve work efficiency.
Smart Images

Figure CN119012173A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent robot communication technology, and in particular to a communication method and system applied to an intelligent robot. Background Art
[0002] Existing intelligent robot communication methods mostly adopt a single mode, which is difficult to cope with complex environmental changes and diverse communication needs. When there are multiple intelligent robots performing work tasks in an area, the work routes of multiple intelligent robots are prone to intersection, which makes it easy for multiple intelligent robots to collide, resulting in abnormal operation of the intelligent robots, thereby affecting work efficiency.
[0003] To this end, we propose a communication method and system for intelligent robots to solve the above-mentioned problems. Summary of the invention
[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.
[0005] In view of the above-mentioned problems existing in the existing communication methods and systems applied to intelligent robots, the present invention is proposed.
[0006] Therefore, the purpose of the present invention is to provide a communication method and system for an intelligent robot, which can automatically select and switch different communication modes according to the environment and task requirements, and adaptively optimize the communication strategy through a machine learning algorithm to achieve low-latency, high-reliability, energy-saving and secure communication.
[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0008] A communication method applied to an intelligent robot comprises the following steps:
[0009] Step 1: Multimodal communication initialization: When the robot is initialized, multiple communication modes are activated, including but not limited to Wi-Fi, Bluetooth, and 5G. The appropriate initial communication mode is selected according to the environmental characteristics and task requirements;
[0010] Step 2: Environmental perception: Collect surrounding environment data through sensors such as cameras, microphones or lidar and identify factors in the environment that affect communication, such as signal interference, obstacles, and network congestion;
[0011] Step 3: Adaptive communication mode selection: Dynamically adjust the communication mode based on the information provided by environmental perception, use self-learning algorithms to optimize the communication mode selection strategy, collect and store communication history data, and analyze the best communication mode selection and adjustment strategy in different environments;
[0012] Step 4: Communication quality monitoring: Real-time monitoring of the quality parameters of each communication mode, such as signal strength, transmission speed, delay, and packet loss rate. Based on the communication quality monitoring data, the priority and frequency of use of the communication mode are adjusted;
[0013] Step 5: Multimodal communication fusion: During the communication process, multiple communication modes are allowed to work simultaneously to improve the stability and bandwidth of communication, integrate data from different communication modes, and remove redundant and conflicting information;
[0014] Step 6: Task-specific communication adjustment: Further optimize the communication according to the specific tasks performed by the robot. When performing video transmission tasks, give priority to communication modes with larger bandwidth; when performing low-latency control tasks, give priority to communication modes with smaller delays.
[0015] Step 7: Collaborative communication: When multiple robots work together, a shared communication strategy library is established, and the communication quality and optimization methods in steps 3 to 6 are shared among the robots to achieve collaborative communication optimization.
[0016] As a preferred solution of the communication method applied to an intelligent robot according to the present invention, the self-learning algorithm in step 3 adopts a deep network algorithm, which specifically includes:
[0017] 1) Status indication:
[0018] The state s includes the following environmental factors:
[0019] s1: signal interference level;
[0020] s2: obstacle density;
[0021] s3: Network congestion level
[0022] 2) Action representation:
[0023] Action a indicates the selected communication mode:
[0024] a1: Wi-Fi;
[0025] a2: Bluetooth;
[0026] a3: 5G;
[0027] 3) Reward function:
[0028] The reward function r(s,a) is defined by the communication quality parameter:
[0029] r(s,a)=w1·Q signal +w2·Q speed -w3·Q delay -w4·Q loss
[0030] The weight parameters are:
[0031] w1=0.4, w2=0.3, w3=0.2, w4=0.1
[0032] 4) Q-value function:
[0033] The Q-value function Q(s,a) represents the expected cumulative reward after performing action a in state s. The Q-value function is approximated by a deep neural network Q(s,a;θ), where θ is the parameter of the neural network.
[0034] 5) Loss function:
[0035] The loss function is used to minimize the gap between the actual Q value and the predicted Q value. The actual Q value is calculated by the Bellman equation:
[0036]
[0037] Where γ is the discount factor, θ - is the parameter of the target network, which is used to stabilize the training. The loss function is defined as:
[0038] L(θ)=E[(yQ(s,a;θ( 2 ].
[0039] As a preferred solution of the communication method applied to an intelligent robot of the present invention, the algorithm steps of the self-learning algorithm include:
[0040] A1. Initialization:
[0041] Initialize the Q network Q(s,a;θ) and the target network Q(s,a;θ - ), and set the target network parameters θ - =θ;
[0042] Initialize experience replay pool D;
[0043] A2. Collection experience:
[0044] Perform actions in the environment, observe the results and rewards, and store them in the experience replay pool D;
[0045] A3. Random sampling:
[0046] Randomly draw a mini-batch (s, a, r, s') of samples from the experience replay pool;
[0047] A4. Calculate the target Q value:
[0048] For each sample (s,a,r,s'), calculate the target Q value y:
[0049]
[0050] A5. Gradient descent:
[0051] Use stochastic gradient descent to minimize the loss function L(θ) and update the parameters θ of the Q network:
[0052]
[0053] Among them, α is the learning rate;
[0054] A6. Update the objective function:
[0055] At certain intervals, the parameters θ of the Q network are copied to the target network θ - .
[0056] As a preferred solution of the communication method applied to an intelligent robot of the present invention, the reward function r(s,a) of the self-learning algorithm performs threshold judgment and strategy update:
[0057] Set the threshold to r threshold =50, if r(s,5G)≥r threshold , then the selected communication mode is considered valid;
[0058] If r(s,5G) <r threshold , then consider adjusting the communication mode selection strategy.
[0059] As a preferred solution of the communication method applied to the intelligent robot of the present invention, the real-time communication adjustment in step 6 includes:
[0060] (1) Perceiving the current environment status: Using sensors to detect signal interference levels, obstacle density, and network congestion in real time;
[0061] (2) Select the best action a: Select the optimal communication mode based on the current state s and Q network;
[0062] (3) Execute the action and obtain the reward r: execute the selected communication mode, record the communication quality parameters, and calculate the reward;
[0063] (4) Update strategy: Continuously optimize the Q network through gradient descent to achieve adaptive communication mode selection.
[0064] As a preferred solution of the communication method applied to the intelligent robot of the present invention, in step 7, when the robot performs a specific task, the communication method is further optimized according to the task characteristics and the current environment state, including:
[0065] Relationship between mission characteristics and communication optimization:
[0066] a. Data transmission requirements
[0067] Tasks with high real-time requirements: such as tasks that require immediate response or transmit large amounts of data; communication modes with faster transmission speeds, such as 5G, are preferred;
[0068] Low-latency tasks: For tasks that require low latency, such as remote control or real-time video transmission, communication modes with lower transmission latency should be given priority;
[0069] b. Data volume and stability requirements
[0070] Large data transmission: In tasks that require large amounts of data transmission, consider the balance between transmission speed and stability and choose a communication mode that provides high speed and low packet loss rate;
[0071] Tasks with high stability requirements: For example, long-running monitoring tasks or tasks that require long-term stable connections, communication modes with better transmission stability should be given priority.
[0072] As a preferred solution of the communication method applied to the intelligent robot of the present invention, the optimized communication method further comprises:
[0073] Dynamic environment perception and adaptive optimization:
[0074] c. Real-time environmental monitoring
[0075] Signal interference changes: Use sensors to monitor changes in surrounding signal interference in real time and adjust the communication frequency band or channel in a timely manner;
[0076] Obstacle movement: Detects the movement or change of obstacles and adjusts the communication mode to avoid signal blocking;
[0077] Network congestion: monitor network load and congestion, and dynamically select a communication mode suitable for the current network status;
[0078] d. Adaptive communication strategy update
[0079] Feedback-based optimization: Dynamically adjust communication strategies and selections based on feedback from actual communication results, such as communication quality parameters and reward values;
[0080] Continuous optimization of reinforcement learning: Use learning algorithms to continuously learn and update communication strategies to adapt to environmental changes and dynamic adjustments to task requirements.
[0081] As a preferred solution of the communication method applied to the intelligent robot of the present invention, the communication system applied to the intelligent robot includes the following modules:
[0082] Multimodal communication module: supports multiple communication modes, such as WiFi, Bluetooth, and 5G, and can automatically switch according to the environment;
[0083] Environmental perception module: uses sensors to perceive the surrounding environment in real time, including signal strength, interference, and network load information;
[0084] Task management module: evaluates communication performance requirements, such as bandwidth, latency, and reliability, based on the robot's current task requirements;
[0085] Self-learning optimization module: Based on machine learning algorithms, it adaptively optimizes communication strategies and continuously learns and adjusts communication parameters;
[0086] Data processing module: responsible for data compression, encryption, decryption and transmission to ensure the efficiency and security of data transmission.
[0087] Beneficial effects of the present invention: The present invention can automatically select and switch different communication modes according to the environment and task requirements, and achieve low-latency, high-reliability, energy-saving and secure communication through steps such as multimodal communication fusion, environmental perception, adaptive communication mode selection, and self-learning communication optimization. This method not only improves the flexibility and adaptability of robot communication, but also continuously optimizes the communication strategy through self-learning algorithms. Furthermore, the intelligent robot can also dynamically optimize the communication method according to the characteristics of specific tasks and real-time environmental changes to ensure the efficiency and stability of task execution. This adaptive communication optimization strategy based on task characteristics and environmental perception can effectively respond to different work scenarios and task requirements. BRIEF DESCRIPTION OF THE DRAWINGS
[0088] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:
[0089] Figure 1 The present invention is a flow chart of a communication method and system for an intelligent robot. DETAILED DESCRIPTION
[0090] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0091] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0092] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0093] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.
[0094] Reference Figure 1 , provides a communication method applied to an intelligent robot, comprising the following steps:
[0095] Step 1: Multimodal communication initialization: When the robot is initialized, multiple communication modes are activated, including but not limited to Wi-Fi, Bluetooth, and 5G. The appropriate initial communication mode is selected according to the environmental characteristics and task requirements;
[0096] Step 2: Environmental perception: Collect surrounding environment data through sensors such as cameras, microphones or lidar and identify factors in the environment that affect communication, such as signal interference, obstacles, and network congestion;
[0097] Step 3: Adaptive communication mode selection: Dynamically adjust the communication mode based on the information provided by environmental perception, use self-learning algorithms to optimize the communication mode selection strategy, collect and store communication history data, and analyze the best communication mode selection and adjustment strategy in different environments;
[0098] Step 4: Communication quality monitoring: Real-time monitoring of the quality parameters of each communication mode, such as signal strength, transmission speed, delay, and packet loss rate. Based on the communication quality monitoring data, the priority and frequency of use of the communication mode are adjusted;
[0099] Step 5: Multimodal communication fusion: During the communication process, multiple communication modes are allowed to work simultaneously to improve the stability and bandwidth of communication, integrate data from different communication modes, and remove redundant and conflicting information;
[0100] Step 6: Task-specific communication adjustment: Further optimize the communication according to the specific tasks performed by the robot. When performing video transmission tasks, give priority to communication modes with larger bandwidth; when performing low-latency control tasks, give priority to communication modes with smaller delays.
[0101] Step 7: Collaborative communication: When multiple robots work together, a shared communication strategy library is established, and the communication quality and optimization methods in steps 3 to 6 are shared among the robots to achieve collaborative communication optimization.
[0102] The self-learning algorithm in step 3 adopts a deep network algorithm, which specifically includes:
[0103] 1) Status indication:
[0104] The state s includes the following environmental factors:
[0105] s1: signal interference level;
[0106] s2: obstacle density;
[0107] s3: Network congestion level
[0108] 2) Action representation:
[0109] Action a indicates the selected communication mode:
[0110] a1: Wi-Fi;
[0111] a2: Bluetooth;
[0112] a3: 5G;
[0113] 3) Reward function:
[0114] The reward function r(s,a) is defined by the communication quality parameter:
[0115] r(s,a)=w1·Q signal +w2·Q speed -w3·Q delay -w4·Q loss
[0116] The weight parameters are:
[0117] w1=0.4, w2=0.3, w3=0.2, w4=0.1
[0118] 4) Q-value function:
[0119] The Q-value function Q(s,a) represents the expected cumulative reward after performing action a in state s. The Q-value function is approximated by a deep neural network Q(s,a;θ), where θ is the parameter of the neural network.
[0120] 5) Loss function:
[0121] The loss function is used to minimize the gap between the actual Q value and the predicted Q value. The actual Q value is calculated by the Bellman equation:
[0122]
[0123] Where γ is the discount factor, θ - is the parameter of the target network, which is used to stabilize the training. The loss function is defined as:
[0124] L(θ)=E[(yQ(s,a;θ)) 2 ].
[0125] Furthermore, the algorithm steps of the self-learning algorithm include:
[0126] A1. Initialization:
[0127] Initialize the Q network Q(s,a;θ) and the target network Q(s,a;θ - ), and set the target network parameters θ - =θ;
[0128] Initialize experience replay pool D;
[0129] A2. Collection experience:
[0130] Perform actions in the environment, observe the results and rewards, and store them in the experience replay pool D;
[0131] A3. Random sampling:
[0132] Randomly draw a mini-batch (s, a, r, s') of samples from the experience replay pool;
[0133] A4. Calculate the target Q value:
[0134] For each sample (s,a,r,s'), calculate the target Q value y:
[0135]
[0136] A5. Gradient descent:
[0137] Use stochastic gradient descent to minimize the loss function L(θ) and update the parameters θ of the Q network:
[0138]
[0139] Among them, α is the learning rate;
[0140] A6. Update the objective function:
[0141] At certain intervals, the parameters θ of the Q network are copied to the target network θ - ;
[0142] The reward function r(s,a) of the self-learning algorithm performs threshold judgment and strategy update:
[0143] Set the threshold to r threshold =50, if r(s,5G)≥r threshold , then the selected communication mode is considered valid;
[0144] If r(s,5G) <r threshold , then consider adjusting the communication mode selection strategy;
[0145] The specific examples are as follows:
[0146] Assume that when the intelligent robot performs a task, it selects the communication mode based on the current environment state s and Q value, and how to make threshold judgments:
[0147] Status indication and initial settings:
[0148] Assume that the current environment state s is:
[0149] Signal interference level s1 = 0.7;
[0150] Obstacle density s2 = 0.5;
[0151] Network congestion level s3 = 0.6;
[0152] Q value calculation and action selection, according to the current state s, calculate the Q value Q(s,a) of each communication mode
[0153] Assume the current Q value:
[0154] Q(s,Wi-Fi)=50
[0155] Q(s,Bluetooth)=45
[0156] Q(s,5G)=55
[0157] Select action a according to the Q value:
[0158] Select action a = 5G, because Q(s, 5G) is the highest;
[0159] Perform actions and reward calculations:
[0160] Execute the selected communication mode 5G and calculate the reward r(s,5G) based on the communication quality parameter
[0161] Assume that in the current environment, the communication quality parameters are:
[0162] Signal strength Qsignal =90
[0163] Transmission speed Q speed =80
[0164] Delay Q delay =10
[0165] Packet loss rate Q loss =5
[0166] Calculate the reward r(s,5G):
[0167] r(s,5G)=0.4×90+0.3×80-0.2×10-0.1×5
[0168] =36+34-2-0.5
[0169] =57.5
[0170] According to the actual reward r(s,5G)=57.5, threshold judgment and strategy update are performed:
[0171] r(s,5G)=57.5≥50, so the selected communication mode 5G is effective and no strategy adjustment is required;
[0172] The above interaction examples show how the intelligent robot can select the communication mode and make threshold judgments based on the current state and Q value. This reinforcement learning-based method enables the intelligent robot to achieve more effective communication mode selection in the process of continuous learning and optimization to cope with different environmental changes and task requirements.
[0173] The real-time communication adjustment in step 6 includes:
[0174] (1) Perceiving the current environment status: Using sensors to detect signal interference levels, obstacle density, and network congestion in real time;
[0175] (2) Select the best action a: Select the optimal communication mode based on the current state s and Q network;
[0176] (3) Execute the action and obtain the reward r: execute the selected communication mode, record the communication quality parameters, and calculate the reward;
[0177] (4) Update strategy: Continuously optimize the Q network through gradient descent to achieve adaptive communication mode selection.
[0178] Wherein, in step 7, when the robot performs a specific task, the communication method is further optimized according to the task characteristics and the current environment state, including:
[0179] Relationship between mission characteristics and communication optimization:
[0180] a. Data transmission requirements
[0181] Tasks with high real-time requirements: such as tasks that require immediate response or transmit large amounts of data; communication modes with faster transmission speeds, such as 5G, are preferred;
[0182] Low-latency tasks: For tasks that require low latency, such as remote control or real-time video transmission, communication modes with lower transmission latency should be given priority;
[0183] b. Data volume and stability requirements
[0184] Large data transmission: In tasks that require large amounts of data transmission, consider the balance between transmission speed and stability and choose a communication mode that provides high speed and low packet loss rate;
[0185] Tasks with high stability requirements: For example, long-running monitoring tasks or tasks that require long-term stable connections, communication modes with better transmission stability should be given priority.
[0186] The optimized communication method further comprises:
[0187] Dynamic environment perception and adaptive optimization:
[0188] c. Real-time environmental monitoring
[0189] Signal interference changes: Use sensors to monitor changes in surrounding signal interference in real time and adjust the communication frequency band or channel in a timely manner;
[0190] Obstacle movement: Detects the movement or change of obstacles and adjusts the communication mode to avoid signal blocking;
[0191] Network congestion: monitor network load and congestion, and dynamically select a communication mode suitable for the current network status;
[0192] d. Adaptive communication strategy update
[0193] Feedback-based optimization: Dynamically adjust communication strategies and selections based on feedback from actual communication results, such as communication quality parameters and reward values;
[0194] Continuous optimization of reinforcement learning: Use learning algorithms to continuously learn and update communication strategies to adapt to environmental changes and dynamic adjustments to task requirements.
[0195] Specific example scenario:
[0196] Real-time video surveillance tasks:
[0197] Suppose a robot needs to perform real-time video surveillance tasks, such as during construction site inspections or security operations:
[0198] Analysis of mission characteristics: The mission requires real-time transmission of high-definition video streams, with high requirements for transmission speed and stability, and moderate requirements for delay.
[0199] Environmental monitoring: The robot monitors the surrounding signal interference, obstacle density and network congestion in real time.
[0200] Communication optimization strategy:
[0201] When signal interference is low and obstacles are few, 5G is preferred for high-speed data transmission.
[0202] If network congestion or increased obstacles are detected, switch to a more stable communication mode such as Wi-Fi or Bluetooth in time.
[0203] The communication system applied to intelligent robots includes the following modules:
[0204] Multimodal communication module: supports multiple communication modes, such as WiFi, Bluetooth, and 5G, and can automatically switch according to the environment;
[0205] Environmental perception module: uses sensors to perceive the surrounding environment in real time, including signal strength, interference, and network load information;
[0206] Task management module: evaluates communication performance requirements, such as bandwidth, latency, and reliability, based on the robot's current task requirements;
[0207] Self-learning optimization module: Based on machine learning algorithms, it adaptively optimizes communication strategies and continuously learns and adjusts communication parameters;
[0208] Data processing module: responsible for data compression, encryption, decryption and transmission to ensure the efficiency and security of data transmission.
[0209] This embodiment also provides a computer device, which is suitable for a communication method applied to an intelligent robot, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement a communication method applied to an intelligent robot as proposed in the above embodiment.
[0210] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0211] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a communication method for an intelligent robot as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0212] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A communication method applied to an intelligent robot, characterized in that: The following steps are involved: Step 1: Multimodal communication initialization: When the robot is initialized, multiple communication modes are activated, including but not limited to Wi-Fi, Bluetooth, and 5G. The appropriate initial communication mode is selected according to the environmental characteristics and task requirements; Step 2: Environmental perception: Collect surrounding environment data through sensors such as cameras, microphones or lidar and identify factors in the environment that affect communication, such as signal interference, obstacles, and network congestion; Step 3: Adaptive communication mode selection: Dynamically adjust the communication mode based on the information provided by environmental perception, use self-learning algorithms to optimize the communication mode selection strategy, collect and store communication history data, and analyze the best communication mode selection and adjustment strategy in different environments; Step 4: Communication quality monitoring: Real-time monitoring of the quality parameters of each communication mode, such as signal strength, transmission speed, delay, and packet loss rate. Based on the communication quality monitoring data, the priority and frequency of use of the communication mode are adjusted; Step 5: Multimodal communication fusion: During the communication process, multiple communication modes are allowed to work simultaneously to improve the stability and bandwidth of communication, integrate data from different communication modes, and remove redundant and conflicting information; Step 6: Task-specific communication adjustment: Further optimize the communication according to the specific tasks performed by the robot. When performing video transmission tasks, give priority to communication modes with larger bandwidth; when performing low-latency control tasks, give priority to communication modes with smaller delays. Step 7: Collaborative communication: When multiple robots work together, a shared communication strategy library is established, and the communication quality and optimization methods in steps 3 to 6 are shared among the robots to achieve collaborative communication optimization.
2. The communication method applied to an intelligent robot according to claim 1, characterized in that: The self-learning algorithm in step 3 adopts a deep network algorithm, which specifically includes: 1) Status indication: Status s includes the following environmental factors: s1: signal interference level; s2: obstacle density; s3: Network congestion level 2) Action representation: Action a indicates the selected communication mode: a1: Wi-Fi; a2: Bluetooth; a3: 5G; 3) Reward function: The reward function r(s,a) is defined by the communication quality parameter: r(s,a)=w1·Q signal +w2·Q speed -w3·Q delay -w4·Q loss The weight parameters are: w1=0.4, w2=0.3, w3=0.2, w4=0.1 4) Q-value function: The Q-value function Q(s,a) represents the expected cumulative reward after performing action a in state s. The Q-value function is approximated by a deep neural network Q(s,a;θ), where θ is the parameter of the neural network. 5) Loss function: The loss function is used to minimize the gap between the actual Q value and the predicted Q value. The actual Q value is calculated by the Bellman equation: Where γ is the discount factor, θ - is the parameter of the target network, which is used to stabilize the training. The loss function is defined as: L(θ)=E[(yQ(s,a;θ)) 2 ]。 3. The communication method applied to an intelligent robot according to claim 2, characterized in that: The algorithm steps of the self-learning algorithm include: A1. Initialization: Initialize the Q network Q(s,a;θ) and the target network Q(s,a;θ - ), and set the target network parameters θ - =θ; Initialize experience replay pool D; A2. Collection experience: Perform actions in the environment, observe the results and rewards, and store them in the experience replay pool D; A3. Random sampling: Randomly draw a mini-batch (s, a, r, s') of samples from the experience replay pool; A4. Calculate the target Q value: For each sample (s,a,r,s'), calculate the target Q value y: A5. Gradient descent: Use stochastic gradient descent to minimize the loss function L(θ) and update the parameters θ of the Q network: Among them, α is the learning rate; A6. Update the objective function: At certain intervals, the parameters θ of the Q network are copied to the target network θ - .
4. The communication method applied to an intelligent robot according to claim 3, characterized in that: The reward function r(s,a) of the self-learning algorithm performs threshold judgment and strategy update: Set the threshold to r threshold =50, if r(s,5G)≥r threshold , then the selected communication mode is considered valid; If r(s,5G) <r threshold , then consider adjusting the communication mode selection strategy.
5. The communication method applied to an intelligent robot according to claim 4, characterized in that: The real-time communication adjustment in step 6 includes: (1) Perceiving the current environment status: Using sensors to detect signal interference levels, obstacle density, and network congestion in real time; (2) Select the best action a: Select the optimal communication mode based on the current state s and Q network; (3) Execute the action and obtain the reward r: execute the selected communication mode, record the communication quality parameters, and calculate the reward; (4) Update strategy: Continuously optimize the Q network through gradient descent to achieve adaptive communication mode selection.
6. The communication method applied to an intelligent robot according to claim 1, characterized in that: In step 7, when the robot performs a specific task, the communication method is further optimized according to the task characteristics and the current environment state, including: Relationship between mission characteristics and communication optimization: a. Data transmission requirements Tasks with high real-time requirements: such as tasks that require immediate response or transmit large amounts of data; communication modes with faster transmission speeds, such as 5G, are preferred; Low-latency tasks: For tasks that require low latency, such as remote control or real-time video transmission, communication modes with lower transmission latency should be given priority; b. Data volume and stability requirements Large data transmission: In tasks that require large amounts of data transmission, consider the balance between transmission speed and stability and choose a communication mode that provides high speed and low packet loss rate; Tasks with high stability requirements: For example, long-running monitoring tasks or tasks that require long-term stable connections, communication modes with better transmission stability should be given priority.
7. The communication method for an intelligent robot according to claim 6, characterized in that: The optimized communication method further comprises: Dynamic environment perception and adaptive optimization: c. Real-time environmental monitoring Signal interference changes: Use sensors to monitor changes in surrounding signal interference in real time and adjust the communication frequency band or channel in a timely manner; Obstacle movement: Detects the movement or change of obstacles and adjusts the communication mode to avoid signal blocking; Network congestion: monitor network load and congestion, and dynamically select a communication mode suitable for the current network status; d. Adaptive communication strategy update Feedback-based optimization: Dynamically adjust communication strategies and selections based on feedback from actual communication results, such as communication quality parameters and reward values; Continuous optimization of reinforcement learning: Use learning algorithms to continuously learn and update communication strategies to adapt to environmental changes and dynamic adjustments to task requirements.
8. The communication method applied to an intelligent robot according to claim 6, characterized in that: The communication system applied to intelligent robots includes the following modules: Multimodal communication module: supports multiple communication modes, such as WiFi, Bluetooth, and 5G, and can automatically switch according to the environment; Environmental perception module: uses sensors to perceive the surrounding environment in real time, including signal strength, interference, and network load information; Task management module: evaluates communication performance requirements, such as bandwidth, latency, and reliability, based on the robot's current task requirements; Self-learning optimization module: Based on machine learning algorithms, it adaptively optimizes communication strategies and continuously learns and adjusts communication parameters; Data processing module: responsible for data compression, encryption, decryption and transmission to ensure the efficiency and security of data transmission.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a communication method applied to an intelligent robot as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a communication method applied to an intelligent robot as described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Control method of intelligent medical robot based on WiFi and 5G converged communication
CN111510972A
Communication network switching method and device, intelligent robot and storage medium
CN112469098A
Multi-mobile robot autonomous obstacle avoidance method based on deep reinforcement learning
CN117873116A
Autonomous navigation robot
CN117991775A
Artificial intelligence system for learning robotic control policies
US10792810B1
Cited By
Motion mode control method and system for robot with water-air dual-purpose tail fin
CN119937606A
A robot motion mode control method and system with a dual-purpose tail fin for water and air
CN119937606B
High-speed wireless transmission system for real-time communication of six-axis spraying robot
CN120186772A
Anti-interference multi-band adaptive wireless communication control method and system
CN121397551A
Robot wireless communication module and data forwarding method
CN121568184A
