Robot intelligent signal collecting and processing system and method

Abstract

The invention relates to the field of intelligent signal processing, and provides a robot intelligent signal acquisition and processing system and method, which adopts a signal processing technology based on deep learning to process and analyze an infrared detection echo signal and an ultrasonic detection echo signal acquired by a hotel robot in a moving operation process so as to acquire an intelligent signal of the hotel robot. Therefore, the surrounding environment when the hotel robot moves and operates is known, and an obstacle avoidance path is intelligently generated based on the surrounding environment when the hotel robot moves. Thus, by comprehensively utilizing the two detection modes, the accuracy and reliability of environment perception of the hotel robot can be improved, and then optimization of the obstacle avoidance path and improvement of the obstacle avoidance precision are facilitated.

Description

Technical Field

[0001] The present application relates to the field of intelligent signal processing, and more specifically, to a robot intelligent signal acquisition and processing system and method. Background Art

[0002] Hotel robots are intelligent devices used in hotel scenarios with multiple functions, designed to facilitate hotel operations and guest services. Hotels are crowded places, and in order to ensure that hotel robots can move freely during operation without bumping into guests and employees, and at the same time avoid collisions with hotel walls, furniture, equipment and other facilities, hotel robots need to have good obstacle avoidance capabilities.

[0003] Due to the frequent movement of people and diverse placement of items in hotels, the environment is relatively complex. The traditional obstacle avoidance method that relies on a single sensor may result in misjudgment or omission due to various factors in the environment, and each sensor also has its weak detection areas.

[0004] Therefore, a robot intelligent signal acquisition and processing solution is needed. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present application provides a robot intelligent signal acquisition and processing system and method.

[0006] A robot intelligent signal acquisition and processing method, comprising:

[0007] Obtain infrared detection echo signals and ultrasonic detection echo signals collected by the hotel robot during its mobile operation;

[0008] Performing signal processing on the infrared detection echo signal and the ultrasonic detection echo signal respectively to obtain an infrared detection feature vector and an ultrasonic detection feature vector;

[0009] The infrared detection feature vector and the ultrasonic detection feature vector are fused by modulated view projection based on feature topological association expression to obtain a hotel robot mobile operation environment detection feature vector;

[0010] Based on the detection feature vector of the mobile operating environment of the hotel robot, an obstacle avoidance path of the hotel robot is obtained.

[0011] A robot intelligent signal acquisition and processing system, comprising:

[0012] The signal data acquisition module is used to obtain the infrared detection echo signal and the ultrasonic detection echo signal collected by the hotel robot during its mobile operation;

[0013] A signal data processing module, used for performing signal processing on the infrared detection echo signal and the ultrasonic detection echo signal respectively to obtain an infrared detection feature vector and an ultrasonic detection feature vector;

[0014] A signal feature fusion module, used for performing modulation view projection fusion on the infrared detection feature vector and the ultrasonic detection feature vector based on feature topological association expression to obtain a hotel robot mobile operation environment detection feature vector;

[0015] The robot obstacle avoidance path generation module is used to obtain the obstacle avoidance path of the hotel robot based on the feature vector detected in the mobile operating environment of the hotel robot.

[0016] This application has significant technical effects due to the adoption of the above technical solutions:

[0017] The robot intelligent signal acquisition and processing system and method provided by the present application adopts a signal processing technology based on deep learning, and processes and analyzes the infrared detection echo signal and ultrasonic detection echo signal collected by the hotel robot during the mobile operation, so as to understand the surrounding environment of the hotel robot during the mobile operation, and intelligently generate an obstacle avoidance path based on the surrounding environment during the movement. In this way, by comprehensively utilizing the two detection methods, the accuracy and reliability of the hotel robot's perception of the environment can be improved, which is conducive to optimizing the obstacle avoidance path and improving the obstacle avoidance accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0019] Figure 1 Flow chart of a robot intelligent signal acquisition and processing method according to an embodiment of the present application.

[0020] Figure 2 This is a flowchart of performing signal processing on the infrared detection echo signal and the ultrasonic detection echo signal to obtain an infrared detection feature vector and an ultrasonic detection feature vector, respectively, in the robot intelligent signal acquisition and processing method according to an embodiment of the present application.

[0021] Figure 3 The present invention is a flowchart of performing signal feature extraction on the infrared detection echo signal to obtain the infrared detection feature vector in the robot intelligent signal acquisition and processing method according to an embodiment of the present application.

[0022] Figure 4 The present invention is a flowchart of performing signal feature extraction on the ultrasonic detection echo signal to obtain the ultrasonic detection feature vector in the robot intelligent signal acquisition and processing method according to an embodiment of the present application.

[0023] Figure 5 4 is a system block diagram of a robot intelligent signal acquisition and processing system according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0025] As a place with a high density of people, a large number of guests and employees shuttle through it every day. In such an environment, the emergence of hotel robots has brought great convenience to the operation and guest service of the hotel. Hotel robots can perform a variety of tasks such as guiding guests to their rooms, delivering room supplies, and delivering items. However, to ensure that these robots can complete their work smoothly, good obstacle avoidance is essential. For guests and employees, their routes in the hotel are uncertain. They may suddenly change direction, stop, or stop in the corridor to talk. If the hotel robot does not have a reliable obstacle avoidance function, it is likely to collide with them, which will seriously affect the guests' stay experience and may even cause disputes and complaints. In terms of the physical environment of the hotel, there are various facilities inside the hotel. If the hotel robot cannot accurately avoid these facilities during operation, it may cause damage to itself, and it will also cause damage to the hotel's facilities, causing economic losses to the hotel.

[0026] Since the hotel environment has the characteristics of frequent movement of people and complex placement of items, the traditional obstacle avoidance method that relies on a single sensor has many problems. First, different types of sensors have their own weak detection areas, and using a single sensor may cause misjudgment. Secondly, interference factors in the environment will also affect the obstacle avoidance effect of a single sensor. Therefore, a robot intelligent signal acquisition and processing solution is expected.

[0027] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also demonstrated a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for robot intelligent signal acquisition and processing.

[0028] Figure 1Flowchart of the robot intelligent signal acquisition and processing method according to the embodiment of the present application. Figure 1 As shown, the robot intelligent signal acquisition and processing method according to the embodiment of the present application includes: S110, acquiring infrared detection echo signals and ultrasonic detection echo signals collected by the hotel robot during its mobile operation; S120, performing signal processing on the infrared detection echo signals and the ultrasonic detection echo signals respectively to obtain infrared detection feature vectors and ultrasonic detection feature vectors; S130, performing modulated perspective projection fusion based on feature topological association expression on the infrared detection feature vectors and the ultrasonic detection feature vectors to obtain the hotel robot mobile operation environment detection feature vector; S140, obtaining the obstacle avoidance path of the hotel robot based on the hotel robot mobile operation environment detection feature vector.

[0029] In step S110, the infrared detection echo signal and ultrasonic detection echo signal collected by the hotel robot during the mobile operation are obtained. It should be understood that the generation of infrared detection echo signals mainly depends on infrared sensors. The human body and other heat sources emit infrared rays of specific wavelengths, which can be captured by infrared sensors and converted into electrical signals. When the hotel robot is moving, the infrared sensor it carries will continuously scan the surrounding environment, capture the infrared rays emitted by the human body, heat sources, etc., and generate corresponding infrared detection echo signals. The infrared detection echo signal mainly contains information such as the position and intensity of the heat source in the environment. Since the infrared wavelengths and intensities emitted by the human body and other heat sources are different, the infrared sensor can identify the type and position of the heat source by analyzing these signals. By analyzing the infrared detection echo signal, the hotel robot can perceive the position and dynamic changes of the heat source (such as the human body) in the surrounding environment in real time, so as to adjust the walking path in time to avoid collision with the heat source. The generation of ultrasonic detection echo signals depends on ultrasonic sensors. Ultrasonic sensors emit high-frequency sound waves, which are reflected when encountering obstacles to form echo signals. After receiving these echo signals, the sensor converts them into electrical signals for processing. The ultrasonic detection echo signal mainly contains information such as the distance, shape and position of the obstacle. By analyzing the parameters such as the intensity, time and frequency of the echo signal, the specific position and shape of the obstacle can be inferred. By analyzing the ultrasonic detection echo signal, the position and shape of obstacles in the surrounding environment can be perceived in real time, so as to plan the optimal walking path. For example, when the robot detects an obstacle in front of it, it will adjust the walking direction or speed according to the position and shape of the obstacle to avoid collision with the obstacle. In general, infrared detection echo signals and ultrasonic detection echo signals together provide the hotel robot with rich environmental perception information, enabling the hotel robot to perceive the position and dynamic changes of heat sources and obstacles in the surrounding environment in real time, so as to plan the optimal obstacle avoidance path.

[0030] In step S120, the infrared detection echo signal and the ultrasonic detection echo signal are respectively processed to obtain an infrared detection feature vector and an ultrasonic detection feature vector. Specifically, Figure 2 The present invention is a flowchart of performing signal processing on the infrared detection echo signal and the ultrasonic detection echo signal to obtain the infrared detection feature vector and the ultrasonic detection feature vector in the robot intelligent signal acquisition and processing method according to the embodiment of the present application. Figure 2 As shown, the infrared detection echo signal and the ultrasonic detection echo signal are respectively processed to obtain an infrared detection feature vector and an ultrasonic detection feature vector, including: S121, performing signal feature extraction on the infrared detection echo signal to obtain the infrared detection feature vector; S122, performing signal feature extraction on the ultrasonic detection echo signal to obtain the ultrasonic detection feature vector.

[0031] More specifically, Figure 3 The flowchart of the method for collecting and processing intelligent signals of a robot according to an embodiment of the present application is to extract the signal features of the infrared detection echo signal to obtain the infrared detection feature vector. Figure 3 As shown, signal feature extraction is performed on the infrared detection echo signal to obtain the infrared detection feature vector, including: S1211, inputting the waveform diagram of the infrared detection echo signal into an infrared signal processor to obtain an infrared detection feature diagram; S1212, performing maximum value pooling processing on each feature matrix along the channel dimension on the infrared detection feature diagram to obtain the infrared detection feature vector.

[0032] In step S1211, the waveform of the infrared detection echo signal is input into the infrared signal processor to obtain the infrared detection feature map. Accordingly, considering that the original collected infrared detection echo signal often contains a large amount of noise and interference information, these noise and interference information will affect the hotel robot's accurate perception of the surrounding environment. In order to reduce these noise and interference information, and extract useful feature information from the infrared detection echo signal, and then provide more accurate data support for subsequent obstacle avoidance path planning, in the technical solution of the present application, it is necessary to input the waveform of the infrared detection echo signal into the infrared signal processor for processing. It should be noted that the infrared signal processor in the present application refers to a convolutional neural network model using a channel attention mechanism. This model can automatically extract useful feature information from the input infrared detection echo signal waveform and generate an infrared detection feature map. It should be understood that the channel attention mechanism can change the resource allocation method according to the importance of the feature, so that resources are more inclined to important features. For infrared detection, this means that the hotel robot can more accurately identify heat sources and potential obstacles in the environment without being disturbed by other irrelevant information.

[0033] In step S1212, the infrared detection feature map is subjected to maximum pooling processing of each feature matrix along the channel dimension to obtain the infrared detection feature vector. Accordingly, considering that the infrared detection feature map contains rich environmental information, it also contains some redundant and unnecessary detail information. These redundant information may increase the complexity and computational complexity of subsequent processing, and may also affect the robot's accurate perception of the surrounding environment. In order to reduce the data dimension, reduce the computational complexity, and extract more critical feature information, based on this, in the technical solution of the present application, the infrared detection feature map is subjected to maximum pooling processing of each feature matrix along the channel dimension to obtain the infrared detection feature vector.

[0034] More specifically, Figure 4 The present invention is a flowchart of extracting signal features from the ultrasonic detection echo signal to obtain the ultrasonic detection feature vector in the robot intelligent signal acquisition and processing method according to an embodiment of the present application. Figure 4 As shown, signal feature extraction is performed on the ultrasonic detection echo signal to obtain the ultrasonic detection feature vector, including: S1221, inputting the waveform diagram of the ultrasonic detection echo signal into an ultrasonic signal processor to obtain an ultrasonic detection feature diagram; S1222, performing maximum value pooling processing on each feature matrix along the channel dimension on the ultrasonic detection feature diagram to obtain the ultrasonic detection feature vector.

[0035] In step S1221, the waveform of the ultrasonic detection echo signal is input into the ultrasonic signal processor to obtain the ultrasonic detection feature map. It should be understood that the ultrasonic detection technology can obtain information such as the distance, shape, and structure of the surrounding environment by emitting ultrasonic waves to the surrounding environment and receiving the reflected signal. In order to extract useful feature information from the waveform of the ultrasonic detection echo signal, and then better characterize the environmental changes of the hotel robot during mobile operation, it is necessary to input the waveform of the ultrasonic detection echo signal into the ultrasonic signal processor for processing. It should be noted that the ultrasonic signal processor in this application is a deep separable convolutional neural network model. Those of ordinary skill in the art should know that the deep separable convolutional neural network model is a lightweight convolutional neural network structure, which decomposes the traditional convolution operation into two parts: deep convolution and point-by-point convolution. This structure can significantly reduce the amount of calculation and parameter of the model while maintaining good performance. When faced with input data such as the waveform of the ultrasonic detection echo signal, its feature information can be extracted more quickly, improving real-time performance. In addition, due to the low computational efficiency and model complexity of the deep separable convolutional neural network model, it is more suitable for running in embedded systems, which enables the hotel robot to maintain good environmental perception performance in a resource-constrained environment.

[0036] In step S1222, the ultrasonic detection feature map is subjected to maximum pooling processing of each feature matrix along the channel dimension to obtain the ultrasonic detection feature vector. It should be understood that the ultrasonic detection feature map usually contains a large number of data points, which represent different feature information. Pooling processing compresses the feature map in the channel dimension by selecting the maximum value in each feature matrix, thereby reducing the dimension of the data. As the data dimension decreases, the amount of calculation required for subsequent processing steps will also be reduced accordingly, which helps to improve the processing speed and efficiency of the entire system. And the maximum value pooling retains the maximum value in each feature matrix, which usually represents the most significant or important features. By extracting key features and removing redundant information, it can help the hotel robot more accurately identify obstacles and targets in the environment, thereby improving its obstacle avoidance and navigation accuracy.

[0037] In step S130, the infrared detection feature vector and the ultrasonic detection feature vector are fused by modulated perspective projection based on feature topological association expression to obtain the hotel robot mobile operation environment detection feature vector. It should be understood that infrared detection and ultrasonic detection have certain complementarity in principle and application. Infrared detection mainly depends on the infrared radiation emitted by the object, can sense the temperature and thermal radiation characteristics of the object, and is suitable for detecting heat sources and temperature differences. Ultrasonic detection senses the distance and shape of the object by emitting and receiving ultrasonic waves, and is insensitive to the material and surface characteristics of the object. In order to comprehensively utilize their respective advantages and provide more comprehensive and accurate environmental information, the infrared detection feature vector and the ultrasonic detection feature vector can be fused. By fusing these two feature vectors, the hotel robot can more accurately perceive obstacles and targets in the surrounding environment. This helps to improve the accuracy and reliability of obstacle avoidance and reduce the risk of collision with obstacles.

[0038] In particular, considering that infrared detection and ultrasonic detection are two different physical detection technologies, they have significant differences in detection principles, signal characteristics, and environmental adaptability. These differences lead to a more significant feature heterogeneity between the infrared detection feature vector and the ultrasonic detection feature vector generated by the signals collected by these two technologies after extraction. And because the infrared detection feature vector and the ultrasonic detection feature vector come from different feature spaces, their feature manifolds (geometric structures of feature spaces) may not match. This means that in the fusion process, the correlation and complementarity between different feature vectors may not be effectively utilized, resulting in the fused feature vector being unable to fully express the information of the original feature space. In addition, the ideal feature fusion should maintain the smoothness of the feature manifold, that is, the change of the fused feature vector in the feature space should be continuous and smooth. However, due to the feature heterogeneity between the two vectors, the fused feature vector may be discontinuous or mutated in some areas, which will affect the accuracy of feature expression. Based on this, in the technical solution of the present application, the infrared detection feature vector and the ultrasonic detection feature vector are fused by modulated perspective projection based on feature topological association expression to obtain the hotel robot mobile operation environment detection feature vector.

[0039] Specifically, in an embodiment of the present application, the infrared detection feature vector and the ultrasonic detection feature vector are subjected to a modulation perspective projection fusion based on a feature topological association expression to obtain a hotel robot mobile operating environment detection feature vector, including: constructing a hotel robot mobile operating environment detection distance topological matrix between the infrared detection feature vector and the ultrasonic detection feature vector; constructing a hotel robot mobile operating environment detection characteristic value granularity association matrix between the infrared detection feature vector and the ultrasonic detection feature vector; performing topological association modulation on the hotel robot mobile operating environment detection characteristic value granularity association matrix based on the hotel robot mobile operating environment detection distance topological matrix to obtain a hotel robot mobile operating environment detection topological modulation association matrix; using the hotel robot mobile operating environment detection topological modulation association matrix as a perspective co-projection space, projecting the infrared detection feature vector and the ultrasonic detection feature vector to the perspective co-projection space to obtain a perspective modulated infrared detection feature vector and a perspective modulated ultrasonic detection feature vector; fusing the perspective modulated infrared detection feature vector and the perspective modulated ultrasonic detection feature vector to obtain the hotel robot mobile operating environment detection feature vector.

[0040] In an embodiment of the present application, another expression method of performing modulated perspective projection fusion based on feature topological association expression on the infrared detection feature vector and the ultrasonic detection feature vector to obtain the mobile operation environment detection feature vector of the hotel robot can be: the infrared detection feature vector and the ultrasonic detection feature vector are processed by the following formula to obtain the mobile operation environment detection feature vector of the hotel robot; wherein the formula is:

[0041] M t =D(V1,V2)

[0042]

[0043] V c =α·V1′+β·V2′

[0044] Wherein, V1 represents the infrared detection feature vector, V2 represents the ultrasonic detection feature vector, and D(V1, V2) is the hotel robot mobile operating environment detection distance topology matrix between the infrared detection feature vector and the ultrasonic detection feature vector, that is, d i,j =d(v 1i ,v 2j ), d i,j is the eigenvalue of the position (i, j) in the detection distance topology matrix of the mobile operating environment of the hotel robot, d(v 1i ,v 2j ) represents the distance between the eigenvalue of the ith position of the infrared detection eigenvector and the eigenvalue of the jth position of the ultrasonic detection eigenvector, and V1 and V2 are both column vectors, M t represents the detection distance topology matrix of the mobile operating environment of the hotel robot, T represents the transpose of the vector, Represents matrix multiplication, M v represents the granularity correlation matrix of the characteristic value of the mobile operating environment detection of the hotel robot, exp represents the natural exponential function, M c represents the topological modulation correlation matrix of the hotel robot mobile operation environment detection, V1′ represents the view angle modulation infrared detection feature vector, V2′ represents the view angle modulation ultrasonic detection feature vector, α and β represent weighted hyperparameters, V c Represents the detection feature vector of the mobile operating environment of the hotel robot.

[0045] That is, in the technical solution of the present application, the infrared detection feature vector and the ultrasonic detection feature vector are subjected to a modulation perspective projection fusion based on the feature topological association expression, which first constructs a hotel robot mobile operating environment detection distance topological matrix between the infrared detection feature vector and the ultrasonic detection feature vector. This step utilizes the idea of ​​graph theory, takes the eigenvalues ​​of each position in the infrared detection feature vector and the ultrasonic detection feature vector as nodes, and uses the distance metric function to determine the low-dimensional embedding expression of the edges between nodes, so as to construct a feature expression that can quantify the topological association relationship between the infrared detection feature vector and the ultrasonic detection feature vector. This step is crucial to understanding the spatial distribution of data points and their mutual connections, and also provides basic structural information for subsequent steps.

[0046] Next, a hotel robot mobile operating environment detection feature value granularity association matrix is ​​constructed between the infrared detection feature vector and the ultrasonic detection feature vector. This step focuses on exploring the correlation between the internal attributes of the feature vector. In a specific example, the product between the transposed vectors of the infrared detection feature vector and the ultrasonic detection feature vector is calculated to obtain the hotel robot mobile operating environment detection feature value granularity association matrix. Furthermore, the hotel robot mobile operating environment detection feature value granularity association matrix is ​​topologically associated modulated based on the hotel robot mobile operating environment detection distance topological matrix to obtain the hotel robot mobile operating environment detection topological modulation association matrix. That is, the eigenvalue granularity association information of the infrared detection feature vector and the ultrasonic detection feature vector is driven to wander on the distance topological map to construct a low-dimensional modulation perspective co-projection space domain for mapping the infrared detection feature vector and the ultrasonic detection feature vector to a continuous high-dimensional regression space attribute.

[0047] Next, the hotel robot mobile operating environment detection topology modulation association matrix is ​​used as the perspective co-projection space, and the infrared detection feature vector and the ultrasonic detection feature vector are projected into the perspective co-projection space to obtain the perspective modulation infrared detection feature vector and the perspective modulation ultrasonic detection feature vector. That is, the key to this technical solution is to find an implicit third space with modulation capability, in which as much information of the original high-dimensional data as possible is retained, so that the converted new feature vector not only reduces the dimension, but also maintains the relative position relationship between the original features.

[0048] Finally, the view-modulated infrared detection feature vector and the view-modulated ultrasonic detection feature vector are fused to obtain the hotel robot mobile operating environment detection feature vector. Fusion can be achieved in a variety of forms, ranging from simple arithmetic average to complex ensemble learning algorithms, depending on the application scenario and the goals pursued. The final hotel robot mobile operating environment detection feature vector combines the main features of the two sets of input data and provides a more comprehensive data representation, which is not only conducive to improving the performance of machine learning models, but also promotes the ability of cross-modal or multi-source data analysis, thereby significantly enhancing the understanding and utilization efficiency of complex data structures.

[0049] In step S140, based on the hotel robot mobile operating environment detection feature vector, the obstacle avoidance path of the hotel robot is obtained. Specifically, in an embodiment of the present application, based on the hotel robot mobile operating environment detection feature vector, the obstacle avoidance path of the hotel robot is obtained, including: passing the hotel robot mobile operating environment detection feature vector through a robot obstacle avoidance path generator to obtain a generation result, and the generation result is the obstacle avoidance path of the hotel robot. It should be understood that the hotel robot mobile operating environment detection feature vector contains rich environmental information, such as the position, shape, size of the obstacle, and the relative distance between the robot and the obstacle. This information is the basis for the robot to plan the obstacle avoidance path. However, the original feature vector data is complex and cannot be directly used to guide the movement of the robot. Therefore, it is necessary to process and analyze these feature vectors through a robot obstacle avoidance path generator to generate an obstacle avoidance path suitable for the robot to move. The robot obstacle avoidance path generator is a deep neural network model that can interpret and convert the input hotel robot mobile operating environment detection feature vector through training, thereby generating a safe and efficient obstacle avoidance path. The obstacle avoidance path provides the hotel robot with a clear direction and path for movement, enabling the hotel robot to move autonomously and safely along the predetermined route.

[0050] In summary, the robot intelligent signal collection and processing method based on the embodiment of the present application is explained, which adopts the signal processing technology based on deep learning, and processes and analyzes the infrared detection echo signal and ultrasonic detection echo signal collected by the hotel robot during the mobile operation, so as to understand the surrounding environment of the hotel robot during the mobile operation, and intelligently generate an obstacle avoidance path based on the surrounding environment during the movement. In this way, by comprehensively utilizing the two detection methods, the accuracy and reliability of the hotel robot's perception of the environment can be improved, which is conducive to optimizing the obstacle avoidance path and improving the obstacle avoidance accuracy.

[0051] Figure 5 : is a system block diagram of a robot intelligent signal acquisition and processing system according to an embodiment of the present application. Figure 5As shown, according to the robot intelligent signal acquisition and processing system 100 of the embodiment of the present application, it includes: a signal data acquisition module 110, which is used to obtain infrared detection echo signals and ultrasonic detection echo signals collected by the hotel robot during the mobile operation; a signal data processing module 120, which is used to perform signal processing on the infrared detection echo signal and the ultrasonic detection echo signal respectively to obtain an infrared detection feature vector and an ultrasonic detection feature vector; a signal feature fusion module 130, which is used to perform modulated perspective projection fusion on the infrared detection feature vector and the ultrasonic detection feature vector based on feature topological association expression to obtain a hotel robot mobile operation environment detection feature vector; a robot obstacle avoidance path generation module 140, which is used to obtain the obstacle avoidance path of the hotel robot based on the hotel robot mobile operation environment detection feature vector.

[0052] Here, those skilled in the art can understand that the specific functions and operations of each unit and module in the above-mentioned robot intelligent signal acquisition and processing system 100 have been referred to above. Figures 1 to 4 The robot intelligent signal acquisition and processing method has been introduced in detail, and therefore, its repeated description will be omitted.

[0053] In summary, the robot intelligent signal acquisition and processing system 100 based on the embodiment of the present application is explained, which adopts the signal processing technology based on deep learning, and processes and analyzes the infrared detection echo signal and ultrasonic detection echo signal collected by the hotel robot during the mobile operation, so as to understand the surrounding environment of the hotel robot during the mobile operation, and intelligently generate an obstacle avoidance path based on the surrounding environment during the movement. In this way, by comprehensively utilizing the two detection methods, the accuracy and reliability of the hotel robot's perception of the environment can be improved, which is conducive to optimizing the obstacle avoidance path and improving the obstacle avoidance accuracy.

[0054] As described above, the robot intelligent signal acquisition and processing system 100 according to the embodiment of the present application can be implemented in various wireless terminals, such as a server for robot intelligent signal acquisition and processing. In one example, the robot intelligent signal acquisition and processing system 100 according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the robot intelligent signal acquisition and processing system 100 can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the robot intelligent signal acquisition and processing system 100 can also be one of the many hardware modules of the wireless terminal.

[0055] Alternatively, in another example, the robot intelligent signal acquisition and processing system 100 and the wireless terminal may also be separate devices, and the robot intelligent signal acquisition and processing system 100 may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0056] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details of the above application are only for the purpose of illustration and ease of understanding, rather than limitation, and the above details do not limit the present application to the use of the above specific details to be implemented.

[0057] In this application, words such as "including", "comprising", "having", etc. are open words, meaning "including but not limited to", and can be used interchangeably therewith. The words "or" and "and" used herein mean the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably therewith.

[0058] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0059] It should also be noted that in the system and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0060] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present application.

[0061] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A robot intelligent signal acquisition and processing method, characterized in that: include: Obtain infrared detection echo signals and ultrasonic detection echo signals collected by the hotel robot during its mobile operation; Performing signal processing on the infrared detection echo signal and the ultrasonic detection echo signal respectively to obtain an infrared detection feature vector and an ultrasonic detection feature vector; The infrared detection feature vector and the ultrasonic detection feature vector are fused by modulated view projection based on feature topological association expression to obtain a hotel robot mobile operation environment detection feature vector; Based on the detection feature vector of the mobile operating environment of the hotel robot, an obstacle avoidance path of the hotel robot is obtained.

2. The robot intelligent signal acquisition and processing method according to claim 1, characterized in that: The infrared detection echo signal and the ultrasonic detection echo signal are respectively processed to obtain an infrared detection feature vector and an ultrasonic detection feature vector, including: Extracting signal features of the infrared detection echo signal to obtain the infrared detection feature vector; Signal feature extraction is performed on the ultrasonic detection echo signal to obtain the ultrasonic detection feature vector.

3. The robot intelligent signal acquisition and processing method according to claim 2, characterized in that: Extracting signal features from the infrared detection echo signal to obtain the infrared detection feature vector includes: Inputting the waveform diagram of the infrared detection echo signal into an infrared signal processor to obtain an infrared detection characteristic diagram; The infrared detection feature map is subjected to maximum pooling processing of each feature matrix along the channel dimension to obtain the infrared detection feature vector.

4. The robot intelligent signal acquisition and processing method according to claim 3 is characterized in that: Extracting signal features from the ultrasonic detection echo signal to obtain the ultrasonic detection feature vector includes: Inputting the waveform diagram of the ultrasonic detection echo signal into an ultrasonic signal processor to obtain an ultrasonic detection characteristic diagram; The ultrasonic detection feature map is subjected to maximum value pooling processing of each feature matrix along the channel dimension to obtain the ultrasonic detection feature vector.

5. The robot intelligent signal acquisition and processing method according to claim 4, characterized in that: The infrared signal processor is a convolutional neural network model using a channel attention mechanism, and the ultrasonic signal processor is a deep separable convolutional neural network model.

6. The robot intelligent signal acquisition and processing method according to claim 5, characterized in that: The infrared detection feature vector and the ultrasonic detection feature vector are fused by modulated view projection based on feature topological association expression to obtain a hotel robot mobile operation environment detection feature vector, including: Constructing a hotel robot mobile operating environment detection distance topology matrix between the infrared detection feature vector and the ultrasonic detection feature vector; Constructing a granularity correlation matrix of hotel robot mobile operating environment detection eigenvalues ​​between the infrared detection eigenvector and the ultrasonic detection eigenvector; Based on the hotel robot mobile operating environment detection distance topology matrix, the hotel robot mobile operating environment detection characteristic value granularity association matrix is ​​topologically modulated to obtain a hotel robot mobile operating environment detection topology modulation association matrix; Taking the hotel robot mobile operation environment detection topology modulation correlation matrix as the perspective co-projection space, projecting the infrared detection feature vector and the ultrasonic detection feature vector into the perspective co-projection space to obtain the perspective modulation infrared detection feature vector and the perspective modulation ultrasonic detection feature vector; The visual angle modulated infrared detection feature vector and the visual angle modulated ultrasonic detection feature vector are fused to obtain the hotel robot mobile operation environment detection feature vector.

7. The robot intelligent signal acquisition and processing method according to claim 6, characterized in that: Based on the hotel robot mobile operating environment detection feature vector, an obstacle avoidance path of the hotel robot is obtained, including: passing the hotel robot mobile operating environment detection feature vector through a robot obstacle avoidance path generator to obtain a generation result, and the generation result is the obstacle avoidance path of the hotel robot.

8. A robot intelligent signal acquisition and processing system, characterized in that: include: The signal data acquisition module is used to obtain the infrared detection echo signal and the ultrasonic detection echo signal collected by the hotel robot during its mobile operation; A signal data processing module, used for performing signal processing on the infrared detection echo signal and the ultrasonic detection echo signal respectively to obtain an infrared detection feature vector and an ultrasonic detection feature vector; A signal feature fusion module, used for performing modulation view projection fusion on the infrared detection feature vector and the ultrasonic detection feature vector based on feature topological association expression to obtain a hotel robot mobile operation environment detection feature vector; The robot obstacle avoidance path generation module is used to obtain the obstacle avoidance path of the hotel robot based on the feature vector detected in the mobile operating environment of the hotel robot.

9. The robot intelligent signal acquisition and processing system according to claim 8, characterized in that: The signal data processing module comprises: An infrared detection echo signal processing unit, used for performing signal feature extraction on the infrared detection echo signal to obtain the infrared detection feature vector; The ultrasonic detection echo signal processing unit is used to extract signal features of the ultrasonic detection echo signal to obtain the ultrasonic detection feature vector.

10. The robot intelligent signal acquisition and processing system according to claim 9, characterized in that: The robot obstacle avoidance path generation module is used to obtain the obstacle avoidance path of the hotel robot based on the feature vector of the hotel robot's mobile operating environment detection, including: passing the feature vector of the hotel robot's mobile operating environment detection through a robot obstacle avoidance path generator to obtain a generation result, and the generation result is the obstacle avoidance path of the hotel robot.

Images