Application of Artificial Intelligence Detection System Based on Multi-sensor Data Fusion

The preliminary step in the navigation of Unmanned Vehicles is to detect and identify the horizon line. One method to locate the horizon and obstacles in an image is through a supervised learning, semantic segmentation algorithm using Neural Networks. Unmanned Aerial Vehicles (UAVs) are rapidly gaining prominence in military, commercial and civilian applications. For the safe navigation of UAVs, there poses a requirement for an accurate and efficient obstacle detection and avoidance. The position of the horizon and obstacles can also be used for adjusting flight parameters and estimating altitude. It can also be used for the navigation of Unmanned Ground Vehicles (UGV), by neglecting the part of the image above the horizon to reduce the processing time. Locating the horizon and identifying the various obstacles in an image can help in minimizing collisions and high costs due to failure of UAVs and UGVs. To achieve a robust and accurate system to aid navigation of autonomous vehicles, the efficiency and accuracy of Convolutional Neural Networks (CNN) and Recurrent-CNNs (RCNN) are analysed. It is observed via experimentation that the RCNN model classifies test images with higher accuracy.

A tethered flight vehicle such as Subzero III can be a reliable test-bed for AUV control techniques provided that the tether effects be removed by feed-forward control. To achieve the composite control idea, a numerical scheme for prediction of tether effects has been proposed and assessed. We argue that the composite control scheme can also be applied to the control of an ROV during the deployment of the umbilical. The H∞ approach has been applied to the design of the autopilots for autonomous underwater vehicles. The autopilots developed have the following features: (1) they have simpler structures than conventional H∞ design and the performance degrada tion caused by the controller order reduction is negligible; (2) rate feedback is applied for heading and depth control to improve tracking performance; (3) the overshoot specification is considered in the design by choosing suitable weighting functions. The results of both nonlinear simulations and water trials in two different tanks show that the autopilots are robust to model uncertainty, external disturbances and varying dynamics of the vehicle and exhibit good tracking performance. Thus the effectiveness of robust control for AUVs appears promising.

Due to the rapid development of precision manufacturing technology, much research has been conducted in the field of multisensor measurement and data fusion technology with a goal of enhancing monitoring capabilities in terms of measurement accuracy and information richness, thereby improving the efficiency and precision of manufacturing. In a multisensor system, each sensor independently measures certain parameters. Then, the system uses a relevant signal-processing algorithm to combine all of the independent measurements into a comprehensive set of measurement results. The purpose of this paper is to describe multisensor measurement and data fusion technology and its applications in precision monitoring systems. The architecture of multisensor measurement systems is reviewed, and some implementations in manufacturing systems are presented. In addition to the multisensor measurement system, related data fusion methods and algorithms are summarized. Further perspectives on multisensor monitoring and data fusion technology are included at the end of this paper.

This study constructs an integrated obstacle avoidance control strategy that can account for both lateral and longitudinal dynamic obstacles, enabling vehicles to quickly and stably evade obstacles in even emergency scenarios, thereby preventing accidents in complex road environments. Firstly, based on the safety distance model, a risk area dynamic partition method that considers both lateral and longitudinal directions is established. Subsequently, within the Frenet coordinate system, quintic polynomial candidate paths are generated based on the vehicle’s acceleration, speed, and position before and after lane-changing, and the optimal path is determined with consideration of driving safety and comfort, as well as the constraints associated with it. Finally, utilizing a two-degree-of-freedom vehicle dynamics model and a lateral tracking error model, a lateral tracking controller based on Linear Quadratic Regulator (LQR) and a longitudinal tracking controller based on double Proportional-Integral-Derivative (PID) approach are designed. The results of hardware-in-the-loop experiments demonstrate that, compared to the LQR algorithm, the proposed strategy more effectively ensures the stability and obstacle avoidance capability of the vehicle during operation. Furthermore, data collected under various scenarios indicate that the proposed strategy meets the requirements for tracking performance and driving comfort while successfully ensuring obstacle avoidance. Overall, the proposed method satisfies the criteria for safety, comfort, and stability in vehicle obstacle avoidance within complex environments.

Formation control and obstacle avoidance for multi-agent systems have attracted more and more attention. In this paper, the problems of formation control and obstacle avoidance are investigated by means of a consensus algorithm. A novel distributed control model is proposed for the multi-agent system to form the anticipated formation as well as achieve obstacle avoidance. Based on the consensus algorithm, a distributed control function consisting of three terms (formation control term, velocity matching term, and obstacle avoidance term) is presented. By establishing a novel formation control matrix, a formation control term is constructed such that the agents can converge to consensus and reach the anticipated formation. A new obstacle avoidance function is developed by using the modified potential field approach to make sure that obstacle avoidance can be achieved whether the obstacle is in a dynamic state or a stationary state. A velocity matching term is also put forward to guarantee that the velocities of all agents converge to the same value. Furthermore, stability of the control model is proven. Simulation results are provided to demonstrate the effectiveness of the proposed control.

The obstacle avoidance controller is a key autonomous component which involves the control of tractor system dynamics, such as the yaw lateral dynamics, the longitudinal dynamics, and nonlinear constraints including the speed and steering angles limits during the path-tracking process. To achieve the obstacle avoidance ability of control accuracy, an independent path re-planning controller is proposed based on ROS (Robot Operating System) nonlinear model prediction in this paper. In the design process, the obstacle avoidance function and an objective function are introduced. Based on these functions, the obstacle avoidance maneuvering performance is transformed into a nonlinear quadratic optimization problem with vehicle dynamic constraints. Moreover, the tractor dynamics maneuvering performance can be effectively adjusted through the proposed objective function. To validate the proposed algorithm, a ROS based tractor dynamics model and the SLAM (Simultaneous Localization and Mapping) are established for numerical simulations under different speed. The maximum obstacle avoidance deviation in the simulation is 0.242 m at 10 m/s, and 0.416 m at 30 m/s. The front-wheel rotation angle and lateral velocity are within the constraint range during the whole tracking process. The numerical results show that the designed controller can achieve the tractor obstacle avoidance ability with good accuracy under different conditions. Keywords: ROS, obstacle avoidance, nonlinear model prediction, agricultural tractor DOI: 10.25165/j.ijabe.20191206.4907 Citation: Liu Z D, Lv Z Q, Zheng W X, Zhang W Z, Cheng X X. Design of obstacle avoidance controller for agricultural tractor based on ROS. Int J Agric & Biol Eng, 2019; 12(6): 58–65.

In the paper, optimal trajectory generation method is proposed, which produces trajectories approaching the target location with smooth accelerations and continuous curvatures, fulfilling the vehicle kinematic restrictions. Firstly, a fixed number of alternative trajectories are generated in the Frenet-Serret Frame via initial and terminal states of motion based on a global path which is acquired by global path planning in a topological map. These meet the requirement of comfortability and feasibility for autonomous driving. And then the best trajectory is chosen from alternatives as optimal trajectory with a small cost in association with non-holonomic vehicle constraints and obstacle avoidance. The proposed method satisfies distance-keeping, velocity-keeping, collision-avoiding, etc. The performance of the approach is verified by practical experiments at last.

At first, according to the feature of ceramic kiln, this paper studies a fundamental data fusion method which is applied to ceramic kiln temperature control system. This method is used to solve the parameter estimation problem in measurement noise environment. Then, it proposes a kind of intelligent control structure of ceramic kiln temperature control system based on multi-sensor data fusion technology. At last, this data fusion method is applied to intelligent temperature control system of ceramic kiln. The result shows that the method proposed is effective and feasible.

Autonomous driving is the most important form of automotive intelligent development, and vehicle obstacle avoidance is an important function of the autonomous driving technology. This paper proposed an overtaking obstacle algorithm for autonomous driving based on dynamic trajectory planning, which is mainly composed of dynamic trajectory planning and trajectory tracking control. The Matlab /Simulink and CarSim joint simulation are used to evaluate the effect of autonomous control. The simulation results show that the overtaking obstacle avoidance algorithm can dynamically plan the overtaking trajectory and achieve accurate and stable tracking under different vehicle speed conditions. The whole system is real-time and robust.

With China's exploration of the sea, unmanned boats on the water are receiving more and more attention. Due to the complex situation on the water, unmanned boat obstacle avoidance still has defects. To address the above problems, this paper designs unmanned fish-finding and obstacle avoidance based on Pixhawk. The Kalman filter algorithm is used for sensor information fusion, which realizes the state estimation of the fish-finding unmanned ship. The BUG2 obstacle avoidance algorithm is used for obstacle avoidance, that optimizes the automatic obstacle avoidance function of the fish-finding unmanned ship. The fish finder is used to detect the position information of the fish, that realizes the function of the fish-finding unmanned ship tracking the fish. The PID control algorithm is used to control the driving of the ship, which makes the fish-finding unmanned ship converge to the desired course quickly and accurately. The lateral error of the vessel is within 1m. The simulation results verify the feasibility of the system, and the sea trial experiments of the unmanned fish-finding vessel prove the reliability and stability of the system.

At present, multi-sensor data fusion technology has been applied in many fields, and we have to understand the algorithm principle of multisensor data fusion technology, master the basic theory of multisensor data fusion technology, and analyze the application field of multisensor data fusion technology. The technical challenges of its application area should be understood. The discussion on its development direction has promoted the wide application of multisensor data fusion technology. By improving the query planning, query interpretation, and cache query optimization mechanism of different data organization models, a scalable and efficient distributed hybrid online analytical processing system is designed and implemented. With the opening of the medical system reform, the construction of the medical security system will be continuously improved. The in-depth reform of the medical security system will affect the medical treatment of more than one billion people, involving thousands of households, and it is a great cause for the welfare of the people. In this paper, exploration and research are carried out, combined with the basic algorithm and typical application of data fusion, and the construction of urban residents’ medical insurance is studied. The experimental results show that the Cavani index of medical expenses generally shows a downward trend in urban and rural areas, and the urban area has decreased from −0.1916 in 2012 to −0.2995 in 2020. This paper focuses on the in-depth study of the development process, actual situation, and existing problems of the social medical insurance system for urban residents, compares the development models of urban medical insurance in other places, and tries to put forward valuable and constructive countermeasures for the medical insurance system for urban residents.

The paper designed a WLAN system with RFID systems joint locating algorithm based on Federated Kalman Filtering. For the problem in indoor mobile node single positioning system, such as insufficient positioning accuracy, longer positioning time and not ideal algorithm complexity, it was proposed that the federated filtering techniques was applied in the location system, and was combined with data from WLAN and RFID to realize all accuracy improved. In the system, sub-filter use unscented Kalman filter algorithm independent measurement updates and time update, and the subsystem information is fused with the main filter based on no feedback mode. It was proved from the result that the calculation improved was of feasibility, which reduced unscented Kalman filter calculation, decreased maximum deviation and minimum deviation and improved the positioning accuracy. Introduction With the increase of the number of mobile devices and improvement of the degree of intelligence, location technology [1] is highly valued by the researcher as the core support functions of various kinds of mobile applications. At present, common indoor positioning technology includes ultrasonic positioning technology, WLAN positioning technology, Zigbee positioning technology, infrared positioning technology and RFID positioning technology. One single positioning technology is difficult to achieve a satisfactory result in practice, so multi-sensor data fusion technology has become an important issue in the field of indoor mobile node localization. WLAN positioning technology has developed rapidly in recent years,which mainly includes Nibble system[2] based on acquisition and analysis of noise ratio or signal quality, WHAM! Positioning system[3] based on receiving the signal strength of AP, Ekahau positioning system[4] , Horus positioning systems and Rice systems.The RFID system,whose positioning time is shorter, the precision is higher, received much concern for its advantages of non-line and non contract ,although the positioning range is limited to the distance between the transmitter and the receiver .This paper is to effectively improve the positioning accuracy of the mobile node and real-time through information fusion of WLAN positioning system and RFID positioning system based on Federated Kalman Filtering, which has certain practical value. Theoretical basis Federated Kalman Filtering Model Traditional Kalman filtering technology for multi-sensor data fusion methods generally includes centralized Kalman filtering and the decentralized Kalman filter. Federated filter proposed by Carlson[5] achieves good effect in practical application because of its small amount of calculation, good fault-tolerant performance and flexible design. Fusion algorithm based on Federated Kalman Filtering includes algorithm both whose estimate for each sub filter is correlated and uncorrelated. Due to the premise that the various sub filters is uncorrelated can not be guaranteed in the actual use,this paper mainly study the fusion algorithm for the estimate of each sub filter,using the variance upper bound technique to transform the filtering algorithm,thus each sub filter will be estimated from the correlated state.Federated filter is a kind of two-stage filtering structure. It is assumed that the state estimation of each sub filter can be 4th International Conference on Machinery, Materials and Computing Technology (ICMMCT 2016) © 2016. The authors Published by Atlantis Press 2001 expressed as: ˆ ˆ ˆ ci i bi X X X   =       . ˆ ci X is the estimate of the common state c X for each sub filter. ˆ bi X is the proprietary state estimate of filter i . Process design of Federated Kalman filter Under normal circumstances, federated filter process mainly includes four processes as follow : information distribution, information update, measurement update of information and information fusion. Step1 Distribution of information.Determine the proportionality coefficient of information distribution,between the main filters and sub filters as shown in formula (1). 1 k Q − and ( ) 1 | g k k P − refer to system process information.In formula (1), parameter i β is called an information distribution coefficient to meet the conditions of 0 i β > and distribution principle in formula (2).

For the purpose of energy saving and energy efficiency, the LED intelligent dimming system making use of solar power supply is designed in this paper. The system is based on STC12C5A60S2 microcontroller with multiple pyroelectric infrared detectors and light intensity sensors, in which LED dimming will be achieved according to the analysis and computation results through Multi-sensor data fusion technology. PWM dimming is adopted in the system depending on presetting programmable counter array (PCA) module of microcontroller in pulse width modulation (PWM) operation mode. Following the discussion about principle, composition and achievement, the Multi-sensor data fusion analysis is stated in accordance with different space distribution of light intensity sensors. Experiments show that the system is in simple structure and stable and reliable with the features of energy saving and intelligent.

Obstacle Avoidance for Unmanned Sea Surface Vehicles: A Hierarchical Approach

Visual obstacle avoidance is widely applied to unmanned aerial vehicles (UAVs) and mobile robot fields. A simple system architecture, low power consumption, optimized processing, and real‐time performance are extremely needed due to the limited payload of some mini UAVs. To address these issues, an obstacle avoidance system harnessing the rate encoding features of a photonic spiking neuron based on a Fabry–Pérot (FP) laser is proposed, which simulates the monocular vision. Here, time to collision is used to describe the distance of obstacles. The experimental results show that the FP laser excites ultra‐fast spike responses in real time for the following cases, facilitating the generation of control commands by motor neurons to realize accurate decision‐making. Four cases of mobile obstacle avoidance scenarios, including “Constant velocity approach”, “Approach and retreat”, “The motion state involving stays”, and “Approach with different velocities”, and obstacle avoidance problems with multiple stationary obstacles appearing simultaneously are experimentally analyzed. The system exhibits a spike response rate of up to 5 GHz. This work proves the feasibility of applying the ultra‐fast photonic obstacle avoidance system to UAVs and other fields in the future and highlights the potential of photonic neuromorphic processor platforms.