Search results

The purpose of this paper is to present a novel position estimation method to accurately locate an object. An accelerometer-based error correction method is also developed to correct the positioning error caused by signal drift of a wireless network. Finally, the method is also utilized to locate cows in a farm for monitoring the action of standing heat.

The proposed method adopts the received signal strength indicator (RSSI) of a wireless sensor network (WSN) to compute the position of an object. The RSSI signal can be submitted from an endpoint device. A complex environment destabilizes the RSSI value, making the position estimation inaccurate. Therefore, a three-axial accelerometer is adopted to correct the position estimation accuracy. Timer and acceleration are two major factors in computing the error correction value to adjust the position estimate.

The proposed method is tested on a farm management system for positioning dairy cows accurately. Devices with WSN module and three-axial accelerometer are mounted on the cows to monitor their positions and actions.

If cows in a crowded farm are close to each other, then the position estimation method is unable to position each cow correctly because too many close objects cause interference in the wireless network.

Experimental results demonstrate that the proposed method improves the position accuracy, and monitor the heat action of the cows effectively.

No position estimation method has been utilized to locate cows in a farm, especially for monitoring their actions via WSN and accelerometer. The proposed method adopts an accelerometer to efficiently improve the position error caused from the signal drift of WSN.

Deployment of deep neural networks on embedded devices is becoming increasingly popular because it can reduce latency and energy consumption for data communication. This paper aims to give out a method for deployment the deep neural networks on a quad-rotor aircraft for further expanding its application scope.

In this paper, a design scheme is proposed to implement the flight mission of the quad-rotor aircraft based on multi-sensor fusion. It integrates attitude acquisition module, global positioning system position acquisition module, optical flow sensor, ultrasonic sensor and Bluetooth communication module, etc. A 32-bit microcontroller is adopted as the main controller for the quad-rotor aircraft. To make the quad-rotor aircraft be more intelligent, the study also proposes a method to deploy the pre-trained deep neural networks model on the microcontroller based on the software packages of the RT-Thread internet of things operating system.

This design provides a simple and efficient design scheme to further integrate artificial intelligence (AI) algorithm for the control system design of quad-rotor aircraft.

This method provides an application example and a design reference for the implementation of AI algorithms on unmanned aerial vehicle or terminal robots.

Unmanned vehicles flight is controlled by embedded circuits in the aircraft, under the remote control of a pilot on the ground. This circuit, called autopilot, represents one of the key elements inside the vehicles. The authors developed one of the smallest autopilot, specifically designed for low-weight low-power applications. The paper aims to discuss these issues.

The system is based on STM32 ARM Cortex M3 microcontroller. It includes an onboard 9 DOF IMU (MPU9150) and a 2.4 GHz wireless transceiver (nRF24L01+).

The embedded lightweight kinematic autopilot (ELKA) can pilot up to eight servomotors, and can be used to monitor more than 100 sensors. The final assembled board is 28×21 mm2 and weighs around 1.2 grams (battery excluded), and has successfully passed initial functionality tests.

The authors presented the design, fabrication and initial tests of a lightweight kinematic autopilot (ELKA board version 1.0). The system has been designed in order to upgrade the state-of-art capability in sensing and processing over a previous autopilot (GINA), which is of similar weight and size. The small size (28×21 mm2) and the lightweight (around 1.2 grams) make ELKA one of the smallest autopilot in the world.

This paper aims to reveal the authors’ conceptual and experimental work on an innovative avionics paradigm for small unmanned aerial vehicles (UAVs).

This novel approach stipulates that, rather than being centralized at the autopilot, control of avionics devices is instead distributed among controllers – spread over the airframe span, in response to avionics devices’ natural location requirements. The latter controllers are herein referred to as edge controllers by the first author.

The edge controller manifests increased efficiency in a number of functions, some of which are unburdened from the autopilot. The edge controller establishes a new paradigm of structure and design of small UAVs avionics such that any functionality related to the periphery of the airframe is implemented in the controller.

The research encompasses a workbench prototype testing on a breadboard, as the presented idea is a novel concept. Further, another test has been conducted with four controllers mounted on a quadcopter; results from the vertical attitude sustenance are disclosed herein.

The motivation behind developing this paradigm was the need to position certain avionics devices at different locations on the airframe. Due to their inherent functional requirements, most of these devices have hitherto been placed at the periphery of the aircraft construction.

The current paper describes the novel avionics paradigm, compares it to the standard approach and further reveals two experimental setups with testing results.

The purpose of this paper is to develop an information system which is based on the Internet of things (IoT) and used to support the communication and coordination in a cooperative robot team.

The architecture of the IoT applications for decision-making activities in a complex system is elaborated, the focus lies on the effective implementation of system interactions at the device-level. A case study is provided to verify system performances.

The IoT concept has been introduced in an information system of a football robot team to support the coordination among team players. Various sensors are used to collect data from IoT, and data are processed for the controls of robotic players to achieve the better performance at the system level. The field test has shown the feasibility and effectiveness.

To investigate how IoT can be utilized in an information system for making complex decisions effectively, the authors use the decision-support system for a football robot team to illustrate the approaches in developing data acquisition infrastructure, processing and utilizing real-time data for the communication and coordination of robot players in a dynamic competing environment. While the presented work has shown the feasibility of an IoT-based information system, more work are needed to integrate advanced sensors within the IoT and develop more intelligent algorithms to replace manually remote control for the operations of robot players.

The proposed system is specifically for a football robot team; however, the associated approaches are applicable to any decentralized system for developing an information system to support IoT-based communication and coordination within the system in the real-time mode.

The exploration of IoT applications is still at its early stage, existing relevant work is mostly limited to the development of system architecture, sensor networks, and communication protocols. In this paper, the methods on how to use massive real-time data for decision-making of a decentralized team have been investigated, and the proposed system has its theoretical significance to developing other decentralized wireless sensor networks and decision-making systems.

This paper aims to present a novel modular robot that provides a flexible framework for exploring adaptive locomotion.

A new modular robot is presented called YaMoR (for “Yet another Modular Robot”). Each YaMoR module contains an FPGA and a microcontroller supporting a wide range of control strategies and high computational power. The Bluetooth interface included in each YaMoR module allows wireless communication between the modules and controlling the robot from a PC. A control software called Bluemove was developed and implemented that allows easy testing of the capabilities for locomotion of a large variety of robot configurations.

With the help of the control software called Bluemove, different configurations of the YaMoR modules were tested like a wheel, caterpillar or configurations with limbs and their capabilities for locomotion.

This paper demonstrates that modular robots can act as a powerful framework for exploring locomotion of a large variety of different types of robots. Although present research is limited to exploring locomotion, YaMoR modules are designed to be general purpose and support a variety of applications.

The brushless direct current motor (BLDCM) is widely accepted and adopted by many industries instead of direct current motors due to high reliability during operation. Brushless direct current (BLDC) has outstanding efficiency as losses that arise out of voltage drops at brushes and friction losses are eliminated. The main factor that affects the performance is temperature introduced in the internal copper core windings. The control of motor speed generates high temperature in BLDC operation. The high temperature is due to presence of ripples in the operational current. The purpose is to present an effective controlling mechanism for speed management and to improve the performance of BLDCM to activate effective management of speed.

The purpose is to present an optimal algorithm based on modified moth-flame optimization algorithm over recurrent neural network (MMFO-RNN) for speed management to improve the performance. The core objective of the presented work is to achieve improvement in performance without affecting the design of the system with no additional circuitry. The management of speed in BLDCM has been achieved through reduction or minimization of ripples encircled with torque of the motor. The implementation ends in two stages, namely, controlling the loop of torque and controlling the loop of speed. The MMFO-RNN starts with error optimization, which arises from both the loops, and most effective values have been achieved through MMFO-RNN protocol.

The parameters are enriched with Multi Resolution Proportional Integral and Derivative (MRPID) controller operation to achieve minimal ripples for the torque of BLDC and manage the speed of the motor. The performance is increased by adopting this technique approximately 12% in comparison with the existing methodology, which is the main contributions of the presented work. The outcomes are analyzed with the existing methodologies through MATLAB Simulink tool, and the comparative analyses suggest that better performance of the proposed system produces over existing techniques, and proto type model is developed and cross verifies the proposed system.

The MMFO-RNN starts with error optimization, which arises from both the loops, and most effective values have been achieved through MMFO-RNN protocol. The parameters are enriched with MRPID controller operation to achieve nil or minimal ripples and to encircle the torque of Brushless Direct Current and manage the speed.

The purpose of this paper is to propose an indirect design for sliding surface as a function of position and velocity of each joint (for mounted manipulator on base) and center of mass of mobile base which includes rotation of wheels. The aim is to control the mobile base and its mounted arms using a unified sliding surface.

A new implementation of sliding mode control has been proposed for wheeled mobile manipulators, regulation and tracking cases. In the conventional sliding mode design, the position and velocity of each coordinate are often considered as the states in the sliding surface, and consequently, the input control is found based on them. A mobile robot consisted of non-holonomic constraints, makes the definition of the sliding surface more complex and it cannot simply include the coordinates of the system.

Formulism of both sliding mode control and non-singular terminal sliding mode control were presented and implemented on Scout robot. The simulations were validated with experimental studies, which led to satisfactory analysis. The non-singular terminal sliding mode control actually had a better performance, as it was illustrated that at time 10 s, the error for that was only 8.4 mm, where the error for conventional sliding mode control was 11.2 mm.

This work proposes sliding mode and non-singular terminal sliding mode control structure for wheeled mobile robot with a sliding surface including state variables: center of mass of base, wheels’ rotation and arm coordinates.

Deep learning techniques are unavoidable in a variety of domains such as health care, computer vision, cyber-security and so on. These algorithms demand high data transfers but require bottlenecks in achieving the high speed and low latency synchronization while being implemented in the real hardware architectures. Though direct memory access controller (DMAC) has gained a brighter light of research for achieving bulk data transfers, existing direct memory access (DMA) systems continue to face the challenges of achieving high-speed communication. The purpose of this study is to develop an adaptive-configured DMA architecture for bulk data transfer with high throughput and less time-delayed computation.

The proposed methodology consists of a heterogeneous computing system integrated with specialized hardware and software. For the hardware, the authors propose an field programmable gate array (FPGA)-based DMAC, which transfers the data to the graphics processing unit (GPU) using PCI-Express. The workload characterization technique is designed using Python software and is implementable for the advanced risk machine Cortex architecture with a suitable communication interface. This module offloads the input streams of data to the FPGA and initiates the FPGA for the control flow of data to the GPU that can achieve efficient processing.

This paper presents an evaluation of a configurable workload-based DMA controller for collecting the data from the input devices and concurrently applying it to the GPU architecture, bypassing the hardware and software extraneous copies and bottlenecks via PCI Express. It also investigates the usage of adaptive DMA memory buffer allocation and workload characterization techniques. The proposed DMA architecture is compared with the other existing DMA architectures in which the performance of the proposed DMAC outperforms traditional DMA by achieving 96% throughput and 50% less latency synchronization.

The proposed gated recurrent unit has produced 95.6% accuracy in characterization of the workloads into heavy, medium and normal. The proposed model has outperformed the other algorithms and proves its strength for workload characterization.