scholarly journals MUSSOL: A Micro-Uas to Survey Ship Cargo hOLds

2021 ◽  
Vol 13 (17) ◽  
pp. 3419
Author(s):  
Francisco Bonnin-Pascual ◽  
Emilio Garcia-Fidalgo ◽  
Joan P. Company-Corcoles ◽  
Alberto Ortiz
Keyword(s):  
Visual Inspection ◽  
Obstacle Detection ◽  
Level Control ◽  
Control Software ◽  
Full System ◽  
Aerial Robots ◽  
Collision Prevention ◽  
Cost Efficient ◽  
Inspection Tasks ◽  
High Level

Because of their high maneuverability and fast deployment times, aerial robots have recently gained popularity for automating inspection tasks. In this paper, we address the visual inspection of vessel cargo holds, aiming at safer, cost-efficient and more intensive visual inspections of ships by means of a multirotor-type platform. To this end, the vehicle is equipped with a sensor suite able to supply the surveyor with imagery from relevant areas, while the control software is supporting the operator during flight with enhanced functionalities and reliable autonomy. All this has been accomplished in the context of the supervised autonomy (SA) paradigm, by means of extensive use of behaviour-based high-level control (including obstacle detection and collision prevention), all specifically devised for visual inspection. The full system has been evaluated both in laboratory and in real environments, on-board two different vessels. Results show the vehicle effective for the referred application, in particular due to the inspection-oriented capabilities it has been fitted with.

scholarly journals Visual-Based SLAM Configurations for Cooperative Multi-UAV Systems with a Lead Agent: An Observability-Based Approach

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4243 ◽  
Author(s):  
Juan-Carlos Trujillo ◽  
Rodrigo Munguia ◽  
Edmundo Guerra ◽  
Antoni Grau
Keyword(s):  
Fundamental Problem ◽  
Position Estimation ◽  
Level Control ◽  
Aerial Robots ◽  
Control Scheme ◽  
High Level ◽  
System Configurations ◽  
Theoretical Results ◽  
Multi Uav ◽  
Nonlinear Observability

In this work, the problem of the cooperative visual-based SLAM for the class of multi-UA systems that integrates a lead agent has been addressed. In these kinds of systems, a team of aerial robots flying in formation must follow a dynamic lead agent, which can be another aerial robot, vehicle or even a human. A fundamental problem that must be addressed for these kinds of systems has to do with the estimation of the states of the aerial robots as well as the state of the lead agent. In this work, the use of a cooperative visual-based SLAM approach is studied in order to solve the above problem. In this case, three different system configurations are proposed and investigated by means of an intensive nonlinear observability analysis. In addition, a high-level control scheme is proposed that allows to control the formation of the UAVs with respect to the lead agent. In this work, several theoretical results are obtained, together with an extensive set of computer simulations which are presented in order to numerically validate the proposal and to show that it can perform well under different circumstances (e.g., GPS-challenging environments). That is, the proposed method is able to operate robustly under many conditions providing a good position estimation of the aerial vehicles and the lead agent as well.

scholarly journals Efficient Binarized Convolutional Layers for Visual Inspection Applications on Resource-Limited FPGAs and ASICs

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1511
Author(s):  
Taylor Simons ◽  
Dah-Jye Lee
Keyword(s):  
Neural Networks ◽  
Visual Inspection ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Quality Inspection ◽  
Agricultural Produce ◽  
Resource Limited ◽  
Inspection Tasks ◽  
Computational Resources ◽  
Small Models

There has been a recent surge in publications related to binarized neural networks (BNNs), which use binary values to represent both the weights and activations in deep neural networks (DNNs). Due to the bitwise nature of BNNs, there have been many efforts to implement BNNs on ASICs and FPGAs. While BNNs are excellent candidates for these kinds of resource-limited systems, most implementations still require very large FPGAs or CPU-FPGA co-processing systems. Our work focuses on reducing the computational cost of BNNs even further, making them more efficient to implement on FPGAs. We target embedded visual inspection tasks, like quality inspection sorting on manufactured parts and agricultural produce sorting. We propose a new binarized convolutional layer, called the neural jet features layer, that learns well-known classic computer vision kernels that are efficient to calculate as a group. We show that on visual inspection tasks, neural jet features perform comparably to standard BNN convolutional layers while using less computational resources. We also show that neural jet features tend to be more stable than BNN convolution layers when training small models.

scholarly journals Learning-Based Autonomous UAV System for Electrical and Mechanical (E&M) Device Inspection

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1385
Author(s):  
Yurong Feng ◽  
Kwaiwa Tse ◽  
Shengyang Chen ◽  
Chih-Yung Wen ◽  
Boyang Li
Keyword(s):  
System Design ◽  
State Estimation ◽  
Unmanned Aerial Vehicles ◽  
Visual Inspection ◽  
Spatial Information ◽  
Free Flight ◽  
Object State ◽  
Aerial Vehicles ◽  
Inspection Tasks ◽  
Autonomous Inspection

The inspection of electrical and mechanical (E&M) devices using unmanned aerial vehicles (UAVs) has become an increasingly popular choice in the last decade due to their flexibility and mobility. UAVs have the potential to reduce human involvement in visual inspection tasks, which could increase efficiency and reduce risks. This paper presents a UAV system for autonomously performing E&M device inspection. The proposed system relies on learning-based detection for perception, multi-sensor fusion for localization, and path planning for fully autonomous inspection. The perception method utilizes semantic and spatial information generated by a 2-D object detector. The information is then fused with depth measurements for object state estimation. No prior knowledge about the location and category of the target device is needed. The system design is validated by flight experiments using a quadrotor platform. The result shows that the proposed UAV system enables the inspection mission autonomously and ensures a stable and collision-free flight.

scholarly journals Multi-Sensor Fusion for Aerial Robots in Industrial GNSS-Denied Environments

2021 ◽  
Vol 11 (9) ◽  
pp. 3921
Author(s):  
Paloma Carrasco ◽  
Francisco Cuesta ◽  
Rafael Caballero ◽  
Francisco J. Perez-Grau ◽  
Antidio Viguria
Keyword(s):  
Sensor Fusion ◽  
Computational Efficiency ◽  
Probabilistic Approach ◽  
Laser Scanner ◽  
Industrial Applications ◽  
Experimental Results ◽  
Added Value ◽  
Aerial Robots ◽  
3D Localization ◽  
High Level

The use of unmanned aerial robots has increased exponentially in recent years, and the relevance of industrial applications in environments with degraded satellite signals is rising. This article presents a solution for the 3D localization of aerial robots in such environments. In order to truly use these versatile platforms for added-value cases in these scenarios, a high level of reliability is required. Hence, the proposed solution is based on a probabilistic approach that makes use of a 3D laser scanner, radio sensors, a previously built map of the environment and input odometry, to obtain pose estimations that are computed onboard the aerial platform. Experimental results show the feasibility of the approach in terms of accuracy, robustness and computational efficiency.

scholarly journals Deep Reinforcement Learning for End-to-End Local Motion Planning of Autonomous Aerial Robots in Unknown Outdoor Environments: Real-Time Flight Experiments

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2534
Author(s):  
Oualid Doukhi ◽  
Deok-Jin Lee
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Autonomous Navigation ◽  
Control Technique ◽  
Local Motion ◽  
Aerial Robots ◽  
Novel Approach ◽  
Outdoor Environments ◽  
Aerial Vehicle ◽  
High Level

Autonomous navigation and collision avoidance missions represent a significant challenge for robotics systems as they generally operate in dynamic environments that require a high level of autonomy and flexible decision-making capabilities. This challenge becomes more applicable in micro aerial vehicles (MAVs) due to their limited size and computational power. This paper presents a novel approach for enabling a micro aerial vehicle system equipped with a laser range finder to autonomously navigate among obstacles and achieve a user-specified goal location in a GPS-denied environment, without the need for mapping or path planning. The proposed system uses an actor–critic-based reinforcement learning technique to train the aerial robot in a Gazebo simulator to perform a point-goal navigation task by directly mapping the noisy MAV’s state and laser scan measurements to continuous motion control. The obtained policy can perform collision-free flight in the real world while being trained entirely on a 3D simulator. Intensive simulations and real-time experiments were conducted and compared with a nonlinear model predictive control technique to show the generalization capabilities to new unseen environments, and robustness against localization noise. The obtained results demonstrate our system’s effectiveness in flying safely and reaching the desired points by planning smooth forward linear velocity and heading rates.

Automatic Control of Molten Metal Flow for Improving Casting Performance

2011 ◽  
Vol 693 ◽  
pp. 179-184
Author(s):  
Thomas Jarlsmark ◽  
Jan Strömbeck ◽  
Mikael Terner ◽  
Jerry Wilkins
Keyword(s):  
Molten Metal ◽  
Metal Flow ◽  
Casting Process ◽  
Direct Chill ◽  
Level Control ◽  
Level Measurement ◽  
Cost Efficient ◽  
Molten Metal Flow ◽  
Automatic Level ◽  
Rolling Ingot

The ways to gain better quality and higher casting performance is an urgent topic among aluminium producers today. This issue is also often on the agenda at conferences like this and the subjects and technologies to achieve this varies. Controlling the molten metal flow by maintaining predefined levels or level patterns is one of many powerful tools to reach this goal. Precimeter Control specializes in applications for non-ferrous molten metal level measurement and molten metal flow control. By integration, or retrofitting, any new or existing casting line can easily be automatically controlled and gain improved casting performance in a cost efficient way. This paper will focus on the main benefits from automatic level control and how some plants have achieved improvements in their casting process of DC (Direct Chill) slab (or rolling ingot) casting after implementing such technology.

scholarly journals Robust Tracking Controller for a DC/DC Buck-Boost Converter–Inverter–DC Motor System

Energies ◽  
2018 ◽  
Vol 11 (10) ◽  
pp. 2500 ◽  
Author(s):  
Eduardo Hernández-Márquez ◽  
Carlos Avila-Rea ◽  
José García-Sánchez ◽  
Ramón Silva-Ortigoza ◽  
Gilberto Silva-Ortigoza ◽  
...  
Keyword(s):  
Motor System ◽  
Dc Motor ◽  
Boost Converter ◽  
Differential Flatness ◽  
Robust Tracking ◽  
Level Control ◽  
Tracking Controller ◽  
The One ◽  
High Level ◽  
Better Than

This paper has two aims. The first is to develop a robust hierarchical tracking controller for the DC/DC Buck-Boost–inverter–DC motor system. This controller considers a high level control for the inverter–DC motor subsystems and a low level control for the DC/DC Buck-Boost converter subsystem. Such controls solve the tracking task associated with the angular velocity of the motor shaft and the output voltage of the converter, respectively, via the differential flatness approach. The second aim is to present a comparison of the robust hierarchical controller to a passive controller. This, with the purpose of showing that performance achieved with the hierarchical controller proposed in this paper, is better than the one achieved with the passive controller. Both controllers are experimentally implemented on a prototype of the DC/DC Buck-Boost–inverter–DC motor system by using Matlab-Simulink along with the DS1104 board from dSPACE. According to experimental results, the proposal in the present paper achieves a better performance than the passive controller.

scholarly journals Brake systems: a mind of their own

2021 ◽  
pp. 27-34
Author(s):  
Michael Ellims
Keyword(s):  
Failure Modes ◽  
Electronic Control ◽  
Hydraulic Systems ◽  
Control Software ◽  
The Road ◽  
Current Production ◽  
On The Road ◽  
High Level ◽  
Electronic Sensors ◽  
Systems Failure

Brake systems fitted to current production vehicles are not the relativity straightforward hydraulic systems that many people expect. Rather they have evolved into complex systems which are on their own deliberately capable of affecting the behaviour of a vehicle. Crucially they depend on computers, software and electronic sensors to allow them to form a model of how the vehicle is expected to behave on the road and how it is actually behaving. Like any artefact they can, and do fail. This paper provides a high-level overview of the braking systems currently in place, how these systems act and present some examples of how they have failed in practice. Index words: vehicles; vehicle electronics; electronic control; software; brake systems; failure modes

scholarly journals A flexible user-interface for audiovisual presentation and interactive control in neurobehavioral experiments

F1000Research ◽  
2013 ◽  
Vol 2 ◽  
pp. 20
Author(s):  
Christopher T Noto ◽  
Suleman Mazhar ◽  
James Gnadt ◽  
Jagmeet S Kanwal
Keyword(s):  
User Interface ◽  
Data Acquisition ◽  
Digital Signal Processor ◽  
Digital Signal ◽  
Stimulus Presentation ◽  
Cost Effective ◽  
Level Control ◽  
Interactive Control ◽  
High Level ◽  
Behavioral Monitoring

A major problem facing behavioral neuroscientists is a lack of unified, vendor-distributed data acquisition systems that allow stimulus presentation and behavioral monitoring while recording neural activity. Numerous systems perform one of these tasks well independently, but to our knowledge, a useful package with a straightforward user interface does not exist. Here we describe the development of a flexible, script-based user interface that enables customization for real-time stimulus presentation, behavioral monitoring and data acquisition. The experimental design can also incorporate neural microstimulation paradigms. We used this interface to deliver multimodal, auditory and visual (images or video) stimuli to a nonhuman primate and acquire single-unit data. Our design is cost-effective and works well with commercially available hardware and software. Our design incorporates a script, providing high-level control of data acquisition via a sequencer running on a digital signal processor to enable behaviorally triggered control of the presentation of visual and auditory stimuli. Our experiments were conducted in combination with eye-tracking hardware. The script, however, is designed to be broadly useful to neuroscientists who may want to deliver stimuli of different modalities using any animal model.

Sign in / Sign up

Export Citation Format

Share Document