Search results for: autonomous learning

Authors: Jared Beard, Ali Baheri

Abstract:

As autonomous systems become more prominent in society, ensuring their safe application becomes increasingly important. This is clearly demonstrated with autonomous cars traveling through a crowded city or robots traversing a warehouse with heavy equipment. Human environments can be complex, having high dimensional state and action spaces. This gives rise to two problems. One being that analytic solutions may not be possible. The other is that in simulation based approaches, searching the entirety of the problem space could be computationally intractable, ruling out formal methods. To overcome this, approximate solutions may seek to find failures or estimate their likelihood of occurrence. One such approach is adaptive stress testing (AST) which uses reinforcement learning to induce failures in the system. The premise of which is that a learned model can be used to help find new failure scenarios, making better use of simulations. In spite of these failures AST fails to find particularly sparse failures and can be inclined to find similar solutions to those found previously. To help overcome this, multi-fidelity learning can be used to alleviate this overuse of information. That is, information in lower fidelity can simulations can be used to build up samples less expensively, and more effectively cover the solution space to find a broader set of failures. Recent work in multi-fidelity learning has passed information bidirectionally using “knows what it knows” (KWIK) reinforcement learners to minimize the number of samples in high fidelity simulators (thereby reducing computation time and load). The contribution of this work, then, is development of the bidirectional multi-fidelity AST framework. Such an algorithm, uses multi-fidelity KWIK learners in an adversarial context to find failure modes. Thus far, a KWIK learner has been used to train an adversary in a grid world to prevent an agent from reaching its goal; thus demonstrating the utility of KWIK learners in an AST framework. The next step is implementation of the bidirectional multi-fidelity AST framework described. Testing will be conducted in a grid world containing an agent attempting to reach a goal position and adversary tasked with intercepting the agent as demonstrated previously. Fidelities will be modified by adjusting the size of a time-step, with higher-fidelity effectively allowing for more responsive closed loop feedback. Results will compare the single KWIK AST learner with the multi-fidelity algorithm with respect to number of samples, distinct failure modes found, and relative effect of learning after a number of trials.

Keywords: multi-fidelity reinforcement learning, multi-fidelity simulation, safety validation, falsification

Procedia PDF Downloads 157

Authors: Ashish Kumar, Munesh Raghuraj Varma, Nisarg Joshi, Gujjula Vishwa Teja, Srikanth Sambi, Arpit Awasthi

Abstract:

Autonomous driving vehicles are revolutionizing the transportation system of the 21st century. This has been possible due to intensive research put into making a robust, reliable, and intelligent program that can perceive and understand its environment and make decisions based on the understanding. It is a very data-intensive task with data coming from multiple sensors and the amount of data directly reflects on the performance of the system. Researchers have to design the preprocessing pipeline for different datasets with different sensor orientations and alignments before the dataset can be fed to the model. This paper proposes a solution that provides a method to unify all the data from different sources into a uniform format using the intrinsic and extrinsic parameters of the sensor used to capture the data allowing the same pipeline to use data from multiple sources at a time. This also means easy adoption of new datasets or In-house generated datasets. The solution also automates the complete deep learning pipeline from preprocessing to post-processing for various tasks allowing researchers to design multiple custom end-to-end pipelines. Thus, the solution takes care of the input and output data handling, saving the time and effort spent on it and allowing more time for model improvement.

Keywords: augmentation, autonomous driving, camera, custom end-to-end pipeline, data unification, lidar, post-processing, preprocessing

Procedia PDF Downloads 123

Authors: Maximilian Richter

Abstract:

Implementing shared autonomous electric vehicles (SAEVs) has many advantages. The main advantages are achieved when SAEVs are offered as on-demand services by a fleet operator. However, autonomous mobility on demand (AMoD) will be distributed nationwide only if a fleet operation is economically profitable for the operator. This paper proposes a microscopic approach to modeling two implementation scenarios of an AMoD fleet. The city of Zurich is used as a case study, with the results and findings being generalizable to other similar European and North American cities. The data are based on the traffic model of the canton of Zurich (Gesamtverkehrsmodell des Kantons Zürich (GVM-ZH)). To determine financial profitability, demand is based on the simulation results and combined with analyzing the costs of a SAEV per kilometer. The results demonstrate that depending on the scenario; journeys can be offered profitably to customers for CHF 0.3 up to CHF 0.4 per kilometer. While larger fleets allowed for lower price levels and increased profits in the long term, smaller fleets exhibit elevated efficiency levels and profit opportunities per day. The paper concludes with recommendations for how fleet operators can prepare themselves to maximize profit in the autonomous future.

Keywords: autonomous vehicle, mobility on demand, traffic simulation, fleet provider

Procedia PDF Downloads 124

Authors: Nacer Eddine Chelbi, Ayet Bagane, Annie Saleh, Claude Sauvageau, Denis Gingras

Abstract:

As recently stated by National Highway Traffic Safety Administration (NHTSA), to demonstrate the expected performance of a highly automated vehicles system, test approaches should include a combination of simulation, test track, and on-road testing. In this paper, we propose a new validation method for autonomous vehicles involving on-road tests (Field Operational Tests), test track (Test Matrix) and simulation (Worst Case Scenarios). We concentrate our discussion on the simulation aspects, in particular, we extend recent work based on Importance Sampling by using a Metropolis-Hasting algorithm (MHS) to sample collected data from the Safety Pilot Model Deployment (SPMD) in lane-change scenarios. Our proposed MH sampling method will be compared to the Importance Sampling method, which does not perform well in high-dimensional problems. The importance of this study is to obtain a sampler that could be applied to high dimensional simulation problems in order to reduce and optimize the number of test scenarios that are necessary for validation and certification of autonomous vehicles.

Keywords: automated driving, autonomous emergency braking (AEB), autonomous vehicles, certification, evaluation, importance sampling, metropolis-hastings sampling, tests

Procedia PDF Downloads 288

Authors: Mbadiwe S. Benyeogor, Oladayo O. Olakanmi, Kosisochukwu P. Nnoli, Olusegun I. Lawal, Eric JJ. Gratton

Abstract:

For a robot or any vehicular system to navigate in off-road terrain, its driving mechanisms and the electro-software system must be capable of generating, controlling, and moderating sufficient mechanical power with precision. This paper proposes an autonomous robot with a gyro-stabilized active suspension system in form of a hybrid quadrupedal wheel drive mechanism. This system is to serve as a miniature model for demonstrating how off-road vehicles can be robotized into efficient terramechanical mobile platforms that are capable of self-balanced autonomous navigation and maneuvering on rough and uneven topographies. Results from tests and analysis show that the developed system performs as expected. Therefore, our model and control devices can be adapted to computerizing, automating, and upgrading the operation of unmanned ground vehicles for off-road navigation.

Keywords: active suspension, autonomous robots, edge computing, navigational sensors, terramechanics

Procedia PDF Downloads 154

Authors: Tugrul Oktay, Mehmet Konar, Mustafa Soylak, Firat Sal, Murat Onay, Orhan Kizilkaya

Abstract:

In this paper, autonomous performance of a small manufactured unmanned helicopter is tried to be increased. For this purpose, a small unmanned helicopter is manufactured in Erciyes University, Faculty of Aeronautics and Astronautics. It is called as ZANKA-Heli-I. For performance maximization, autopilot parameters are determined via minimizing a cost function consisting of flight performance parameters such as settling time, rise time, overshoot during trajectory tracking. For this purpose, a stochastic optimization method named as simultaneous perturbation stochastic approximation is benefited. Using this approach, considerable autonomous performance increase (around %23) is obtained.

Keywords: small helicopters, hierarchical control, stochastic optimization, autonomous performance maximization, autopilots

Procedia PDF Downloads 582

Authors: Bo Yang, Christopher Monterola

Abstract:

Urban intersection control without the use of the traffic light has the potential to vastly improve the efficiency of the urban traffic flow. For most proposals in the literature, such lightless intersection control depends on the mass market commercialization of highly intelligent autonomous vehicles (AV), which limits the prospects of near future implementation. We present an efficient lightless intersection traffic control scheme that only requires Level 1 AV as defined by NHTSA. The technological barriers of such lightless intersection control are thus very low. Our algorithm can also accommodate a mixture of AVs and conventional vehicles. We also carry out large scale numerical analysis to illustrate the feasibility, safety and robustness, comfort level, and control efficiency of our intersection control scheme.

Keywords: intersection control, autonomous vehicles, traffic modelling, intelligent transport system

Procedia PDF Downloads 455

Authors: Tugrul Oktay, Mehmet Konar, Mohamed Abdallah Mohamed, Murat Aydin, Firat Sal, Murat Onay, Mustafa Soylak

Abstract:

In this paper, it is aimed to improve autonomous flight performance of a load-carrying (payload: 3 kg and total: 6kg) unmanned aerial vehicle (UAV) through active wing and horizontal tail active morphing and also integrated autopilot system parameters (i.e. P, I, D gains) and UAV parameters (i.e. extension ratios of wing and horizontal tail during flight) design. For this purpose, a loadcarrying UAV (i.e. ZANKA-II) is manufactured in Erciyes University, College of Aviation, Model Aircraft Laboratory is benefited. Optimum values of UAV parameters and autopilot parameters are obtained using a stochastic optimization method. Using this approach autonomous flight performance of UAV is substantially improved and also in some adverse weather conditions an opportunity for safe flight is satisfied. Active morphing and integrated design approach gives confidence, high performance and easy-utility request of UAV users.

Keywords: unmanned aerial vehicles, morphing, autopilots, autonomous performance

Procedia PDF Downloads 673

Authors: M-M. Mohamed Ahmed, Nacer K. M’Sirdi, Aziz Naamane

Abstract:

In this paper, a longitudinal and lateral control approach based on a nonlinear observer is proposed for a convoy of autonomous vehicles to follow a desired trajectory. To authors best knowledge, this topic has not yet been sufficiently addressed in the literature for the control of multi vehicles. The modeling of the convoy of the vehicles is revisited using a robotic method for simulation purposes and control design. With these models, a sliding mode observer is proposed to estimate the states of each vehicle in the convoy from the available sensors, then a sliding mode control based on this observer is used to control the longitudinal and lateral movement. The validation and performance evaluation are done using the well-known driving simulator Scanner-Studio. The results are presented for different maneuvers of 5 vehicles.

Keywords: autonomous vehicles, convoy, non-linear control, non-linear observer, sliding mode

Procedia PDF Downloads 140

Authors: Haozhe Xiang

Abstract:

With the rise of the Internet of Things era, intelligent products are gradually integrating into people's lives. Pedestrian trajectory prediction has become a key issue, which is crucial for the motion path planning of intelligent agents such as autonomous vehicles, robots, and drones. In the current technological context, deep learning technology is becoming increasingly sophisticated and gradually replacing traditional models. The pedestrian trajectory prediction algorithm combining neural networks and attention mechanisms has significantly improved prediction accuracy. Based on in-depth research on deep learning and pedestrian trajectory prediction algorithms, this article focuses on physical environment modeling and learning of historical trajectory time dependence. At the same time, social interaction between pedestrians and scene interaction between pedestrians and the environment were handled. An improved pedestrian trajectory prediction algorithm is proposed by analyzing the existing model architecture. With the help of these improvements, acceptable predicted trajectories were successfully obtained. Experiments on public datasets have demonstrated the algorithm's effectiveness and achieved acceptable results.

Keywords: deep learning, graph convolutional network, attention mechanism, LSTM

Procedia PDF Downloads 70

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

The design of adaptive systems that take advantage of financial markets while reducing the risk can bring more stagnant wealth into the global market. However, most efforts made to generate successful deals in trading financial assets rely on Supervised Learning (SL), which suffered from various limitations. Deep Reinforcement Learning (DRL) offers to solve these drawbacks of SL approaches by combining the financial assets price "prediction" step and the "allocation" step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. In this paper, a continuous action space approach is adopted to give the trading agent the ability to gradually adjust the portfolio's positions with each time step (dynamically re-allocate investments), resulting in better agent-environment interaction and faster convergence of the learning process. In addition, the approach supports the managing of a portfolio with several assets instead of a single one. This work represents a novel DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem, or what is referred to as The Agent Environment as Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. More specifically, we design an environment that simulates the real-world trading process by augmenting the state representation with ten different technical indicators and sentiment analysis of news articles for each stock. We then solve the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, which can learn policies in high-dimensional and continuous action spaces like those typically found in the stock market environment. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of deep reinforcement learning in financial markets over other types of machine learning such as supervised learning and proves its credibility and advantages of strategic decision-making.

Keywords: the stock market, deep reinforcement learning, MDP, twin delayed deep deterministic policy gradient, sentiment analysis, technical indicators, autonomous agent

Procedia PDF Downloads 178

Authors: Mingming Jiang

Abstract:

This literature review aims to offer an overview of existing research on learning analytics and learning design, the alignment between the two, and how learning analytics has been leveraged to inform learning design in higher education. Current research suggests a need to create more alignment and integration between learning analytics and learning design in order to not only ground learning analytics on learning sciences but also enable data-driven decisions in learning design to improve learning outcomes. In addition, multiple conceptual frameworks have been proposed to enhance the synergy and alignment between learning analytics and learning design. Future research should explore this synergy further in the unique context of higher education, identifying learning analytics metrics in higher education that can offer insight into learning processes, evaluating the effect of learning analytics outcomes on learning design decision-making in higher education, and designing learning environments in higher education that make the capturing and deployment of learning analytics outcomes more efficient.

Keywords: learning analytics, learning design, big data in higher education, online learning environments

Procedia PDF Downloads 170

Authors: Tomasz Robert Kuczerski

Abstract:

The high complexity of the algorithm of the autonomous tandem detonator system creates an optimization problem due to the parallel operation of several machine states of the system. Many years of experience and classic analyses have led to a partially optimized model. Limitations on the energy resources of this class of autonomous systems make it necessary to search for more effective methods of optimisation. The use of the Quantum Approximate Optimization Algorithm (QAOA) in these studies shows the most promising results. With the help of multiple evaluations of several qubit quantum circuits, proper results of variable parameter optimization were obtained. In addition, it was observed that the increase in the number of assessments does not result in further efficient growth due to the increasing complexity of optimising variables. The tests confirmed the effectiveness of the QAOA optimization method.

Keywords: algorithm analysis, autonomous system, quantum optimization, tandem detonator

Procedia PDF Downloads 92

Authors: Amanuel Berhanu Kesamo

Abstract:

This paper presents both circuit simulation and hardware implementation of a robot vehicle that can be either controlled manually via Bluetooth with video streaming or navigate autonomously to a target point by avoiding obstacles. In manual mode, the user controls the mobile robot using C# windows form interfaced via Bluetooth. The camera mounted on the robot is used to capture and send the real time video to the user. In autonomous mode, the robot plans the shortest path to the target point while avoiding obstacles along the way. Ultrasonic sensor is used for sensing the obstacle in its environment. An efficient path planning algorithm is implemented to navigate the robot along optimal route.

Keywords: Arduino Uno, autonomous, Bluetooth module, path planning, remote controlled robot, ultra sonic sensor

Procedia PDF Downloads 142

Authors: Vivek Paul, Abel Nelly, Shoeb A Adeel, R. Tilak, S. Maheshwaran, S. Pulikeshi, Roshan Antony, C. S. Suraj

Abstract:

This paper presents the complete design and development cycle of a 20 cm span fixed wing micro air vehicle that was developed at CSIR-NAL, under the micro air vehicle development program. The design is a cropped delta flying wing MAV with a modified N22 airfoil of 12.3% thickness. The design was fabricated using the fused deposition method- RPT technique. COTS components were procured and integrated into this RPT prototype. A commercial autopilot that was proven in the earlier MAV designs was used for this MAV. The MAV was flown fully autonomous for 14mins at an open field. The flight data showed good performance as expected from the MAV design. The paper also describes about the process involved in the design of MAVs.

Keywords: autopilot, autonomous mode, flight testing, MAV, RPT

Procedia PDF Downloads 519

Authors: Napat Watjanatepin, Wikorn Wong-Satiean

Abstract:

The objective of this research is to design and construct the PV-Wind hybrid autonomous system for the greenhouse plantation, and analyze the technical performance of the PV-Wind energy system. This design depends on the water consumption in the greenhouse by using 24 of the fogging mist each with the capability of 24 liter/min. The operating time is 4 times per day, each round for 15 min. The fogging system is being driven by water pump with AC motor rating 0.5 hp. The load energy consumed is around 1.125 kWh/d. The designing results of the PV-Wind hybrid energy system is that sufficient energy could be generated by this system. The results of this study can be applied as a technical data reference for other areas in the central part of Thailand.

Keywords: PV-Wind hybrid autonomous system, greenhouse plantation, fogging system, central part of Thailand

Procedia PDF Downloads 313

Authors: Narjis Zehra

Abstract:

After automobile revolution 1.0, we have automobile revolution 2.0 standing at the horizon, Autonomous Vehicles (AVs). While the technology is developing into more adaptable form, the conversations around its impact on our cities have already started on multiple scales, from academic institutions and community town halls, to the offices of mayors. In order to explore more the AVs impact on Urban transformation, we first inquire if cities can be redesigned or rebuilt. Secondly, we discuss expectation management for the public and policy in terms of what people think/believe AV technology will deliver, and what the current technological evidence suggests the technology and its adoption will look like. Thirdly, based on these discussions, we take Pittsburgh, PA, as a case study to extrapolate what other cities might need to do in order to prepare themselves for the upcoming technological revolution, that may impact more than just the research institutes. Finally, we conclude by suggesting a political way forward to embed urban design with AV technology for equitable cities of tomorrow.

Keywords: urban design, autonomous vehicles, transformation, policy

Procedia PDF Downloads 106

Authors: Maximilian A. Richter

Abstract:

The public authority needs to understand the role and impacts of autonomous vehicle (AV) on the mobility system. At present, however, research shows that the impact of AV on cities varies. As a consequence, it is difficult to make recommendations to policymakers on how they should prepare for the future when so much remains unknown about this technology. The study aims to provide an overview of the literature on how autonomous vehicles will affect the cities and traffic of the future. To this purpose, the most important studies are first selected, and their results summarized. Further on, it will be clarified which advantages AV have for cities and how it can lead to an improvement in the current problems/challenges of cities. To achieve the research aim and objectives, this paper approaches a literature review. For this purpose, in a first step, the most important studies are extracted. This is limited to studies that are peer-reviewed and have been published in high-ranked journals such as the Journal of Transportation: Part A. In step 2, the most important key performance indicator (KPIs) (such as traffic volume or energy consumption) are selected from the literature research. Due to the fact that different terms are used in the literature for similar statements/KPIs, these must first be clustered. Furthermore, for each cluster, the changes from the respective studies are compiled, as well as their survey methodology. In step 3, a sensitivity analysis per cluster is made. Here, it will be analyzed how the different studies come to their findings and on which assumptions, scenarios, and methods these calculations are based. From the results of the sensitivity analysis, the success factors for the implementation of autonomous vehicles are drawn, and statements are made under which conditions AVs can be successful.

Keywords: autonomous vehicles, city of the future, literature review, traffic simulations

Procedia PDF Downloads 106

Authors: Julian Y. Raheema, Michael R. Hess, Raymond C. Provost, Mark Bilinski

Abstract:

The world is rapidly moving towards advancing and utilizing artificial intelligence and autonomous robotics. The ground-breaking Boston Dynamics quadruped robot, SPOT, was designed for industrial and commercial tasks requiring limited autonomous navigation. Out of the box, SPOT has route memorization and playback – it can repeat a path that it has been manually piloted through, but it cannot autonomously navigate an area that has not been previously explored. The presented SPOT payload package is built on ROS framework to support autonomous navigation and mapping of an unexplored environment. The package is fully integrated with SPOT to take advantage of motor controls and collision avoidance that comes natively with the robot. The payload runs all computations onboard, takes advantage of visual odometry SLAM and uses an Intel RealSense depth camera and Velodyne LiDAR sensor to generate 2D and 3D maps while in autonomous navigation mode. These maps are fused into the navigation stack to generate a costmap to enable the robot to safely navigate the environment without causing damage to the surroundings or the robot. The operator defines the operational zone and start location and then sends the explore command to have SPOT explore, generate 2D and 3D maps of the environment and return to the start location to await the operator's next command. The benefit of the presented package is that it is much lighter weight and less expensive than previous approaches and, importantly, operates in GPS-denied scenarios, which is ideal for indoor mapping. There are numerous applications that are hazardous to humans for SPOT enhanced with the autonomy payload, including disaster response, nuclear inspection, mine inspection, and so on. Other less extreme uses cases include autonomous 3D and 2D scanning of facilities for inspection, engineering and construction purposes.

Keywords: autonomous, SLAM, quadruped, mapping, exploring, ROS, robotics, navigation

Procedia PDF Downloads 90

Authors: Hanbhin Ryu, Ilkwon Yun

Abstract:

Automotive industry targets to provide an improvement in safety and convenience through realizing fully autonomous vehicle. For partially realizing fully automated driving, Current vehicles already feature varieties of advanced driver assistance system (ADAS) for safety and infotainment systems for the driver’s convenience. This paper presents Cloud Connected Vehicle (CCV) which connected vehicles with cloud data center via the access network to control the vehicle for achieving next autonomous driving form and describes its features. This paper also describes the shortcoming of the existing In-Vehicle Network (IVN) to be a next generation IVN of CCV and organize the 802.3 Ethernet, the next generation of IVN, related research issue to verify the feasibility of using Ethernet. At last, this paper refers to additional considerations to adopting Ethernet-based IVN for CCV.

Keywords: autonomous vehicle, cloud connected vehicle, ethernet, in-vehicle network

Procedia PDF Downloads 479

Authors: Ahmet Ozcan, Onder Alparslan, Anil Sezgin, Omer Cetin

Abstract:

The use of unmanned systems for different purposes has become very popular over the past decade. Expectations from these systems have also shown an incredible increase in this parallel. But meeting the demands of the tasks are often not possible with the usage of a single unmanned vehicle in a mission, so it is necessary to use multiple autonomous vehicles with different abilities together in coordination. Therefore the usage of the same type of vehicles together as a swarm is helped especially to satisfy the time constraints of the missions effectively. In other words, it allows sharing the workload by the various numbers of homogenous platforms together. Besides, it is possible to say there are many kinds of problems that require the usage of the different capabilities of the heterogeneous platforms together cooperatively to achieve successful results. In this case, cooperative working brings additional problems beyond the homogeneous clusters. In the scenario presented as an example problem, it is expected that an autonomous ground vehicle, which is lack of its position information, manage to perform point-to-point navigation without losing its way in a previously unknown labyrinth. Furthermore, the ground vehicle is equipped with very limited sensors such as ultrasonic sensors that can detect obstacles. It is very hard to plan or complete the mission for the ground vehicle by self without lost its way in the unknown labyrinth. Thus, in order to assist the ground vehicle, the autonomous air drone is also used to solve the problem cooperatively. The autonomous drone also has limited sensors like downward looking camera and IMU, and it also lacks computing its global position. In this context, it is aimed to solve the problem effectively without taking additional support or input from the outside, just benefiting capabilities of two autonomous vehicles. To manage the point-to-point navigation in a previously unknown labyrinth, the platforms have to work together coordinated. In this paper, cooperative work of heterogeneous unmanned systems is handled in an applied sample scenario, and it is mentioned that how to work together with an autonomous ground vehicle and the autonomous flying platform together in a harmony to take advantage of different platform-specific capabilities. The difficulties of using heterogeneous multiple autonomous platforms in a mission are put forward, and the successful solutions are defined and implemented against the problems like spatially distributed tasks planning, simultaneous coordinated motion, effective communication, and sensor fusion.

Keywords: unmanned systems, heterogeneous autonomous vehicles, coordination, task planning

Procedia PDF Downloads 128

Authors: Ahmad Forouzantabar, Mohammad Azadi, Alireza Alesaadi

Abstract:

This paper describes a sliding mode controller for autonomous underwater vehicles (AUVs). The dynamic of AUV model is highly nonlinear because of many factors, such as hydrodynamic drag, damping, and lift forces, Coriolis and centripetal forces, gravity and buoyancy forces, as well as forces from thruster. To address these difficulties, a nonlinear sliding mode controller is designed to approximate the nonlinear dynamics of AUV and improve trajectory tracking. Moreover, the proposed controller can profoundly attenuate the effects of uncertainties and external disturbances in the closed-loop system. Using the Lyapunov theory the boundedness of AUV tracking errors and the stability of the proposed control system are also guaranteed. Numerical simulation studies of an AUV are included to illustrate the effectiveness of the presented approach.

Keywords: lyapunov stability, autonomous underwater vehicle, sliding mode controller, electronics engineering

Procedia PDF Downloads 610

Authors: Angelos Kaminis, Dakotah Stirnweis

Abstract:

Advances in robotic technology have driven the development of improved robotic companions in the last couple decades. However, commercially available robotic companions lack the ability to create an emotional connection with their user. By developing a companion robot that has a symbiotic relationship with a plant, an element of co-dependency is introduced into the human companion robot dynamic. This companion robot, while theoretically capable of providing most of the plant’s needs, still requires human interaction for watering, moving obstacles, and solar panel cleaning. To facilitate the interaction between human and robot, the robot is capable of limited auditory and visual communication to help express its and the plant’s needs. This paper seeks to fully describe the Autonomous Plant Care Robot system and its symbiotic relationship with its botanical ward and the plant and robot’s dependent relationship with their owner.

Keywords: symbiotic, robotics, autonomous, plant-care, companion

Procedia PDF Downloads 144

Authors: Anita Khadka, Gregory Epiphaniou, Carsten Maple

Abstract:

There is a dramatic surge in the adoption of machine learning (ML) techniques in many areas, including the nuclear industry (such as fault diagnosis and fuel management in nuclear power plants), autonomous systems (including self-driving vehicles), space systems (space debris recovery, for example), medical surgery, network intrusion detection, malware detection, to name a few. With the application of learning methods in such diverse domains, artificial intelligence (AI) has become a part of everyday modern human life. To date, the predominant focus has been on developing underpinning ML algorithms that can improve accuracy, while factors such as resiliency and robustness of algorithms have been largely overlooked. If an adversarial attack is able to compromise the learning method or data, the consequences can be fatal, especially but not exclusively in safety-critical applications. In this paper, we present an in-depth analysis of five adversarial attacks and three defence methods on a crack detection ML model. Our analysis shows that it can be dangerous to adopt machine learning techniques in security-critical areas such as the nuclear industry without rigorous testing since they may be vulnerable to adversarial attacks. While common defence methods can effectively defend against different attacks, none of the three considered can provide protection against all five adversarial attacks analysed.

Keywords: adversarial machine learning, attacks, defences, nuclear industry, crack detection

Procedia PDF Downloads 158

Authors: Konstantinos Sofianos, Michael Stefanidakis

Abstract:

Nowadays, advances in information and communication technologies offer a range of opportunities for new approaches, methods, and tools in the field of education and training. Teacher-centered learning has changed to student-centered learning. E-learning has now matured and enables the design and construction of intelligent learning systems. A smart learning system fully adapts to a student's needs and provides them with an education based on their preferences, learning styles, and learning backgrounds. It is a wise friend and available at any time, in any place, and with any digital device. In this paper, we propose an intelligent learning system, which includes an ontology with all elements of the learning process (learning objects, learning activities) and a massive open online course (MOOC) system. This intelligent learning system can be used in music education.

Keywords: intelligent learning systems, e-learning, music education, ontology, semantic web

Procedia PDF Downloads 311

Authors: Raahil Sheikh, Abhishek Maurya, Priya Gujjar, Himanshu Dwivedi, Prathamesh Minde

Abstract:

UAVs have been an initial member of our environment since it's the first used by Austrian warfare in Venice. At that stage, they were just pilotless balloons equipped with bombs to be dropped on enemy territory. Over time, technological advancements allowed UAVs to be controlled remotely or autonomously. This study shall mainly focus on the intensification of pre-existing manual drones equipping them with a variety of sensors and making them autonomous, and capable, and purposing them for a variety of roles, including thermal sensing, data collection, tracking creatures, forest fires, volcano detection, hydrothermal studies, urban heat, Island measurement, and other environmental research. The system can also be used for reconnaissance, research, 3D mapping, and search and rescue missions. This study mainly focuses on automating tedious tasks and reducing human errors as much as possible, reducing deployment time, and increasing the overall efficiency, efficacy, and reliability of the UAVs. Creation of a comprehensive Ground Control System UI (GCS) enabling less trained professionals to be able to use the UAV with maximum potency. With the inclusion of such an autonomous system, artificially intelligent paths and environmental gusts and concerns can be avoided.

Keywords: UAV, drone, autonomous system, thermal imaging

Procedia PDF Downloads 75

Authors: Raahil Sheikh, Prathamesh Minde, Priya Gujjar, Himanshu Dwivedi, Abhishek Maurya

Abstract:

UAVs have been an initial member of our environment since it's the first used by Austrian warfare in Venice. At that stage, they were just pilotless balloons equipped with bombs to be dropped on enemy territory. Over time, technological advancements allowed UAVs to be controlled remotely or autonomously. This study shall mainly focus on the intensification of pre-existing manual drones equipping them with a variety of sensors and making them autonomous, and capable, and purposing them for a variety of roles, including thermal sensing, data collection, tracking creatures, forest fires, volcano detection, hydrothermal studies, urban heat, Island measurement, and other environmental research. The system can also be used for reconnaissance, research, 3D mapping, and search and rescue missions. This study mainly focuses on automating tedious tasks and reducing human errors as much as possible, reducing deployment time, and increasing the overall efficiency, efficacy, and reliability of the UAVs. Creation of a comprehensive Ground Control System UI (GCS) enabling less trained professionals to be able to use the UAV with maximum potency. With the inclusion of such an autonomous system, artificially intelligent paths and environmental gusts and concerns can be avoided

Keywords: UAV, autonomous systems, drones, geo thermal imaging

Procedia PDF Downloads 85

Authors: Mortez Alijani, Anas Osman

Abstract:

Recently, the popularity of Unmanned aerial vehicles (UAVs) has skyrocketed amidst the unprecedented events and the global pandemic, as they play a key role in both the security and health sectors, through surveillance, taking test samples, transportation of crucial goods and spreading awareness among civilians. However, the process of designing and producing such aerial robots is suppressed by the internal and external constraints that pose serious challenges. Landing is one of the key operations during flight, especially, the autonomous landing of UAVs on a moving platform is a scientifically complex engineering problem. Typically having a successful automatic landing of UAV on a moving platform requires accurate localization of landing, fast trajectory planning, and robust control planning. To achieve these goals, the information about the autonomous landing process such as the intersection point, the position of platform/UAV and inclination angle are more necessary. In this study, the mathematical approach to this problem in the X-Y axis based on the inclination angle and position of UAV in the landing process have been presented. The experimental results depict the accurate position of the UAV, intersection between UAV and moving platform and inclination angle in the landing process, allowing prediction of the intersection point.

Keywords: autonomous landing, inclination angle, unmanned aerial vehicles, moving platform, X-Y axis, intersection point

Procedia PDF Downloads 164

Authors: Arwa Khannoussi, Alexandru-Liviu Olteanu, Pritesh Narayan, Catherine Dezan, Jean-Philippe Diguet, Patrick Meyer, Jacques Petit-Frere

Abstract:

Due to the nature of autonomous Unmanned Aerial Vehicles (UAV) missions, it is important that the decisions of a UAV stay consistent with the priorities of an operator, while at the same time allowing them to be easily audited and explained. We propose a multi-layer decision engine that integrates the operator (human) preferences by using the Multi-Criteria Decision Aiding (MCDA) methods. A software implementation of a UAV simulator and of the decision engine is presented to highlight the advantage of using such techniques on high-level decisions. We demonstrate that, with such a preference-based decision engine, the decisions of the UAV are compatible with the priorities of the operator, which in turn increases her/his confidence in its autonomous behavior.

Keywords: autonomous UAV, multi-criteria decision aiding, multi-layers decision engine, operator's preferences, traceable decisions, UAV simulation

Procedia PDF Downloads 255

Authors: Lihong Wu, Raymond Young

Abstract:

The ability to learn is one of the most critical skills in the information age. However, many students do not have a clear understanding of what learning is, what they are learning, and why they are learning. Many students study simply to pass rather than to learn something useful for their career and their life. They have a misconception about learning and a wrong attitude towards learning. This research explores student attitudes to study in management education and explores how to intercede to lead students from shallow to deeper modes of learning.

Keywords: knowledge, surface learning, deep learning, education

Procedia PDF Downloads 501