Search results for: autonomous weapon systems

Authors: Brwa Abdulrahman Abubaker

Abstract:

Recently, there has been a lot of interest in the difficult task of applying reinforcement learning to autonomous mobile robots. Conventional reinforcement learning (TRL) techniques have many drawbacks, such as lengthy computation times, intricate control frameworks, a great deal of trial and error searching, and sluggish convergence. In this paper, a modified Spiking Neural Network (SNN) is used to offer a distinct method for autonomous mobile robot learning and control in unexpected surroundings. As a learning algorithm, the suggested model combines dopamine modulation with spike-timing-dependent plasticity (STDP). In order to create more computationally efficient, biologically inspired control systems that are adaptable to changing settings, this work uses the effective and physiologically credible Izhikevich neuron model. This study is primarily focused on creating an algorithm for target tracking in the presence of obstacles. Results show that the SNN trained with three obstacles yielded an impressive 96% success rate for our proposal, with collisions happening in about 4% of the 214 simulated seconds.

Keywords: spiking neural network, spike-timing-dependent plasticity, dopamine modulation, reinforcement learning

Procedia PDF Downloads 21

Authors: Viridiana Edith Ardura Perea, José Luis Bermúdez Alcocer

Abstract:

The purpose of this paper is to establish the influence of shading on a Building Integrated Photovoltaic (BIPV) system´s performance in an urban context. The PV systems of the Science Center of Complexity (Centro de Ciencias de la Complejidad) Building based in the Main Campus of the National and Autonomous University of Mexico (UNAM) in Mexico City was taken as case study.  The PV systems are placed on the rooftop and on the south façade of the building.  The south-façade PV system, operating as sunshades, consists of two strings:  one at the ground floor and the other one at the first floor.  According to the building’s facility manager, the south-façade PV system generates 42% less electricity per kilowatt peak (kWp) installed than the one on the roof.  The methods applied in this study were Solar Radiation Analysis (SRA) simulations performed with the Insight 360 Plug-in from Revit 2018^® and an on-site measurement using specialized tools.  The results of the SRA simulations showed that the shading casted by the PV system placed on the first floor on top of the PV system of the ground floor decreases its solar incident radiation over 50%.  The simulation outcome was compared and validated to the measured data obtained from the on-site measurement.  In conclusion, the loss factor achieved from the shading of the PVs is due to the surroundings and the PV system´s own design.  The south-façade BIPV system’s deficient design generates critical losses on its performance and decreases its profitability.

Keywords: building integrated photovoltaics design, energy analysis software, shading losses, solar radiation analysis

Procedia PDF Downloads 179

Authors: Alicja Starczewska, Aleksander Nawrat, Krzysztof Daniec, Jarosław Homa, Kacper Hołda

Abstract:

Border Gateway Protocol is the main routing protocol that enables routing establishment between all autonomous systems, which are the basic administrative units of the internet. Due to the poor protection of BGP, it is important to use additional BGP security systems. Many solutions to this problem have been proposed over the years, but none of them have been implemented on a global scale. This article describes a system capable of building images of real-time BGP network topology in order to detect BGP anomalies. Our proposal performs a detailed analysis of BGP messages that come into local network cards supplemented by information collected by remote collectors in different localizations.

Keywords: BGP, BGP hijacking, cybersecurity, detection

Procedia PDF Downloads 78

Authors: Mattias Bergstrom

Abstract:

Significance of the Study: This research will provide new insights into the risks with digital embedded infrastructure. Through this research, we will analyze each risk and its potential negation strategies, especially for AI and autonomous automation. Moreover, the analysis that is presented in this paper will convey valuable information for future research that can create more stable, secure, and efficient autonomous systems. To learn and understand the risks, a large IoT system was envisioned, and risks with hardware, tampering, and cyberattacks were collected, researched, and evaluated to create a comprehensive understanding of the potential risks. Potential solutions have then been evaluated on an open source IoT hardware setup. This list shows the identified passive and active risks evaluated in the research. Passive Risks: (1) Hardware failures- Critical Systems relying on high rate data and data quality are growing; SCADA systems for infrastructure are good examples of such systems. (2) Hardware delivers erroneous data- Sensors break, and when they do so, they don’t always go silent; they can keep going, just that the data they deliver is garbage, and if that data is not filtered out, it becomes disruptive noise in the system. (3) Bad Hardware injection- Erroneous generated sensor data can be pumped into a system by malicious actors with the intent to create disruptive noise in critical systems. (4) Data gravity- The weight of the data collected will affect Data-Mobility. (5) Cost inhibitors- Running services that need huge centralized computing is cost inhibiting. Large complex AI can be extremely expensive to run. Active Risks: Denial of Service- It is one of the most simple attacks, where an attacker just overloads the system with bogus requests so that valid requests disappear in the noise. Malware- Malware can be anything from simple viruses to complex botnets created with specific goals, where the creator is stealing computer power and bandwidth from you to attack someone else. Ransomware- It is a kind of malware, but it is so different in its implementation that it is worth its own mention. The goal with these pieces of software is to encrypt your system so that it can only be unlocked with a key that is held for ransom. DNS spoofing- By spoofing DNS calls, valid requests and data dumps can be sent to bad destinations, where the data can be extracted for extortion or to corrupt and re-inject into a running system creating a data echo noise loop. After testing multiple potential solutions. We found that the most prominent solution to these risks was to use a Peer 2 Peer consensus algorithm over a blockchain to validate the data and behavior of the devices (sensors, storage, and computing) in the system. By the devices autonomously policing themselves for deviant behavior, all risks listed above can be negated. In conclusion, an Internet middleware that provides these features would be an easy and secure solution to any future autonomous IoT deployments. As it provides separation from the open Internet, at the same time, it is accessible over the blockchain keys.

Keywords: IoT, security, infrastructure, SCADA, blockchain, AI

Procedia PDF Downloads 107

Authors: Christian Rathgeber, Franz Winkler, Dirk Odenthal, Steffen Müller

Abstract:

In this contribution a structure for high level lateral vehicle tracking control based on the disturbance observer is presented. The structure is characterized by stationary compensating side forces disturbances and guaranteeing a cooperative behavior at the same time. Driver inputs are not compensated by the disturbance observer. Moreover the structure is especially useful as it robustly stabilizes the vehicle. Therefore the parameters are selected using the Parameter Space Approach. The implemented algorithms are tested in real world scenarios.

Keywords: disturbance observer, trajectory tracking, robust control, autonomous driving, cooperative driving

Procedia PDF Downloads 564

Authors: Ruvaitha Banu, Amaladhithyan Krishnamoorthy

Abstract:

IoT networks today solve various consumer problems, from home automation systems to aiding in driving autonomous vehicles with the exploration of multiple devices. For example, in an autonomous vehicle environment, multiple sensors are available on roads to monitor weather and road conditions and interact with each other to aid the vehicle in reaching its destination safely and timely. IoT systems are predominantly dependent on the cloud environment for data storage, and computing needs that result in latency problems. With the advent of Fog networks, some of this storage and computing is pushed to the edge/fog nodes, saving the network bandwidth and reducing the latency proportionally. Managing the data stored in these fog nodes becomes crucial as it might also store sensitive information required for a certain application. Data management in fog nodes is strenuous because Fog networks are dynamic in terms of their availability and hardware capability. It becomes more challenging when the nodes in the network also live a short span, detaching and joining frequently. When an end-user or Fog Node wants to access, read, or write data stored in another Fog Node, then a new protocol becomes necessary to access/manage the data stored in the fog devices as a conventional static way of managing the data doesn’t work in Fog Networks. The proposed solution discusses a protocol that acts by defining sensitivity levels for the data being written and read. Additionally, a distinct data distribution and replication model among the Fog nodes is established to decentralize the access mechanism. In this paper, the proposed model implements stewardship towards the data stored in the Fog node using the application of Reinforcement Learning so that access to the data is determined dynamically based on the requests.

Keywords: IoT, fog networks, data stewardship, dynamic access policy

Procedia PDF Downloads 59

Authors: Jamie Wong, Daisy Sang, Chang-Shyh Peng

Abstract:

Geofence is a virtual fence defined by a preset physical radius around a target location. Geofencing App provides location-based services which define the actionable operations upon the crossing of a geofence. Geofencing requires continual location tracking, which can consume noticeable amount of battery power. Additionally, location updates need to be frequent and accurate or order so that actions can be triggered within an expected time window after the mobile user navigate through the geofence. In this paper, we build an Android mobile geofencing Application to remotely and autonomously control a power switch.

Keywords: location based service, geofence, autonomous, remote switch

Procedia PDF Downloads 317

Authors: David L. Olson, Stephen B. H. Bruder, Adam S. Watkins, Cleon E. Davis

Abstract:

In global navigation satellite systems (GNSS), denied settings such as indoor environments, autonomous mobile robots are often limited to dead-reckoning navigation techniques to determine their position, velocity, and attitude (PVA). Localization is typically accomplished by employing an inertial measurement unit (IMU), which, while precise in nature, accumulates errors rapidly and severely degrades the localization solution. Standard sensor fusion methods, such as Kalman filtering, aim to fuse precise IMU measurements with accurate aiding sensors to establish a precise and accurate solution. In indoor environments, where GNSS and no other a priori information is known about the environment, effective sensor fusion is difficult to achieve, as accurate aiding sensor choices are sparse. However, an opportunity arises by employing a depth camera in the indoor environment. A depth camera can capture point clouds of the surrounding floors and walls. Extracting attitude from these surfaces can serve as an accurate aiding source, which directly combats errors that arise due to gyroscope imperfections. This configuration for sensor fusion leads to a dramatic reduction of PVA error compared to traditional aiding sensor configurations. This paper provides the theoretical basis for the depth camera aiding sensor method, initial expectations of performance benefit via simulation, and hardware implementation, thus verifying its veracity. Hardware implementation is performed on the Quanser Qbot 2™ mobile robot, with a Vector-Nav VN-200™ IMU and Kinect™ camera from Microsoft.

Keywords: autonomous mobile robotics, dead reckoning, depth camera, inertial navigation, Kalman filtering, localization, sensor fusion

Procedia PDF Downloads 207

Authors: Imam Taufiqurrahman, Anugrah Adiwilaga, Egi Hidayat, Bambang Riyanto Trilaksono

Abstract:

Autonomous Underwater Vehicle glider is one of the renewal of underwater vehicles. This vehicle is one of the autonomous underwater vehicles that are being developed in Indonesia. Glide ability is obtained by controlling the buoyancy and attitude of the vehicle using the movers within the vehicle. The glider motion mechanism is expected to provide energy resistance from autonomous underwater vehicles so as to increase the cruising range of rides while performing missions. The control system on the vehicle consists of three parts: controlling the attitude of the pitch, the buoyancy engine controller and the yaw controller. The buoyancy and pitch controls on the vehicle are sequentially referring to the finite state machine with pitch angle and depth of diving inputs to obtain a gliding cycle. While the yaw control is done through the rudder for the needs of the guide system. This research is focused on design and implementation of control system of Autonomous Underwater Vehicle glider based on PID anti-windup. The control system is implemented on an ARM TS-7250-V2 device along with a mathematical model of the vehicle in MATLAB using the hardware-in-the-loop simulation (HILS) method. The TS-7250-V2 is chosen because it complies industry standards, has high computing capability, minimal power consumption. The results show that the control system in HILS process can form glide cycle with depth and angle of operation as desired. In the implementation using half control and full control mode, from the experiment can be concluded in full control mode more precision when tracking the reference. While half control mode is considered more efficient in carrying out the mission.

Keywords: control system, PID, underwater glider, marine robotics

Procedia PDF Downloads 374

Authors: Rahul Paul, Kedar Nath Das

Abstract:

The paradigm of Reinforcement Learning (RL) has become prominent in training intelligent agents to make decisions in environments that are both dynamic and uncertain. The primary objective of RL is to optimize the policy of an agent in order to maximize the cumulative reward it receives throughout a given period. Nevertheless, the process of optimization presents notable difficulties as a result of the inherent trade-off between exploration and exploitation, the presence of extensive state-action spaces, and the intricate nature of the dynamics involved. Evolutionary Optimization Methods (EOMs) have garnered considerable attention as a supplementary approach to tackle these challenges, providing distinct capabilities for optimizing RL policies and value functions. The ongoing advancement of research in both RL and EOMs presents an opportunity for significant advancements in autonomous decision-making systems. The convergence of these two fields has the potential to have a transformative impact on various domains of artificial intelligence (AI) applications. This article highlights the considerable influence of EOMs in enhancing the capabilities of RL. Taking advantage of evolutionary principles enables RL algorithms to effectively traverse extensive action spaces and discover optimal solutions within intricate environments. Moreover, this paper emphasizes the practical implementations of EOMs in the field of RL, specifically in areas such as robotic control, autonomous systems, inventory problems, and multi-agent scenarios. The article highlights the utilization of EOMs in facilitating RL agents to effectively adapt, evolve, and uncover proficient strategies for complex tasks that may pose challenges for conventional RL approaches.

Keywords: machine learning, reinforcement learning, loss function, optimization techniques, evolutionary optimization methods

Procedia PDF Downloads 81

Authors: Ioana Pisica, Dimitrios Gkritzapis

Abstract:

The significance of UAS in scientific applications has been amply demonstrated in recent years. The combinations of portability and quasi-static positioning by means of flying in close loop path make them versatile and efficient in the inspection of power systems infrastructure. In this paper, we critically assess several platforms and sensor capabilities to identify their pros and cons in relation to the power systems assets to be monitored. In this respect, it is paramount the flights to be conducted by using UAS which bear certain suitable features, such as responsive and easy control, video capturing in real time, autonomous routing of pre-planned flight programming with differentiating payloads. The outcome of this research is a set of optimal requirements for power system assets monitoring with UAS.

Keywords: platforms, power system, sensors, UAVs

Procedia PDF Downloads 285

Authors: V. S. S. Kumar, V. Ramya

Abstract:

In the modern electronic warfare, the signal scenario is changing at a rapid pace with the introduction of Low Probability of Intercept (LPI) radars. In the modern battlefield, radar system faces serious threats from passive intercept receivers such as Electronic Attack (EA) and Anti-Radiation Missiles (ARMs). To perform necessary target detection and tracking and simultaneously hide themselves from enemy attack, radar systems should be LPI. These LPI radars use a variety of complex signal modulation schemes together with pulse compression with the aid of advancement in signal processing capabilities of the radar such that the radar performs target detection and tracking while simultaneously hiding enemy from attack such as EA etc., thus posing a major challenge to the ES/ELINT receivers. Today an increasing number of LPI radars are being introduced into the modern platforms and weapon systems so these LPI radars created a requirement for the armed forces to develop new techniques, strategies and equipment to counter them. This paper presents various modulation techniques used in generation of LPI signals and development of Time Frequency Algorithms to analyse those signals.

Keywords: anti-radiation missiles, cross terms, electronic attack, electronic intelligence, electronic warfare, intercept receiver, low probability of intercept

Procedia PDF Downloads 472

Authors: Simone Cinquemani, Lorenzo Mantovani, Aleksander Dabek

Abstract:

New technologies in agriculture are opening new challenges and new opportunities. Among these, certainly, robotics, vision, and artificial intelligence are the ones that will make a significant leap, compared to traditional agricultural techniques, possible. In particular, the indoor farming sector will be the one that will benefit the most from these solutions. Vertical farming is a new field of research where mechanical engineering can bring knowledge and know-how to transform a highly labor-based business into a fully autonomous system. The aim of the research is to develop a multi-purpose, modular, and perfectly integrated platform for crop production in indoor vertical farming. Activities will be based both on hardware development such as automatic tools to perform different activities on soil and plants, as well as research to introduce an extensive use of monitoring techniques based on machine learning algorithms. This paper presents the preliminary results of a research project of a vertical farm living lab designed to (i) develop and test vertical farming cultivation practices, (ii) introduce a very high degree of mechanization and automation that makes all processes replicable, fully measurable, standardized and automated, (iii) develop a coordinated control and management environment for autonomous multiplatform or tele-operated robots in environments with the aim of carrying out complex tasks in the presence of environmental and cultivation constraints, (iv) integrate AI-based algorithms as decision support system to improve quality production. The coordinated management of multiplatform systems still presents innumerable challenges that require a strongly multidisciplinary approach right from the design, development, and implementation phases. The methodology is based on (i) the development of models capable of describing the dynamics of the various platforms and their interactions, (ii) the integrated design of mechatronic systems able to respond to the needs of the context and to exploit the strength characteristics highlighted by the models, (iii) implementation and experimental tests performed to test the real effectiveness of the systems created, evaluate any weaknesses so as to proceed with a targeted development. To these aims, a fully automated laboratory for growing plants in vertical farming has been developed and tested. The living lab makes extensive use of sensors to determine the overall state of the structure, crops, and systems used. The possibility of having specific measurements for each element involved in the cultivation process makes it possible to evaluate the effects of each variable of interest and allows for the creation of a robust model of the system as a whole. The automation of the laboratory is completed with the use of robots to carry out all the necessary operations, from sowing to handling to harvesting. These systems work synergistically thanks to the knowledge of detailed models developed based on the information collected, which allows for deepening the knowledge of these types of crops and guarantees the possibility of tracing every action performed on each single plant. To this end, artificial intelligence algorithms have been developed to allow synergistic operation of all systems.

Keywords: automation, vertical farming, robot, artificial intelligence, vision, control

Procedia PDF Downloads 39

Authors: Robson C. Santos, Julio C. P. Ribeiro, Iorran M. de Castro, Luan C. F. Rodrigues, Sandro R. L. Silva, Diego M. Quesada

Abstract:

The work aims to develop a robot in the form of autonomous vehicle to detect, inspection and mapping of underground pipelines through the ATmega328 Arduino platform. Hardware prototyping very similar to C / C ++ language that facilitates its use in robotics open source, resembles PLC used in large industrial processes. The robot will traverse the surface independently of direct human action, in order to automate the process of detecting buried pipes, guided by electromagnetic induction. The induction comes from coils that sends the signal to the Arduino microcontroller contained in that will make the difference in intensity and the treatment of the information, then this determines actions to electrical components such as relays and motors, allowing the prototype to move on the surface and getting the necessary information. The robot was developed by electrical and electronic assemblies that allowed test your application. The assembly is made up of metal detector coils, circuit boards and microprocessor, which interconnected circuits previously developed can determine, process control and mechanical actions for a robot (autonomous car) that will make the detection and mapping of buried pipelines plates.

Keywords: robotic, metal detector, embedded system, pipeline inspection

Procedia PDF Downloads 614

Authors: Bhaargav Gupta P., Vignesh N., Nithish Kumar R., Rahul J., Nivetha Ruvah D.

Abstract:

Delivering essential medical supplies to rural and underserved areas is challenging due to infrastructure limitations and logistical barriers, often resulting in inefficiencies and delays. Traditional delivery methods are hindered by poor road networks, long distances, and difficult terrains, compromising timely access to vital resources, especially in emergencies. This paper introduces an autonomous drone system engineered to optimize last-mile delivery. By utilizing advanced navigation and object-detection algorithms, such as region-based convolutional neural networks (R-CNN), our drones efficiently avoid obstacles, identify safe landing zones, and adapt dynamically to varying environments. Equipped with high-precision GPS and autonomous capabilities, the drones effectively navigate complex, remote areas with minimal dependence on established infrastructure. The system includes a dedicated mobile application for secure order placement and real-time tracking, and a secure payload box with OTP verification ensures tamper-resistant delivery to authorized recipients. This project demonstrates the potential of automated drone technology in healthcare logistics, offering a scalable and eco-friendly approach to enhance accessibility and service delivery in underserved regions. By addressing logistical gaps through advanced automation, this system represents a significant advancement toward sustainable, accessible healthcare in remote areas.

Keywords: region-based convolutional neural network, one time password, global positioning system, autonomous drones, healthcare logistics

Procedia PDF Downloads 9

Authors: Isabella B. Davidman

Abstract:

Violence used against Jewish women in both the Eastern European pogroms and during the Nazi era was specifically gendered, targeting their female identity and dignity of womanhood. Not only did these acts of gendered violence dehumanize Jewish women, but they also hurt the Jewish community as a whole. The devastating sexual violence that women endured during the pogroms and the Nazi era caused profound trauma. Out of shame and fear, silence about women’s experiences of sexual abuse manifests in forms that words cannot translate. Women have turned to art and other means of storytelling to convey their female experiences in visual and non-verbal ways. Therefore, this paper aims to address the historical accounts of gendered violence against Jewish women during the pogroms and Nazi era, as well as art that reflects upon the female experience, in order to understand the emotional impact resulting from these events. To analyze the artwork, a feminist analysis was used to understand the intersection of gender with the other systems of inequality, such as systemic anti-semitism, in women’s lives; this ultimately explained the ways in which cultural productions undermine and reinforce the political and social oppression of women by exploring how art confronts the exploitation of women's bodies. By analyzing the art in the context of specific acts of violence, such as public rape, as a strategic weapon, we are able to understand women’s experiences and how these experiences, in turn, challenged their womanhood. Additionally, these atrocities, which often occurred in the public space, were dismissed and forgotten due to the social stigma of rape. In this sense, the experiences of women in pogroms and the Nazi era were both highly unacknowledged and forgotten. Therefore, the art that was produced during those time periods, as well as those after those events, gives voice to the profound silence on the narratives of Jewish women. Sexual violence is a weapon of war used to cause physical and psychological destruction, not only as a product of war. In both the early twentieth-century pogroms and the Holocaust, the sexual violence that Jewish women endured was fundamentally the same: the rape of Jewish women became a focal target in the theater of violence– women were not raped because they were women, but specifically, because they were Jewish women. Although the events of the pogroms and the Holocaust are in the past, the art that serves as testimony to the experience of Jewish women remains an everlasting reminder of the gendered violence that occurred. Even though covert expressions, such as an embroidered image of a bird eating an apple, the artwork gives voice to the many silenced victims of sexualized and gendered violence.

Keywords: gendered violence, holocaust, Nazi era, pogroms

Procedia PDF Downloads 104

Authors: Eric Neidhardt

Abstract:

A well-functioning public transport system that is accepted and used by the general population contributes a lot to a sustainable city. Especially young and elderly people rely on public transport to get to work, go shopping, visit a doctor, and take advantage of entertainment options. The sustainability of a public transport system can be considered from different points of view. In urban areas, acceptance is particularly important. As many people as possible should use public transport and not their private vehicle. This reduces traffic jams and increases air quality. In rural areas, the cost efficiency of public transport is especially important. Longer distances and a low population density mean that these modes of transportation can rarely be used cost-effectively. It is crucial to avoid a low utilization, because empty rides are neither sustainable nor cost-effective. With a demand-oriented approach, we try to both improve flexibility and therefore attractiveness for the user and improve cost- efficiency. The vehicles only operate when they are needed and only where they are needed. Empty rides are avoided to improve sustainability. In the subproject "Autonomous public driving" of the project RealLabHH, such a system was implemented and tested in Hamburg-Bergedorf, a suburb of Hamburg. In this paper, some of the steps necessary for this are considered from a technical point of view, and problems that arose in real-life use are addressed.

Keywords: public transport, demand-oriented, autonomous driving, RealLabHH

Procedia PDF Downloads 193

Authors: Bruno Nascimento, Cristina Wanzeller, Jorge Silva, João A. Dias, André Barbosa, José Ribeiro

Abstract:

The increasing complexity of logistics operations stems from evolving business needs, such as the shift from mass production to mass customization, which demands greater efficiency and flexibility. In response, Industry 4.0 and 5.0 technologies provide improved solutions to enhance operational agility and better meet market demands. The management of kitting zones, combined with the use of Autonomous Mobile Robots, faces challenges related to coordination, resource optimization, and rapid response to customer demand fluctuations. Additionally, implementing lean manufacturing practices in this context must be carefully orchestrated by intelligent systems and human operators to maximize efficiency without sacrificing the agility required in an advanced production environment. This paper proposes and implements a microservices-based architecture integrating principles from Industry 4.0 and 5.0 with lean manufacturing practices. The architecture enhances communication and coordination between autonomous vehicles and kitting management systems, allowing more efficient resource utilization and increased scalability. The proposed architecture focuses on the modularity and flexibility of operations, enabling seamless flexibility to change demands and the efficient allocation of resources in realtime. Conducting this approach is expected to significantly improve logistics operations’ efficiency and scalability by reducing waste and optimizing resource use while improving responsiveness to demand changes. The implementation of this architecture provides a robust foundation for the continuous evolution of kitting management and process optimization. It is designed to adapt to dynamic environments marked by rapid shifts in production demands and real-time decision-making. It also ensures seamless integration with automated systems, aligning with Industry 4.0 and 5.0 needs while reinforcing Lean Manufacturing principles.

Keywords: microservices, event-driven, kitting, AMR, lean manufacturing, industry 4.0, industry 5.0

Procedia PDF Downloads 24

Authors: Migena Mana, Ahmed Khalid Syed, Abdul Malik, Nikhil Cherian

Abstract:

In recent years, advancements in deep learning enabled researchers to tackle the problem of self-driving cars. Car companies use huge datasets to train their deep learning models to make autonomous cars a reality. However, this approach has certain drawbacks in that the state space of possible actions for a car is so huge that there cannot be a dataset for every possible road scenario. To overcome this problem, the concept of reinforcement learning (RL) is being investigated in this research. Since the problem of autonomous driving can be modeled in a simulation, it lends itself naturally to the domain of reinforcement learning. The advantage of this approach is that we can model different and complex road scenarios in a simulation without having to deploy in the real world. The autonomous agent can learn to drive by finding the optimal policy. This learned model can then be easily deployed in a real-world setting. In this project, we focus on three RL algorithms: Q-learning, Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO). To model the environment, we have used TORCS (The Open Racing Car Simulator), which provides us with a strong foundation to test our model. The inputs to the algorithms are the sensor data provided by the simulator such as velocity, distance from side pavement, etc. The outcome of this research project is a comparative analysis of these algorithms. Based on the comparison, the PPO algorithm gives the best results. When using PPO algorithm, the reward is greater, and the acceleration, steering angle and braking are more stable compared to the other algorithms, which means that the agent learns to drive in a better and more efficient way in this case. Additionally, we have come up with a dataset taken from the training of the agent with DDPG and PPO algorithms. It contains all the steps of the agent during one full training in the form: (all input values, acceleration, steering angle, break, loss, reward). This study can serve as a base for further complex road scenarios. Furthermore, it can be enlarged in the field of computer vision, using the images to find the best policy.

Keywords: autonomous driving, DDPG (deep deterministic policy gradient), PPO (proximal policy optimization), reinforcement learning

Procedia PDF Downloads 149

Authors: Anukriti Kumar, Tanmay Singh, Dinesh Kumar Vishwakarma

Abstract:

Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.

Keywords: multiclass classification, convolution neural network, OpenCV

Procedia PDF Downloads 176

Authors: V. U. Ameera

Abstract:

Rape has become an epidemic in India. Rape becomes a repressive weapon, which used to make them silent or used sometimes as a mode of punishment. Even for marrying above their status or for caste violation through a marriage of their choice, women are sentenced for mass rape, and the retribution is done in the presence of her family and villagers. Dalit or lower class women are brutally raped in a process of chastisement carried out by the upper class to keep the former always under their feet. Even in police stations, women are raped so that, their wretched condition will compel them to blurt out the truth. In a patriarchal society, for every trespass of woman, she is retaliated with a trespass into her body, which they think is the finest fine she can pay, as they are still driven by Victorian morality and believe once ‘the jewel’ is stolen, it is stolen forever. Even when the reports of brutal rapes comes out, those who are in responsible position also take the girls to task for going out in inappropriate time. As it is elsewhere in the world, in India too rape is a destructive weapon used to destroy men folk morally and psychologically, as they deem their honor rest in their protecting the purity of their women. During the communal skirmishes, as it is evident from Gujarat and Muzzafar Nagar recently, women are subjected to mass rape so that they can terrorize their men. Even women writers are threatened with rape for criticizing the maneuvers and manipulations of political parties. This becomes possible because of the undue weight given to the chastity of women. This study intends to analyze the nature of rapes occurring in India, including its use as a tool to establish and perpetuate the dominant position of men in social power structures. The study reveals how society, media and literature have imbibed and spread the notion of this sacred glass bowl which is the proud possession of men, the breaking of which steals them of their honor.

Keywords: guardians of chastity, patriarchal mindset, power tool, punishment rape

Procedia PDF Downloads 217

Authors: Mohammad Moonesun

Abstract:

One of the most important future technologies is related to solar Autonomous Underwater Vehicles (AUVs). In this technical paper, some aspects of solar winged AUV design are mentioned. The case study is for Arya project. The submarine movement cyclograms, weight quotas for internal equipment, hydrodynamic test results are mentioned, and some other technical notes are discussed here. The main body is the SUBOFF type and has two hydroplanes on the both sides of the body with the NACA0015 cross section. On these two hydroplanes, two 50-W photovoltaic panel will be mounted. Four small hydroplanes with the same cross section of the NACA0015 are arranged at the stern of the body at a 90° angle to each other. This test is performed in National Iranian Marine Laboratory with the length of 402 m.

Keywords: AUV, solar, model test, hydrodynamic resistance

Procedia PDF Downloads 131

Authors: R. Dariani, S. Schmidt, R. Kasper

Abstract:

Based on a non-linear single track model which describes the dynamics of vehicle, an optimal path planning strategy is developed. Real time optimization is used to generate reference control values to allow leading the vehicle alongside a calculated lane which is optimal for different objectives such as energy consumption, run time, safety or comfort characteristics. Strict mathematic formulation of the autonomous driving allows taking decision on undefined situation such as lane change or obstacle avoidance. Based on position of the vehicle, lane situation and obstacle position, the optimization problem is reformulated in real-time to avoid the obstacle and any car crash.

Keywords: autonomous driving, obstacle avoidance, optimal control, path planning

Procedia PDF Downloads 370

Authors: Carlos Gordon, Patricio Encalada, Henry Lema, Diego Leon, Dennis Chicaiza

Abstract:

The following work presents a proposal of autonomous navigation of mobile robots implemented in an omnidirectional robot Kuka Youbot. We have been able to perform the integration of robotic operative system (ROS) and machine learning algorithms. ROS mainly provides two distributions; ROS hydro and ROS Kinect. ROS hydro allows managing the nodes of odometry, kinematics, and path planning with statistical and probabilistic, global and local algorithms based on Adaptive Monte Carlo Localization (AMCL) and Dijkstra. Meanwhile, ROS Kinect is responsible for the detection block of dynamic objects which can be in the points of the planned trajectory obstructing the path of Kuka Youbot. The detection is managed by artificial vision module under a trained neural network based on the single shot multibox detector system (SSD), where the main dynamic objects for detection are human beings and domestic animals among other objects. When the objects are detected, the system modifies the trajectory or wait for the decision of the dynamic obstacle. Finally, the obstacles are skipped from the planned trajectory, and the Kuka Youbot can reach its goal thanks to the machine learning algorithms.

Keywords: autonomous navigation, machine learning, path planning, robotic operative system, open source computer vision library

Procedia PDF Downloads 177

Authors: Mirza Mohibulla Baig, Imil Hamda Imran, Tri Bagus Susilo, Sami El Ferik

Abstract:

The paper deals with system identification and control a nonlinear model of semi-autonomous underwater vehicle (UUV). The input-output data is first generated using the experimental values of the model parameters and then this data is used to compute the estimated parameter values. In this study, we use the semi-autonomous UUV LAURS model, which is developed by the Sensors and Actuators Laboratory in University of Sao Paolo. We applied three methods to identify the parameters: integral method, which is a classical least square method, recursive least square, and weighted recursive least square. In this paper, we also apply three different inputs (step input, sine wave input and random input) to each identification method. After the identification stage, we investigate the control performance of yaw motion of nonlinear semi-autonomous Unmanned Underwater Vehicle (UUV) using feedback linearization-based controller. In addition, we compare the performance of the control with an integral and a non-integral part along with state feedback. Finally, disturbance rejection and resilience of the controller is tested. The results demonstrate the ability of the system to recover from such fault.

Keywords: system identification, underwater vehicle, integral method, recursive least square, weighted recursive least square, feedback linearization, integral error

Procedia PDF Downloads 536

Authors: M. S. Nikitenko, S. A. Kizilov, D. Y. Khudonogov

Abstract:

The paper considers an approach to a machine vision operating system combined with using a grid of light markers. This approach is used to solve several scientific and technical problems, such as measuring the capability of an apron feeder delivering coal from a lining return port to a conveyor in the technology of mining high coal releasing to a conveyor and prototyping an autonomous vehicle obstacle detection system. Primary verification of a method of calculating bulk material volume using three-dimensional modeling and validation in laboratory conditions with relative errors calculation were carried out. A method of calculating the capability of an apron feeder based on a machine vision system and a simplifying technology of a three-dimensional modelled examined measuring area with machine vision was offered. The proposed method allows measuring the volume of rock mass moved by an apron feeder using machine vision. This approach solves the volume control issue of coal produced by a feeder while working off high coal by lava complexes with release to a conveyor with accuracy applied for practical application. The developed mathematical apparatus for measuring feeder productivity in kg/s uses only basic mathematical functions such as addition, subtraction, multiplication, and division. Thus, this fact simplifies software development, and this fact expands the variety of microcontrollers and microcomputers suitable for performing tasks of calculating feeder capability. A feature of an obstacle detection issue is to correct distortions of the laser grid, which simplifies their detection. The paper presents algorithms for video camera image processing and autonomous vehicle model control based on obstacle detection machine vision systems. A sample fragment of obstacle detection at the moment of distortion with the laser grid is demonstrated.

Keywords: machine vision, machine vision operating system, light markers, measuring capability, obstacle detection system, autonomous transport

Procedia PDF Downloads 114

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: Weihua Ruan, Kuan-Chou Chen

Abstract:

This paper is concerned with a system of Hamilton-Jacobi-Bellman equations coupled with an autonomous dynamical system. The mathematical system arises in the differential game formulation of political economy models as an infinite-horizon continuous-time differential game with discounted instantaneous payoff rates and continuously and discretely varying state variables. The existence of a weak solution of the PDE system is proven and a computational scheme of approximate solution is developed for a class of such systems. A model of democratization is mathematically analyzed as an illustration of application.

Keywords: Hamilton-Jacobi-Bellman equations, infinite-horizon differential games, continuous and discrete state variables, political-economy models

Procedia PDF Downloads 377

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: Do-Jin Jang, Sung-Ah Kim

Abstract:

A kinetic façade responds to user requirements and environmental conditions.  In designing a kinetic façade, kinetic patterns play a key role in determining its performance. This paper proposes a biomimetic method for the multi-objective optimization for kinetic façade design. The autonomous decentralized control system is combined with flocking algorithm. The flocking agents are autonomously reacting to sensor values and bring about kinetic patterns changing over time. A series of experiments were conducted to verify the potential and limitations of the flocking based decentralized control. As a result, it could show the highest performance balancing multiple objectives such as solar radiation and openness among the comparison group.

Keywords: biomimicry, flocking algorithm, autonomous decentralized control, multi-objective optimization

Procedia PDF Downloads 517