Twirre is a new architecture for mini-UAV platforms designed for autonomous flight in both GPS-enabled and GPS-deprived applications. The architecture consists of low-cost hardware and software components. High-level control software enables autonomous operation. Exchanging or upgrading hardware components is straightforward and the architecture is an excellent starting point for building low-cost autonomous mini-UAVs for a variety of applications. Experiments with an implementation of the architecture are in development, and preliminary results demonstrate accurate indoor navigation
MULTIFILE
Autonomously exploring and mapping is one of the open challenges of robotics and artificial intelligence. Especially when the environments are unknown, choosing the optimal navigation directive is not straightforward. In this paper, we propose a reinforcement learning framework for navigating, exploring, and mapping unknown environments. The reinforcement learning agent is in charge of selecting the commands for steering the mobile robot, while a SLAM algorithm estimates the robot pose and maps the environments. The agent, to select optimal actions, is trained to be curious about the world. This concept translates into the introduction of a curiosity-driven reward function that encourages the agent to steer the mobile robot towards unknown and unseen areas of the world and the map. We test our approach in explorations challenges in different indoor environments. The agent trained with the proposed reward function outperforms the agents trained with reward functions commonly used in the literature for solving such tasks.
MULTIFILE
Twirre V2 is the evolution of an architecture for mini-UAV platforms which allows automated operation in both GPS-enabled and GPSdeprived applications. This second version separates mission logic, sensor data processing and high-level control, which results in reusable software components for multiple applications. The concept of Local Positioning System (LPS) is introduced, which, using sensor fusion, would aid or automate the flying process like GPS currently does. For this, new sensors are added to the architecture and a generic sensor interface together with missions for landing and following a line have been implemented. V2 introduces a software modular design and new hardware has been coupled, showing its extensibility and adaptability
DOCUMENT
Drones have been verified as the camera of 2024 due to the enormous exponential growth in terms of the relevant technologies and applications such as smart agriculture, transportation, inspection, logistics, surveillance and interaction. Therefore, the commercial solutions to deploy drones in different working places have become a crucial demand for companies. Warehouses are one of the most promising industrial domains to utilize drones to automate different operations such as inventory scanning, goods transportation to the delivery lines, area monitoring on demand and so on. On the other hands, deploying drones (or even mobile robots) in such challenging environment needs to enable accurate state estimation in terms of position and orientation to allow autonomous navigation. This is because GPS signals are not available in warehouses due to the obstruction by the closed-sky areas and the signal deflection by structures. Vision-based positioning systems are the most promising techniques to achieve reliable position estimation in indoor environments. This is because of using low-cost sensors (cameras), the utilization of dense environmental features and the possibilities to operate in indoor/outdoor areas. Therefore, this proposal aims to address a crucial question for industrial applications with our industrial partners to explore limitations and develop solutions towards robust state estimation of drones in challenging environments such as warehouses and greenhouses. The results of this project will be used as the baseline to develop other navigation technologies towards full autonomous deployment of drones such as mapping, localization, docking and maneuvering to safely deploy drones in GPS-denied areas.
Autonomous Guided Vehicles (AGV) worden hedendaags breed toegepast in verschillende sectoren als agri, logistiek en zorg. De taken die AGV’s verrichten zijn veelal gericht op het indoor transporteren van goederen en vereisen daarom een precieze en robuuste locatiebepaling. Indoor lokalisatie is een ‘key-technology’ daar het in allerlei toepassingsgebieden een fundamentele rol speelt. Tot op heden is er geen algemeen toepasbare techniek voorhanden en is het noodzakelijk om de omgeving uit te rusten met een op maat gemaakt lokalisatiesysteem wat duur, tijdrovend en inflexibel is. Een veelbelovende techniek is Magnetic-Simulataneous-Localisation-And-Mapping (MagSLAM). Deze techniek is berust op een verstoord aardmagnetisch veld door de aanwezigheid van vele ‘indoor’ ferromagnetische structuren. Deze verstoringen zijn specifiek voor de plek binnen het gebouw en zodoende als informatiebron gezien kunnen worden. Deze wijze biedt een aantal fundamentele voordelen ten opzichte van camera, radio of tag gebaseerde lokalisatiesystemen. Het doel van dit KIEM-project is een onderzoek naar de vraag in hoeverre we het magnetisch veld als informatieprovider kunnen gebruiken om het lokalisatievraagstuk voor AGV’s te kunnen helpen. De belangrijkste onderzoekvraag daarbij is “Hoe kunnen we de MagSLAM-technologie opwerken en inpassen in een AGV-systeem?” Daarbij rekening houdend met uitdagingen als kalibratie, fusie van sensordata (bijvoorbeeld odometrie) en het robuust zijn voor grote inductiestromen (bijvoorbeeld motoren en laadcircuits). Saxion en haar partners zetten zich de komende jaren in op de sleuteltechnologieën voor robotica als perception, navigation, cognition en artificial-intelligence welke allen integraal onderdeel vormen in dit KIEM project. Het project zal uit 4 fases bestaan: allereerst een inventarisatie van huidige MagSLAM-algoritmiek en AGVpositioneringssystemen (IST), een systeem- en gebruikerseisen onderzoek (SOLL) en tenslotte een analyse om de technologie op te werken en te passen (GAP).
Due to the exponential growth of ecommerce, the need for automated Inventory management is crucial to have, among others, up-to-date information. There have been recent developments in using drones equipped with RGB cameras for scanning and counting inventories in warehouse. Due to their unlimited reach, agility and speed, drones can speed up the inventory process and keep it actual. To benefit from this drone technology, warehouse owners and inventory service providers are actively exploring ways for maximizing the utilization of this technology through extending its capability in long-term autonomy, collaboration and operation in night and weekends. This feasibility study is aimed at investigating the possibility of developing a robust, reliable and resilient group of aerial robots with long-term autonomy as part of effectively automating warehouse inventory system to have competitive advantage in highly dynamic and competitive market. To that end, the main research question is, “Which technologies need to be further developed to enable collaborative drones with long-term autonomy to conduct warehouse inventory at night and in the weekends?” This research focusses on user requirement analysis, complete system architecting including functional decomposition, concept development, technology selection, proof-of-concept demonstrator development and compiling a follow-up projects.
