This thesis focuses on vision-based detection and observation of small, slow-moving targets using a gimballed fixed-wing unmanned aircraft system (UAS). Generally, visual tracking algorithms are tuned to detect motion of relatively large objects in the scene with noticeably significant motion; therefore, applications such as high-altitude visual searches for human motion often ignore target motion as noise. Furthermore, after a target is identified, arbitrary maneuvers for transitioning to overhead orbits for better observation may result in temporary or permanent loss of target visibility. We present guidelines for tuning parameters of the Visual Multiple Target Tracking (Visual MTT) algorithm to enhance its detection capabilities for very small, slow-moving targets in high-resolution images. We show that the tuning approach is able to detect walking motion of a human described by 10-15 pixels from high altitudes. An algorithm is then presented for defining rotational bounds on the controllable degrees of freedom of an aircraft and gimballed camera system for maintaining visibility of a known ground target. Critical rotations associated with the fastest loss or acquisition of target visibility are also defined. The accuracy of these bounds are demonstrated in simulation and simple applications of the algorithm are described for UAS. We also present a path planning and control framework for defining and following both dynamically and visually feasibly transition trajectories from an arbitrary point to an orbit over a known target for further observation. We demonstrate the effectiveness of this framework in maintaining constant target visibility while transitioning to the intended orbit as well as in transitioning to a lower altitude orbit for more detailed visual analysis of the intended target.

<div><div><div><p>Globally, there are more than 727 million people aged 65 years and older in the world, and the elderly population is expected to grow more than double in the next three decades. Families search for affordable and quality care for their senior loved ones will have an effect on the care-giving profession. A personal robot assistant could help with daily tasks such as carrying things for them and keeping track of their routines, relieving the burdens of human caregivers. Performing mentioned tasks usually requires the robot to autonomously navi- gate. An autonomous navigation robot should collect the knowledge of its surroundings by mapping the environment, find its position in the map and calculate trajectories by avoiding obstacles. Furthermore, to assign specific tasks which are in various locations, robot has to categorize the rooms in addition to memorizing the respective coordinates. In this research, methods have been developed to achieve autonomous navigation and room categorization of a mobile robot within indoor environments. A Simultaneously Localization and Map- ping (SLAM) algorithm has been used to build the map and localize the robot. Gmapping, a method of SLAM, was applied by utilizing an odometry and a 2D Light Detection and Ranging (LiDAR) sensor. The trajectory to achieve the goal position by an optimal path is provided by path planning algorithms, which is divided into two parts namely, global and local planners. Global path planning has been produced by DIJKSTRA and local path planning by Dynamic Window Approach (DWA). While exploring new environments with Gmapping and trajectory planning algorithms, rooms in the generated map were classified by a powerful deep learning algorithm called Convolutional Neural Network (CNN). Once the environment is explored, the robots localization in the 2D space is done by Adaptive Monte Carlo Localization (AMCL). To utilize and test the methods above, Gazebo software by The Robotic Operating System (ROS) was used and simulations were performed prior to real life experiments. After the trouble-shooting and feedback acquired from simulations, the robot was able to perform above tasks and later tested in various indoor environments. The environment was mapped successfully by Gmapping and the robot was located within the map by AMCL. Compared to the theoretical maximum efficient path, the robot was able to plan the trajectory with acceptable deviation. In addition, the room names were classified with minimum of 85% accuracy by CNN algorithm. Autonomous navigation results show that the robot can assist elderly people in their home environment by successfully exploring, categorizing and navigating between the rooms.</p></div></div></div>

Unmanned aircraft systems (UASs) are an important future technology with early generations already being used in many areas of application encompassing both military and civilian domains. This thesis proposes a number of integration techniques for combining control-based navigation with more abstract path planning functionality for UASs. These techniques are empirically tested and validated using an RMAX helicopter platform used in the UASTechLab at Linköping University. Although the thesis focuses on helicopter platforms, the techniques are generic in nature and can be used in other robotic systems. At the control level a navigation task is executed by a set of control modes. A framework based on the abstraction of hierarchical concurrent state machines for the design and development of hybrid control systems is presented. The framework is used to specify  reactive behaviors and for sequentialisation of control modes. Selected examples of control systems deployed on UASs are presented. Collision-free paths executed at the control level are generated by path planning algorithms.We propose a path replanning framework extending the existing path planners to allow dynamic repair of flight paths when new obstacles or no-fly zones obstructing the current flight path are detected. Additionally, a novel approach to selecting the best path repair strategy based on machine learning technique is presented. A prerequisite for a safe navigation in a real-world environment is an accurate geometrical model. As a step towards building accurate 3D models onboard UASs initial work on the integration of a laser range finder with a helicopter platform is also presented. Combination of the techniques presented provides another step towards building comprehensive and robust navigation systems for future UASs.

Mobile robotics has been very discussed and wide spread topic recently.   This due to the development in the computer technology that allows us to create   better and more sophisticated robots. The goal of this effort is to create robots   that will be able to autonomously move in the chosen environment. To achieve this goal,   it is necessary for the robot to create the map of its environment, where   the motion planning will occur. Nowadays, the probabilistic algorithms based   on the SLAM algorithm are considered standard in the mapping in these times.   This Phd. thesis deals with the proposal of the motion planning of the robot with   stereocamera placed on the pan-and-tilt unit. The motion planning is designed with   regard to the use of algorithms, which will look for the significant features   in the pair of the images. With the use of the triangulation the map, or a model will be created.     The benefits of this work can be divided into three parts. In the first one the way   of marking the free area, where the robot will plan its motion, is described. The second part   describes the motion planning of the robot in this free area. It takes into account   the properties of the SLAM algorithm and it tries to plan the exploration in order to create   the most precise map. The motion of the pan-and-tilt unit is described in the third part.   It takes advantage of the fact that the robot can observe places that are in the different   directions than the robot moves. This allows us to observe much bigger space without   losing the information about the precision of the movements.

No description available.

<div>Exploring and surveilling the marine environment away from shore is critical for scientific, economic, and military purposes as we progress through the 21st century. Until recently, these missions far from shore were only possible using manned surface vehicles. Over the past decade, advances in energy density, actuators, electronics, and controls have enabled great improvements in vehicle endurance, yet, no solution is capable of supporting persistent operation especially when considering power hungry scientific surveys. This dissertation summarizes contributions related to the development of an adaptable underwater docking station and associated navigation solutions to allow applications in the wide range of maritime missions. The adaptable docking system is a novel approach to the standard funnel shaped docking station design that enables the dock to be collapsible, portable, and support a wide range of vehicles. It has been optimized and tested extensively in simulation. Field experiments in both pool and open water validate the simulation results. The associated control strategies for approach and terminal homing are also introduced and studied in simulation and field trials. These strategies are computationally efficient and enable operation in a variety of scenarios and conditions. Combined, the adaptable docking system and associated navigation strategies can form a baseline for future extended endurance missions away from manned support.</div>

In this dissertation, we focus on two fundamental problems related to the navigation of ground robots and small Unmanned Aerial Vehicle (UAVs): cooperative localization and path planning. The theme running through in all of the work is the use of bearing only sensors, with a focus on monocular video cameras mounted on ground robots and UAVs. To begin with, we derive the conditions for the complete observability of the bearing-only cooperative localization problem. The key element of this analysis is the Relative Position Measurement Graph (RPMG). The nodes of an RPMG represent vehicle states and the edges represent bearing measurements between nodes. We show that graph theoretic properties like the connectivity and the existence of a path between two nodes can be used to explain the observability of the system. We obtain the maximum rank of the observability matrix without global information and derive conditions under which the maximum rank can be achieved. Furthermore, we show that for the complete observability, all of the nodes in the graph must have a path to at least two different landmarks of known location. The complete observability can also be obtained without landmarks if the RPMG is connected and at least one of the robots has a sensor which can measure its global pose, for example a GPS receiver. We validate these conditions by simulation and experimental results. The theoretical conditions to attain complete observability in a localization system is an important step towards reliable and efficient design of localization and path planning algorithms. With such conditions, a designer does not need to resort to exhaustive simulations and/or experimentation to verify whether a given selection of a control strategy, topology of the sensor network, and sensor measurements meets the observability requirements of the system. In turn, this leads to decreased requirements of time, cost, and effort for designing a localization algorithms. We use these observability conditions to develop a technique, for camera equipped UAVs, to cooperatively geo-localize a ground target in an urban terrain. We show that the bearing-only cooperative geo-localization technique overcomes the limitation of requiring a low-flying UAV to maintain line-of-sight while flying high enough to maintain GPS lock. We design a distributed path planning algorithm using receding horizon control that improves the localization accuracy of the target and of all of the UAVs while satisfying the observability conditions. Next, we use the observability analysis to explicitly design an active local path planning algorithm for UAVs. The algorithm minimizes the uncertainties in the time-to-collision (TTC) and bearing estimates while simultaneously avoiding obstacles. Using observability analysis we show that maximizing the observability and collision avoidance are complementary tasks. We provide sufficient conditions of the environment which maximizes the chances obstacle avoidance and UAV reaching the goal. Finally, we develop a reactive path planner for UAVs using sliding mode control such that it does not require range from the obstacle, and uses bearing to obstacle to avoid cylindrical obstacles and follow straight and curved walls. The reactive guidance strategy is fast, computationally inexpensive, and guarantees collision avoidance.

<p> Trajectory planning is a field with widespread utility, and imitation learning pipelines<br> show promise as an accessible training method for trajectory planning. MPNet is the state<br> of the art for imitation learning with respect to success rates. MPNet has two general<br> components to its runtime: a neural network predicts the location of the next anchor point in<br> a trajectory, and then planning infrastructure applies sampling-based techniques to produce<br> near-optimal, collision-less paths. This distinction between the two parts of MPNet prompts<br> investigation into the role of the neural architectures in the Neural Motion Planning pipeline,<br> to discover where improvements can be made. This thesis seeks to explore the importance<br> of neural architecture choice by removing the planning structures, and comparing MPNet’s<br> feedforward anchor point predictor with that of a continuous model trained to output a<br> continuous trajectory from start to goal. A new state of the art model in continuous learning<br> is the Neural Flow model. As a continuous model, it possess a low standard deviation runtime<br> which can be properly leveraged in the absence of planning infrastructure. Neural Flows also<br> output smooth, continuous trajectory curves that serve to reduce noisy path outputs in the<br> absence of lazy vertex contraction. This project analyzes the performance of MPNet, Resnet<br> Flow, and Coupling Flow models when sampling-based planning tools such as dropout, lazy<br> vertex contraction, and replanning are removed. Each neural planner is trained end-to-end in<br> an imitation learning pipeline utilizing a simple feedforward encoder, a CNN-based encoder,<br> and a Pointnet encoder to encode the environment, for purposes of comparison. Results<br> indicate that performance is competitive, with Neural Flows slightly outperforming MPNet’s<br> success rates on our reduced dataset in Simple2D, and being slighty outperformed by MPNet<br> with respect to collision penetration distance in our UR5 Cubby test suite. These results<br> indicate that continuous models can compete with the performance of anchor point predictor<br> models when sampling-based planning techniques are not applied. Neural Flow models also<br> have other benefits that anchor point predictors do not, like continuity guarantees, the ability<br> to select a proportional location in a trajectory to output, and smoothness. </p>

Det här projektet optimerar ett system som använder den statiska sökalgoritmen A* för att fåen autonom drönare att kunna undvika rörliga och målsökande hinder på sin färd emot enangiven måldestination. Optimeringen bygger på tidigare arbeten där bland annat ModelPredictive Control (MPC) har en stor påverkan på det implementerade systemet.Resultatet av projektet visar att det är möjligt att optimera ett system som använder sig av enstatisk planeringsalgoritm genom lokal planering inom det område drönaren har kunskap om.Ett högt planeringstempo där drönaren enbart följer första delen i den genererade planen,möjliggör att drönaren hela tiden kan anpassa sig till förändringar i omgivningen och undvikakollision. / This project optimizes a system that uses the static search algorithm A* to enable anautonomous drone to avoid moving and target-seeking obstacles on its way to a specifieddestination. The optimization is based on previous work where Model Predictive Control(MPC) has a major impact on the implemented system.The result of the project shows that it is possible to optimize a system using a static planningalgorithm through local planning in the area of which the drone has knowledge. A highplanning pace enables the drone to follow the first part of the generated plan, which meansthat the drone can constantly adapt to changes in the surroundings and avoid collisions.

This thesis presents an approach to solve an optimal path planning problem for a swarm of drones. We optimize and improve information retrieval in area exploration within applications such a ‘Search and Rescue’-missions or reconnaissance missions. For this, dynamic programming has been used as a solving approach for a optimization problem. Different scenarios have been examined for two types of system, a single-agent system and a multi-agent system. First, there have been restrictions on the agents movement in a grid map and for that, optimal paths have been computed for both systems. Thereafter, two different solving approaches within dynamic programming have been tested and compared. The greedy approach which is a standard use where each agent computes the most optimal path from its own perspective and a simultaneous solving approach where the agents compute the most optimal paths according to all agents perspective. The simultaneous solving approach performed better than the greedy approach, which was expected since it is a more swarm optimal approach. However, it has a higher computational complexity which grows exponentially unlike to the greedy approach. Lastly, we discuss the case when the agents are allowed to move in all directions to optimize the information retrieval for the swarm. Here, dynamic programming turns out to have limitations for our use and purpose. For future work, a suggestion is to model the problem with multiple objective functions instead of one as has been done in this thesis. Also, it would be interesting trying another solving method for the problem. To this, I give example of two methods that would be interesting to compare, using model predictive control or a machine learning-based solution such as reinforcement learning. / Denna avhandling presenterar ett tillvägagångssätt för att lösa ett optimalt ruttplanerings problem för en drönarsvärm. Vi optimerar och förbättrar informationsinhämtningen i områdesutforskning inom applikationer som ’Search and Rescue’-uppdrag eller spaningsuppdrag. För detta har dynamisk programmering använts som en lösningsmetod till optimeringsproblem. Olika scenarier har undersökts för två typer av system, ett en-agent system och ett fler-agent system. Först har agenterna varit begränsade hur de har fått röra sig i en rutnätskarta och för det fallet har optimala vägar beräknats för båda systemen. Därefter har två olika lösningssätt inom dynamisk programmering testats och jämförts. Det giriga tillvägagångssättet som är en standardanvändning där varje agent beräknar den mest optimala vägen ur sitt eget perspektiv och en simultan lösningsmetod där agenterna beräknar de mest optimala vägarna enligt alla agenters perspektiv. Den simultana lösningsstrategin presterade bättre än den giriga, vilket var väntat eftersom det är ett mer svärmoptimalt tillvägagångssätt. Den har dock en högre beräkningskomplexitet som växer exponentiellt jämfört med den giriga metoden. Till sist diskuterar vi fallet då agenterna får röra sig i alla riktningar för att optimera informationssökningen för svärmen. Här visar sig dynamisk programmering ha begränsningar för våran användning och syfte. För framtida arbete är ett förslag att modellera problemet med flera mål funktioner istället för en som har gjorts i denna avhandling. Det skulle också vara intressant att prova ett annat lösningssätt för problemet. Till detta ger jag exempel på två metoder som skulle vara intressanta att jämföra, genom att använda modell prediktiv styrning eller en maskininlärningsbaserad lösning såsom förstärkande inlärning.