1.
Blanch, Krister, 1991
(författare)
Beyond-application datasets and automated fair benchmarking
2023
Licentiatavhandling (övrigt vetenskapligt/konstnärligt) abstract
Beyond-application perception datasets are generalised datasets that emphasise the fundamental components of good machine perception data. When analysing the history of perception datatsets, notable trends suggest that design of the dataset typically aligns with an application goal. Instead of focusing on a specific application, beyond-application datasets instead look at capturing high-quality, high-volume data from a highly kinematic environment, for the purpose of aiding algorithm development and testing in general. Algorithm benchmarking is a cornerstone of autonomous systems development, and allows developers to demonstrate their results in a comparative manner. However, most benchmarking systems allow developers to use their own hardware or select favourable data. There is also little focus on run time performance and consistency, with benchmarking systems instead showcasing algorithm accuracy. By combining both beyond-application dataset generation and methods for fair benchmarking, there is also the dilemma of how to provide the dataset to developers for this benchmarking, as the result of a high-volume, high-quality dataset generation is a significant increase in dataset size when compared to traditional perception datasets. This thesis presents the first results of attempting the creation of such a dataset. The dataset was built using a maritime platform, selected due to the highly dynamic environment presented on water. The design and initial testing of this platform is detailed, as well as as methods of sensor validation. Continuing, the thesis then presents a method of fair benchmarking, by utilising remote containerisation in a way that allows developers to present their software to the dataset, instead of having to first locally store a copy. To test this dataset and automatic online benchmarking, a number of reference algorithms were required for initial results. Three algorithms were built, using the data from three different sensors captured on the maritime platform. Each algorithm calculates vessel odometry, and the automatic benchmarking system was utilised to show the accuracy and run-time performance of these algorithms. It was found that the containerised approach alleviated data management concerns, prevented inflated accuracy results, and demonstrated precisely how computationally intensive each algorithm was.
2.
Estrela, Vania V., et al.
(författare)
Conclusions
2020
Ingår i: Imaging and Sensing for Unmanned Aircraft Systems Volume 2. - : Institution of Engineering and Technology. - 9781785616440 - 9781785616457 ; , s. 247-248
Bokkapitel (övrigt vetenskapligt/konstnärligt) abstract
The current awareness in unmanned aerial vehicles (UAVs) has prompted not only military applications but also civilian uses. Aerial vehicles’ requirements aspire to guarantee a higher level of safety comparable to see-and-avoid conditions for piloted aeroplanes. The process of probing obstacles in the path of a vehicle and determining whether they pose a threat, alongside measures to avoid these issues, is known as see and avoid or sense and avoid. Other types of decision-making tasks can be accomplished using computer vision and sensor integration since they have a great potential to improve the performance of the UAVs. Macroscopically, UAVs are cyber-physical systems (CPSs) that can benefit from all types of sensing frameworks, despite severe design constraints, such as precision, reliable communication, distributed processing capabilities and data management. This book is paying attention to several issues that are still under discussions in the field of UAV-CPSs. Thus, several trends and needs are discussed to foster criticism from the readers and to provide further food for thought.
3.
Nalpantidis, Lazaros, et al.
(författare)
Obtaining reliable depth maps for robotic applications from a quad-camera system
2009
Ingår i: INTELLIGENT ROBOTICS AND APPLICATIONS, PROCEEDINGS. - Berlin : Springer Berlin/Heidelberg. - 9783642108167 ; , s. 906-916
Konferensbidrag (övrigt vetenskapligt/konstnärligt) abstract
Autonomous navigation behaviors in robotics often require reliable depth maps. The use of vision sensors is the most popular choice in such tasks. On the other hand, accurate vision-based depth computing methods suffer from long execution times. This paper proposes a novel quad-camera based system able to calculate fast and accurately a single depth map of a scenery. The four cameras are placed on the corners of a square. Thus, three, differently oriented, stereo pairs result when considering a single reference image (namely an horizontal, a vertical and a diagonal pair). The proposed system utilizes a custom tailored, simple, rapidly executed stereo correspondence algorithm applied to each stereo pair. This way, the computational load is kept within reasonable limits. A reliability measure is used in order to validate each point of the resulting disparity maps. Finally, the three disparity maps are fused together according to their reliabilities. The maximum reliability is chosen for every pixel. The final output of the proposed system is a highly reliable depth map which can be used for higher level robotic behaviors.
4.
Imaging and sensing for unmanned aircraft systems Volume 2: Deployment and applications
2020
Samlingsverk (redaktörskap) (övrigt vetenskapligt/konstnärligt) abstract
This two volume book set explores how sensors and computer vision technologies are used for the navigation, control, stability, reliability, guidance, fault detection, self-maintenance, strategic re-planning and reconfiguration of unmanned aircraft systems (UAS). Volume 1 concentrates on UAS control and performance methodologies including Computer Vision and Data Storage, Integrated Optical Flow for Detection and Avoidance Systems, Navigation and Intelligence, Modeling and Simulation, Multisensor Data Fusion, Vision in Micro-Aerial Vehicles (MAVs), Computer Vision in UAV using ROS, Security Aspects of UAV and Robot Operating System, Vision in Indoor and Outdoor Drones, Sensors and Computer Vision, and Small UAVP for Persistent Surveillance. Volume 2 focuses on UAS deployment and applications including UAV-CPSs as a Testbed for New Technologies and a Primer to Industry 5.0, Human-Machine Interface Design, Open Source Software (OSS) and Hardware (OSH), Image Transmission in MIMO-OSTBC System, Image Database, Communications Requirements, Video Streaming, and Communications Links, Multispectral vs Hyperspectral Imaging, Aerial Imaging and Reconstruction of Infrastructures, Deep Learning as an Alternative to Super Resolution Imaging, and Quality of Experience (QoE) and Quality of Service (QoS).
5.
Ambrus, Rares
(författare)
Unsupervised construction of 4D semantic maps in a long-term autonomy scenario
2017
Doktorsavhandling (övrigt vetenskapligt/konstnärligt) abstract
Robots are operating for longer times and collecting much more data than just a few years ago. In this setting we are interested in exploring ways of modeling the environment, segmenting out areas of interest and keeping track of the segmentations over time, with the purpose of building 4D models (i.e. space and time) of the relevant parts of the environment.Our approach relies on repeatedly observing the environment and creating local maps at specific locations. The first question we address is how to choose where to build these local maps. Traditionally, an operator defines a set of waypoints on a pre-built map of the environment which the robot visits autonomously. Instead, we propose a method to automatically extract semantically meaningful regions from a point cloud representation of the environment. The resulting segmentation is purely geometric, and in the context of mobile robots operating in human environments, the semantic label associated with each segment (i.e. kitchen, office) can be of interest for a variety of applications. We therefore also look at how to obtain per-pixel semantic labels given the geometric segmentation, by fusing probabilistic distributions over scene and object types in a Conditional Random Field.For most robotic systems, the elements of interest in the environment are the ones which exhibit some dynamic properties (such as people, chairs, cups, etc.), and the ability to detect and segment such elements provides a very useful initial segmentation of the scene. We propose a method to iteratively build a static map from observations of the same scene acquired at different points in time. Dynamic elements are obtained by computing the difference between the static map and new observations. We address the problem of clustering together dynamic elements which correspond to the same physical object, observed at different points in time and in significantly different circumstances. To address some of the inherent limitations in the sensors used, we autonomously plan, navigate around and obtain additional views of the segmented dynamic elements. We look at methods of fusing the additional data and we show that both a combined point cloud model and a fused mesh representation can be used to more robustly recognize the dynamic object in future observations. In the case of the mesh representation, we also show how a Convolutional Neural Network can be trained for recognition by using mesh renderings.Finally, we present a number of methods to analyse the data acquired by the mobile robot autonomously and over extended time periods. First, we look at how the dynamic segmentations can be used to derive a probabilistic prior which can be used in the mapping process to further improve and reinforce the segmentation accuracy. We also investigate how to leverage spatial-temporal constraints in order to cluster dynamic elements observed at different points in time and under different circumstances. We show that by making a few simple assumptions we can increase the clustering accuracy even when the object appearance varies significantly between observations. The result of the clustering is a spatial-temporal footprint of the dynamic object, defining an area where the object is likely to be observed spatially as well as a set of time stamps corresponding to when the object was previously observed. Using this data, predictive models can be created and used to infer future times when the object is more likely to be observed. In an object search scenario, this model can be used to decrease the search time when looking for specific objects.
6.
Estrela, Vania V., et al.
(författare)
Conclusions
2020
Ingår i: Imaging and Sensing for Unmanned Aircraft Systems Volume 1. - : Institution of Engineering and Technology. - 9781785616426 - 9781785616433 ; , s. 333-335
Bokkapitel (övrigt vetenskapligt/konstnärligt) abstract
The current awareness in UAVs has prompted not only military applications but also civilian uses. Aerial vehicles’ requirements aspire to guarantee a higher level of safety comparable to see-and-avoid conditions for piloted aeroplanes. The process of probing obstacles in the path of a vehicle, and to determine if they pose a threat, alongside measures to avoid problems, is known as see-and-avoid or sense and-avoid involves a great deal of decision-making. Other types of decisionmaking tasks can be accomplished using computer vision and sensor integration since they have great potential to improve the performance of UAVs. Macroscopically, Unmanned Aerial Systems (UASs) are cyber-physical systems (CPSs) that can benefit from all types of sensing frameworks, despite severe design constraints such as precision, reliable communication, distributed processing capabilities, and data management.
7.
Wasik, Zbigniew, 1973-
(författare)
A behavior-based control system for mobile manipulation
2005
Doktorsavhandling (övrigt vetenskapligt/konstnärligt) abstract
The field of industrial robotics can be defined as the study, design and use of robot manipulators for manufacturing. Although the problem of designing a controller for industrial robots has been subject of intensive study, a number of assumptions are usually made which may seriously limit the applicability of these robots. First, the robotic manipulator is usually considered to be positioned at one place, which means that it can only work in its limited working envelope fixed to this position. Second, it is usually assumed that the environment of the manipulator (workcell) is carefully engineered to suit the task and the configuration of the arm. Finally, the control program of the manipulator is often designed assuming that the task will not change. These restriction make current industrial robots unsuitable for the new demands of flexible automation in small and medium enterprises. In this thesis, we develop techniques that extend the applicability of current robotic manipulators, by addressing the above limitations. We propose an approach to sensor-based manipulation that: 1) has flexible and modular control system, in order to easily to new tasks and environments, 2) the execution is sensor-based for robustness in less controlled environment, and 3) our approach applies to the more general problem of combined mobility and manipulation, in order to extend the work space of the manipulator.
8.
9.
Wiberg, Viktor, et al.
(författare)
Sim-to-real transfer of active suspension control using deep reinforcement learning
Annan publikation (övrigt vetenskapligt/konstnärligt) abstract
We explore sim-to-real transfer of deep reinforcement learning controllers for a heavy vehicle with active suspensions designed for traversing rough terrain. While related research primarily focuses on lightweight robots with electric motors and fast actuation, this study uses a forestry vehicle with a complex hydraulic driveline and slow actuation. We simulate the vehicle using multibody dynamics and apply system identification to find an appropriate set of simulation parameters. We then train policies in simulation using various techniques to mitigate the sim-to-real gap, including domain randomization, action delays, and a reward penalty to encourage smooth control. In reality, the policies trained with action delays and a penalty for erratic actions perform at nearly the same level as in simulation. In experiments on level ground, the motion trajectories closely overlap when turning to either side, as well as in a route tracking scenario. When faced with a ramp that requires active use of the suspensions, the simulated and real motions are in close alignment. This shows that the actuator model together with system identification yields a sufficiently accurate model of the actuators. We observe that policies trained without the additional action penalty exhibit fast switching or bang-bang control. These present smooth motions and high performance in simulation but transfer poorly to reality. We find that policies make marginal use of the local height map for perception, showing no indications of look-ahead planning. However, the strong transfer capabilities entail that further development concerning perception and performance can be largely confined to simulation.
10.
Wzorek, Mariusz, 1978-
(författare)
Selected Aspects of Navigation and Path Planning in Unmanned Aircraft Systems
2011
Licentiatavhandling (övrigt vetenskapligt/konstnärligt) abstract
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.
