Robots are increasingly deployed in various locations to automate tasks, including in barns. However, in barns cows can obstruct the sensors such as LiDAR or camera, leading to a lack of environmental information. As a result, the robot’s localization system only relies on odometry at those moments, introducing additional uncertainty to the robot’s pose. When the visibility of the environment is restored, the robot may mistakenly believe it is in a location that does not correspond to its actual position. The first contribution of this master thesis is a novel method for improving the self-localization in barns by implementing a line detection algorithm which is called Line Adaptive Monte Carlo Localization (LAMCL). The novelty is that only line segments are used to detect a localization error instead of corners between different line segments. It also retains the robot’s current pose to filter out fault-detected localization errors. In addition, the new approach is applied in a dynamic environment. The proposed method combines the Split-and-Merge line detection algorithm with AMCL. The detected line segments are compared with the walls in the environment to identify localization errors. When an error is detected, the robot’s pose is adjusted by placing a section of the particles at the location of the error. In this way, the robot can find its true location again. The second contribution is a new dataset. This new dataset, called DataCow, consists of four recorded routes in a barn with GT on a handful of spots to evaluate the self-localization. DataCow includes the pseudo-2D LiDAR scans and the odometry of a robot driving through a barn. This dataset is used to evaluate the new self-localization method LAMCL. Through the experiments, it has been discovered that this new method improves the system’s recovery ability, but the accuracy and precision are compromised.

Inadvertent bird nest destruction by autonomous mowing machines poses significant threats to the breeding success of meadow birds. Drone-based detection methods represent the current state-of-the-art for bird nest localization to attain mower circumvention. However, they only identify 80% of bird nests with average localization error of 3.344 meters and are restricted to specific application times. This paper introduces alternative, fully automated nest localization systems integrated with autonomous mowers. Two strategies are proposed, 1) Directly detecting bird nests using thermal data, or 2) Indirectly, by tracking birds and extrapolating their trajectories back to their nests using RGBD data. These methods were validated with warmed chicken eggs hidden in grasslands and with drones simulating bird flight. YOLOv8 models were modified for both approaches. The thermal localization method is able to detect all bird nests with an average confidence of 73.4%. It allows for real-time localization and yields one unnecessary nest circumvention for every ten bird nests saved due to false positives. This method is shown to be effective in all breeding season temperatures, both day and night. Conversely, the trajectory extrapolation method detects birds with an average confidence of 82.2% and has localization error of 0.794 meters. Birds taking flight prematurely or from locations other than nests impact the number of bird nests saved and the number of unnecessary circumventions. It is demonstrated that this method fails to detect birds during nighttime. In conclusion, an automated thermal-based localization system integrated with autonomous mowers outperforms both RGBD- and current state-of-the-art drone-based methods. This study highlights therefore the potential of thermal-based solutions for bird nest protection in grasslands.

An increase in the intelligence of autonomous driving functionalities demands detailed analysis of the behaviour of traffic participants. This level of analysis requires datasets that accurately describe the movement of all objects in a specific scene. Recent developments in small Unmanned Aerial Vehicles (sUAVs) and drones introduce an interesting approach to extract this type of data: applying object detection and tracking methods to imagery captured by sUAVs/drones to extract kinematic parameters of traffic participants. Analysing the behaviour of vehicles in urban traffic has been the topic of research for many years. However, vehicle detection and tracking pipelines used in the proposed approaches lack the required accuracy in estimating a vehicle's orientation and contours. Vehicle detection methods used in recent approaches detect vehicles as Axis-aligned Bounding Boxes (ABBs) that contain no information about a vehicle's orientation and contours. Alternatively, vehicles could be detected as Oriented Bounding Boxes (OBBs) that do contain this information. For low-altitude aerial imagery, however, the amount of publicly available data to train methods using OBB detections is scarce. To fill the gap in data availability, this thesis introduces the novel `Axis-aligned to Oriented Bounding Boxes' methodology (A2OBB). Based on a non-linear least squares approximation of the geometrical relationship between an ABB and an OBB, A2OBB finds a set of OBB parameters that fit optimally in all provided ABBs. As such, A2OBB can be applied (1) as an enhancement tool to convert existing ABB annotations to OBBs or (2) as an extension to existing detection networks that perform detections in ABB format. This thesis contributes by formulating the novel A2OBB methodology and by performing a detailed analysis on its OBB reconstruction performance. In four experiments, an analysis is performed investigating the impact of two assumptions made in the proposed methodology on the reconstruction performance. The results of the experiments illustrate a sensitivity to: (1) a change in perspective between the observed vehicle and the camera, (2) a mismatch between the perceived shape of vehicles and the assumed rectangular shape and (3) the error introduced by the detection network (in the application of extending ABB detection networks). To reduce the impact of the shape mismatch, a correction factor is introduced that significantly improves the reconstruction performance. As such, A2OBB can be used to reconstruct OBBs from a set of manually annotated ABBs with a length and width approximation accurate within 5% and 15% of their respective ground-truths and an optimal orientation with an average error below 2.5°. Overall, manually annotated ABBs are converted to OBBs with an average Intersection over Union (IoU) of 85%. Detections resulting from an in-house out-of-the-box implementation of a YOLOv3 network are reconstructed with a length and width bias of 4.5% and 10% of their respective ground-truth and with an orientation error below 5° but above 2.5°. Overall, the reconstructed OBBs for these detected ABBs have an IoU of 77%. Note that the orientations resulting from A2OBB’s reconstructions comprise one of four possible solutions. A subsequent step is required to find the correct version.

3D human pose estimation is a widely researched computer vision task that could be applied in scenarios such as virtual reality and human-robot interaction. With the lack of depth information, 3D estimation from monocular images is an inherently ambiguous problem. On top of that, unrealistic human poses have been overlooked in the majority of papers since joint detection is the only focus. Our work consists of two parts, an end-to-end 2D-3D lifting pipeline and a novel kinematic human model integrated approach. We start with Pose Estimation using TRansformer (PETR), an approach that does not require temporal information and has the attention mechanism to model the inter-joint relationship from RGB images. In the approach with human model, we emphasize pose similarity rather than focusing on joint detection. We propose a new metric, called Mean Per Bone Vector Error (MPBVE), that evaluates poses regardless of a human body’s gender, weight, or age. We introduce Pose Estimation on Bone Rotation using Transformer (PEBRT), a novel approach that regresses rotation matrices for 16 human bones, assuming labeled 2D poses as input. Our human model encapsulates joint angle and bone length constraints. Existing methods treat these constraints as an additional loss term, which does not guarantee realistic final out- puts. Our method does not require temporal information or receptive fields to generate kinematically realistic human poses. We demonstrate that PEBRT is capable of delivering comparable results on Human3.6M to existing methods.

Automated bin-picking is a difficult task that requires solving multiple robotic vision problems including object detection and grasp proposal generation. Current methods use deep learning to approach each of the vision problems of bin-picking separately with the main focus on generating the grasp proposals. For grasp proposal generation, neural networks are taught to detect grasp locations by directly proposing or scoring locations. The problem with this method is that it binds the network to a specific decision making process that is encoded into the dataset. We propose a novel architecture we call map-grasp that does not propose grasp locations but instead produces property maps describing measurable, physical object properties while simultaneously detecting and classifying items in an image. We devised a method to automatically generate a dataset containing these property maps from a point cloud, from which we can then determine a grasping location based on custom criteria. We train our network on a training set containing 1845 images and then test it on a physical system where we attempt over 700 grasps on 66 different items. We compare our performance on a current state-of-the-art analytical method and show that our network can outperform it, achieving an 82.16% first-try success rate and a 89.73% total clear rate.

The world is heading more and more towards automation, that goes for transportation as well. Various car manufactures already have released level 2 autonomous vehicles meaning that the future is not that far away. An essential part of driving is of course detecting and obeying the traffic signs. Advanced Driver Assistance Systems (ADAS) like speed limit detection systems or a more advanced variant the Traffic Sign Detection (TSD) systems are integrated in top-of-the-line car models in order to increase safety and relieve some ofthe drivers workload. These systems attempt to make drivers aware of incoming signs on the road and warn them against possible danger or in some cases even take control over the vehicle. As in many computer vision systems differences in lighting, weather conditions, motion blur, and poor image quality can reduce the effectiveness of these systems. In case of the Traffic Sign Detection systems other challenges arise like differences in sign position and in the condition (dirty, deformed, discolored etc.) of the sign itself. In order to fully rely on such system all these challenges have to be overcome. The goal of this thesis is to enhance a traffic sign detection model that requires relatively low processing power in such a manner that it can compete with traffic sign models that show great results and achieve high accuracy but require high processing power maintaining the ability to operate in real time. The suggested BoBT method increases the accuracy of a model at the cost of inference speed. There is a small difference in precisely localizing the traffic signs compared to state of the art models but in terms of detecting traffic signs the difference is less than a percent with the highest accuracy model. Not to mention that it still outperforms these models in terms of speed.

This thesis proposes a novel algorithm, Wi-Closure, to improve computational efficiency and robustness of map matching in multi-robot SLAM. Current state-of-the-art techniques connect maps with inter-robot loop closures, that are usually found through place recognition. Wi-Closure decreases the computational overhead of these approaches by pruning the search space of potential loop closures, prior to evaluation by a typical place recognition algorithm. Wi-Closure achieves this by identifying where trajectories are close to each other through sensing spatial information directly from the wireless communication signal. Then, place recognition is only performed on scans taken at locations close to each other. Wireless sensing provides information even when operating in non-line-of-sight or without existing communication infrastructure. The validity of Wi-Closure is demonstrated in simulation and hardware experiments. Results show that using Wi-closure greatly reduces computation time, by 54% in simulation and by 77% in hardware, compared with a multi-robot SLAM baseline. Importantly, this is achieved without sacrificing accuracy. Using Wi-Closure reduces absolute trajectory estimation error by 99% in simulation and 89% in hardware experiments. This improvement is due in part to Wi-Closure’s ability to avoid catastrophic optimization failure that typically occurs with classical approaches in challenging repetitive environments.

For an Autonomous Vehicle (AV) to traverse safely in traffic, It is vital it can anticipate the behavior of surrounding traffic participants using motion prediction. Current motion prediction approaches can be categorized into object-centered and object-agnostic methods and are primarily based on deep learning. The former relies on a human-engineered pipeline of object detection and tracking, of which the errors can accumulate in the motion predictions. The latter does not rely on this pipeline; however, it lacks the ability to learn object representations causing blurriness and object disappearances for longer-term predictions which forms a safety hazard. This thesis proposes two methods to improve the performance of the object-agnostic sequence-to-sequence Occupancy Grid Map (OGM) prediction networks, trained on the Waymo Open Perception dataset. The first method uses inter-pixel loss functions, i.e. the SSIM and Sinkhorn losses, instead of the ubiquitously used per-pixel losses, to train the PredRNN++ Occupancy Grid Map (OGM) prediction network. Inter-pixel losses take into account the spatial relations between grid cells during the evaluation of OGMs, whereas per-pixel losses evaluate each grid cell’s value independently. The quantitative results demonstrate that using inter-pixel losses can improve short term predictions with a prediction horizon of T = 5 for the Mean Squared Error (MSE) by 4.3%, Image Similarity (IS) by 7.8%, Average Precision (AP) by 0.3%, metrics. For the longer term, T = 15, the predictions improve for the MSE by 5.0%, IS by 20.5%, AP by 0.1%, and Accuracy by 0.6%. Furthermore, the use of inter-pixel losses reduces blurriness and object disappearances. The second method is based on multi-task learning. By training the PredRNN++ to perform the prediction task together with the semantic segmentation task on the predicted OGMs, it is expected to learn object representations which it uses to improve the prediction quality. The quantitative results show that multi-task learning does not improve the OGM predictions. However, some qualitative results show that multi-task learning reduces blurriness and object disappearances.

Robot Care Systems (RCS) is involved in the development of the WEpod, an autonomous shuttle which can transfer up to six people. Based on a predefined map of the environment, the shuttle is able to navigate through mixed traffic its perception sensors such as camera, radar and lidar sensors. This study is acquired in collaboration with RCS and focuses on two parts: assessing the influence of different factors on the domain shift and assessing the importance of depth information in the transformation of scene understanding from image space to top view. For the WEpod, or any self-driving vehicle to safely travel over the road and through traffic, it is important to understand road scenes that appear in our daily life. This scene understanding is the base for a successful and reliable future of autonomous vehicles. Deploying a Convolutional Neural Network (CNN) in order to execute the task of semantic segmentation is a typical approach to attain such understanding of the surroundings. However, when a CNN is trained on a certain source domain and then deployed on a different (target) domain, the network will often execute the task poorly. This is the result of differences between the source and target domain and is referred to as domain shift. Although it is a common problem, the factors that cause these differences are not yet fully explored. We filled this research gap with the investigation of ten different factors. To explore these factors, a base network was generated by a two-step fine-tuning procedure on an existing convolutional neural network (SegNet) which is pretrained on the CityScapes dataset (dataset for semantic segmentation). Fine-tuning on part of the RobotCar dataset (road scenery dataset recorded in Oxford, UK) is followed by a second fine-tuning step. The latter is done on part of the KITTI dataset (road scenery dataset recorded throughout Germany). Experiments are conducted in order to obtain the influence of each factor on a successful domain adaptation (i.e. negligible domain shift). The influence of factors on the domain shift based on semantic segmentation is assessed by comparing the result of every factor to the result on the base network. Results consist of the F1-measure and Jaccard index for drivable path segmentation and occupancy segmentation although the emphasis lies on the drivable path segmentation. Significant positive influence on the estimation of drivable path for the WEpod domain was obtained when the ground truth labels only consisted of two labels (i.e. drivable path and non-drivable path) instead of three classes. This performance gain is signed by an increase of 8 percent points for both the IoU and the F1 metric. Making all images intrinsically consistent, and thus removing all geometric differences between the camera sensors, resulted in a larger increase of performance metrics. Compared to the baseline, both the Jaccard index and F1 metric increased with 10 percent points. The training order is a main contributor for domain adaptation with an increase of the IoU metric of 18 percent points and 20 percent points for the F1 metric. This shows that the target domain (WEpod) is more closely related to RobotCar than to KITTI. Although the investigation of different factors potentially can realise a better performance on the WEpod domain, understanding the environment in image space is not enough because path planning is utilised in top view. Hence, a transformation between image space and top view is needed to use the scene understanding based on semantic segmentation to the full extent. For this transformation, three setups are utilised with each a different form of depth information available: no depth information, ground truth depth information and estimated depth information. This approach gains insight into the relevance of depth information on the usability of scene understanding. The accuracy of top view transformations is measured in the form of four metrics: raw lateral error, scaled lateral error, overlap length and a count metric. The first metric is concerned with the raw difference between the estimated and ground truth trajectory. The second metric is a scaled form of the former. The overlap length measures to what extent the trajectory is estimated while the count metric takes into account if the estimated trajectory is present in top view. From the experiments it is concluded that depth information plays an important role in the lateral sense of the trajectories while it is of less importance for the longitudinal length of the trajectory. It is also noticed that depth information does not necessarily needs to be dense. Moreover, the sparse but ground truth depth information leads to a better trajectory.

During the last decades, people detection has received great attention in computer vision and pattern recognition because of its various applications. Though there are thousands of papers provide approaches for people detection, most of them focus on datasets from side view. People detection from overhead cameras, as an important situation for surveillance, is essential to research. This work based on annotated videos from MatchNMingle dataset, which are taken by overhead cameras. The videos were taken in a mingle after a speed-dating event. People are annotated by bounding boxes contain their body. In this crowded social scene, people occlusion is one of the challenge barriers for detection. In this work, we study the relation between people occlusion and detecting performance by experiments. Based on a deep network consisting of GoogLeNet and Overfeat, we analyze the performance of detectors trained with various occlusion distribution at different occlusion level. On the ground of experiment results, we attempt to promote the performance by selection of training data. Apart from this, as an attempt for promotion, we train head detectors by newly collected head annotation. The performance evaluation of these two methods indicates their potential for people detection in crowded scene.

To be able to understand the dynamic driving environment, an autonomous vehicle needs to predict the mo- tion of other traffic participants in the driving scene. Motion prediction can be done based on experience and recently observed series of past events, and entails reasoning about probable outcomes with these past ob- servations. Aspects that influence driving behavior comprise many factors, such as general driving physics, infrastructure geometry, traffic rules, weather and so on. Models that are used today are incapable of including many of these aspects. These deep learning models often rely heavily on the past driven trajectory as an information source for future prediction. Sparsely, some work has been done to include interaction between vehicles or some infrastructural features to the model. The lack of information regarding the driving scene can be seen as a missed opportunity, because it is a use- ful feature source to predict the motion of a vehicle. Especially when a map of the driving scene is available, reliable information regarding the road layout can be extracted. In this thesis, a model architecture is sought that is aware of the interaction between vehicles, and that un- derstands the geometry of the roads in the scene. Importantly, map information regarding the driving scene should be used as the primary source of information regarding the road geometry. First, a baseline deep learning model is constructed, that can generate predictions based on the past observed trajectory. To add interaction features to the model, a social pooling module is introduced. The social pooling method allows to efficiently include the driving behavior of other vehicles in the scene. To introduce reliable, map-based road information to the model, two novel methods are proposed. In the first, the predictions from a model are used to extract features in a map. These features describe the road scene around the predicted location, and are used to update these predictions. In the second method, the semantic map is only used to extract a road segment ahead of the vehicle. A road-RNN is introduced to con- struct features regarding the road segment, and an attention mechanism to determine what part of the road segment is relevant for the predictions. These modules are referred to as road-refinement and road-attention respectively. The importance of including both road geometry and interaction methods in the model is shown by con- structing 5 different models that vary in their road-geometric and interaction awareness. A baseline deep learning model is used and extended with a road-geometry module, an interaction module, a combination of the two, or none. To test the prediction capabilities of the models, they are trained on two different datasets. The first dataset, called i80, consists of trajectory recordings from a straight highway with dense traffic. The other dataset is a curved version of the i80, called i80c, where the trajectories and road are transformed to introduce road-geometric variations in the data. The prediction performances from the models clearly show the importance of both interaction-aware and road-geometry aware modeling. The road-refinement and road-attention models outperform the road-agnostic baseline model on the i80c data, showing better understanding of the road layout. Comparison between these models learns that the road-attention model is more effective for road-geometry inclusion. Additionally, the performance increase for interaction-aware models compared to the baseline clearly shows the importance of interaction in modeling on both datasets.The model that combines the interaction and road-attention modules shows outstanding prediction performance on the challenging i80c dataset compared to all other models. From the predictions it can be seen that the model understands the road layout ahead of the subject vehicle, as well as the interactive forces that are in play.

Underwater position estimation is challenging due to the absence of Global Navigation Satellite System (GNSS) signals. Underwater vehicles are typically equipped with a Doppler Velocity Log (DVL) that measures the velocity relative to the seafloor. Aside from the velocity, the DVL also measures the range of each of the four beams. When compared against a bathymetry height map, these measured ranges provide additional information enabling improving position estimates. Unfortunately, surveys often occur in areas where detailed bathymetry maps are unavailable. In these cases, bathymetry Simultaneous Localization and Mapping (SLAM) could be used to improve the position estimates compared to the velocity integration position. With SLAM, the map is being estimated during the mission while at the same time using the map for position determination. In this thesis, reduced rank Gaussian processes (GPs) are used as map representation for SLAM. The downside of regular GPs is a time complexity of O(n^3) , reduced rank GPs improve the computation performance. GPs provide Gaussian distributions at any point, leading to a neat integration with probabilistic SLAM algorithms. To the best of the author’s knowledge, this has not been used in bathymetry SLAM. This report investigates how reduced rank approximated GPs, representing the bathymetry, can be integrated into a SLAM algorithm to improve the position estimates of an underwater vehicle equipped with a DVL and low-quality gyroscopes. A squared exponential kernel is used as GPs model of the bathymetry. The reduced rank approximation is vital for real-time SLAM performance. This map representation is integrated with a Rao Blackwellized particle filter (RBPF) that estimates both the underwater vehicle’s trajectory and the bathymetry map. The SLAM algorithm is evaluated using data from an underwater vehicle operated at the surface such that a GNSS reference position is available. Experiments of the SLAM algorithm show a reduced position error compared to the GNSS reference. The resulting algorithm has a computation time of up to 30 times faster than the Autonomous Underwater Vehicle (AUV) collects data while improving position estimates. This concludes that the RBPF using reduced rank GPs is capable of onboard improved position estimation on underwater vehicles.

The gap between predicted brain age and chronological age could serve as biomarker for early-stage neurodegeneration and as potentially as a risk indicator for dementia. We assess the utility of this age gap as a risk biomarker for incident dementia in a general elderly population. The brain age is estimated from longitudinal brain magnetic resonance imaging (MRI) data using deep learning models. From the population-based Rotterdam Study, 5656 dementia-free and stroke-free participants (mean age 64.67±9.82, 54.73% women) underwent brain MRI at 1.5T, including three-dimensional (3D) T1-weighted sequence, between 2006 and 2015. All participants were followed for incident dementia until 2016. During 6.66±2.46 years of follow-up, 159 subjects developed dementia. The entire dataset was split into control (N=5497) and incident dementia (N=159) groups. We then built a convolutional neural network (CNN) model trained on the control group to predict brain age based on brain MRI. Model prediction performance was measured in mean absolute error MAE=4.45±3.59 years of brain age prediction. Reproducibility of prediction was tested using the intra-class correlation coefficient ICC=0.97 (95% confidence interval CI=0.96-0.98), computed on a subset of 80 subjects. Hereafter, we investigated the gap between model predicted age and chronological age of the incident dementia group data, compared to control group. Logistic regressions and Cox proportional hazards models were used to assess the association of the age gap with incident dementia, adjusted for years of education, ApoE4 allele carriership, GM and intracranial volume. These models showed that the age gap was significantly related to incident dementia (odds ratio OR=1.11 and 95% confidence intervals CI=1.05-1.16; hazard ratio HR=1.11 and 95% CI=1.06-1.15, respectively). Additionally, we computed the attention maps of CNN, which shows the importance of brain regions for age prediction. These were particularly focused on the amygdalae and hippocampi. We show that the gap between predicted and chronological brain age is a biomarker, associated with a risk of dementia development. This suggests that it can potentially be used as a complimentary biomarker for early-stage dementia risk screening.

To bring down the number of traffic accidents and increase people’s mobility companies, such as Robot Engineering Systems (RES) try to put automated vehicles on the road. RES is developing the WEpod, a shuttle capable of autonomously navigating through mixed traffic. This research has been done in cooperation with RES to improve the localization capabilities of the WEpod. The WEpod currently localizes using its GPS and lidar sensors. These have proven to be not accurate and reliable enough to safely navigate through traffic. Therefore, other methods of localization and mapping have been investigated. The primary method investigated in this research is monocular Simultaneous Localization and Mapping (SLAM). Based on literature and practical studies, ORB-SLAM has been chosen as the implementation of SLAM. Unfortunately, ORB-SLAM is unable to initialize the setup when applied on WEpod images. Literature has shown that this problem can be solved by adding depth information to the inputs of ORB-SLAM. Obtaining depth information for the WEpod images is not an arbitrary task. The sensors on the WEpod are not capable of creating the required dense depth-maps. A Convolutional Neural Network (CNN) could be used to create the depth-maps. This research investigates whether adding a depth-estimating CNN solves this initialization problem and increases the tracking accuracy of monocular ORB-SLAM. A well performing CNN is chosen and combined with ORB-SLAM. Images pass through the depth estimating CNN to obtain depth-maps. These depth-maps together with the original images are used in ORB-SLAM, keeping the whole setup monocular. ORB-SLAM with the CNN is first tested on the Kitti dataset. The Kitti dataset is used since monocular ORB- SLAM initializes on Kitti images and ground-truth depth-maps can be obtained for Kitti images. Monocular ORB-SLAM’s tracking accuracy has been compared to ORB-SLAM with ground-truth depth-maps and to ORB-SLAM with estimated depth-maps. This comparison shows that adding estimated depth-maps in- creases the tracking accuracy of ORB-SLAM, but not as much as the ground-truth depth images. The same setup is tested on WEpod images. The CNN is fine-tuned on 7481 Kitti images as well as on 642 WEpod images. The performance on WEpod images of both CNN versions are compared, and used in combination with ORB-SLAM. The CNN fine-tuned on the WEpod images does not perform well, missing details in the estimated depth-maps. However, this is enough to solve the initialization problem of ORB-SLAM. The combination of ORB-SLAM and the Kitti fine-tuned CNN has a better tracking accuracy than ORB-SLAM with the WEpod fine-tuned CNN. It has been shown that the initialization problem on WEpod images is solved as well as the tracking accuracy is increased. These results show that the initialization problem of monocular ORB-SLAM on WEpod images is solved by adding the CNN. This makes it applicable to improve the current localization methods on the WEpod. Using only this setup for localization on the WEpod is not possible yet, more research is necessary. Adding this setup to the current localization methods of the WEpod could increase the localization of the WEpod. This would make it safer for the WEpod to navigate through traffic. This research sets the next step into creating a fully autonomous vehicle which reduces traffic accidents and increases the mobility of people.

Recent advances in Artificial Intelligence and Computer Vision have been showed to be promising for automated land use classification of remotely sensed data. However, current state-of-the-art per-pixel segmentation networks fail to accurately capture geometrical and topological properties on land use segmentation, as these methods have inherently a lot of freedom. These geometrical and topological properties of land use structures are crucial for describing land usage on topographical maps, as their purpose is to present insight into topology and borders of land use structures. In order to preserve the geometrical and topological properties of land use structures, a novel segmentation method is introduced and tested on road structures in this thesis. Unlike current state-of-the-art segmentation networks, this new method performs the segmentation task by utilizing shape regression techniques as currently applied by state-of-the-art object detection networks. As modern object detection methods are only able to perform regression on simplistic shapes, and road structures generally describe complex shapes, a new topology preserving annotation generation method is introduced that subdivides a complex road structure into a set of oriented rectangular shapes. Since not many publicly available land use datasets contain both aerial images and per-pixel annotations, a new dataset based on aerial images and land use annotations, covering large areas of the Netherlands, is introduced as well. The results show that the novel segmentation method is capable of learning the newly introduced road structure representation, which preserves geometrical and topological properties. The connectedness property, however, is lost. The novel method does currently not outperform current state-of-the-art per-pixel segmentation networks, although several directions for future work are proposed to improve the segmentation performance of the shape regression based technique and preserve the connectedness property.

Our world is rapidly changing, leading to various technological achievements in diverse areas of expertise. Among the most evolving are autonomous robots, machines and vehicles, enormously extending human capabilities. While this trend became quite familiar for land-based vehicles, innovations in the underwater domain lag behind, mainly due to the harsh environmental conditions encountered. This in large contrast with worldwide growing needs for autonomous underwater solutions, like dredging. Nevertheless, for underwater vehicles becoming autonomously, various technological challenges must be overcome. The most essential one is finding a proper answer to the question; where in the underwater world am I? Autonomous robots are usually be able to operate in complex environments using external reference systems such as Global Positioning System (GPS) to locate themselves inside their environment. However, these are not accessible in underwater applications, since water strongly attenuates electromagnetic signals, notably GPS. Hence, various alternative methods for Simultaneous Localization And Mapping (SLAM) for underwater applications are employed, among which the method of anchoring inertial measurements on environmental landmarks, perceived with an exteroceptive Sonar. The ultimate goal of this procedure is to correct for errors in the inertial measurements, using the environmental perception available in the Sonar scans. Nevertheless, due to practical underwater issues, it still is not readily available and even barely investigated in open scientific research. This thesis aims at the development of an underwater localization algorithm, using onboard inertial sensors and Sonar. The overall system design consists of several individual software procedures, executing certain assignments, together ultimately solving for the localization task. The developed system was tested using ground truth in form of a real-world dataset obtained several years ago in an abandoned marina. This showed that most individual procedures were able to provide good results, while having a low computational complexity in relation to online operations. However, it is quite a challenge to obtain results accurate enough to properly correct for positional errors, by using the designed system. Although showing potential, it still is not entirely decent in terms of accuracy and computational burden. This is likely due to the sparsity of the extracted Sonar measurements. Data is lacking to further verify the system, hence several questions remain open regarding its universal applicability in case of different scenarios, dynamic environments and long trajectories. In this context, more in-depth research is needed into the algorithms that are influenced by the Sonar measurements, to increase the accuracy of the overall system, while gaining more insight in its computational behaviour. Additionally, also more real-world experiments are essential, to extensively verify the designed system. In conclusion, the results showed that it is possible to correct for inertial errors, using the system developed. Furthermore, it demonstrates that most procedures individually produce good results in real-time. Hence, this study can be seen as a positive step in the right direction, forming a basis for future research in solutions that are generically applicable in online real underwater world operations.

The aim of the thesis is to develop methods and algorithms for the development of a robust perception system that is capable of dealing with adverse weather conditions. Robust environmental perception is important in order to guarantee safety for the automated vehicle and the road users in the neighborhood. To create a robust perception system, a sensor setup should be selected with multiple sensing modalities. Commonly used sensing modalities in the field of intelligent vehicles are lidar, camera and radar sensors. This thesis addresses three subjects that are important for robust perception, namely sensor selection, extrinsic calibration and object tracking....@en