For a mobile robot to engage in exploration of a-priori unknown environments it must be able to identify locations which will yield new information when visited. This thesis presents two novel algorithms which attempt to answer the question of choosing where a robot should go next in a partially explored workspace. To begin we describe the process of acquiring highly accurate dense 3D data from a stereo camera. This approach combines techniques from a number of existing implementations and is demonstrated to be more accurate than a range of commercial offerings. Combined with state of the art visual odometry based pose estimation we can use these point clouds to drive exploration. The first exploration algorithm we present is an attempt to represent the three dimensional world as a continuous two dimensional surface. The surface is maintained as a planar graph structure in which vertices correspond to points in space as seen by the stereo camera. Edges connect vertices which have been seen as adjacent pixels in a stereo image pair, and have a weight equal to the Euclidean distance between the end points. Discontinuities in the input stereo data manifest as areas of the graph with high average edge weight, and by moving the camera to view such areas and merging the new scan with the existing graph, we push back the boundary of the explored workspace. Motivated by scaling and precision problems with the graph-based method, we present a second exploration algorithm based on continuum methods. We show that by solving Laplace’s equation over the freespace of the partially explored environment, we can guide exploration by following streamlines in the resulting vector field. Choosing appropriate boundary conditions ensures that these streamlines run parallel to obstacles and are guaranteed to lead to a frontier – a boundary between explored and unexplored space. Results are shown which demonstrate this method fully exploring three dimensional environments and outperforming oft-used information gain based approaches. We show how analysis of the potential field solution can be used to identify volumes of the workspace which have been fully explored, thus reducing future computation.

Scalable autonomy requires a robot to be able to recognize and contend with the uncertainty in its knowledge of the world stemming from its noisy sensors and actu- ators. The regions it chooses to explore, and the paths it takes to get there, must take this uncertainty into account. In this thesis we outline probabilistic approaches to represent that world; to construct plans over it; and to determine which part of it to explore next. We present a new technique to create probabilistic cost maps from overhead im- agery, taking into account the uncertainty in terrain classification and allowing for spatial variation in terrain cost. A probabilistic cost function combines the output of a multi-class classifier and a spatial probabilistic regressor to produce a probability density function over terrain for each grid cell in the map. The resultant cost map facilitates the discovery of not only the shortest path between points on the map, but also a distribution of likely paths between the points. These cost maps are used in a path planning technique which allows the user to trade-off the risk of returning a suboptimal path for substantial increases in search speed. We precompute a probability distribution which precisely approximates the true distance between any grid cell in the map and goal cell. This distribution under- pins a number of A* search heuristics we present, which can characterize and bound the risk we are prepared to take in gaining search efficiency while sacrificing optimal path length. Empirically, we report efficiency increases in excess of 70% over standard heuristic search methods. Finally, we present a global approach to the problem of robotic exploration, uti- lizing a hybrid of a topological data structure and an underlying metric mapping process. A ‘Gap Navigation Tree’ is used to motivate global target selection and occluded regions of the environment (‘gaps’) are tracked probabilistically using the metric map. In pursuing these gaps we are provided with goals to feed to the path planning process en route to a complete exploration of the environment. The combination of these three techniques represents a framework to facilitate robust exploration in a-priori unknown environments.

Thesis (M.Eng)--University of Wollongong, 2005. / Typescript. Includes bibliographical references: leaf 96-101.

<p> In this research project, a system is proposed to aid the visually impaired by providing partial contextual information of the surroundings using 360&deg; view camera combined with deep learning is proposed. The system uses a 360&deg; view camera with a mobile device to capture surrounding scene information and provide contextual information to the user in the form of audio. The system could also be used for other applications such as logo detection which visually impaired users can use for shopping assistance. </p><p> The scene information from the spherical camera feed is classified by identifying objects that contain contextual information of the scene. That is achieved using convolutional neural networks (CNN) for classification by leveraging CNN transfer learning properties using the pre-trained VGG-19 network. There are two challenges related to this paper, a classification and a segmentation challenge. As an initial prototype, we have experimented with general classes such restaurants, coffee shops and street signs. We have achieved a 92.8% classification accuracy in this research project.</p><p>

This thesis addresses information theoretic methods for control of one or several active cameras in the context of visual surveillance. This approach has two advantages. Firstly, any system dealing with real inputs must take into account noise in the measurements and the underlying system model. Secondly, the control of cameras in surveillance often has different, potentially conflicting objectives. Information theoretic metrics not only yield a way to assess the uncertainty in the current state estimate, they also provide means to choose the observation parameters that optimally reduce this uncertainty. The latter property allows comparison of sensing actions with respect to different objectives. This allows specification of a preference for objectives, where the generated control will fulfil these desired objectives accordingly. The thesis provides arguments for the utility of information theoretic approaches to control visual surveillance systems, by addressing the following objectives in particular: Firstly, how to choose a zoom setting of a single camera to optimally track a single target with a Kalman filter. Here emphasis is put on an arbitration between loss of track due to noise in the observation process, and information gain due to higher accuracy after successful observation. The resulting method adds a running average of the Kalman filter’s innovation to the observation noise, which not only ameliorates tracking performance in the case of unexpected target motions, but also provides a higher maximum zoom setting. The second major contribution of this thesis is a term that addresses exploration of the supervised area in an information theoretic manner. The reasoning behind this term is to model the appearance of new targets in the supervised environment, and use this as prior uncertainty about the occupancy of areas currently not under observation. Furthermore, this term uses the performance of an object detection method to gauge the information that observations of a single location can yield. Additionally, this thesis shows experimentally that a preference for control objectives can be set using a single scalar value. This linearly combines the objective functions of the two conflicting objectives of detection and exploration, and results in the desired control behaviour. The third contribution is an objective function that addresses classification methods. The thesis shows in detail how the information can be derived that can be gained from the classification of a single target, under consideration of its gaze direction. Quantitative and qualitative validation show the increase in performance when compared to standard methods.

This thesis describes a system which is able to track the pose of a hand-held camera as it moves around a scene. The system builds a 3D map of point landmarks in the world while tracking the pose of the camera relative to this map using a process called simultaneous localisation and mapping (SLAM). To achieve real-time performance, the map must be kept sparse, but rather than observing only the mapped landmarks like previous systems, observations are made of features across the entire image. Their deviation from the predicted epipolar geometry is used to further constrain the estimated inter-frame motion and so improves the overall accuracy. The consistency of the estimation is also improved by performing the estimation in a camera-centred coordinate frame. As with any such system, tracking failure is inevitable due to occlusion or sudden motion of the camera. A relocalisation module is presented which monitors the SLAM system, detects tracking failure, and then resumes tracking as soon as the conditions have improved. This relocalisation process is achieved using a new landmark recognition algorithm which is trained on-line and provides high recall and a fast recognition time. The relocalisation module can also be used to achieve place recognition for a loop closure detection system. By taking into account both the geometry and appearance information when determining a loop closure this module is able to outperform previous loop closure detection techniques used in monocular SLAM. After recognising an overlap, the map is then corrected using a novel trajectory alignment technique that is able to cope with the inherent scale ambiguity in monocular SLAM. By incorporating all of these new techniques, the system presented can perform as a robust augmented reality system, or act as a navigation tool which could be used on a mobile robot in indoor and outdoor environments.

No description available.

<p>"Anthropomorphic Attachments" undertakes an examination of the human as a highly nebulous, fluid, multiple, and often contradictory concept, one that cannot be approached directly or in isolation, but only in its constitutive relationality with the world. Rather than trying to find a way outside of the dualism between human and not-human, I take up the concept of anthropomorphization as a way to hypersaturate the question of the human. Within this hypersaturated field of inquiry, I focus on the specific anthropomorphic relationalities between human and humanoid technology. Focusing primarily on contemporary U.S. technologies and cultural forms, my dissertation looks at artificial intelligence and robotics in conversation with their cultural imaginaries in contemporary literature, science fiction, film, performance art, and video games, and in conversation with contemporary philosophies of the human, the posthuman, and technology. In reading these discourses as shaping, informing, and amplifying each other and the multiple conceptions of the human they articulate, "Anthropomorphic Attachments" attends to these multiple humans and the multiple morphologies by which anthropomorphic relationalities imagine and inscribe both humanoid technologies and the human itself.</p> / Dissertation

As a large generation ages, the collective financial and ethical responsibility to prevent egregious bodily harm through fall prevention and gait assistant exoskeleton devices increases. Risk for falls increases with age and the severity of the fall does as well. To support this elderly population, motorized exoskeletons can both increase stability as well as respond faster to fall scenarios, but current models do not more around the existing biological framework. Giving participants a range of motion in key pelvic areas can closely approximate synchronous rotation around the femoral head, while limiting an increase in their sagittal profile. Utilizing 3D printed components while incorporating existing orthic methods provide short production times on modular designs. Although primarily mechanically based, these designs consider electronic requirements and are capable for supporting movement for a 200 lbs. user at a brisk walking pace for 1 hour.

Object detection in autonomous driving systems is a critical functionality demanding precise implementation. However, existing solutions often rely on single-sensor systems, leading to insufficient data representation and diminished accuracy and speed in object detection. Our research addresses these challenges by integrating fusion-based object detection frameworks and augmentation techniques, incorporating both camera and LiDAR sensor data. Firstly, we introduce Sniffer Faster R-CNN (SFR-CNN), a novel fusion framework that enhances regional proposal generation by refining proposals from both LiDAR and image-based sources, thereby accelerating detection speed. Secondly, we propose Sniffer Faster R-CNN++, a late fusion network that integrates pre-trained single-modality detectors, improving detection accuracy while reducing computational complexity. Our approach employs enhanced proposal refinement algorithms to enhance the detection of distant objects, resulting in significant improvements in accuracy on challenging datasets like KITTI and nuScenes. Finally, to address the sparsity inherent in LiDAR data, we introduce a novel method that generates virtual LiDAR points from camera images, augmented with semantic labels to detect sparsely distributed and occluded objects effectively and integration of distance-aware data augmentation (DADA) further enhances the model's ability to recognize distant objects, leading to significant improvements in detection accuracy overall.