Recent developments in 3D Gaussian Splatting have significantly enhanced novel view synthesis, yet generating high-quality renderings from extreme novel viewpoints or partially observed regions remains challenging. Meanwhile, diffusion models exhibit strong generative capabilities, but their lack of awareness of specific scene information hinders accurate 3D reconstruction tasks. To address these limitations, we introduce GSFix3D, a novel framework that improves the visual fidelity in under-constrained regions by distilling prior knowledge from diffusion models into 3D representations, while preserving consistency with observed scene details. At its core is GSFixer, a latent diffusion model obtained via our customized finetuning protocol that can leverage both mesh and 3D Gaussians to adapt pretrained generative models to a variety of environments and artifact types from different reconstruction methods, enabling robust novel view repair for unseen camera poses. Moreover, we propose a random mask augmentation strategy that empowers GSFixer to plausibly inpaint missing regions. Experiments on challenging benchmarks demonstrate that our GSFix3D and GSFixer achieve state-of-the-art performance, requiring only minimal scene-specific fine-tuning on captured data. Realworld test further confirms its resilience to potential pose errors. Our code and data are publicly available: https://github.com/GSFix3D/GSFix3D.

Future robots are envisioned as versatile systems capable of performing a variety of household tasks. The big question remains, how can we bridge the embodiment gap while minimizing physical robot learning, which fundamentally does not scale well. We argue that learning from in-the-wild human videos offers a promising solution for robotic manipulation tasks, as vast amounts of relevant data already exist on the internet. In this work, we present VidBot, a framework enabling zero-shot robotic manipulation using learned 3D affordance from in-the-wild monocular RGB-only human videos. VidBot leverages a pipeline to extract explicit representations from them, namely 3D hand trajectories from videos, combining a depth foundation model with structure-from-motion techniques to reconstruct temporally consistent, metric-scale 3D affordance representations agnostic to embodiments. We introduce a coarse-to-fine affordance learning model that first identifies coarse actions from the pixel space and then generates fine-grained interaction trajectories with a diffusion model, conditioned on coarse actions and guided by test-time constraints for context-aware interaction planning, enabling substantial generalization to novel scenes and embodiments. Extensive experiments demonstrate the efficacy of VidBot, which significantly outperforms counterparts across 13 manipulation tasks in zero-shot settings and can be seamlessly deployed across robot systems in real-world environments. VidBot paves the way for leveraging everyday human videos to make robot learning more scalable.

We propose visual-inertial simultaneous localization and mapping that tightly couples sparse reprojection errors, inertial measurement unit pre-integrals, and relative pose factors with dense volumetric occupancy mapping. Hereby depth predictions from a deep neural network are fused in a fully probabilistic manner. Specifically, our method is rigorously uncertainty-aware: first, we use depth and uncertainty predictions from a deep network not only from the robot's stereo rig, but we further probabilistically fuse motion stereo that provides depth information across a range of baselines, therefore drastically increasing mapping accuracy. Next, predicted and fused depth uncertainty propagates not only into occupancy probabilities but also into alignment factors between generated dense submaps that enter the probabilistic non-linear least squares estimator. This submap representation offers globally consistent geometry at scale. Our method is thoroughly evaluated in two benchmark datasets, resulting in localization and mapping accuracy that exceeds the state of the art, while simultaneously offering volumetric occupancy directly usable for downstream robotic planning and control in real-time.

This paper proposes SOLVR, a unified pipeline for learning based LiDAR-Visual re-localisation which performs place recognition and 6-DoF registration across sensor modalities. We propose a strategy to align the input sensor modalities by leveraging stereo image streams to produce metric depth predictions with pose information, followed by fusing multiple scene views from a local window using a probabilistic occupancy framework to expand the limited field-of-view of the camera. Additionally, SOLVR adopts a flexible definition of what constitutes positive examples for different training losses, allowing us to simultaneously optimise place recognition and registration performance. Furthermore, we replace RANSAC with a registration function that weights a simple least-squares fitting with the estimated inlier likelihood of sparse keypoint correspondences, improving performance in scenarios with a low inlier ratio between the query and retrieved place. Our experiments on the KITTI and KITTI360 datasets show that SOLVR achieves state-of-the-art performance for LiDAR-Visual place recognition and registration, particularly improving registration accuracy over larger distances between the query and retrieved place.

Forests are vital to our ecosystems, acting as carbon sinks, climate stabilizers, biodiversity centers, and wood sources. Due to their scale, monitoring and managing forests takes a lot of work. Forestry robotics offers the potential for enabling efficient and sustainable foresting practices through automation. Despite increasing interest in this field, the scarcity of robotics datasets and benchmarks in forest environments is hampering progress in this domain. In this paper, we present a real-world, longitudinal dataset for forestry robotics that enables the development and comparison of approaches for various relevant applications, ranging from semantic interpretation to estimating traits relevant to forestry management. The dataset consists of multiple recordings of the same plots in a forest in Switzerland during three different growth periods. We recorded the data with a mobile 3D LiDAR scanning setup. Additionally, we provide semantic annotations of trees, shrubs, and ground, instance-level annotations of trees, as well as more fine-grained annotations of tree stems and crowns. Furthermore, we provide reference field measurements of traits relevant to forestry management for a subset of the trees. Together with the data, we also provide open-source baseline panoptic segmentation and tree trait estimation approaches to enable the community to bootstrap further research and simplify comparisons in this domain.

Autonomous exploration of unknown space is an essential component for the deployment of mobile robots in the real world. Safe navigation is crucial for all robotics applications and requires accurate and consistent maps of the robot's surroundings. To achieve full autonomy and allow deployment in a wide variety of environments, the robot must rely on onboard state estimation which is prone to drift over time. We propose a Micro Aerial Vehicle (MAV) exploration framework based on local submaps to allow retaining global consistency by applying loop-closure corrections to the relative submap poses. To enable large-scale exploration we efficiently compute global, environment-wide frontiers from the local submap frontiers and use a sampling-based next-best-view exploration planner. Our method seamlessly supports using either a LiDAR sensor or a depth camera, making it suitable for different kinds of MAV platforms. We perform comparative evaluations in simulation against a state-of-the-art submap-based exploration framework to showcase the efficiency and reconstruction quality of our approach. Finally, we demonstrate the applicability of our method to real-world MAVs, one equipped with a LiDAR and the other with a depth camera.

Autonomous navigation is needed for several robotics applications. In this paper we present an autonomous Micro Aerial Vehicle (MAV) system which purely relies on cost-effective and light-weight passive visual and inertial sensors to perform large-scale autonomous navigation in outdoor, unstructured and cluttered environments. We leverage visual-inertial simultaneous localization and mapping (VI-SLAM) for accurate MAV state estimates and couple it with a volumetric occupancy submapping system to achieve a scalable mapping framework which can be directly used for path planning. To ensure the safety of the MAV during navigation, we also propose a novel reference trajectory anchoring scheme that deforms the reference trajectory the MAV is tracking upon state updates from the VI-SLAM system in a consistent way, even upon large state updates due to loop-closures. We thoroughly validate our system in both real and simulated forest environments and at peak velocities up to 3 m/s – while not encountering a single collision or system failure. To the best of our knowledge, this is the first system which achieves this level of performance in such an unstructured environment using low-cost passive visual sensors and fully on-board computation, including VI-SLAM. Code available at https://github.com/ethz-mrl/mrl_navigation.

Loop closures are essential for correcting odometry drift and creating consistent maps, especially in the context of large-scale navigation. Current methods using dense point clouds for accurate place recognition do not scale well due to computationally expensive scan-to-scan comparisons. Alternative object-centric approaches are more efficient but often struggle with sensitivity to viewpoint variation. In this work, we introduce REGRACE, a novel approach that addresses these challenges of scalability and perspective difference in re-localization by using LiDAR-based submaps. We introduce rotation-invariant features for each labeled object and enhance them with neighborhood context through a graph neural network. To identify potential revisits, we employ a scalable bag-of-words approach, pooling one learned global feature per submap. Additionally, we define a revisit with geometrical consistency cues rather than embedding distance, allowing us to recognize far-away loop closures. Our evaluations demonstrate that REGRACE achieves similar results compared to state-ofthe-art place recognition and registration baselines while being twice as fast. Code and models are publicly available†.

Abstract While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezuma’s Revenge–one of the most challenging RL tasks in the Atari2600 game suite. We propose Int-HRL: Hierarchical RL with intention-based sub-goals that are inferred from human eye gaze. Our novel sub-goal extraction pipeline is fully automatic and replaces the need for manual sub-goal annotation by human experts. Our evaluations show that replacing hand-crafted sub-goals with automatically extracted intentions leads to an HRL agent that is significantly more sample efficient than previous methods.

To empower mobile robots with usable maps as well as highest state estimation accuracy and robustness, we present OKVIS2-X: a state-of-the-art multi-sensor Simultaneous Localization and Mapping (SLAM) system building dense volumetric occupancy maps, while scalable to large environments and operating in realtime. Our unified SLAM framework seamlessly integrates different sensor modalities: visual, inertial, measured or learned depth, LiDAR and Global Navigation Satellite System (GNSS) measurements. Unlike most state-of-the-art SLAM systems, we advocate using dense volumetric map representations when leveraging depth or range-sensing capabilities. We employ an efficient submapping strategy that allows our system to scale to large environments, showcased in sequences of up to 9 kilometers. OKVIS2-X enhances its accuracy and robustness by tightly-coupling the estimator and submaps through map alignment factors. Our system provides globally consistent maps, directly usable for autonomous navigation. To further improve the accuracy of OKVIS2-X, we also incorporate the option of performing online calibration of camera extrinsics. Our system achieves the highest trajectory accuracy in EuRoC against stateof-the-art alternatives, outperforms all competitors in the Hilti22 VI-only benchmark, while also proving competitive in the LiDAR version, and showcases state of the art accuracy in the diverse and large-scale sequences from the VBR dataset. Code available at: https://github.com/ethz-mrl/OKVIS2-X

We introduce DyNFL, a novel neural field-based approach for high-fidelity re-simulation of LiDAR scans in dynamic driving scenes. DyNFL processes LiDAR measurements from dynamic environments, accompanied by bounding boxes of moving objects, to construct an editable neural field. This field, comprising separately reconstructed static background and dynamic objects, allows users to modify viewpoints, adjust object positions, and seamlessly add or remove objects in the re-simulated scene. A key innovation of our method is the neural field composition technique, which effectively integrates reconstructed neural assets from various scenes through a ray drop test, accounting for occlusions and transparent surfaces. Our evaluation with both synthetic and real-world environments demonstrates that DyNFL substantially improves dynamic scene LiDAR simulation, offering a combination of physical fidelity and flexible editing capabilities. [project page]

Autonomous navigation is one of the key requirements for every potential application of mobile robots in the real-world. Besides high-accuracy state estimation, a suitable and globally consistent representation of the 3D environment is indispensable. We present a fully tightly-coupled LiDAR-Visual-Inertial SLAM system and 3D mapping framework applying local submapping strategies to achieve scalability to large-scale environments. A novel and correspondence-free, inherently probabilistic, formulation of LiDAR residuals is introduced, expressed only in terms of the occupancy fields and its respective gradients. These residuals can be added to a factor graph optimisation problem, either as frame-to-map factors for the live estimates or as map-to-map factors aligning the submaps with respect to one another. Experimental validation demonstrates that the approach achieves state-of-the-art pose accuracy and furthermore produces globally consistent volumetric occupancy submaps which can be directly used in downstream tasks such as navigation or exploration.

We present FuncGrasp, a framework that can infer dense yet reliable grasp configurations for unseen objects using one annotated object and single-view RGB-D observation via categorical priors. Unlike previous works that only transfer a set of grasp poses, FuncGrasp aims to transfer infinite configurations parameterized by an object-centric continuous grasp function across varying instances. To ease the transfer process, we propose Neural Surface Grasping Fields (NSGF), an effective neural representation defined on the surface to densely encode grasp configurations. Further, we exploit function-to-function transfer using sphere primitives to establish semantically meaningful categorical correspondences, which are learned in an unsupervised fashion without any expert knowledge. We showcase the effectiveness through extensive experiments in both simulators and the real world. Remarkably, our framework significantly outperforms several strong baseline methods in terms of density and reliability for generated grasps.

In this paper, we consider a Micro Aerial Vehicle (MAV) system teleoperated by a non-expert and introduce a perceptive safety filter that leverages Control Barrier Functions (CBFs) in conjunction with Visual-Inertial Simultaneous Localization and Mapping (VI-SLAM) and dense 3D occupancy mapping to guarantee safe navigation in complex and unstructured environments. Our system relies solely on onboard IMU measurements, stereo infrared images, and depth images and autonomously corrects teleoperated inputs when they are deemed unsafe. We define a point in 3D space as unsafe if it satisfies either of two conditions: (i) it is occupied by an obstacle, or (ii) it remains unmapped. At each time step, an occupancy map of the environment is updated by the VI-SLAM by fusing the onboard measurements, and a CBF is constructed to parameterize the (un)safe region in the 3D space. Given the CBF and state feedback from the VI-SLAM module, a safety filter computes a certified reference that best matches the teleoperation input while satisfying the safety constraint encoded by the CBF. In contrast to existing perception-based safe control frameworks, we directly close the perception-action loop and demonstrate the full capability of safe control in combination with real-time VI-SLAM without any external infrastructure or prior knowledge of the environment. We verify the efficacy of the perceptive safety filter in real-time MAV experiments using exclusively onboard sensing and computation and show that the teleoperated MAV is able to safely navigate through unknown environments despite arbitrary inputs sent by the teleoperator.

Terrestrial laser scanning (TLS) is the standard technique used to create accurate point clouds for digital forest inventories. However, the measurement process is demanding, requiring up to two days per hectare for data collection, significant data storage, as well as resource-heavy post-processing of 3D data. In this work, we present a real-time mapping and analysis system that enables online generation of forest inventories using mobile laser scanners that can be mounted e.g. on mobile robots. Given incrementally created and locally accurate submaps—data payloads—our approach extracts tree candidates using a custom, Voronoi-inspired clustering algorithm. Tree candidates are reconstructed using an algorithm based on the Hough transform, which enables robust modeling of the tree stem. Further, we explicitly incorporate the incremental nature of the data collection by consistently updating the database using a pose graph LiDAR SLAM system. This enables us to refine our estimates of the tree traits if an area is revisited later during a mission. We demonstrate competitive accuracy to TLS or manual measurements using laser scanners that we mounted on backpacks or mobile robots operating in conifer, broad-leaf and mixed forests. Our results achieve RMSE of 1.93 cm, a bias of 0.65 cm and a standard deviation of 1.81 cm (averaged across these sequences)—with no post-processing required after the mission is complete.

Current visual navigation systems often treat the environment as static, lacking the ability to adaptively interact with obstacles. This limitation leads to navigation failure when encountering unavoidable obstructions. In response, we introduce IN-Sight, a novel approach to self-supervised path planning, enabling more effective navigation strategies through interaction with obstacles. Utilizing RGB-D observations, IN-Sight calculates traversability scores and incorporates them into a semantic map, facilitating long-range path planning in complex, maze-like environments. To precisely navigate around obstacles, IN-Sight employs a local planner, trained imperatively on a differentiable costmap using representation learning techniques. The entire framework undergoes end-to-end training within the state-of-the-art photorealistic Intel SPEAR Simulator. We validate the effectiveness of IN-Sight through extensive benchmarking in a variety of simulated scenarios and ablation studies. Moreover, we demonstrate the system’s real-world applicability with zero-shot sim-to-real transfer, deploying our planner on the legged robot platform ANYmal, showcasing its practical potential for interactive navigation in real environments.

Abstract Visual reconstruction of fast non-rigid object deformations over time is a challenge for conventional frame-based cameras. In recent years, event cameras have gained significant attention due to their bio-inspired properties, such as high temporal resolution and high dynamic range. In this paper, we propose a novel approach for reconstructing such deformations using event measurements. Under the assumption of a static background, where all events are generated by the motion, our approach estimates the deformation of objects from events generated at the object contour in a probabilistic optimization framework. It associates events to mesh faces on the contour and maximizes the alignment of the line of sight through the event pixel with the associated face. In experiments on synthetic and real data of human body motion, we demonstrate the advantages of our method over state-of-the-art optimization and learning-based approaches for reconstructing the motion of human arms and hands. In addition, we propose an efficient event stream simulator to synthesize realistic event data for human motion.

Perceiving 3D structures from RGB images based on CAD model primitives can enable an effective, efficient 3D object-based representation of scenes. However, current approaches rely on supervision from expensive yet imperfect annotations of CAD models associated with real images, and encounter challenges due to the inherent ambiguities in the task - both in depth-scale ambiguity in monocular perception, as well as inexact matches of CAD database models to real observations. We thus propose DiffCAD, the first weakly-supervised probabilistic approach to CAD retrieval and alignment from an RGB image. We learn a probabilistic model through diffusion, modeling likely distributions of shape, pose, and scale of CAD objects in an image. This enables multi-hypothesis generation of different plausible CAD reconstructions, requiring only a few hypotheses to characterize ambiguities in depth/scale and inexact shape matches. Our approach is trained only on synthetic data, leveraging monocular depth and mask estimates to enable robust zero-shot adaptation to various real target domains. Despite being trained solely on synthetic data, our multi-hypothesis approach can even surpass the supervised state-of-the-art on the Scan2CAD dataset by 5.9% with 8 hypotheses.

Exploration of unknown space with an autonomous mobile robot is a well-studied problem. In this work we broaden the scope of exploration, moving beyond the pure geometric goal of uncovering as much free space as possible. We believe that for many practical applications, exploration should be contextualised with semantic and object-level understanding of the environment for task-specific exploration. Here, we study the task of bothfinding specific objects in unknown space as well as reconstructing them to a target level of detail. We therefore extend our environment reconstruction to not only consist of a background map, but also object-level and semantically fused submaps. Importantly, we adapt our previous objective function of uncovering as much free space as possible in as little time as possible with two additional elements: first, we require a maximum observation distance of background surfaces to ensure target objects are not missed by image-based detectors because they are too small to be detected. Second, we require an even smaller maximum distance to the found objects in order to reconstruct them with the desired accuracy. We further created a Micro Aerial Vehicle (MAV) semantic exploration simulator based on Habitat in order to quantitatively demonstrate how our framework can be used to efficiently find specific objects as part of exploration. Finally, we showcase this capability can be deployed in real-world scenes involving our drone equipped with an Intel RealSense D455 RGB-D camera.

Visual-Inertial (VI) sensors are popular in robotics, self-driving vehicles, and augmented and virtual reality applications. In order to use them for any computer vision or state-estimation task, a good calibration is essential. However, collecting informative calibration data in order to render the calibration parameters observable is not trivial for a non-expert. In this work, we introduce a novel VI calibration pipeline that guides a non-expert with the use of a graphical user interface and information theory in collecting informative calibration data with Next-Best-View and Next-Best-Trajectory suggestions to calibrate the intrinsics, extrinsics, and temporal misalignment of a VI sensor. We show through experiments that our method is faster, more accurate, and more consistent than state-of-the-art alternatives. Specifically, we show how calibrations with our proposed method achieve higher accuracy estimation results when used by state-of-the-art VI Odometry as well as VI-SLAM approaches. The source code of our software can be found on: https://github.com/chutsu/yac.

Robust, fast, and accurate human state - 6D pose and posture - estimation remains a challenging problem. For real-world applications, the ability to estimate the human state in realtime is highly desirable. In this paper, we present BodySLAM++, a fast, efficient, and accurate human and camera state estimation framework relying on visual-inertial data. BodySLAM++ extends an existing visual-inertial state estimation framework, OKVIS2, to solve the dual task of estimating camera and human states simultaneously. Our system improves the accuracy of both human and camera state estimation with respect to baseline methods by 26 % and 12%, respectively, and achieves realtime performance at 15+ frames per second on an Intel i7-model CPU. Experiments were conducted on a custom dataset containing both ground truth human and camera poses collected with an indoor motion tracking system.

An accurate and uncertainty-aware 3D human body pose estimation is key to enabling truly safe but efficient human-robot interactions. Current uncertainty-aware methods in 3D human pose estimation are limited to predicting the uncertainty of the body posture, while effectively neglecting the body shape and root pose. In this work, we present GloPro, which to the best of our knowledge the first framework to predict an uncertainty distribution of a 3D body mesh including its shape, pose, and root pose, by efficiently fusing visual clues with a learned motion model. We demonstrate that it vastly outperforms state-of-the-art methods in terms of human trajectory accuracy in a world coordinate system (even in the presence of severe occlusions), yields consistent uncertainty distributions, and can run in real-time. Our code will be released upon acceptance at https:$I$Igithub. coml smartroboticslab/GloPro.

We present a real-time visual-inertial dense mapping method capable of performing incremental 3D mesh reconstruction with high quality using only sequential monocular images and inertial measurement unit (IMU) readings. 6-DoF camera poses are estimated by a robust feature-based visual-inertial odometry (VIO), which also generates noisy sparse 3D map points as a by-product. We propose a sparse point aided multi-view stereo neural network (SPA-MVSNet) that can effectively leverage the informative but noisy sparse points from the VIO system. The sparse depth from VIO is firstly completed by a single-view depth completion network. This dense depth map, although naturally limited in accuracy, is then used as a prior to guide our MVS network in the cost volume generation and regularization for accurate dense depth prediction. Predicted depth maps of keyframe images by the MVS network are incrementally fused into a global map using TSDF-Fusion. We extensively evaluate both the proposed SPA-MVSNet and the entire dense mapping system on several public datasets as well as our own dataset, demonstrating the system’s impressive generalization capabilities and its ability to deliver high-quality 3D reconstruction online. Our proposed dense mapping system achieves a 39.7% improvement in F-score over existing systems when evaluated on the challenging scenarios of the EuRoC dataset.

We propose a keypoint-based object-level SLAM framework that can provide globally consistent 6DoF pose estimates for symmetric and asymmetric objects alike. To the best of our knowledge, our system is among the first to utilize the camera pose information from SLAM to provide prior knowledge for tracking keypoints on symmetric objects - ensuring that new measurements are consistent with the current 3D scene. Moreover, our semantic key-point network is trained to predict the Gaussian covariance for the keypoints that captures the true error of the prediction, and thus is not only useful as a weight for the residuals in the system's optimization problems, but also as a means to detect harmful statistical outliers without choosing a manual threshold. Experiments show that our method provides competitive performance to the state of the art in 6DoF object pose estimation, and at a real-time speed. Our code, pre-trained models, and keypoint labels are available https://github.com/rpng/suo_slam.

In this paper, we propose a novel object-level mapping system that can simultaneously segment, track, and reconstruct objects in dynamic scenes. It can further predict and complete their full geometries by conditioning on reconstructions from depth inputs and a category-level shape prior with the aim that completed object geometry leads to better object reconstruction and tracking accuracy. For each incoming RGB-D frame, we perform instance segmentation to detect objects and build data associations between the detection and the existing object maps. A new object map will be created for each unmatched detection. For each matched object, we jointly optimise its pose and latent geometry representations using geometric residual and differential rendering residual towards its shape prior and completed geometry. Our approach shows better tracking and reconstruction performance compared to methods using traditional volumetric mapping or learned shape prior approaches. We evaluate its effectiveness by quantitatively and qualitatively testing it in both synthetic and real-world sequences.

Robotic applications are continuously striving towards higher levels of autonomy. To achieve that goal, a highly robust and accurate state estimation is indispensable. Combining visual and inertial sensor modalities has proven to yield accurate and locally consistent results in short-term applications. Unfortunately, visual-inertial state estimators suffer from the accumulation of drift for long-term trajectories. To eliminate this drift, global measurements can be fused into the state estimation pipeline. The most known and widely available source of global measurements is the Global Positioning System (GPS). In this paper, we propose a novel approach that fully combines stereo Visual-Inertial Simultaneous Localisation and Mapping (SLAM), including visual loop closures, with the fusion of global sensor modalities in a tightly-coupled and optimisation-based framework. Incorporating measurement uncertainties, we provide a robust criterion to solve the global reference frame initialisation problem. Furthermore, we propose a loop-closure-like optimisation scheme to compensate drift accumulated during outages in receiving GPS signals. Experimental validation on datasets and in a real-world experiment demonstrates the robustness of our approach to GPS dropouts as well as its capability to estimate highly accurate and globally consistent trajectories compared to existing state-of-the-art methods.

In this paper, we present a tightly-coupled visual-inertial object-level multi-instance dynamic SLAM system. Even in extremely dynamic scenes, it can robustly optimise for the camera pose, velocity, IMU biases and build a dense 3D reconstruction object-level map of the environment. Our system can robustly track and reconstruct the geometries of arbitrary objects, their semantics and motion by incrementally fusing associated colour, depth, semantic, and foreground object probabilities into each object model thanks to its robust sensor and object tracking. In addition, when an object is lost or moved outside the camera field of view, our system can reliably recover its pose upon re-observation. We demonstrate the robustness and accuracy of our method by quantitatively and qualitatively testing it in real-world data sequences.

Event cameras are bio-inspired sensors that differ from conventional frame cameras: Instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes, and output a stream of events that encode the time, location and sign of the brightness changes. Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of μs), very high dynamic range (140 dB versus 60 dB), low power consumption, and high pixel bandwidth (on the order of kHz) resulting in reduced motion blur. Hence, event cameras have a large potential for robotics and computer vision in challenging scenarios for traditional cameras, such as low-latency, high speed, and high dynamic range. However, novel methods are required to process the unconventional output of these sensors in order to unlock their potential. This paper provides a comprehensive overview of the emerging field of event-based vision, with a focus on the applications and the algorithms developed to unlock the outstanding properties of event cameras. We present event cameras from their working principle, the actual sensors that are available and the tasks that they have been used for, from low-level vision (feature detection and tracking, optic flow, etc.) to high-level vision (reconstruction, segmentation, recognition). We also discuss the techniques developed to process events, including learning-based techniques, as well as specialized processors for these novel sensors, such as spiking neural networks. Additionally, we highlight the challenges that remain to be tackled and the opportunities that lie ahead in the search for a more efficient, bio-inspired way for machines to perceive and interact with the world.

By estimating 3D shape and instances from a single view, we can capture information about an environment quickly, without the need for comprehensive scanning and multi-view fusion. Solving this task for composite scenes (such as object stacks) is challenging: occluded areas are not only ambiguous in shape but also in instance segmentation; multiple decompositions could be valid. We observe that physics constrains decomposition as well as shape in occluded regions and hypothesise that a latent space learned from scenes built under physics simulation can serve as a prior to better predict shape and instances in occluded regions. To this end we propose SIMstack, a depth-conditioned Variational Auto-Encoder (VAE), trained on a dataset of objects stacked under physics simulation. We formulate instance segmentation as a centre voting task which allows for class-agnostic detection and doesn’t require setting the maximum number of objects in the scene. At test time, our model can generate 3D shape and instance segmentation from a single depth view, probabilistically sampling proposals for the occluded region from the learned latent space. Our method has practical applications in providing robots some of the ability humans have to make rapid intuitive inferences of partially observed scenes. We demonstrate an application for precise (non-disruptive) object grasping of unknown objects from a single depth view.

Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are appealing as they do not require prior training data, but the same fully self-supervised approach is not possible for semantics because labels are human-defined properties.We extend neural radiance fields (NeRF) to jointly encode semantics with appearance and geometry, so that complete and accurate 2D semantic labels can be achieved using a small amount of in-place annotations specific to the scene. The intrinsic multi-view consistency and smoothness of NeRF benefit semantics by enabling sparse labels to efficiently propagate. We show the benefit of this approach when labels are either sparse or very noisy in room-scale scenes. We demonstrate its advantageous properties in various interesting applications such as an efficient scene labelling tool, novel semantic view synthesis, label denoising, super-resolution, label interpolation and multi-view semantic label fusion in visual semantic mapping systems.

We present an efficient, elastic 3D LiDAR reconstruction framework which can reconstruct up to maximum Li-DAR ranges (60 m) at multiple frames per second, thus enabling robot exploration in large-scale environments. Our approach only requires a CPU. We focus on three main challenges of large-scale reconstruction: integration of long-range LiDAR scans at high frequency, the capacity to deform the reconstruction after loop closures are detected, and scalability for long-duration exploration. Our system extends upon a state-of-the-art efficient RGB-D volumetric reconstruction technique, called supereight, to support LiDAR scans and a newly developed submapping technique to allow for dynamic correction of the 3D reconstruction. We then introduce a novel pose graph clustering and submap fusion feature to make the proposed system more scalable for large environments. We evaluate the performance using two public datasets including outdoor exploration with a handheld device and a drone, and with a mobile robot exploring an underground room network. Experimental results demonstrate that our system can reconstruct at 3 Hz with 60 m sensor range and ~5 cm resolution, while state-of-the-art approaches can only reconstruct to 25 cm resolution or 20 m range at the same frequency.

Exploration and collision-free navigation through an unknown environment is a fundamental task for autonomous robots. In this paper, a novel exploration strategy for Micro Aerial Vehicles (MAVs) is presented. The goal of the exploration strategy is the reduction of map entropy regarding occupancy probabilities, which is reflected in a utility function to be maximised. We achieve fast and efficient exploration performance with tight integration between our octree-based occupancy mapping approach, frontier extraction, and motion planning-as a hybrid between frontier-based and sampling-based exploration methods. The computationally expensive frontier clustering employed in classic frontier-based exploration is avoided by exploiting the implicit grouping of frontier voxels in the underlying octree map representation. Candidate next-views are sampled from the map frontiers and are evaluated using a utility function combining map entropy and travel time, where the former is computed efficiently using sparse raycasting. These optimisations along with the targeted exploration of frontier-based methods result in a fast and computationally efficient exploration planner. The proposed method is evaluated using both simulated and real-world experiments, demonstrating clear advantages over state-of-the-art approaches.

The best way to combine the results of deep learning with standard 3D reconstruction pipelines remains an open problem. While systems that pass the output of traditional multi-view stereo approaches to a network for regularisation or refinement currently seem to get the best results, it may be preferable to treat deep neural networks as separate components whose results can be probabilistically fused into geometry- based systems. Unfortunately, the error models required to do this type of fusion are not well understood, with many different approaches being put forward. Recently, a few systems have achieved good results by having their networks predict probability distributions rather than single values. We propose using this approach to fuse a learned single-view depth prior into a standard 3D reconstruction system. Our system is capable of incrementally producing dense depth maps for a set of keyframes. We train a deep neural network to predict discrete, nonparametric probability distributions for the depth of each pixel from a single image. We then fuse this "probability volume" with another probability volume based on the photometric consistency between subsequent frames and the keyframe image. We argue that combining the probability volumes from these two sources will result in a volume that is better conditioned. To extract depth maps from the volume, we minimise a cost function that includes a regularisation term based on network predicted surface normals and occlusion boundaries. Through a series of experiments, we demonstrate that each of these components improves the overall performance of the system.

Safe and precise reference tracking is a crucial characteristic of Micro Aerial Vehicles (MAVs) that have to operate under the influence of external disturbances in cluttered environments. In this paper, we present a Nonlinear Model Predictive Control (NMPC) that exploits the fully physics based non-linear dynamics of the system. We furthermore show how the moment and thrust control inputs can be transformed into feasible actuator commands. In order to guarantee safe operation despite potential loss of a motor under which we show our system keeps operating safely, we developed an Extended Kalman Filter (EKF) based motor failure identification algorithm. We verify the effectiveness of the developed pipeline in flight experiments with and without motor failures.

We introduce a novel volumetric SLAM pipeline for the integration and rendering of depth images at an adaptive level of detail. Our core contribution is a fusion algorithm which dynamically selects the appropriate integration scale based on the effective sensor resolution given the distance from the observed scene, addressing aliasing issues, reconstruction quality, and efficiency simultaneously. We implement our approach using an efficient octree structure which supports multi-resolution rendering allowing for online frame-to-model alignment. Our qualitative and quantitative experiments demonstrate significantly improved reconstruction quality and up to six-fold execution time speed-ups compared to single resolution grids.

Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities. However, while there has been much work on the correct formulation for geometrical estimation, state-of-the-art systems usually rely on simple semantic representations which store and update independent label estimates for each surface element (depth pixels, surfels, or voxels). Spatial correlation is discarded, and fused label maps are incoherent and noisy. We introduce a new compact and optimisable semantic representation by training a variational auto-encoder that is conditioned on a colour image. Using this learned latent space, we can tackle semantic label fusion by jointly optimising the low-dimenional codes associated with each of a set of overlapping images, producing consistent fused label maps which preserve spatial correlation. We also show how this approach can be used within a monocular keyframe based semantic mapping system where a similar code approach is used for geometry. The probabilistic formulation allows a flexible formulation where we can jointly estimate motion, geometry and semantics in a unified optimisation.

Estimating motion and surrounding geometry of a moving camera remains a challenging inference problem. From an information theoretic point of view, estimates should get better as more information is included, such as is done in dense SLAM, but this is strongly dependent on the validity of the underlying models. In the present paper, we use triangular meshes as both compact and dense geometry representation. To allow for simple and fast usage, we propose a view-based formulation for which we predict the in-plane vertex coordinates directly from images and then employ the remaining vertex depth components as free variables. Flexible and continuous integration of information is achieved through the use of a residual based inference technique. This so-called factor graph encodes all information as mapping from free variables to residuals, the squared sum of which is minimised during inference. We propose the use of different types of learnable residuals, which are trained end-to-end to increase their suitability as information bearing models and to enable accurate and reliable estimation. Detailed evaluation of all components is provided on both synthetic and real data which confirms the practicability of the presented approach.

Detailed 3D reconstruction is an important challenge with application to robotics, augmented and virtual reality, which has seen impressive progress throughout the past years. Advancements were driven by the availability of depth cameras (RGB-D), as well as increased compute power, e.g.\ in the form of GPUs -- but also thanks to inclusion of machine learning in the process. Here, we propose X-Section, an RGB-D 3D reconstruction approach that leverages deep learning to make object-level predictions about thicknesses that can be readily integrated into a volumetric multi-view fusion process, where we propose an extension to the popular KinectFusion approach. In essence, our method allows to complete shape in general indoor scenes behind what is sensed by the RGB-D camera, which may be crucial e.g.\ for robotic manipulation tasks or efficient scene exploration. Predicting object thicknesses rather than volumes allows us to work with comparably high spatial resolution without exploding memory and training data requirements on the employed Convolutional Neural Networks. In a series of qualitative and quantitative evaluations, we demonstrate how we accurately predict object thickness and reconstruct general 3D scenes containing multiple objects.

Dense visual SLAM methods are able to estimate the 3D structure of an environment and locate the observer within them. They estimate the motion of a camera by matching visual information between consecutive frames, and are thus prone to failure under extreme motion conditions or when observing texture-poor regions. The integration of additional sensor modalities has shown great promise in improving the robustness and accuracy of such SLAM systems. In contrast to the popular use of inertial measurements we propose to tightly-couple a dense RGB-D SLAM system with kinematic and odometry measurements from a wheeled robot equipped with a manipulator. The system has real-time capability while running on GPU. It optimizes the camera pose by considering the geometric alignment of the map as well as kinematic and odometric data from the robot. Through experimentation in the real-world, we show that the system is more robust to challenging trajectories featuring fast and loopy motion than the equivalent system without the additional kinematic and odometric knowledge, whilst retaining comparable performance to the equivalent RGB-D only system on easy trajectories.

While the keypoint-based maps created by sparse monocular Simultaneous Localisation and Mapping (SLAM) systems are useful for camera tracking, dense 3D reconstructions may be desired for many robotic tasks. Solutions involving depth cameras are limited in range and to indoor spaces, and dense reconstruction systems based on minimising the photometric error between frames are typically poorly constrained and suffer from scale ambiguity. To address these issues, we propose a 3D reconstruction system that leverages the output of a Convolutional Neural Network (CNN) to produce fully dense depth maps for keyframes that include metric scale. Our system, DeepFusion, is capable of producing real-time dense reconstructions on a GPU. It fuses the output of a semi-dense multiview stereo algorithm with the depth and gradient predictions of a CNN in a probabilistic fashion, using learned uncertainties produced by the network. While the network only needs to be run once per keyframe, we are able to optimise for the depth map with each new frame so as to constantly make use of new geometric constraints. Based on its performance on synthetic and real world datasets, we demonstrate that DeepFusion is capable of performing at least as well as other comparable systems.

Benchmarking mapping and motion estimation algorithms is established practice in robotics and computer vision. As the diversity of datasets increases, in terms of the trajectories, models, and scenes, it becomes a challenge to select datasets for a given benchmarking purpose. Inspired by the Wasserstein distance, this paper addresses this concern by developing novel metrics to evaluate trajectories and the environments without relying on any SLAM or motion estimation algorithm. The metrics, which so far have been missing in the research community, can be applied to the plethora of datasets that exist. Additionally, to improve the robotics SLAM benchmarking, the paper presents a new dataset for visual localization and mapping algorithms. A broad range of real-world trajectories is used in very high-quality scenes and a rendering framework to create a set of synthetic datasets with ground-truth trajectory and dense map which are representative of key SLAM applications such as virtual reality (VR), micro aerial vehicle (MAV) flight, and ground robotics.

We propose a new multi-instance dynamic RGB-D SLAM system using an object-level octree-based volumetric representation. It can provide robust camera tracking in dynamic environments and at the same time, continuously estimate geometric, semantic, and motion properties for arbitrary objects in the scene. For each incoming frame, we perform instance segmentation to detect objects and refine mask boundaries using geometric and motion information. Meanwhile, we estimate the pose of each existing moving object using an object-oriented tracking method and robustly track the camera pose against the static scene. Based on the estimated camera pose and object poses, we associate segmented masks with existing models and incrementally fuse corresponding colour, depth, semantic, and foreground object probabilities into each object model. In contrast to existing approaches, our system is the first system to generate an object-level dynamic volumetric map from a single RGB-D camera, which can be used directly for robotic tasks. Our method can run at 2-3 Hz on a CPU, excluding the instance segmentation part. We demonstrate its effectiveness by quantitatively and qualitatively testing it on both synthetic and real-world sequences.

We propose an online object-level SLAM system which builds a persistent and accurate 3D graph map of arbitrary reconstructed objects. As an RGB-D camera browses a cluttered indoor scene, Mask-RCNN instance segmentations are used to initialise compact per-object Truncated Signed Distance Function (TSDF) reconstructions with object size-dependent resolutions and a novel 3D foreground mask. Reconstructed objects are stored in an optimisable 6DoF pose graph which is our only persistent map representation. Objects are incrementally refined via depth fusion, and are used for tracking, relocalisation and loop closure detection. Loop closures cause adjustments in the relative pose estimates of object instances, but no intra-object warping. Each object also carries semantic information which is refined over time and an existence probability to account for spurious instance predictions. We demonstrate our approach on a hand-held RGB-D sequence from a cluttered office scene with a large number and variety of object instances, highlighting how the system closes loops and makes good use of existing objects on repeated loops. We quantitatively evaluate the trajectory error of our system against a baseline approach on the RGB-D SLAM benchmark, and qualitatively compare reconstruction quality of discovered objects on the YCB video dataset. Performance evaluation shows our approach is highly memory efficient and runs online at 4-8Hz (excluding relocalisation) despite not being optimised at the software level.

The representation of geometry in real-time 3D perception systems continues to be a critical research issue. Dense maps capture complete surface shape and can be augmented with semantic labels, but their high dimensionality makes them computationally costly to store and process, and unsuitable for rigorous probabilistic inference. Sparse feature-based representations avoid these problems, but capture only partial scene information and are mainly useful for localisation only. We present a new compact but dense representation of scene geometry which is conditioned on the intensity data from a single image and generated from a code consisting of a small number of parameters. We are inspired by work both on learned depth from images, and auto-encoders. Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency. Conditioning the depth map on the image allows the code to only represent aspects of the local geometry which cannot directly be predicted from the image. We explain how to learn our code representation, and demonstrate its advantageous properties in monocular SLAM.

We introduce SceneNet RGB-D, a dataset providing pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection. It also provides perfect camera poses and depth data, allowing investigation into geometric computer vision problems such as optical flow, camera pose estimation, and 3D scene labelling tasks. Random sampling permits virtually unlimited scene configurations, and here we provide 5M rendered RGB-D images from 16K randomly generated 3D trajectories in synthetic layouts, with random but physically simulated object configurations. We compare the semantic segmentation performance of network weights produced from pretraining on RGB images from our dataset against generic VGG-16 ImageNet weights. After fine-tuning on the SUN RGB-D and NYUv2 real-world datasets we find in both cases that the synthetically pre-trained network outperforms the VGG-16 weights. When synthetic pre-training includes a depth channel (something ImageNet cannot natively provide) the performance is greater still. This suggests that large-scale high-quality synthetic RGB datasets with task-specific labels can be more useful for pretraining than real-world generic pre-training such as ImageNet. We host the dataset at http://robotvault. bitbucket.io/scenenet-rgbd.html.

A new generation of practical, low-cost indoor robots is now using wide-angle cameras to aid navigation, but usually this is limited to position estimation via sparse feature-based SLAM. Such robots usually have little global sense of the dimensions, demarcation or identities of the rooms they are in, information which would be very useful to enable behaviour with much more high level intelligence. In this paper we show that we can augment an omni-directional SLAM pipeline with straightforward dense stereo estimation and simple and robust room model fitting to obtain rapid and reliable estimation of the global shape of typical rooms from short robot motions. We have tested our method extensively in real homes, offices and on synthetic data. We also give examples of how our method can extend to making composite maps of larger rooms, and detecting room transitions.

Ever more robust, accurate and detailed mapping using visual sensing has proven to be an enabling factor for mobile robots across a wide variety of applications. For the next level of robot intelligence and intuitive user interaction, maps need to extend beyond geometry and appearance - they need to contain semantics. We address this challenge by combining Convolutional Neural Networks (CNNs) and a state-of-the-art dense Simultaneous Localization and Mapping (SLAM) system, ElasticFusion, which provides long-term dense correspondences between frames of indoor RGB-D video even during loopy scanning trajectories. These correspondences allow the CNN's semantic predictions from multiple view points to be probabilistically fused into a map. This not only produces a useful semantic 3D map, but we also show on the NYUv2 dataset that fusing multiple predictions leads to an improvement even in the 2D semantic labelling over baseline single frame predictions. We also show that for a smaller reconstruction dataset with larger variation in prediction viewpoint, the improvement over single frame segmentation increases. Our system is efficient enough to allow real-time interactive use at frame-rates of ≈25Hz.

Real-time monocular SLAM is increasingly mature and entering commercial products. However, there is a divide between two techniques providing similar performance. Despite the rise of ‘dense’ and ‘semi-dense’ methods which use large proportions of the pixels in a video stream to estimate motion and structure via alternating estimation, they have not eradicated feature-based methods which use a significantly smaller amount of image information from keypoints and retain a more rigorous joint estimation framework. Dense methods provide more complete scene information, but in this paper we focus on how the amount of information and different optimisation methods affect the accuracy of local motion estimation (monocular visual odometry). This topic becomes particularly relevant after the recent results from a direct sparse system. We propose a new method for fairly comparing the accuracy of SLAM frontends in a common setting. We suggest computational cost models for an overall comparison which indicates that there is relative parity between the approaches at the settings allowed by current serial processors when evaluated under equal conditions.

While dense visual SLAM methods are capable of estimating dense reconstructions of the environment, they suffer from a lack of robustness in their tracking step, especially when the optimisation is poorly initialised. Sparse visual SLAM systems have attained high levels of accuracy and robustness through the inclusion of inertial measurements in a tightly-coupled fusion. Inspired by this performance, we propose the first tightly-coupled dense RGB-D-inertial SLAM system. Our system has real-time capability while running on a GPU. It jointly optimises for the camera pose, velocity, IMU biases and gravity direction while building up a globally consistent, fully dense surfel-based 3D reconstruction of the environment. Through a series of experiments on both synthetic and real world datasets, we show that our dense visual-inertial SLAM system is more robust to fast motions and periods of low texture and low geometric variation than a related RGB-D-only SLAM system.

We present a scalable, real-time capable method for robust surface reconstruction that explicitly handles multiple scales. As a monocular camera browses a scene, our algorithm processes images as they arrive and incrementally builds a detailed surface model.While most of the existing reconstruction approaches rely on volumetric or point-cloud representations of the environment, we perform depth-map and colour fusion directly into a multi-resolution triangular mesh that can be adaptively tessellated using the concept of Dynamic Level of Detail. Our method relies on least-squares optimisation, which enables a probabilistically sound and principled formulation of the fusion algorithm.We demonstrate that our method is capable of obtaining high quality, close-up reconstruction, as well as capturing overall scene geometry, while being memory and computationally efficient.

Event cameras are bio-inspired vision sensors which mimic retinas to measure per-pixel intensity change rather than outputting an actual intensity image. This proposed paradigm shift away from traditional frame cameras offers significant potential advantages: namely avoiding high data rates, dynamic range limitations and motion blur. Unfortunately, however, established computer vision algorithms may not at all be applied directly to event cameras. Methods proposed so far to reconstruct images, estimate optical flow, track a camera and reconstruct a scene come with severe restrictions on the environment or on the motion of the camera, e.g. allowing only rotation. Here, we propose, to the best of our knowledge, the first algorithm to simultaneously recover the motion field and brightness image, while the camera undergoes a generic motion through any scene. Our approach employs minimisation of a cost function that contains the asynchronous event data as well as spatial and temporal regularisation within a sliding window time interval. Our implementation relies on GPU optimisation and runs in near real-time. In a series of examples, we demonstrate the successful operation of our framework, including in situations where conventional cameras suffer from dynamic range limitations and motion blur.

A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary camera trajectories, without requiring explicit training over the potentially infinite number of camera paths and lengths. Building these pairwise relationships then naturally extends to the next-best-view problem in an active recognition framework. To achieve this, we train a second Convolutional Neural Network to map directly from an observed image to next viewpoint. Finally, we incorporate this into a trajectory optimisation task, whereby the best recognition confidence is sought for a given trajectory length. We present state-of-the-art results in both guided and unguided multi-view recognition on the ModelNet dataset, and show how our method can be used with depth images, greyscale images, or both.

This paper presents a new method for parallel-jaw grasping of isolated objects from depth images, under large gripper pose uncertainty. Whilst most approaches aim to predict the single best grasp pose from an image, our method first predicts a score for every possible grasp pose, which we denote the grasp function. With this, it is possible to achieve grasping robust to the gripper's pose uncertainty, by smoothing the grasp function with the pose uncertainty function. Therefore, if the single best pose is adjacent to a region of poor grasp quality, that pose will no longer be chosen, and instead a pose will be chosen which is surrounded by a region of high grasp quality. To learn this function, we train a Convolutional Neural Network which takes as input a single depth image of an object, and outputs a score for each grasp pose across the image. Training data for this is generated by use of physics simulation and depth image simulation with 3D object meshes, to enable acquisition of sufficient data without requiring exhaustive real-world experiments. We evaluate with both synthetic and real experiments, and show that the learned grasp score is more robust to gripper pose uncertainty than when this uncertainty is not accounted for.

We present a robust real-time method which performs dense reconstruction of high quality height maps from monocular video. By representing the height map as a triangular mesh, and using efficient differentiable rendering approach, our method enables rigorous incremental probabilistic fusion of standard locally estimated depth and colour into an immediately usable dense model. We present results for the application of free space and obstacle mapping by a low-cost robot, showing that detailed maps suitable for autonomous navigation can be obtained using only a single forward-looking camera.

This paper presents the conceptual design, detailed development and flight testing of AtlantikSolar, a 5.6m-wingspan solar-powered Low-Altitude Long-Endurance (LALE) Unmanned Aerial Vehicle (UAV) designed and built at ETH Zurich. The UAV is required to provide perpetual endurance at a geographic latitude of 45°N in a 4-month window centered around June 21st. An improved conceptual design method is presented and applied to maximize the perpetual flight robustness with respect to local meteorological disturbances such as clouds or winds. Airframe, avionics hardware, state estimation and control method development for autonomous flight operations are described. Flight test results include a 12-hour flight relying solely on batteries to replicate night-flight conditions. In addition, we present flight results from Search-And-Rescue field trials where a camera and processing pod were mounted on the aircraft to create high-fidelity 3D-maps of a simulated disaster area.

Robust, accurate pose estimation and mapping at real-time in six dimensions is a primary need of mobile robots, in particular flying Micro Aerial Vehicles (MAVs), which still perform their impressive maneuvers mostly in controlled environments. This work presents a visual-inertial sensor unit aimed at effortless deployment on robots in order to equip them with robust real-time Simultaneous Localization and Mapping (SLAM) capabilities, and to facilitate research on this important topic at a low entry barrier. Up to four cameras are interfaced through a modern ARM-FPGA system, along with an Inertial Measurement Unit (IMU) providing high-quality rate gyro and accelerometer measurements, calibrated and hardware-synchronized with the images. This facilitates a tight fusion of visual and inertial cues that leads to a level of robustness and accuracy which is difficult to achieve with purely visual SLAM systems. In addition to raw data, the sensor head provides FPGA-pre-processed data such as visual keypoints, reducing the computational complexity of SLAM algorithms significantly and enabling employment on resource-constrained platforms. Sensor selection, hardware and firmware design, as well as intrinsic and extrinsic calibration are addressed in this work. Results from a tightly coupled reference visual-inertial motion estimation framework demonstrate the capabilities of the presented system.

This paper presents Skye, a novel blimp design. Skye is a helium-filled sphere of diameter 2.7m with a strong inelastic outer hull and an impermeable elastic inner hull. Four tetrahedrally-arranged actuation units (AU) are mounted on the hull for locomotion, with each AU having a thruster which can be rotated around a radial axis through the sphere center. This design provides redundant control in the six degrees of freedom of motion, and Skye is able to move omnidirectionally and to rotate around any axis. A multi-camera module is also mounted on the hull for capture of aerial imagery or live video stream according to an ‘eyeball’ concept — the camera module is not itself actuated, but the whole blimp is rotated in order to obtain a desired camera view. Skye is safe for use near people — the double hull minimizes the likelihood of rupture on an unwanted collision; the propellers are covered by grills to prevent accidental contact; and the blimp is near neutral buoyancy so that it makes only a light impact on contact and can be readily nudged away. The system is portable and deployable by a single operator — the electronics, AUs, and camera unit are mounted externally and are detachable from the hull during transport; operator control is via an intuitive touchpad interface. The motivating application is in entertainment robotics. Skye has a varied motion vocabulary such as swooping and bobbing, plus internal LEDs for visual effect. Computer vision enables interaction with an audience. Experimental results show dexterous maneuvers in indoor and outdoor environments, and non-dangerous impacts between the blimp and humans.

A typical Inertial Navigation System (INS) fuses acceleration and angular rate readings with aiding measurements obtained by GPS and a compass. Here we present a robust state estimation framework based on the Extended Kalman Filter (EKF) applied to low-cost electronics typically installed on-board small unmanned airplanes. It uses airspeed measurements as a backup operation mode replacing GPS updates when temporarily unavailable. We demonstrate the applicability of the proposed approach to real-world scenarios using a challenging dataset recorded on-board a manned glider including long-term circling. A comparison between the normal operation mode and the backup solution reveals minimal difference between the respective orientation estimates, a position error growth sub-linear with time during GPS outage and a seamless transition back to GPS-based operation.

Effective and efficient generation of keypoints from an image is a well-studied problem in the literature and forms the basis of numerous Computer Vision applications. Established leaders in the field are the SIFT and SURF algorithms which exhibit great performance under a variety of image transformations, with SURF in particular considered as the most computationally efficient amongst the high-performance methods to date. In this paper we propose BRISK1, a novel method for keypoint detection, description and matching. A comprehensive evaluation on benchmark datasets reveals BRISK's adaptive, high quality performance as in state-of-the-art algorithms, albeit at a dramatically lower computational cost (an order of magnitude faster than SURF in cases). The key to speed lies in the application of a novel scale-space FAST-based detector in combination with the assembly of a bit-string descriptor from intensity comparisons retrieved by dedicated sampling of each keypoint neighborhood.

The dynamics of micro coaxial helicopters are coupled, especially in the presence of a stabilizer bar and in dynamic maneuvers. This paper presents a model-based approach for active decoupling of the dynamics of a micro coaxial helicopter. This allows for easier and more accurate operation of the system. The nonlinear model covers all degrees of freedom for attitude and altitude. It accounts for hover and cruise flight situations and explicitly captures the off-axis dynamics and the dynamics of the stabilizer bar. A six-axis force/torque sensor and an RPM measurement system are used in a custom built test bench. It is applied for analysis of the forces and torques generated by the rotors in combination with the dynamics of the drive train and the swashplate. The parameter identification and the model validation is obtained with flight data recorded with a vision-based motion tracking system. The decoupling controller is implemented on the commercial robotic helicopter CoaX and its performance is shown via a motion experiment.

Whenever the realization of a swash plate mechanism is not feasible (e.g. due to miniaturization limitations), center of gravity steering is an interesting alternative to swash plate steering. We present an approach to describe the dynamic behavior of a coaxial micro helicopter steered by a center of gravity shifting mechanism. The mechanical design of an existing system is improved to increase mechanical robustness and steering quality. In parallel, a simulation model is developed and implemented. It is used to estimate the system response to steering inputs, and to compare center of gravity to swash plate steering. Experimental flight results show an improvement of the helicopter performance due to the mechanical redesign.

A propulsion system similar in size and motion to the helical bacterial flagella motor is presented. The system consists of a magnetic nanocoil as a propeller (27 nm thick ribbon, 3 μm in diameter, 30-40 μm long) driven by an arrangement of macro coils. The macro coils generate a rotating field that induces rotational motion in the nanocoil. Viscous forces during rotation result in a net axial propulsion force on the nanocoil. Modeling of fluid mechanics and magnetics was used to estimate the requirements for such a system. The fabrication of the magnetic nanocoils and the system setup are explained. Experimental results from electromagnetic actuation of nanocoils as well as from their propulsion in both paraffin oil and water are presented. This is the first time a propulsion system of this size and motion-type has been fabricated and experimentally verified.