Mobile robots on construction sites require accurate pose estimation to perform autonomous surveying and inspection missions. Localization in construction sites is a particularly challenging problem due to the presence of repetitive features such as flat plastered walls and perceptual aliasing due to apartments with similar layouts inter and intra floors. In this paper, we focus on the global re-positioning of a robot with respect to an accurate scanned mesh of the building solely using LiDAR data. In our approach, a neural network is trained on synthetic LiDAR point clouds generated by simulating a LiDAR in an accurate real-life large-scale mesh. We train a diffusion model with a PointNet++ backbone, which allows us to model multiple position candidates from a single LiDAR point cloud. The resulting model can successfully predict the global position of LiDAR in confined and complex sites despite the adverse effects of perceptual aliasing. The learned distribution of potential global positions can provide multi-modal position distribution. We evaluate our approach across five real-world datasets and show the place recognition accuracy of$77 \% (\pm 2 ~\mathrm{m})$on average while outperforming baselines at a factor of 2 in mean error.

Robots need to know where they are in the world to operate effectively without human support. One common first step for precise robot localization is visual place recognition. It is a challenging problem, especially when the output is required in an online fashion, and the current state-of-the-art approaches that tackle it usually require either large amounts of labeled training data or rely on parameters that need to be tuned manually, often per dataset. One such parameter often used for sequence-based place recognition is the image similarity threshold that allows to differentiate between pairs of images that represent the same place even in the presence of severe environmental and structural changes, and those that represent different places even if they share a similar appearance. Currently, selecting this threshold is a manual procedure and requires human expertise. We propose an automatic similarity threshold selection technique and integrate it into a complete sequence-based place recognition system. The experiments on a broad range of real-world and simulated data show that our approach is capable of matching image sequences under various illumination, viewpoint and underlying structural changes, runs online, and requires no manual parameter tuning while yielding performance comparable to a manual, dataset-specific parameter tuning. Thus, this paper substantially increases the ease of use of visual place recognition in real-world settings.

Our world is non-static, and robots should be able to track its changing geometry. For tracking changes, data asso-ciations between 3D points over time are key. In this paper, we investigate the problem of associating 3D points on plant organs from different mapping runs over time while the plants grow. We achieve a high spatial-temporal matching performance by combining 3D RGB-D SLAM, visual place recognition, and 2D/3D matching exploiting background knowledge. We showcase our approach in a real agricultural glasshouse used to grow sweet peppers, using RGB-D observations from a mobile robot traversing the environment. Our experiments suggest that with our approach, we can robustly make data associations in highly repetitive scenes and under changing geometries caused by plant growth. We see our approach as an important step towards spatial-temporal data association for robotic agriculture.

Maps are an important component of most robotic navigation systems and building maps under uncertainty is often referred to as simultaneous localization and mapping or SLAM. Most SLAM approaches start from scratch and build a map only based on their own observations and odometry information. In this paper, we address the problem of how additional information can be exploited, for example from OpenStreetMap. We extend the standard graph-based SLAM formulation by relating the nodes of the pose-graph with an existing map. As this paper suggests, we can relate the newly built maps with information from publicly available maps with the laser range finder data from the robot and in this way improve the map quality. We implemented and evaluated our approach using real world data taken in urban environments. We illustrate that our extension to graph-based SLAM provides better aligned maps and adds only a marginal computational overhead.

The ability to localize a robot is an important capability and matching of observations under substantial changes is a prerequisite for robust long-term operation. This paper investigates the problem of efficiently coping with seasonal changes in image data. We present an extension of a recent approach [15] to visual image matching using sequence information. Our extension allows for exploiting GPS priors in the matching process to overcome the main computational bottleneck of the previous method and to handle loops within the image sequences. We present an experimental evaluation using real world data containing substantial seasonal changes and show that our approach outperforms the previous method in case a noisy GPS pose prior is available.

High-resolution microprobes are used to record single neuron activity in the brain. This technology is envisaged to be a central component for brain-controlled computers and robots. Current neural probes, however, allow for recording only a small number of the densely spaced electrodes simultaneously. Therefore, we address the problem of autonomously choosing, for a given number, the subset of electrodes with the corresponding size so as to extract as much information as possible. We first present an approach for predicting neural spikes across different channels of the probe. Our method employs nonparametric sparse Gaussian process regression to predict the signal of a channel given the signals recorded at neighboring sites. Second, we utilize the signal predictions for efficiently seeking for the subset of electrodes that minimizes the overall prediction error. In experiments carried out using real neural data, we demonstrate that our selection procedure provides highly accurate results. Furthermore, the solutions found in our experiments are close to the optimal solution.