Publicly available map services are widely used by humans for navigation and nowadays provide almost complete road network data. When utilizing such maps for autonomous navigation with mobile robots one is faced with the problem of inaccuracies of the map and the uncertainty about the position of the robot relative to the map. In this paper, we present a probabilistic approach to autonomous robot navigation using data from OpenStreetMap that associates tracks from Open-StreeetMap with the trails detected by the robot based on its 3D-LiDAR data. It combines semantic terrain information, derived from the 3D-LiDAR data, with a Markov-Chain Monte-Carlo technique to match the tracks from OpenStreetMap with the sensor data. This enables our robot to utilize OpenStreetMap for navigation planning and to still stay on the trails during the execution of these plans. We present the results of extensive experiments carried out in real world settings that demonstrate the robustness of our system regarding the alignment of the vehicle pose relative to the OpenStreetMap data.

Occupancy grid maps are a popular method for representing the environment in the context of robot navigation tasks. However, occupancy grid maps can have a high memory demand that grows quadratically with the range of the sensor. In this paper, we introduce a memory-efficient map representation that is based on a constant set of individual scans. To make these scan-based maps suitable for autonomous robot navigation, we propose probabilistically sound methods for both mapping and localization. To solve the mapping problem, our approach incrementally selects scans based on the additional information they provide relative to the scans previously selected. Using these selected scans, we perform an Monte Carlo Localization (MCL) approach with a sensor model optimized for the scan-based representation of our map. We present extensive experiments in which we evaluate our approach using real world data recorded in a garage parking scenario with an autonomous car as well as a robot localization problem in an indoor environment. The results demonstrate that our approach can cope with high sensor noise and that it achieves comparable localization accuracy while at the same time consuming only a fraction of memory compared to regular occupancy grid maps.

Reliable detection and avoidance of obstacles is a crucial prerequisite for autonomously navigating robots as both guarantee safety and mobility. To ensure safe mobility, the obstacle detection needs to run online, thereby taking limited resources of autonomous systems into account. At the same time, robust obstacle detection is highly important. Here, a too conservative approach might restrict the mobility of the robot, while a more reckless one might harm the robot or the environment it is operating in. In this paper, we present a terrain-adaptive approach to obstacle detection that relies on 3D-Lidar data and combines computationally cheap and fast geometric features, like step height and steepness, which are updated with the frequency of the lidar sensor, with semantic terrain information, which is updated with at lower frequency. We provide experiments in which we evaluate our approach on a real robot on an autonomous run over several kilometers containing different terrain types. The experiments demonstrate that our approach is suitable for autonomous systems that have to navigate reliable on different terrain types including concrete, dirt roads and grass.

The ability to safely navigate is a crucial prerequisite for truly autonomous systems. A robot has to distinguish obstacles from traversable ground. Failing on this task can cause great damage or restrict the robots movement unnecessarily. Due to the security relevance of this problem, great effort is typically spent to design models for individual robots and sensors, and the complexity of such models is correlated to the complexity of the environment and the capabilities of the robot. We present a semi supervised learning approach, where the robot learns its traversability capabilities from a human operating it. From this partially and only positive labeled training data, our approach infers a model for the traversability analysis, thereby requiring very little manual effort for the human. In practical experiments we show that our method can be used for robots that need to reliably navigate on dirt roads as well as for robots that have very restricted traversability capabilities.

Many mobile manipulation tasks require the robot to be accurately localized with respect to the object where the manipulation has to be executed. These tasks include autonomous docking and positioning as well as pick and place or logistics tasks. State-of-the-art approaches to the problem commonly assume that the environment is static and localize the robot with respect to predetermined locations. In this paper, we present an approach that relaxes the static assumption and enables a robot to accurately localize with respect to a reference object that could be moved in the environment. The core of the paper is an extension of the generalized ICP method to handle multiple rigid bodies that move independently to each others. Experiments in both simulated and real world scenarios show that our approach is able to localize the robot with respect to a moved object with an accuracy of less than one centimeter.

In the past, highly effective solutions to the SLAM problem based on solving nonlinear optimization problems have been developed. However, most approaches put their major focus on runtime and accuracy rather than on memory consumption, which becomes especially relevant when large-scale SLAM problems have to be solved. In this paper, we consider the SLAM problem from the point of view of memory consumption and present a novel approximate approach to SLAM with low memory consumption. Our approach achieves this based on a hierarchical decomposition consisting of small submaps with limited size. We perform extensive experiments on synthetic and publicly available datasets. The results demonstrate that in situations in which the representation of the complete map requires more than the available main memory, our approach, in comparison to state-of-the-art exact solvers, reduces the memory consumption and the runtime up to a factor of 2 while still providing highly accurate maps.