Cleaning is widely regarded as one of the most relevant applications of autonomous service robots. The goal of robotic cleaning is to achieve low dirt levels in the whole environment. Low cost consumer robots, however, are typically prone to high motion and sensor uncertainties. Additionally, their cleaning units do not always remove the dirt entirely. As a result, there is a substantial probability that some parts of the environment are not cleaned sufficiently. In this paper, we propose an approach to robotic cleaning that guarantees that in the whole environment, the dirt levels after cleaning are reduced below a user-defined threshold with high confidence. We introduce a novel probabilistic model for jointly estimating the trajectory of the robot and the current dirt distribution in the environment. Based on this estimate, we adapt the future cleaning path during operation such that the robot re-visits areas in which high dirt levels are still likely. We demonstrate the effectiveness of our approach in extensive experiments carried out both in simulation and with a real vacuum cleaning robot, also in comparison to previous approaches.

In this paper, we present a novel mapping system that robustly generates highly accurate 3-D maps using an RGB-D camera. Our approach requires no further sensors or odometry. With the availability of low-cost and light-weight RGB-D sensors such as the Microsoft Kinect, our approach applies to small domestic robots such as vacuum cleaners, as well as flying robots such as quadrocopters. Furthermore, our system can also be used for free-hand reconstruction of detailed 3-D models. In addition to the system itself, we present a thorough experimental evaluation on a publicly available benchmark dataset. We analyze and discuss the influence of several parameters such as the choice of the feature descriptor, the number of visual features, and validation methods. The results of the experiments demonstrate that our system can robustly deal with challenging scenarios such as fast camera motions and feature-poor environments while being fast enough for online operation. Our system is fully available as open source and has already been widely adopted by the robotics community.

Being able to estimate the dirt distribution in an environment makes it possible to compute efficient paths for robotic cleaners. In this paper, we present a novel approach for modeling and estimating the dynamics of the generation of dirt in an environment. Our model uses cell-wise Poisson processes on a regular grid to estimate the distribution of dirt in the environment. It allows for an effective estimation of the dynamics of the generation of dirt and for making predictions about the absolute dirt values. We propose two efficient cleaning policies that are based on the estimated dirt distributions and can easily be adapted to different needs of potential users. Through extensive experiments carried out with a modified iRobot Roomba vacuum cleaning robot and in simulation we demonstrate the effectiveness of our approach.

We present an approach to simultaneous localization and mapping (SLAM) for RGB-D cameras like the Microsoft Kinect. Our system concurrently estimates the trajectory of a hand-held Kinect and generates a dense 3D model of the environment. We present the key features of our approach and evaluate its performance thoroughly on a recently published dataset, including a large set of sequences of different scenes with varying camera speeds and illumination conditions. In particular, we evaluate the accuracy, robustness, and processing time for three different feature descriptors (SIFT, SURF, and ORB). The experiments demonstrate that our system can robustly deal with difficult data in common indoor scenarios while being fast enough for online operation. Our system is fully available as open-source.

In this paper we consider the problem of null space minimization in coverage path planning of 3D surfaces for redundant manipulators. Existing coverage solutions only focus on Euclidean cost functions and often return suboptimal paths with respect to the joint space. In the approach described here, we explicitly consider the null space by treating different inverse kinematics solutions as individual nodes in a graph and model the problem as a generalized traveling salesman problem (GTSP). The GTSP is a generalization of the TSP where the nodes of the graph are subdivided into clusters and at least one node in each cluster needs to be visited. We evaluate our approach using a PR2 robot and complex objects. Our results demonstrate that our method outperforms Euclidean coverage algorithms in terms of manipulation effort and completion time.

Accurate and robust localization is essential for the successful navigation of autonomous mobile robots. The majority of existing localization approaches, however, is based on the assumption that the environment is static which does not hold for most practical application domains. In this paper, we present a localization framework that can robustly track a robot's pose even in non-static environments. Our approach keeps track of the observations caused by unexpected objects in the environment using temporary local maps. It relies both on these temporary local maps and on a reference map of the environment for estimating the pose of the robot. Experimental results demonstrate that by exploiting the observations caused by unexpected objects our approach outperforms standard localization methods for static environments.

Mobile robots rely on the ability to sense the geometry of their local environment in order to avoid obstacles or to explore the surroundings. For this task, dedicated proximity sensors such as laser range finders or sonars are typically employed. Cameras are a cheap and lightweight alternative to such sensors, but do not directly offer proximity information. In this paper, we present a novel approach to learning the relationship between range measurements and visual features extracted from a single monocular camera image. As the learning engine, we apply Gaussian processes, a non-parametric learning technique that not only yields the most likely range prediction corresponding to a certain visual input but also the predictive uncertainty. This information, in turn, can be utilized in an extended grid-based mapping scheme to more accurately update the map. In practical experiments carried out in different environments with a mobile robot equipped with an omnidirectional camera system, we demonstrate that our system is able to produce proximity estimates with an accuracy comparable to that of dedicated sensors such as sonars or infrared range finders.