Can't take my eye off you: attention-driven monocular obstacle detection and 3D mapping. - In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2010, (2010), S. 816-821
Robust and reliable obstacle detection is an important capability for mobile robots. In our previous works we have presented an approach for visual obstacle detection based on feature based monocular scene-reconstruction. Most existing feature-based approaches for visual SLAM and scene reconstruction select their features uniformly over the whole image based on visual saliency only. In this paper we present a novel attention-driven approach that guides the feature selection to image areas that provide the most information for mapping and obstacle detection. Therefore, we present an information theoretic derivation of the expected information gain that results from the selection of new image features. Additionally, we present a method for building a volumetric representation of the robots environment in terms of an occpancy voxel map. The voxel map provides top-down information that is needed for computing the expected information gain. We show that our approach for guided feature selection improves the quality of the created voxel maps and improves the obstacle detection by reducing the risk of missing obstacles.
http://dx.doi.org/10.1109/IROS.2010.5651741
Exploring continuous action spaces with diffusion trees for reinforcement learning. - In: Artificial neural networks - ICANN 2010, (2010), S. 190-199
We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuous action space and organizes them in a hierarchical tree structure. In this tree, each subtree holds a subset of the action samples and thus holds knowledge about a subregion of the action space. Additionally, we store the expected long-term return of the samples of a subtree in the subtrees root. Thus, the diffusion tree integrates both, a sampling technique and a means for representing acquired knowledge in a hierarchical fashion. Sampling of new action samples is done by recursively walking down the tree. Thus, information about subregions stored in the roots of all subtrees of a branching point can be used to direct the search and to generate new samples in promising regions. This facilitates control of the sample distribution, which allows for informed sampling based on the acquired knowledge, e.g. the expected return of a region in the action space. In simulation experiments, we show how this can be used conceptually for exploring the state-action space efficiently.
http://dx.doi.org/10.1007/978-3-642-15822-3_24
Reinforcement learning based neural controllers for dynamic processes without exploration. - In: Artificial neural networks - ICANN 2010, (2010), S. 222-227
In this paper we present a Reinforcement Learning (RL) approach with the capability to train neural adaptive controllers for complex control problems without expensive online exploration. The basis of the neural controller is a Neural fitted Q-Iteration (NFQ). This network is trained with data from the example set enriched with artificial data. With this training scheme, unlike most other existing approaches, the controller is able to learn offline on observed training data of an already closed-loop controlled process with often sparse and uninformative training samples. The suggested neural controller is evaluated on a modified and advanced cartpole simulator and a combustion control of a real waste-incineration plant and can successfully demonstrate its superiority.
http://dx.doi.org/10.1007/978-3-642-15822-3_29
Learning to navigate through crowded environments. - In: IEEE International Conference on Robotics and Automation (ICRA), 2010, ISBN 978-1-4244-5038-1, (2010), S. 981-986
The goal of this research is to enable mobile robots to navigate through crowded environments such as indoor shopping malls, airports, or downtown side walks. The key research question addressed in this paper is how to learn planners that generate human-like motion behavior. Our approach uses inverse reinforcement learning (IRL) to learn human-like navigation behavior based on example paths. Since robots have only limited sensing, we extend existing IRL methods to the case of partially observable environments. We demonstrate the capabilities of our approach using a realistic crowd flow simulator in which we modeled multiple scenarios in crowded environments. We show that our planner learned to guide the robot along the flow of people when the environment is crowded, and along the shortest path if no people are around
http://dx.doi.org/10.1109/ROBOT.2010.5509772
What is different? - modeling the changeability of the environment. - In: Crossing borders within the ABC, (2010), S. 294-299
http://www.db-thueringen.de/servlets/DocumentServlet?id=16991
Estimating light regions in indoor environments for a mobile robot cameraman. - In: Crossing borders within the ABC, (2010), S. 33-37
http://www.db-thueringen.de/servlets/DocumentServlet?id=16901
Building 2D and 3D adaptive-resolution occupancy maps using Nd-Trees. - In: Crossing borders within the ABC, (2010), S. 306-311
http://www.db-thueringen.de/servlets/DocumentServlet?id=17002
Aspects of user specific dialog adaptation for an autonomous robot. - In: Crossing borders within the ABC, (2010), S. 635-640
http://www.db-thueringen.de/servlets/DocumentServlet?id=17205
Realtime user attention and emotion estimation on a mobile robot. - In: Crossing borders within the ABC, (2010), S. 629-634
http://www.db-thueringen.de/servlets/DocumentServlet?id=17204
Real-time activity recognition on a mobile companion robot. - In: Crossing borders within the ABC, (2010), S. 612-617
http://www.db-thueringen.de/servlets/DocumentServlet?id=17179