Publications (33) View all
-
Article: Classifying dynamic objects
[show abstract] [hide abstract]
ABSTRACT: For robots operating in real-world environments, the ability to deal with dynamic entities such as humans, animals, vehicles, or other robots is of fundamental importance. The variability of dynamic objects, however, is large in general, which makes it hard to manually design suitable models for their appearance and dynamics. In this paper, we present an unsupervised learning approach to this model-building problem. We describe an exemplar-based model for representing the time-varying appearance of objects in planar laser scans as well as a clustering procedure that builds a set of object classes from given observation sequences. Extensive experiments in real environments demonstrate that our system is able to autonomously learn useful models for, e.g., pedestrians, skaters, or cyclists without being provided with external class information.Autonomous Robots 04/2012; 26(2):141-151. · 1.50 Impact Factor -
Article: Towards Feature-Based Multi-Hypothesis Localization and Tracking
[show abstract] [hide abstract]
ABSTRACT: In this paper we present a probabilisticfeature-based approach to multi-hypothesis global localization and tracking. Hypotheses are generated using a constraint-based search in the interpretation tree of possible local-to-global -pairings. This results in a set of continuously located position hypotheses of unbounded accuracy. For tracking, the same constraint-based technique is used. It performs track splitting as soon as location ambiguities arise from uncertainties and sensing. This yields a localization technique of extraordinary robusmess which can deal with significant errors from odometry, collisions and kidnapping. Simulation experiments succesfully demonstrate these properties at very low computational cost. The presented approach is theoretically sound which makes that the only parameter is the significance level a on which all statistical decisions are taken.12/2001; -
Article: A Multi Modal Web Interface for Task Supervision and Specification
[show abstract] [hide abstract]
ABSTRACT: In this paper we present a multi-modal web interface for autonomous mobile robots. The purpose of this interface is twofold. It serves as a tool for task supervision for the researcher and task specification for the end-user. The applications envisaged are typical service scenarios like remote inspection, transportation tasks or tour guiding. Instead of post-processing a huge amount of data gathered and stored during operation, it is very desirable for the developer to monitor specific internal variables of the target system in real-time. Sensory information on several levels of abstraction are visualized using state-of-the-art web technology yielding a plug-in-free interface which can be viewed with a standard browser. It provides multi-modal information in several representations: off- and on-board vision, laser and odometry. This tool proved to be indispensable in the developing phase of navigation algorithms for localization, map building, obstacle avoidance and path planning. Modern guidelines for ergonomic interface design like context-sensitive popup menus or clickable goal specification make the interface very intuitive for the end-user. Its practicability is extensively demonstrated in the 'Computer2000' exhibition event, where during 4 days the robot was remote controlled in a fully autonomous mode by visitors of the tradeshow using this interface. Keywords: Multi-modal interface, web interface, task supervision, task specification, mobile robots, remote inspection. 1.09/2001; -
Article: Multisensor on-the-fly localization:: Precision and reliability for applications
[show abstract] [hide abstract]
ABSTRACT: This paper presents an approach for localization using geometric features from a 360° laser range finder and a monocular vision system. Its practicability under conditions of continuous localization during motion in real time (referred to as on-the-fly localization) is investigated in large-scale experiments. The features are infinite horizontal lines for the laser and vertical lines for the camera. They are extracted using physically well-grounded models for all sensors and passed to a Kalman filter for fusion and position estimation. Positioning accuracy close to subcentimeter has been achieved with an environment model requiring 30 bytes/m2. Already with a moderate number of matched features, the vision information was found to further increase this precision, particularly in the orientation. The results were obtained with a fully self-contained system where extensive tests with an overall length of more than 6.4 km and 150,000 localization cycles have been conducted. The final testbed for this localization system was the Computer 2000 event, an annual computer tradeshow in Lausanne, Switzerland, where during 4 days visitors could give high-level navigation commands to the robot via a web interface. This gave us the opportunity to obtain results on long-term reliability and verify the practicability of the approach under application-like conditions. Furthermore, general aspects and limitations of multisensor on-the-fly localization are discussed.Robotics and Autonomous Systems. 09/2001; -
Article: Feature-based multi-hypothesis localization and tracking using geometric constraints
[show abstract] [hide abstract]
ABSTRACT: Mobile robot localization deals with uncertain sensory information as well as uncertain data association. In this paper we present a probabilistic feature-based approach to global localization and pose tracking which explicitly addresses both problems. Location hypotheses are represented as Gaussian distributions. Hypotheses are found by a search in the tree of possible local-to-global feature associations, given a local map of observed features and a global map of the environment. During tree traversal, several types of geometric constraints are used to determine statistically feasible associations. As soon as hypotheses are available, they are tracked using the same constraint-based technique. Track splitting is performed when location ambiguity arises from uncertainties and sensing. This yields a very robust localization technique which can deal with significant errors from odometry, collisions and kidnapping. Experiments in simulation and with a real robot demonstrate these properties at low computational costs.Robotics and Autonomous Systems.
