Search

We present an object pose estimation approach exploiting both geometric depth and photometric color information available from an RGB-D sensor. In contrast to various efforts relying on object segmentation with a known background structure, our approach does not depend on the segmentation and thus exhibits superior performance in unstructured environments. Inspired by a voting-based approach employing an oriented point pair feature, we present a voting-based approach which further incorporates color information from the RGB-D sensor and which exploits parallel power of the modern parallel computing architecture. The proposed approach is extensively evaluated with three state-of-the-art approaches on both synthetic and real datasets, and our approach outperforms the other approaches in terms of both computation time and accuracy. A point pair feature describing both geometric shape and photometric color and its application to a voting-based 6-DOF object pose estimation.Parallel algorithms significantly accelerating the voting process on modern GPU architectures.Effective in unstructured scenes in which the prevailing segmentation-based approaches may not be applicable.

In this paper, we present a vision system for robotic object manipulation tasks in natural, domestic environments. Given complex fetch-and-carry robot tasks, the issues related to the whole detect-approach-grasp loop are considered. Our vision system integrates a number of algorithms using monocular and binocular cues to achieve robustness in realistic settings. The cues are considered and used in connection to both foveal and peripheral vision to provide depth information, segmentation of the object(s) of interest, object recognition, tracking and pose estimation. One important property of the system is that the step from object recognition to pose estimation is completely automatic combining both appearance and geometric models. Experimental evaluation is performed in a realistic indoor environment with occlusions, clutter, changing lighting and background conditions.

Navigation in large-scale environments is composed of different local tasks. To achieve smooth switching between these tasks and thus a continuous control signal, usually a precise map of the environment and an exact pose estimate of the robot are needed. Both are hard to fulfil for experiments in real-world settings. We present a system that shows how one can relax the need for accurate metric models of the environment while at the same time achieving smooth task switching. To facilitate this scheme the dynamical systems approach is used, which incorporates behaviour coordination through competition in a dynamic framework. Feature detectors use sonar data to provide means for local navigation. This ability combined with a simple topological map constitutes a complete navigation system for large-scale office environments. Experiments showed that a Scout robot using this scheme is able to successfully navigate through our whole institute. Through the use of the dynamic behaviour coordination, switching between the navigational tasks occurs in a smooth manner leading to continuous control of the platform.

In this paper, we present a framework for a robotic system with the ability to perform real-world manipulation tasks. The complexity of such tasks determines the precision and freedoms controlled which also affects the robustness and the flexibility of the system. The aspect is on the development of visual system and visual tracking techniques in particular. Since precise tracking and control of a full pose of the object to be manipulated is usually less robust and computationally expensive, we integrate vision and control system where the objectives are to provide the discrete state information required to switch between control modes of different complexity. For this purpose, an integration of simple visual algorithms is used to provide a robust input to the control loop. Consensus theory is investigated as the integration strategy. In addition, a general purpose framework for integration of processes is used to implement the system on a real robot. The proposed approach results in a system which can robustly locate and grasp a door handle and then open the door.

In this paper we present a new technique for on-line extraction of natural point landmarks in an indoor environment. The landmarks are filtered out from sonar data taken from a mobile platform. By storing point landmark positions in a reference map, we can achieve absolute robot localization by doing matching between recently collected landmarks and the reference map. The matching procedure also takes advantage of compass readings to increase computational speed and make the performance more robust. The technique is easily extended to also encompass local robot localization, which is used when the robot navigates autonomously. The position accuracy of the robot as well as its capability to navigate using natural landmarks is illustrated in a number of real world experiments.

Widespread use of mobile robots can only be achieved when framworks that enable specification, design and implementation of systems are available. These frameworks must provide a level of abstraction that enables use of the same methods for different tasks/missions to facilitate fast prototyping and design at low cost. In this paper a Task Description Language (TDL) for task specification is outlined. The tasks are specified as network of processes. The processes are described in terms of finite state machines (FSMs) and their composition is achieved via a set of composition operators, common to many process algebra models. From the obtained description of the task a Discrete Event Systems supervisory controller can be synthesized. To demonstrate that such an approach is suitable basis for description of robot tasks a set of experiments with two different platforms situated in two different laboratories is described. The elementary processes necessary to carry out these experiments are presented. Obtained results are reported for three different experiments. The results demonstrate that the presented framework has the required characteristics.

For navigation in a partially known environment it is possible to provide a model that may be used for guidance in the navigation and as a basis for selective sensing. In this paper a navigation system for an autonomous mobile robot is presented. Both navigation and sensing is built around a graphics model, which enables prediction of the expected scene content. The model is used directly for prediction of line segments which, through matching, allow estimation of position and orientation. In addition, the model is used as a basis for a hierarchical stereo matching that enables dynamic updating of the model with unmodelled objects in the environment. For short-term path planning a set of reactive behaviours is used. The reactive behaviours include use of inverse perspective mapping for generation of occupancy grids, a sonar system and simple gaze holding for monitoring of dynamic obstacles. The full system and its component processes are described and initial experiments with the system are briefly outlined.