Autonomous Robot Navigation in Human-Centered Environments Based on 3D Data Fusion
- PDF / 3,501,938 Bytes
- 10 Pages / 600.03 x 792 pts Page_size
- 50 Downloads / 179 Views
Research Article Autonomous Robot Navigation in Human-Centered Environments Based on 3D Data Fusion ¨ Peter Steinhaus, Marcus Strand, and Rudiger Dillmann Institute for Computer Science and Engineering (CSE), University of Karlsruhe (TH), Haid-und-Neu-Straße 7, 76131 Karlsruhe, Germany Received 1 December 2005; Revised 14 July 2006; Accepted 17 December 2006 Recommended by Ching-Yung Lin Efficient navigation of mobile platforms in dynamic human-centered environments is still an open research topic. We have already proposed an architecture (MEPHISTO) for a navigation system that is able to fulfill the main requirements of efficient navigation: fast and reliable sensor processing, extensive global world modeling, and distributed path planning. Our architecture uses a distributed system of sensor processing, world modeling, and path planning units. In this arcticle, we present implemented methods in the context of data fusion algorithms for 3D world modeling and real-time path planning. We also show results of the prototypic application of the system at the museum ZKM (center for art and media) in Karlsruhe. Copyright © 2007 Peter Steinhaus et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
1.
INTRODUCTION
The problem of navigating mobile systems in dynamic indoor environments is one of the basic problems in the area of mobile robots. Starting not long ago, as a first trend, service robots and especially humanoid robots address more and more human-centered working spaces, so the problem of efficient navigation in such dynamic scenarios seems to be very important. As a second trend, sensor and computing technologies become cheaper, faster, and smaller, enabling the design and implementation of huge sensor networks in the so-called “intelligent buildings” (smart houses). As mobile robots can also be seen as actuators of these intelligent buildings, it seems almost intuitive to combine both techniques, mobile robots and sensor networks, to solve the problem of efficient navigation in dynamic human-centered indoor environments. Looking at the enormous amount of previous works already done in the field of navigation system research, almost all approaches can be categorized with respect to their architectures in one of the following categories.
mobile robotics. The used approaches can be divided into the classes of functional/cybernetic, behavioristic, and hybrid approaches. A typical functional approach can, for example, be found in [1, 2], where global and local planning modules work on a 2D geometrical and topological map to plan subgoals for the mobile systems, using current sensor data to adapt paths while targeting the subgoals. A behaviorbased approach is, for example, given in [3–5], where a set of logical and physical sensor systems is situation-dependent activated to search for edges or obstacles. A hybrid approach which combines the functional del
Data Loading...
