|
One of the fundamental tasks characters have to perform is planning their motions while avoiding
collisions with obstacles in the environment.
We conduct research on motion planning for two- and three-dimensional rigid bodies and articulated robots moving in known virtual environments.
The Corridor Map Method / Indicative Route Method
Current applications require a path planner that is fast (to ensure real-time interaction with the environment) and flexible (to avoid local hazards). In addition, paths need to be natural, i.e. smooth and short. We propose a new framework, the Corridor Map Method, which meets these requirements. 
Roland Geraerts.
Ioannis Karamouzas, Roland Geraerts and Mark Overmars.
Roland Geraerts and Mark H. Overmars.
Roland Geraerts and Mark H. Overmars.
Mark H. Overmars, Ioannis Karamouzas and Roland Geraerts
Roland Geraerts, Arno Kamphuis, Ioannis Karamouzas and Mark H. Overmars
Roland Geraerts and Mark H. Overmars.
Roland Geraerts.
Comparative studies and analyses
We conduct a comparative study of different techniques that are used in the Probabilistic Roadmap Method. In addition, we give a reachability analysis for sampling based planners which leads to a better understanding of the success of the planners. 
Roland Geraerts and Mark H. Overmars.
Roland Geraerts and Mark H. Overmars.
Roland Geraerts and Mark H. Overmars.
Roland Geraerts and Mark H. Overmars.
Roland Geraerts and Mark H. Overmars.
High-quality paths
We present algorithms that increase the quality of a path. That is, we focus on decreasing the path length and increasing the clearance along a path. The techniques can be applied to a broad range of robots which may reside in arbitrary high-dimensional configuration spaces. 
Roland Geraerts and Mark H. Overmars.
Roland Geraerts and Mark H. Overmars.
Roland Geraerts and Mark H. Overmars.
High-quality roadmaps
The Reachability Roadmap Method is a new and efficient algorithm that creates small roadmaps for two- and three-dimensional problems. The algorithm ensures that a path can always be found if one exists. We extend the algorithm such that short paths and high-clearance paths can be extracted from the roadmap in real-time. 
Roland Geraerts and Mark H. Overmars.
Roland Geraerts and Mark H. Overmars.
Ph.D. thesis
The thesis deals with comparing and analyzing sampling-based motion planning techniques, in particular variants of the Probabilistic Roadmap Method (PRM). In addition, quality aspects of paths and roadmaps are investigated. 
Roland Geraerts.
Experimental research
In robotics research, it is often difficult to compare and evaluate techniques experimentally. We identify these difficulties and provides solutions based on our work during the last four years in the field of sampling-based motion planning.
Roland Geraerts.
ASCI conference papers
Roland Geraerts and Mark H.Overmars. On the Analysis and Success of Sampling Based Motion Planning. In Conference of the Advanced School for Computing and Imaging (ASCI'05), pp. 313-319, 2005. Full text: [pdf, ps.gz] Poster [pdf]
Roland Geraerts and Mark H. Overmars.
Last update: February 2, 2010.
|
