A Configuration Space View of View Planning
- 1 October 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21530858,p. 1291-1297
Abstract
For sensor-based robot motion planning, view planning problem refers to planning the next sensing action to further facilitate the motion planning task. In Y. Yu and K. Gupta (2004), C-space entropy was introduced as a measure of knowledge of robot configuration space, or C-space. The robot plans the next sensing action to maximally reduce the expected C-space entropy, also called the maximal expected entropy reduction, or MER criterion. It was shown that MER criterion resulted in much more efficient C-space exploration performance than physical space based view planning criteria, such as to maximize unknown physical volume in each view. From a C-space perspective, MER criterion consists of two important aspects: sensing actions are evaluated in C-space (geometric aspect); these effects are evaluated in an information theoretical sense (stochastic aspect). In this paper, we investigate how much of this better performance is attributable to the paradigmatic shift to evaluating the sensor action in C-space, i.e., the pure geometric component of MER, and how much is attributable to the stochastic aspect of MER. We propose C-space based pure geometric criteria (which are essentially geometric aspect of MER) for view planning and compare them with the MER criterion. We empirically show that a great deal of efficiency is attributable to the pure geometric aspect; however, we also show that the stochastic aspect, despite being based on simple assumptions, result in moderately more efficient C-space exploration over the pure geometric component of MER. We outline explanations for our findingsKeywords
This publication has 16 references indexed in Scilit:
- View planning for exploration via maximal C-space entropy reduction for robot mounted range sensorsAdvanced Robotics, 2007
- C-space Entropy: A Measure for View Planning and Exploration for General Robot-Sensor Systems in Unknown EnvironmentsThe International Journal of Robotics Research, 2004
- View planning for automated three-dimensional object reconstruction and inspectionACM Computing Surveys, 2003
- Provable strategies for vision-guided exploration in three dimensions2002
- Sensor based planning for a planar rod robot: incremental construction of the planar rod-HGVG2002
- Sensor-based probabilistic roadmaps: experiments with an eye-in-hand systemAdvanced Robotics, 2000
- Plan-N-Scan: A Robotic System for Collision-Free Autonomous Exploration and Workspace MappingJournal of Intelligent & Robotic Systems, 1999
- Vision-based motion planning and exploration algorithms for mobile robotsIEEE Transactions on Robotics and Automation, 1998
- Autonomous exploration: driven by uncertaintyIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Explaining Music: Essays and ExplorationsThe Journal of Aesthetics and Art Criticism, 1975