Computing C-space entropy for view planning based on beam sensor model

• Published in: Proceedings 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems : September 30-October 4, EPFL Lausanne, Switzerland Vol. 3; pp. 2389 - 2394 vol.3
• Main Authors: Wang, P., Gupta, K.
• Format: Conference Proceeding
• Language: English
• Published: Piscataway NJ IEEE 2002
• Subjects: Applied sciences; Artificial intelligence; Computational geometry; Computer science; control theory; systems; Control theory. Systems; Entropy; Exact sciences and technology; Humanoid robots; Manipulators; Mobile robots; Orbital robotics; Path planning; Pattern recognition. Digital image processing. Computational geometry; Robot sensing systems; Robotics; Sensor systems; Zinc compounds; Occlusion; Obstacle; Proximity detector; View point; Measurement sensor; Entropy; Path planning; Visibility; Occultation; Robotics
• ISBN: 0780373987; 9780780373983
• DOI: 10.1109/IRDS.2002.1041625

The concept of C-space entropy was recently introduced by the authors (2000, 2001), as a measure of knowledge of C-space for sensor-based path planning and exploration for general robot-sensor systems. 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. The expected C-space entropy computation, however, made two idealized assumptions. The first was that the sensor field of view (FOV) is a point; and the second was that no visibility (or occlusion) constraints are taken into account, i.e., as if the obstacles are transparent. We extend the expected C-space entropy formulation where the sensor FOV is a beam and furthermore, it is subject to visibility constraints, as is the case with real range sensors. Planar simulations show that this new formulation results in more efficient exploration.