A Discrete Event Framework for
Autonomous Observation Under Uncertainty

Tarek M. Sobh and Ruzena Bajcsy

Abstract

We address the problem of observing a moving agent. We advocate a modeling approach for the visual system and its observer, where a discrete event dynamic system (DEDS) frame work is developed and ``events'' are defined as ranges on parameter subsets. In particular, we propose a system for observing a manipulation process, where a robot hand manipulates an object. We recognize the hand/object interaction over time and a stabilizing observer is constructed. Low-level modules are developed for recognizing the events that causes state transitions within the dynamic manipulation system. The work examines closely the possibilities for errors, mistakes and uncertainties in the manipulation system, observer construction process and event identification mechanisms. Some results from a sequence of a peg-in-hole operation are documented.

• Introduction
• Hybrid and Discrete Event Dynamic Systems for Robotic Observation
  • Discrete event dynamic systems for active visual sensing
  • DEDS for Modeling Observers
• State Modeling and Observer Construction
  • State Space Modeling
  • Building the Model
    • A Grasping Task
  • Developing the Observer
  • Examples
• Identifying Motion Events
• Modeling and Recovering 3-D Uncertainties
• Utilizing the Discrete Event Observer
• Experiments
• Conclusions
• References
• About this document ...