A human supervisory approach to rapid world modeling through the use of geometric primitives
A three-dimensional world model is crucial for many robot-oriented tasks. The most efficient mapping configuration use geometric primitives to model environments, and are easy to store and process. In the past, modeling techniques have been either fully manual or autonomous. Manual methods are extremely time consuming but also highly accurate and flexible. On the other hand autonomous techniques are fast but inflexible and often inaccurate. The method presented in this paper combines the two thereby yielding a highly efficient, flexible, and accurate tool. Our methods enable a human supervisor to quickly construct a fully defined world model from unfiltered and unsegmented real-world range data.
- Research Organization:
- Los Alamos National Lab., NM (United States)
- Sponsoring Organization:
- USDOE Assistant Secretary for Human Resources and Administration, Washington, DC (United States); Defense Advanced Research Projects Agency, Arlington, VA (United States)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 563830
- Report Number(s):
- LA-UR--97-3344; ON: DE98001497
- Country of Publication:
- United States
- Language:
- English
Similar Records
Rapid world modeling: Fitting range data to geometric primitives
Rapid world modelling for robotics