3D imaging and analysis have a clear advantage over traditional 2D vision for such applications, because the 3D data eases and enhances the detection and positioning of scene objects and structure. This interpretation allows the developed robots to be able to track their position, identify scene elements and adjust to their environment. 

Often also a range of multiple sensors are necessary to provide the information required for operation planning and execution, and fusing sensor data from different sensors then become essential to ensure robust and reliable recognition of environmental shapes, features and properties, important for robust 3D mapping of the scene. 

To utilize this information, carefully tuned signal processing algorithms are required for combining sensor data. A robust sensor system also requires understanding of the sensors characteristics within when operating in challenging environments, and compensation for any undesired effects.

Related projects

• SEAMLESS - Simultaneous navigation and manipulation in complex dynamic scenes
• New 3D camera to give robots better view
• Pipeline navigation using Time-of-Flight imagery
• Real time fusion of sensor data for dynamic 3D mapping
• Obstacle guided snake locomotion

Related publications

• Pipeline landmark detection for autonomous robot navigation using time-of-flight imagery; Thielemann, J.T.; Breivik, G.M.; Berge, A. Computer Vision and Pattern Recognition Workshops, 2008. CVPR Workshops 2008. IEEE Computer Society Conference on Volume, Issue, 23-28 June 2008 Page(s): 1 - 7
• Adaptive Snake Robot Locomotion: A Benchmarking Facility for Experiments; Sigurd Aksnes Fjerdingen, John Reidar Mathiassen, Henrik Schumann-Olsen and Erik Kyrkjebø; European Robotics Symposium 2008,  Springer Tracts in Advanced Robotics  serial no  44, 2008,  pp. 13-22.  Berlin / Heidelberg, Springer.

If you are interested in more information about robot navigation please contact Henrik Schumann-Olsen .
 

The snake AIKO was equipped with a 3D time-of-flight camera for obstacle guided navigation. A live demonstration of the concept was held at the Technoport exhibition in Trondheim.