Docket #: S02-125
Target Tracking System
This patented method enables a mobile observer robot to track an unpredictable moving target in an unknown indoor environment cluttered by obstacles. The algorithm computes a motion strategy based exclusively on current sensor information in real time – no global map or historical sensor data is required. This technology can be applied to a variety of fields, including military, surgical, commercial and consumer robotics, and computer animation.
Applications
- Robotics:
- Military - missile control and visual tracking when there are obstacles that occclude the view
- Surveillance cameras
- Consumer and household robotics
- Graphic animation of digital actors - to select successive viewpoints for displaying in a virtual environment
- Surgery - controllable cameras to keep a patient's tissue under observation despite obstructions from people and instruments
Advantages
- Avoids visual obstructions - quickly adjust its trajectory to that of the target
- Computationally efficient
Publications
- "Real-Time Combinatorial Tracking of a Target Moving Unpredictably Among Obstacles." H.H. Gonzalez-Banos, C.Y. Lee, and J.C. Latombe. IEEE Int. Conf. on Robotics and Automation, Washington D.C., May 2002.
Related Links
Similar Technologies
-
Stanford Drone Dataset: Multi-scale, Multi-target social navigation S17-376Stanford Drone Dataset: Multi-scale, Multi-target social navigation
-
Layered electroactive polymers for robust and reliable variable-stiffness suspensions in robotics, prosthetics and autonomous vehicles S15-122Layered electroactive polymers for robust and reliable variable-stiffness suspensions in robotics, prosthetics and autonomous vehicles
-
MEMS phased array for high-speed, random access variable focusing and control for LIDAR and 3D imaging S18-327MEMS phased array for high-speed, random access variable focusing and control for LIDAR and 3D imaging