Cooperative sensing in dynamic environments

This work presents methods for tracking objects from noisy and unreliable data taken by a team of robots. We develop a multi-object tracking algorithm based on Kalman filtering and a single-object tracking method involving a combination of Kalman filtering and Markov localization for outlier detection. We apply these methods in the context of robot soccer for robots participating in the RoboCup middle-size league and compare them to a simple averaging method. Results including situations from real competition games are presented.

Authors

• Markus Dietl
• Jens-Steffen Gutmann
• Bernhard Nebel

Keywords

• Robot sensing systems
• Sensor fusion
• Kalman filters
• Finite impulse response filter
• Working environment noise
• Filtering algorithms
• Mobile robots
• Robot vision systems
• Cameras
• History
• Kalman Filter
• Noisy Data
• Outlier Detection
• Unreliable Data
• Swarm Robotics
• Real Game
• Multi-object Tracking
• Grid Cells
• Constant Speed
• Team Sports
• Multiple Objects
• Single Object
• Motion Model
• Probabilistic Method
• Mobile Robot
• Sensor Model
• Geometric Method
• Ambiguous Situations
• Simultaneous Localization And Mapping
• Laser Ranging
• Ball Position
• Robotic Group
• Ball Rolling
• Soccer Field
• Integration Of Sensors
• Kalman Filter Approach
• Kalman Filter Method