Model-based echolocation of environmental objects

This paper presents an algorithm that can recognize and localize objects given a model of their contours using only ultrasonic range data. The algorithm exploits a physical model of the ultrasonic beam and combines several readings to extract outline object segments from the environment. It then detects patterns of outline segments that correspond to predefined models of object contours, performing both object recognition and localization. The algorithm is robust since it can account for noise and inaccurate readings as well as efficient since it uses a relaxation technique that can incorporate new data incrementally without recalculating from scratch. >

Authors

• Juan Carlos Santamaría
• Ronald C. Arkin

Keywords

• Object recognition
• Mobile robots
• Data mining
• Object detection
• Noise robustness
• Sensor phenomena and characterization
• Data structures
• Sonar measurements
• Robot sensing systems
• Histograms
• Object Location
• Relaxation Techniques
• Beam Model
• Clustering Algorithm
• Simulation Environment
• Segmentation Model
• Cluster Centers
• Pairwise Interactions
• Object Shape
• Matching Process
• Real-world Environments
• Mobile Robot
• Shape Model
• Intermediate Features
• Obstacle Avoidance
• Ultrasonic Sensors
• Consecutive Readings
• Shape Recognition
• Occupancy Grid
• Total Increment
• Obstacle Location