Map-based priors for localization

Localization from sensor measurements is a fundamental task for navigation. Particle filters are among the most promising candidates to provide a robust and real-time solution to the localization problem. They instantiate the localization problem as a Bayesian altering problem and approximate the posterior density over location by a weighted sample set. In this paper, we introduce map-based priors for localization, using the semantic information available in maps to bias the motion model toward areas of higher probability. We, show that such priors, under a particular assumption, can easily be incorporated in the particle filter by means of a pseudo likelihood. The resulting filter is more reliable and more accurate. We show experimental results on a GPS based outdoor people tracker that illustrate the approach and highlight its potential.

Authors

• Sang Min Oh
• Sarah Tariq
• Bruce N. Walker
• Frank Dellaert

Keywords

• Global Positioning System
• Bayesian methods
• Satellites
• Dead reckoning
• Navigation
• Robustness
• Filters
• Filtering theory
• Sensor fusion
• Sensor systems
• Semantic Information
• Local Problems
• Sensor Measurements
• Posterior Density
• Motion Model
• Particle Filter
• Root Mean Square Error
• Sampling Weights
• Measurement Model
• Outdoor Environments
• Energy Function
• Gaussian Model
• Bayesian Framework
• Predictive Distribution
• Top Right
• Map Information
• Unconditional Model
• Tall Buildings
• Augmented Model
• True Path
• Global Positioning System Receiver
• Robot Localization
• Predictive Density
• Dark Grey
• Local Transition