CELLO-EM: Adaptive sensor models without ground truth

We present an algorithm for providing a dynamic model of sensor measurements. Rather than depending on a model of the vehicle state and environment to capture the distribution of possible sensor measurements, we provide an approximation that allows the sensor model to depend on the measurement itself. Building on previous work, we show how the sensor model predictor can be learned from data without access to ground truth labels of the vehicle state or true underlying distribution, and we show our approach to be a generalization of non-parametric kernel regressors. Our algorithm is demonstrated in simulation and on real world data for both laser-based scan matching odometry and RGB-D camera odometry in an unknown map. The performance of our algorithm is shown to quantitatively improve estimation, both in terms of consistency and absolute accuracy, relative to other algorithms and to fixed covariance models.

Authors

• William Vega-Brown
• Nicholas Roy

Keywords

• Robot sensing systems
• Kernel
• Vectors
• Hidden Markov models
• Vehicles
• Approximation methods
• Sensor Model
• Dynamic Model
• Measurement Model
• Sensor Measurements
• Vehicle State
• Odometry
• Laser Scanning
• Morphine
• Kernel Function
• Conditional Independence
• Kalman Filter
• Gaussian Process
• Set Of Observations
• Optical Flow
• Mobile Robot
• Latent State
• Covariance Estimation
• Raw Measurements
• Motion Estimation
• Kernel Estimation
• True Covariance
• Measurement Covariance
• Linear Gaussian
• Kernel Regression
• Exponential Family
• Prediction Vector
• Sensor Data
• Feature Space
• Process Noise
• Raw Sensor Data