Controlling a Robotic Stereo Camera Under Image Quantization Noise
This work addresses the challenge of robust camera control for target localization in robotics, though it appears incremental as it builds on existing NBV and Kalman Filter approaches with specific noise modeling.
The paper tackles the problem of controlling a mobile stereo camera to localize targets under image quantization noise by computing Next-Best-Views that minimize cumulative state covariance, using a Kalman Filter and a two-stage control decomposition. Simulations and real experiments demonstrate accurate target localization, with a novel data-driven method introduced to handle unmodeled uncertainties like calibration errors and ensure Kalman Filter stability.
In this paper, we address the problem of controlling a mobile stereo camera under image quantization noise. Assuming that a pair of images of a set of targets is available, the camera moves through a sequence of Next-Best-Views (NBVs), i.e., a sequence of views that minimize the trace of the targets' cumulative state covariance, constructed using a realistic model of the stereo rig that captures image quantization noise and a Kalman Filter (KF) that fuses the observation history with new information. The proposed algorithm decomposes control into two stages: first the NBV is computed in the camera relative coordinates, and then the camera moves to realize this view in the fixed global coordinate frame. This decomposition allows the camera to drive to a new pose that effectively realizes the NBV in camera coordinates while satisfying Field-of-View constraints in global coordinates, a task that is particularly challenging using complex sensing models. We provide simulations and real experiments that illustrate the ability of the proposed mobile camera system to accurately localize sets of targets. We also propose a novel data-driven technique to characterize unmodeled uncertainty, such as calibration errors, at the pixel level and show that this method ensures stability of the KF.