Uncertainty Constrained Differential Dynamic Programming in Belief Space for Vision Based Robots
Shatil Rahman, and Steven L. Waslander.
IEEE Robotics and Automation Letters (RA-L), 2021
A novel trajectory optimization formulation that incorporates inequality constraints on uncertainty and a novel Augmented Lagrangian based stochastic differential dynamic programming method in belief space.
DC-VINS: Dynamic Camera Visual Inertial Navigation System with Online Calibration
Jason Rebello, Chunshang Li and Steven L. Waslander.
ICCV Workshop, 2021
we present the online extrinsic calibration between a dynamic camera mounted to an actuated mechanism and an IMU mounted to the body of the vehicle integrated into a Visual Odometry pipeline.
Towards End-to-end Learning of Visual Inertial Odometry with an EKF
Chunshang Li and S.L. Waslander
Conference on Computer and Robot Vision (CRV), 2020
In this paper, we propose the first end-to-end trainable visual-inertial odometry (VIO) algorithm that leverages a robo-centric Extended Kalman Filter (EKF)..
AC/DCC: Accurate Calibration of Dynamic Camera Clusters for Visual SLAM
Jason Rebello, Augus Fung and Steven L. Waslander
International Conference on Robotics and Automation (ICRA),, 2020
A novel method that performs accurate calibration of a Dynamic Camera Cluster with multiple static cameras using a pose-loop error formulation. We also present an analysis of the degenerate parameters.
Visual Measurement Integrity Monitoring for UAV Localization
Chengyao Li, and Steven L. Waslander.
IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), 2019
A novel approach inspired by RAIM to monitor the integrity of visual localization for UAV. The algorithm first detects and rejects measurement outliers and calculates the protection level of the position estimation.