Hengbo Tang

The navigation system of a mobile robot is usually a combination of different sensors. In order to align these measurements, the intrinsic parameters of each sensor and the spatio-temporal extrinsic parameters among them are required to be precisely calibrated. In this paper, a simultaneous intrinsic and extrinsic calibration algorithm of a visual-odometric system is proposed. An initialization process is designed to generate rough estimation of the camera intrinsics, the odometric parameters, and the spatio extrinsic parameters. Then, a joint optimization problem is iteratively solved to obtain a refined calibration result. By taking temporal delay into consideration during the calibration process, the estimation accuracy is highly improved. Experiments are conducted with simulation datasets and also an industrial autonomous guided vehicle (AGV) system. The results are presented to validate the efficiency of our algorithm.

This paper focuses on the motion estimation problem of ground vehicles using odometry and monocular visual sensors. While the keyframe-based batch optimization methods become the mainstream approach in mobile vehicle localization and mapping, the keyframe poses are usually represented by SE(3) in vision-based methods or SE(2) in methods based on range scanners. For a ground vehicle, this paper proposes a new SE(2)-constrained SE(3) parameterization of its poses, which can be easily achieved in the batch optimization framework using specially formulated edges. Utilizing such a parameterization of poses, a complete odometry-vision-based motion estimation system is developed. The system is designed in a commonly used structure of graph optimization, providing high modularity and flexibility for further implementation or adaptation. Its superior performance in terms of accuracy on a ground vehicle platform is validated by real-world experiments in industrial indoor environments.

Extrinsic calibration is one of the most important problems in robotics, whose objective is to estimate the relative poses among the sensors and the robot. Currently, most on-line solutions of extrinsic calibration are based on the Gaussian filters, which estimate all the system states iteratively. However, a large number of the system states are not related to calibration. Estimating all these redundant states may highly increase the dimensionality of the problem, and therefore, undermine the calibration performance in both efficiency and robustness. In this paper, we propose an innovative on-line calibration algorithm, called constraint Gaussian filter with virtual measurements (VMCGF). The nature of VMCGF is a filter with a compact state vector containing only the states of interest, also called essential states. Violating the modeling principles of the traditional Gaussian filters, the measurements cannot be expressed by the observation function with the essential states solely. Exploiting the constraints between the measurements and the essential states, virtual measurements are generated according to the properties of the generalized chi-square distribution. Although originally developed to solve the calibration problem, VMCGF is a general filtering algorithm, that can be applied to solve other problems that might suffer from redundant states. The implementation of VMCGF on a camera odometry calibration problem is introduced, and its observability properties are analyzed. Both simulations and experiments are conducted to validate our algorithm.

This paper focuses on the simultaneous extrinsic-odometric calibration of a mobile robot system equipped with odometric devices and a monocular camera. Most current approaches are based on either optimization or Gaussian filter, which depends on a manually provided initial guess. In this paper, we propose a two-step fully automatic calibration algorithm, which does not require any prior knowledge of the un-calibrated parameters. In the first step, both the odometric parameters and the extrinsic ones are estimated through a non-iterative auto initialization process. In the second step, a joint optimization problem is solved iteratively to obtain a refined calibration result. By exploiting the planar motion constraints of the landmark measurements, our auto initialization method outperforms a comparison approach in robustness against the image noise. Experiments are conducted with data sets collected from both simulation and an autonomous guided vehicle system, which validates the improvement.

This paper focuses on the calibration of a mobile robot system with odometry and a monocular camera. Most current approaches are based on either batch optimization or Bayesian filter, which require a good initial guess to obtain the optimal calibration results. In this paper, a two-step calibration algorithm is proposed for a fully automatic calibration of the camera-odometry system, consisting of: 1) a non-iterative auto initialization step for spatial extrinsic calibration based on the landmark measurements and 2) a joint optimization step to estimate both the spatio-temporal extrinsic parameters and the odometric parameters. By exploiting the planar constraints of landmark measurements, our auto initialization method can achieve better accuracy compared with the current solutions. Experiments are conducted based on both the simulation data sets and also the real world data sets collected from an autonomous guided vehicle (AGV) system, which validate our algorithm compared with a VO-based non-iterative method.