UTS site search

Gibson Hu

Image of Gibson Hu
Senior Software Engineer, School of Mechanical and Mechatronic Engineering


Hu, G., Khosoussi, K. & Huang, S. 2013, 'Towards a Reliable SLAM Back-End', IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Tokyo, Japan, pp. 37-43.
View/Download from: UTS OPUS or Publisher's site
In the state-of-the-art approaches to SLAM, the problem is often formulated as a non-linear least squares. SLAM back-ends often employ iterative methods such as Gauss-Newton or Levenberg-Marquardt to solve that problem. In general, there is no guarantee on the global convergence of these methods. The back-end might get trapped into a local minimum or even diverge depending on how good the initial estimate is. Due to the large noise in odometry data, it is not wise to rely on dead reckoning for obtaining an initial guess, especially in long trajectories. In this paper we demonstrate how M-estimation can be used as a bootstrapping technique to obtain a reliable initial guess. We show that this initial guess is more likely to be in the basin of attraction of the global minimum than existing bootstrapping methods. As the main contribution of this paper, we present new insights about the similarities between robustness against outliers and robustness against a bad initial guess. Through simulations and experiments on real data, we substantiate the reliability of our proposed method.
Hu, G., Huang, S., Zhao, L., Alempijevic, A. & Dissanayake, G. 2012, 'A Robust RGB-D SLAM algorithm', 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Algarve, Portugal, pp. 1174-1179.
View/Download from: UTS OPUS or Publisher's site
Recently RGB-D sensors have become very popular in the area of Simultaneous Localisation and Mapping (SLAM). The major advantage of these sensors is that they provide a rich source of 3D information at relatively low cost. Unfortunately, these sensors in their current forms only have a range accuracy of up to 4 metres. Many techniques which perform SLAM using RGB-D cameras rely heavily on the depth and are restrained to office type and geometrically structured environments. In this paper, a switching based algorithm is proposed to heuristically choose between RGB-BA and RGBD-BA based local maps building. Furthermore, a low cost and consistent optimisation approach is used to join these maps. Thus the potential of both RGB and depth image information are exploited to perform robust SLAM in more general indoor cases. Validation of the proposed algorithm is performed by mapping a large scale indoor scene where traditional RGB-D mapping techniques are not possible.
Wang, H., Hu, G., Huang, S. & Dissanayake, G. 2012, 'On the Structure of Nonlinearities in Pose Graph SLAM', 2012 Robotics: Science and Systems Conference, The MIT Press, Sydney, Australia, pp. 1-8.
View/Download from: UTS OPUS
Pose graphs have become an attractive representation for solving Simultaneous Localization and Mapping (SLAM) problems. In this paper, we analyze the structure of the nonlinearities in the 2D SLAM problem formulated as the optimizing of a pose graph. First, we prove that finding the optimal configuration of a very basic pose graph with 3 nodes (poses) and 3 edges (relative pose constraints) with spherical covariance matrices, which can be formulated as a six dimensional least squares optimization problem, is equivalent to solving a one dimensional optimization problem. Then we show that the same result can be extended to the optimizing of a pose graph with two anchor nodes where every edge is connecting to one of the two anchor nodes. Furthermore, we prove that the global minimum of the resulting one dimensional optimization problem must belong to a certain interval and there are at most 3 minima in that interval. Thus the globally optimal pose configuration of the pose graph can be obtained very easily through the bisection method and closed-form formulas.