Liu Haotian, Chen Guang, Liu Yinlong, Liang Zichen, Zhang Ruiqi, Knoll Alois
State Key Laboratory of Vehicle NVH and Safety Technology, Chongqing, China.
School of Automotive Studies, Tongji University, Shanghai, China.
Front Neurorobot. 2022 Mar 3;16:820703. doi: 10.3389/fnbot.2022.820703. eCollection 2022.
Planar motion constraint occurs in visual odometry (VO) and SLAM for Automated Guided Vehicles (AGVs) or mobile robots in general. Conventionally, two-point solvers can be nested to RANdom SAmple Consensus to reject outliers in real data, but the performance descends when the ratio of outliers goes high. This study proposes a globally-optimal Branch-and-Bound (BnB) solver for relative pose estimation under general planar motion, which aims to figure out the globally-optimal solution even under a quite noisy environment. Through reasonable modification of the motion equation, we decouple the relative pose into relative rotation and translation so that a simplified bounding strategy can be applied. It enhances the efficiency of the BnB technique. Experimental results support the global optimality and demonstrate that the proposed method performs more robustly than existing approaches. In addition, the proposed algorithm outperforms state-of-art methods in global optimality under the varying level of outliers.
平面运动约束普遍存在于视觉里程计（VO）以及自动导引车（AGV）或移动机器人的同步定位与地图构建（SLAM）中。传统上，两点求解器可嵌套于随机抽样一致性算法中，以剔除真实数据中的异常值，但当异常值比例较高时，性能会下降。本研究提出了一种用于一般平面运动下相对位姿估计的全局最优分支定界（BnB）求解器，其目的是即使在噪声相当大的环境下也能找出全局最优解。通过对运动方程进行合理修改，我们将相对位姿解耦为相对旋转和平移，从而可以应用简化的边界策略。这提高了BnB技术的效率。实验结果支持了全局最优性，并表明所提方法比现有方法表现得更稳健。此外，在所提算法在不同异常值水平下的全局最优性方面优于现有方法。
