A Hierachical Hybrid Method for Simultaneous Localization and Mapping
| Authors: | Huang G.Q., The Hong Kong Polytechnic University, Hong Kong
Rad A.B., The Hong Kong Polytechnic University, Hong Kong
Wong Y.K., The Hong Kong Polytechnic University, Hong Kong |
|---|
| Topic: | 4.3 Robotics |
|---|
| Session: | Guidance, Navigation, and Control of Robots |
|---|
| Keywords: | Autonomous Mobile Robot (AMR), Simultaneous Localization and Mapping (SLAM), Maximum Likelihood (ML), Extended Kalman Filter (EKF), Occupancy grid map, Feature-based map. |
|---|
Abstract
In robotics literature, most of existing Simultaneous Localization and Mapping (SLAM) algorithms are limited by the size and type of the environments they can handle. A few methods can cope with large scale environments. In this paper, we propose a novel hierarchical hybrid method for SLAM in large scale and cyclic environments: locally solve SLAM by Maximum Likelihood (ML) with occupancy grid map, and globally by Extended Kalman Filter (EKF) with feature-based map. Experiments validated on Pioneer 2DX mobile robot demonstrate the capabilities and the robustness of our proposed algorithm.
