Machine learning for LiDAR-based place recognition

Abstract

Simultaneous Localization and Mapping (SLAM) is one of the most essential techniques in many real-world robotic applications. The assumption of static environments is common in most SLAM algorithms, which however, is not the case for most applications. Recent work on semantic SLAM aims to understand the objects in an environment and distinguish dynamic information from a scene context by performing image-based segmentation. However, the segmentation results are often imperfect or incomplete, which can subsequently reduce the quality of mapping and the accuracy of localization. In this Final Year Project, a robust multi-modal semantic framework is presented to solve the SLAM problem in complex and highly dynamic environments. A more powerful object feature representation learning is proposed and the mechanism of re-looking and re-thinking is deployed to the backbone network, which leads to a better segmentation result to the adopted baseline instance segmentation model. Moreover, both geometric-only clustering and visual semantic information are combined to reduce the effect of segmentation error due to small-scale objects, occlusion and motion blur. Thorough experiments have been carried out to evaluate the effectiveness of the proposed multi-modal semantic SLAM method. The experimental results indicate that the proposed SLAM system can precisely identify dynamic objects under recognition imperfection and motion blur. Moreover, the proposed SLAM framework is able to efficiently build a static dense map at a processing rate of more than 10 Hz, which can be implemented in many practical applications.