Compared to diverse feature detectors and descriptors used for visual scenes, describing a
place using structural information is relatively less reported. Recent advances in …

Long‐term operation of robots creates new challenges to Simultaneous Localization and
Map** (SLAM) algorithms. Long‐term SLAM algorithms should adapt to recent changes …

Abstract Simultaneous Localization and Map** (SLAM) and Autonomous Driving are
becoming increasingly more important in recent years. Point cloud-based large scale place …

Loop closure can effectively eliminate the accumulated error and plays an important role in
Simultaneous Localization and Map** (SLAM). There remains challenges in loop …

Typical attempts to improve the capability of visual place recognition techniques include the
use of multi-sensor fusion and the integration of information over time from image …

Combining multiple complementary techniques together has long been regarded as a way
to improve performance. In visual localization, multi-sensor fusion, multi-process fusion of a …

Place recognition is a critical component towards addressing the key problem of
Simultaneous Localization and Map** (SLAM). Most existing methods use visual images; …

3D visual recognition is a prerequisite for most autonomous robotic systems operating in the
real world. It empowers robots to perform a variety of tasks, such as tracking, understanding …

In recent years, place recognition techniques have been extensively studied in the domain
of robotic map**, referred to as appearance-based map**. Nonetheless, the majority of …

Acceptance of social robots in human-robot collaborative environments depends on the
robots' sensitivity to human moral and social norms. Robot behavior that violates norms may …