We present a simple yet effective method to address loop closure detection in simultaneous localisation and mapping using local 3D deep descriptors (L3Ds). L3Ds are emerging compact representations of patches extracted from point clouds that are learnt from data using a deep learning algorithm. We propose a novel overlap measure for loop detection by computing the metric error between points that correspond to mutually-nearest-neighbour descriptors after registering the loop candidate point cloud by its estimated relative pose. This novel approach enables us to accurately detect loops and estimate six degrees-of-freedom poses in the case of small overlaps. We compare our L3D-based loop closure approach with recent approaches on LiDAR data and achieve state-of-the-art loop closure detection accuracy. Additionally, we embed our loop closure approach in RESLAM, a recent edge-based SLAM system, and perform the evaluation on real-world RGBD-TUM and synthetic ICL datasets. Our approach enables RESLAM to achieve a better localisation accuracy compared to its original loop closure strategy.

Three-dimensional (3D) printing technology has been proved to be a powerful tool for the free-form fabrication of titanium (Ti) implants. However, the surface quality of 3D printed Ti implants is not suitable for clinical application directly. Therefore, surface modification of 3D printed Ti implants is required in order to achieve good biocompatibility and osseointegration. In this study, a novel surface modification method of 3D printed Ti–6Al–4V implants has been proposed, which combined acid etching with hydrothermal treatment to construct micro/nanostructures. Polished TC4 sheets (P), electron beam melting Ti sheets (AE), and micro/nanostructured Ti sheets (AMH) were used in this study to evaluate the effects of different surface morphologies on cellular responses. The surface morphology and 3D topography after treatment were detected via scanning electron microscopy and laser scanning microscopy. The results illustrated that a hierarchical structure comprising micro-valleys and nanowires with a surface roughness of 14.388 μm was successfully constructed. Compared with group P samples, the hydrophilicity of group AMH samples significantly increased with a reduced water contact angle from 54.9° to 4.5°. Cell culture experiments indicated that the micro/nanostructures on the material surface could enhance the cell adhesion and proliferation of MC3T3s. The microstructure could enhance bone-to-implant contact, and the nanostructure could directly interact with some cell membrane receptors. Overall, this study proposes a new strategy to construct micro/nanostructures on the surface of 3D printed Ti–6Al–4V implants and may further serve as a potential modification method for better osteogenesis ability.