Accurate and robust localization is a fundamental need for mobile agents. Visual-inertial odometry (VIO) algorithms exploit the information from camera and inertial sensors to estimate position and translation. Recent deep learning based VIO models attract attentions as they provide pose information in a data-driven way, without the need of designing hand-crafted algorithms. Existing learning based VIO models rely on recurrent models to fuse multimodal data and process sensor signal, which are hard to train and not efficient enough. We propose a novel learning based VIO framework with external memory attention that effectively and efficiently combines visual and inertial features for states estimation. Our proposed model is able to estimate pose accurately and robustly, even in challenging scenarios, e.g., on overcast days and water-filled ground, which are difficult for traditional VIO algorithms to extract visual features. Experiments validate that it outperforms both traditional and learning based VIO baselines in different scenes.

Efficient and robust visual place recognition is of great importance to autonomous mobile robots. Recent work has shown that features learned from convolutional neural networks (CNNs) achieve impressed performance with efficient feature size, where most of them are pooled or aggregated from a convolutional feature map. However, convolutional filters only capture the appearance of their perceptive fields, which lack the considerations on how to combine the multiscale appearance for place recognition. In this paper, we propose a novel method to build a multiscale feature pyramid and present two approaches to use the pyramid to augment the place recognition capability. The first approach fuses the pyramid to obtain a new feature map, which has an awareness of both local and semi-global appearance, and the second approach learns an attention model from the feature pyramid to weight the spatial grids on the original feature map. Both approaches combine the multiscale features in the pyramid to suppress the confusing local features while tackling the problem in two different ways. Extensive experiments have been conducted on benchmark datasets with varying degrees of appearance and viewpoint variations. Results show that the proposed approaches achieve superior performance over the networks without the multiscale feature fusion and the multiscale attention components. Analyses on the performance of using different feature pyramids are also provided.

Collaborative simultaneous localization and mapping have a great impact on various applications such as search-and-rescue and agriculture. For each agent, the key to performing collaboration is to measure the motion relative to other participants or external anchors; currently, this is mainly accompanied by (1) matching to the shared maps from other agents or (2) measuring the range to anchors with UWB devices. While requiring multiple agents to visit the same area can decrease the task efficiency and anchors demand a distribution process, this paper proposes to use a monocular camera, an inertial measurement unit (IMU), and a UWB device as the onboard sensors on each agent to build an accurate and efficient centralized collaborative SLAM system. For each participant, visual-inertial odometry is adopted to estimate the motion parameters and build a local map of the explored areas. The agent-to-agent range is measured by the onboard UWB and is published to the central server together with the estimated motion parameters and the reconstructed maps. We designed a global optimization algorithm to make use of the cross-agent map match information detected by a visual place technique, and the agent-to-agent range information to optimize the motion parameter of all the participants and merge the local maps into a global map. Compared with existing collaborative SLAM systems, the proposed system can perform collaboration with onboard UWB measurements only, vision only, and a combination of these; this greatly improves the adaptiveness and robustness of the collaborative system. We also present an in-depth analysis of C2VIR-SLAM in multiple UAV real-flight datasets.

This paper presents a framework for a strapdown Inertial Navigation System (INS) algorithm design by using Lie group and Lie algebra. The general way to solve Lie group differential equations is introduced. Investigations reveal that this general Lie group method provides a simpler unified way to solve differential equations involving direction cosine matrix, quaternion and dual quaternion, which are widely used in INS algorithm design. Furthermore, we also present a new INS algorithm based on the Special Euclidean group se(3) under the guidelines of Lie group method. Analyses show that se(3) algorithm has the same accuracy as a dual quaternion algorithm, this is also justified by numerical simulations. Though the se(3) algorithm has no improvements in accuracy, the general Lie group method used in the design process shows its brevity and uniformity.