19 accepted papers
In this work, we propose HE-VPR, a visual place recognition (VPR) framework that incorporates height estimation. Our system decouples height inference from place recognition, allowing both modules to share a frozen DINOv2 backbone. Two lightweight bypass adapter branches are integrated into our syst…
Accurate pedestrian navigation on edge devices is a critical problem. While artificial neural networks (ANNs) have been shown to effectively solve this problem with acceptable accuracy, their energy consumption limits applications on low-power computation platforms. Spiking neural networks (SNNs) ar…
Aerial Visual Place Recognition (VPR) is critical for Unmanned Aerial Vehicles (UAVs) localization, especially in environments with unstable or unavailable GPS signals. While neural network-based VPR methods have become mainstream, they face significant challenges on UAV platforms. Traditional CNN-b…
Image-goal navigation is a critical task in autonomous visual navigation, requiring the robot to navigate to a target localization specified by an image. Previous works using data-driven methods achieve great success while they mostly leverage simple network architecture and train it from scratch, w
In unknown environments, navigating a robot by a given image to a specific location or instance is critical and challenging. The existing end-to-end approaches require simultaneous implicit learning of multiple subtasks, and modular approaches depend on metric information. Both approaches face high
Aerial Visual Place Recognition (VPR) is critical for Unmanned Aerial Vehicles (UAVs) localization, especially in environments with unstable or unavailable GPS signals. While neural network-based VPR methods have become mainstream, they face significant challenges on UAV platforms. Traditional CNN-b
Visual localization plays an essential role in the autonomous flight of Unmanned Aerial Vehicles (UAVs) especially for the Global Navigation Satellite System (GNSS) denied environments. Existing aerial-based visual localization methods mainly focus on eliminating image variance between database map
This letter develops two distributed algorithms to solve multi-robot task assignment problems (MTAP). We first describe MTAP as an integer linear programming (ILP) problem and then reformulate it as a relaxed convex optimization problem. Based on the saddle-point dynamics, we propose two distributed
Visual Place Recognition (VPR) is a critical technology for achieving robust long-term visual geo-localization. During the past few years, VPR research mainly focused on ground-based platforms in the street-level captured scenes with deep learning methods (e.g. NetVLAD, GeM), but little attention wa
In this work, we propose a solution that leverages geospatial data to initialize the monocular visual-inertial navigation system. For Visual-Inertial Navigation Systems (VINS) operating on UAVs, the ability to perform initialization and relocalization in mid-air is essential. However, degenerate mot
Visual inertial odometry (VIO) is a popular solution for localization in the GPS-denied environment. However, current VIO algorithms' performance degrades in the visual degraded environment due to limited visual features. This paper presents a robust VIO algorithm with learned velocity constraints.
Bundle adjustment (BA) is a well-studied fundamental problem in the robotics and vision community. In man-made environments, coplanar points and lines are ubiquitous. However, the number of works on bundle adjustment with coplanar points and lines is relatively small. This paper focuses on this spec…
The applicability of SLAM algorithms is largely limited to the assumption of scene rigidity. Moreover, dynamic object perception is an essential technique for many robotic applications such as autonomous driving and multi-robot collaboration. In this letter, we present PointSLOT, an online, real-tim
Vision-based localization is an essential problem for autonomous systems while the performance of vision-based odometry degrades in the challenging scenario. This letter presents S-VIO, an RGB-D visual inertial odometry (VIO) which fully uses multi-sensor measurements (i.e. depth, RGB and IMU), hete
Point cloud registration is an essential technique for many tasks including autonomous navigation, augmented/virtual reality and scene reconstruction. In man-made environments, abundant plane features with structural regularities are commonly seen, which is actually beneficial for point cloud regist
Visual Inertial Odometry (VIO) is a widely studied localization technique in robotics. State-of-the-art VIO algorithms are composed of two parts: a frontend which performs visual perception and inertial measurement pre-processing, and a backend which fuses vision and inertial measurements to estimat…
In order to improve the accuracy of simultaneous localization and mapping problem, plane motion assumption is often used for advanced ground vehicle SLAM system. However, such an assumption is not always suitable to complex and changeable road scenes. In this letter, we propose a stereo-vision based
Simultaneous localization and object tracking (SLOT) is essentially important for autonomous systems. Tightly-coupled and loosely-coupled methods are two commonly used back-end frameworks for the state-of-the-art solutions of SLOT problem. However, some inherent limitations exist in these two framew
This letter presents an efficient and accurate simultaneous localization and mapping (SLAM) system in man-made environments. The Manhattan world assumption is imposed, with which the global orientation is obtained. The drift-free rotational motion estimation is derived from the structural regulariti