Li Sun

Over the past decade, the use of 3D Time-of-Flight (ToF) LiDARs in mobile robotics has grown rapidly. Based on our accumulation of relevant research, this paper systematically reviews and analyzes the use of 3D ToF LiDARs for mobile robotics under harsh conditions such as adverse weather, GPS-denied, and highly dynamic environments for both research and industrial applications. The former include LiDAR data processing in adverse weather, object detection, and autonomous navigation. The latter encompasses autonomous driving, service robotics, and public health crises applications. We hope that our efforts can effectively provide readers with a reference based on our hands-on experiences and promote the deployment of existing mature technologies in real-world systems.

Cross-modality pose estimation/localization is a critical challenge for multi-sensor-based perception systems, with applications spanning vehicle localization and online calibrations. In this letter, we introduce a hybrid approach to estimate the camera pose with respect to a point cloud with co-visibility. This approach adopts a coarse-to-fine scheme, utilizing a learning-based pose estimator to initially estimate a coarse pose, followed by an optimization-based method for precise geometry alignment. Initially, we propose a neural network utilizing multi-scale cross-attention to predict the co-visible points between the camera and the point cloud. Simultaneously, a coarse pose is estimated from the tightly-coupled dual-modal features. Initialized by the coarsely estimated pose, an optimization-based approach is employed to minimize the reprojection error of the co-visible point cloud onto the imaging plane. The proposed approach is fully evaluated on the KITTI and nuScenes datasets, and superior experimental results are achieved with the comparison of SOTA methods.

As an intangible cultural heritage of human beings, rice paper technology can be used as a design theme in the environment to improve the cultural quality of the environment. To spread the culture of rice paper, it is necessary to export the cultural content naturally. An immersive environment makes this easier to achieve. In the environment construction of rice paper culture, the atmosphere of rice paper culture is reflected as a whole through space layout and lighting atmosphere. The immersive environment construction with the help of virtual reality technology and interactive technology is a more detailed and vivid visual expression form. Through the overall and detailed visualization scheme design, the effect of inheriting the intangible cultural heritage of Rice paper in the state of deep addiction is realized.

This paper introduces a method and experiment using free-space, pulsed, optical time transfer, through turbid water to synchronize spatially distant chip-scale atomic clocks. This experiment uses one-way time transfer. Clock discrepancy is computed by comparing the measured departure time from Module A to the measured arrival time at the Module B, after accounting for the estimated time of flight. The effect of the turbidity is calculated and compared through clock discrepancy and time transfer stability for an empty tank, still water, turbid water, and fog.

The field of autonomous driving has grown tremendously over the past few years, along with the rapid progress in sensor technology. One of the major purposes of using sensors is to provide environment perception for vehicle understanding, learning and reasoning, and ultimately interacting with the environment. In this paper, we first introduce a multisensor platform allowing vehicle to perceive its surroundings and locate itself in a more efficient and accurate way. The platform integrates eleven heterogeneous sensors including various cameras and lidars, a radar, an IMU (Inertial Measurement Unit), and a GPS-RTK (Global Positioning System / Real-Time Kinematic), while exploits a ROS (Robot Operating System) based software to process the sensory data. Then, we present a new dataset (https://epan-utbm.github.io/utbm_robocar_dataset/) for autonomous driving captured many new research challenges (e.g. highly dynamic environment), and especially for long-term autonomy (e.g. creating and maintaining maps), collected with our instrumented vehicle, publicly available to the community.

This paper proposes a novel approach for global localisation of mobile robots in large-scale environments. Our method leverages learning-based localisation and filtering-based localisation, to localise the robot efficiently and precisely through seeding Monte Carlo Localisation (MCL) with a deeplearned distribution. In particular, a fast localisation system rapidly estimates the 6-DOF pose through a deep-probabilistic model (Gaussian Process Regression with a deep kernel), then a precise recursive estimator refines the estimated robot pose according to the geometric alignment. More importantly, the Gaussian method (i.e. deep probabilistic localisation) and nonGaussian method (i.e. MCL) can be integrated naturally via importance sampling. Consequently, the two systems can be integrated seamlessly and mutually benefit from each other. To verify the proposed framework, we provide a case study in large-scale localisation with a 3D lidar sensor. Our experiments on the Michigan NCLT long-term dataset show that the proposed method is able to localise the robot in 1.94 s on average (median of 0.8 s) with precision 0.75 m in a largescale environment of approximately 0.5 km ² .

Robot-assisted endobronchial intervention requires accurate localisation based on both intra- and pre-operative data. Most existing methods achieve this by registering 2D videos with 3D CT models according to a defined similarity metric with local features. Instead, we formulate the bronchoscopic localisation as a learning-based global localisation using deep neural networks. The proposed network consists of two generative architectures and one auxiliary learning component. The cycle generative architecture bridges the domain variance between the real bronchoscopic videos and virtual views derived from pre-operative CT data so that the proposed approach can be trained through a large number of generated virtual images but deployed through real images. The auxiliary learning architecture leverages complementary relative pose regression to constrain the search space, ensuring consistent global pose predictions. Most importantly, the uncertainty of each global pose is obtained through variational inference by sampling within the learned underlying probability distribution. Detailed validation results demonstrate the localisation accuracy with reasonable uncertainty achieved and its potential clinical value.