Xueming Xiao

• Ph.D
• CVIR leader at Changchun University of Science and Technology

The deployment of the robotic system that executes specific task is being challenged by the prevalence of dynamic objects in real‐world scenes. Two robotic tasks sparked by this challenge, known as dynamic Simultaneous Localization and Mapping (SLAM) and moving object perception, are crucial for enhancing system robustness and reinforcing environme...

Situation awareness on Mars is indispensable for various downstream applications such as navigation and path planning, mapping and scientific discover. However, current Mars rover platform suffered from the absence of global information, leading to mission reduction and the failure of global planning. Compared to the rover, Mars helicopter is a new...

In the scenario of on-orbit servicing, the complex space environment and the strict limitation of spacesuits made the manual control of manipulator extremely inconvenient. Current remote-control methods such as voice control, are commonly affected by the signal ratio, especially in the case of solar wind. Therefore, in this paper, we proposed a ges...

With the increase in the number of types of spectrometers in use, calibration models cannot be shared among different instruments, however, this problem can be solved via calibration transfer (CT). In this study, a variety of modern process analysis technology (PAT) data are taken as the research object. After preprocessing the spectra data using p...

Martian surface, as a typical unstructured terrain, is extremely challenging for Mars exploration missions. Commonly, Mars rovers require multiple sensors to explore such harsh environment, such as depth cameras, range finder and other devices. However, the onboard load, power and storage of rovers are not sufficient to achieve high-level stereosco...

In future multi-agent Mars detection schemes, the Mars helicopter can assist the scientific missions of Mars rovers by providing navigation information and scientific objects. However, Mars surface exhibits a complex topography with diverse objects and similar textures to the background, posing a great challenge for existing CNN-based object detect...

Martian rock segmentation aims to separate rock pixels from background, which plays a crucial role in downstream tasks, such as traversing and geologic analysis by Mars rovers. The U-Nets have achieved certain results in rock segmentation. However, due to the inherent locality of convolution operations, U-Nets are inadequate in modeling global cont...

Semantic segmentation of Mars scenes has a crucial role in Mars rovers science missions. Current convolutional neural network (CNN)-based composition of U-Net has powerful information extraction capabilities; however, convolutional localization suffers from the limited global context modeling capability. Although transformer global modeling has per...

Martian terrain segmentation aims to assign all pixels of an input image with various terrain labels, which provides a firm support for the downstream research on rover traversing and geologic analysis tasks. However, existing studies in this field suffer from limitations in two aspects: one is the lack of large-scale and high-quality Martian terra...

Semantic segmentation of Martian terrain is crucial for the route planning and autonomous navigation of rovers on Mars. However, existing methods are restricted to structured or semi-structured scenes, performing poorly on Mars that is a completely unstructured environment. Therefore, we propose a novel hybrid attention semantic segmentation (HASS)...

Reconfigurable robots have excellent reconfigurability and environmental adaptability, but the configuration design method to select appropriate configuration with different environments has not been fully studied. Most of the existing work is based on the known global environment information, or only focus on the structure design. How to effective...

This article presents two kernel-based rock detection methods for a Mars rover. Rock detection on planetary surfaces is particularly pivotal for planetary vehicles regarding navigation and obstacle avoidance. However, the diverse morphologies of Martian rocks, the sparsity of pixel-wise features, and engineering constraints are great challenges to...

This paper proposes a novel fast terminal sliding mode (FTSM) control scheme, which accelerates convergence of the controlled system both in its approaching and after reaching the sliding manifold. The novelty lies in the design of time-varying sliding surface without a priori knowledge of the initial system states, so achieving insensitivity to th...

This paper presents a high-altitude hazard detection method for Mars landing. Current terminal-triggered methods do not fully support re-targeting maneuvers if all regions are found unsafe. Towards safe landing requirements for future missions, hazard detection should be triggered as soon as possible. We therefore proposed a lidar-based high altitu...

Reconfigurability in versatile systems of modular robots is achieved by appropriately actuating individual modular units. Optimizing the distribution of active and passive modules in modular architecture can significantly reduce both cost and energy of a reconfiguration task. This paper presents a methodology for planning this distribution in modul...

The key issue in on-orbit manipulation is to transport large flexible modules to pre-assembly position accurately. However, the cooperative manipulation by a team of space robots can induce large vibration in the robot-beam system. This paper presents a two-time scale control scheme for vibration minimization in trajectory tracking of the flexible...

In this paper, we propose a novel autonomous Martian rock detection framework via superpixel segmentation. Different from current state-of-the-art pixel-level rock segmenting methods, the proposed method deals with this issue in region level. Image is splitted into homogeneous regions based on intensity information and spatial layout. The heart of...

In this work, we propose a novel auto rock detection scheme via sparse-based background modeling for planetary rover. Instead of pixel-level image processing and pre-training, we deal with the detection issue by region contrast enhancement. Our method consists of a rough detection algorithm to auto-label conservative background regions and a backgr...

This article investigates the order-reduction method for multi-spacecraft cooperative tracking control problems considering non-uniform time delays. The tracking error system is constructed as a linear time-varying (LTV) system since the orbit of the reference point is an ellipse. To facilitate the controller design, a model transformation method i...

In this paper, we present a new autonomous rock detection approach through region contrast. Unlike current state-of-art pixel-level rock segmenting methods, new method deals with this issue in region level, which will significantly reduce the computational cost. Image is firstly splitted into homogeneous regions based on intensity information and s...

An innovative three-dimensional hazard detection algorithm is proposed for a planetary safe landing mission. Typically, plane fitting is carried out to approximate the surface of the planetary terrain. Current state-of-the-art plane estimation methods with a low breakdown point do not meet the requirements of future pinpoint landing missions. In th...