XLXuchen Liu

Xuchen Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xuchen Liu has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Open3D-VQA: A Benchmark for Embodied Spatial Concept Reasoning with Multimodal Large Language Model in Open Space

    by Weichen Zhang, Zile Zhou, Xin Zeng, Liu Xuchen, Jianjie Fang, Chen Gao, Jinqiang Cui, Yong Li, Xinlei Chen, Xiao-Ping Zhang


  • Aqua Slide: An Underwater Leveling Motion Scheme for M-UAAV Utilizing Singularity

    by Dongyue Huang, Minghao Dou, Xuchen Liu, Xinyi Wang, Chenggang Wang, Ben M. Chen

    The underwater leveling motion control of a morphable unmanned aerial–aquatic vehicle (M-UAAV) is essential but lacks an elegant solution. In this article, a scheme named Aqua Slide is proposed for Mirs-Alioth, our predeveloped M-UAAV prototype, to achieve underwater leveling motions by utilizing singularity. For the first time, the singular thrust tilt angle (STTA), i.e., the tilt angle that causes a vehicle to reach singularity, is characterized and defined. For underwater leveling motion generation, STTA is utilized as a key tool. Crucial factors of these motions, i.e., the existence of control direction uncertainty, and coupling effects are identified. Aqua Slide is proposed to tackle the crucial factors in generating underwater leveling motions, consisting of an STTA controller, a primary-auxiliary switch, and an auxiliary controller incorporating the saturated Nussbaum function. A simulation environment, enriched with a detailed model, is established using a Gazebo and hardware-in-the-loop (HITL) configuration. Under similar control parameter settings, full-cycle Gazebo-HITL simulations and experiments reveal the effectiveness of the approach. The vehicle maintains the attitude within a maximum of 5${}^{\circ}$ during the whole procedure. Meanwhile, the ablation studies in Aqua Slide highlight the indispensability of the submodules in the approach. The absence of any module results in undesirable or even divergent behavior of Mirs-Alioth during underwater leveling motions. The preliminary exploration in this article elegantly solves the issue of generating underwater leveling motion for an M-UAAV and provides a referential solution for transitioning from simulation to real-world applications. Video attachment: https://youtu.be/XpViXL0qcvk.


  • TJ-FlyingFish: An Unmanned Morphable Aerial–Aquatic Vehicle System

    by Xuchen Liu, Minghao Dou, Ruixin Yan, Dongyue Huang, Songqun Gao, Biao Wang, Jinqiang Cui, Qinyuan Ren, Lihua Dou, Zhi Gao, et al.

    In this paper, we present in this work a fairly complete process for developing an unmanned aerial–aquatic vehicle system, TJ-FlyingFish, which includes an innovative design methodology of the aerial–aquatic platform and the cross-medium localization, dynamics modeling, and flight control systems. The development faces the challenge how to manipulate locomotion effectively in both water and air which presents substantial differences in fluid properties. Additionally, there are difficulties in perception and navigation because of the discontinuity of mediums. To cope with these challenges, we designed an innovative unmanned aerial–aquatic vehicle with an optimized dual-speed and tilting propulsion configuration. The rotors/propellers operate in different ranges of rotating speed in the two different mediums, providing sufficient thrust and ensuring output efficiency. Besides, thrust vectoring is achieved by rotating each propulsion unit around its mounted arm, facilitating agile underwater cruising. Another key component of our approach is a sophisticated multi-sensor-based cross-medium localization system that combines SLAM, sensor synchronization, and data capture mechanisms, enabling seamless transitions between aerial and aquatic environments, and supporting autonomous operations. The results are fully validated through actual flight experiments.


  • Web crawler for fault diagnosis of CNC machine tools

    by Chaoyu Li, Xuchen Liu, Siyu Qian, Jialu Ren, Xinyi Tang

    In the era of soaring network information resources, as the foundation and an important part of big data, the role of web crawlers is particularly important [1]. In the field of CNC machine tool diagnosis, the data is widely distributed and the data exists in different forms, but with the deepening of industrial automation, digitization and intelligence [2], enterprises urgently need to realize fault diagnosis and troubleshooting of CNC machine tools. Therefore, it is of great practical significance to collect these data and form a knowledge base of CNC machine tool fault diagnosis [3]. This paper introduces the difficulties faced by CNC machine tool fault diagnosis data collection and countermeasures, the basic concepts of web crawlers, distributed crawlers and machine learning-based web crawlers, as well as their respective architectures and crawling strategies.