TLTianyi Li

Tianyi Li

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tianyi Li has a total of 15 co-authors. Here are the top co-authors by number of shared publications:

  • Shiyong Zhang

    College of Artificial Intelligence, Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China

    6 shared publications
  • Xuebo Zhang

    Institute of Robotics and Automatic Information Systems and Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China

    6 shared publications
  • Jing Yuan

    College of Artificial Intelligence, Nankai University, Tianjin, China

    2 shared publications
  • Qianli Dong

    College of Artificial Intelligence, Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China

    2 shared publications
  • Xuetao Zhang

    School of Control Science and Engineering, Dalian University of Technology, Dalian, China

    2 shared publications
  • Haobo Xi

    College of Artificial Intelligence, Institute of Robotics and Automatic Information System, Nankai University, Tianjin, China

    1 shared publication

Latest Publications

  • HIGHSTAR: High-Speed and Efficient Online Autonomous UAV Exploration

    by Qianli Dong, Xuebo Zhang, Shiyong Zhang, Ziyu Wang, Zhe Ma, Tianyi Li, Haobo Xi

    Unmanned aerial vehicles (UAVs) are widely used in autonomous exploration, but their motion speed is underutilized due to inaccurate motion time cost evaluation and high computational cost. Existing methods either fail to consider UAV’s motion tendency and environment simultaneously or can’t ensure real-time planning in large 3-D environments. This paper presents a consistent, high-speed, and efficient online autonomous UAV exploration method. First, a motion primitive activated graph search method is proposed to fully take advantage of the UAV’s current velocity and acceleration. It improves motion time cost evaluation by simulating short-term motion tendencies with motion primitives and reduces the computational cost by searching on a voxel graph with a dynamic upper bound. Then, a minimum time trajectory to the optimal viewpoint with a non-zero terminal velocity constraint in a convex hull is optimized. Finally, an SE(3) coverage trajectory for unknown space around the exploration path is further optimized. Simulations in various environments with different speed settings show that the proposed method’s average UAV velocity is 18.6%−116.1% faster and its exploration efficiency is 13.8%−49.5% higher than state-of-the-art methods. Real-world tests verify its effectiveness. The source code of our method will be released at: https://github.com/NKU-MobFly-Robotics/HighStar.


  • SGS-Planner: A Skeleton-Guided Spatiotemporal Motion Planner for Flight in Constrained Space

    by Tianyi Li, Shiyong Zhang, Xuebo Zhang, Qianli Dong, Junsheng Huang

    This article proposes a skeleton-guided spatiotemporal motion planner (SGS-Planner) for safe and efficient aerial robot navigation in challenging constrained space. The planner takes advantage of a spatial-temporal hierarchical framework to generate a safer and more efficient trajectory rapidly. In spatial planning, different from existing approaches that either ignore the clearance between trajectories and obstacles or suffer from local minima, path smoothing is guided by a skeleton away from obstacles. Specifically, a fast sphere inflation-based skeleton extraction method is elaborately designed for high-clearance path searching. After that, we propose a skeleton-guided path smoothing approach to generate smooth and high-clearance paths, where the smoothing is formulated as unconstrained quadratic programs. In temporal planning, the feasible trajectory is generated along the optimized path by employing an optimal time allocation method and a parallel back-up strategy to guarantee the success of planning. We validate the performance of the proposed method in extensive challenging simulations and real-world environments. Comparative results show that our approach outperforms state-of-the-art methods in terms of planning success rate, average computational efficiency (5–24 times faster), and minimum clearance (12%–177% larger) in restricted space.


  • IR-VIO: Illumination-Robust Visual-Inertial Odometry Based on Adaptive Weighting Algorithm With Two-Layer Confidence Maximization

    by Zhixing Song, Xuebo Zhang, Tianyi Li, Shiyong Zhang, Youwei Wang, Jing Yuan

    Illumination change, image blur, and fast motion dramatically decrease the performance of visual-inertial navigation systems (VINS). This article presents a new illumination-robust visual-inertial odometry (IR-VIO) based on adaptive weighting algorithm with two-layer confidence maximization. First, to prevent the VIO performance degradation caused by poor image quality in complex scenes and ignoring the confidence differences of feature points, we develop a novel adaptive weighting algorithm on the multisensor layer and visual feature layer to better fuse multisensor information and maximize the overall confidence of VIO. Second, to solve the problems of image feature tracking difficulty and excessive image noise in illumination-changing scenes, an image enhancement algorithm is introduced to enhance consecutive images to the same brightness level, while a block noise removal algorithm with constraint protection mechanism is proposed to dynamically remove noise points. Finally, experimental results in the public dataset and real-world environments demonstrate that IR-VIO has superior performance in terms of accuracy and robustness compared with the state-of-the-art methods.


  • CBF Based Geometric Visual Servoing Control for Quadrotors with FOV Constraint

    by Haoran Zhang, Runhua Wang, Xuetao Zhang, Tianyi Li, Shiyong Zhang, Xuebo Zhang

  • Fast Active Aerial Exploration for Traversable Path Finding of Ground Robots in Unknown Environments

    by Shiyong Zhang, Xuebo Zhang, Tianyi Li, Jing Yuan, Yongchun Fang

    This article proposes an autonomous aerial exploration framework for traversable path finding of ground robots in unknown environments to achieve a fast response in search and rescue (SAR) missions. Different from existing works, our method provides a task-oriented active exploration strategy that makes the aerial robot fully autonomous during the exploration and does not require human intervention. To identify the candidate regions which ground robots can go through, a fast incremental traversability estimation algorithm is presented, which can evaluate the traversability of the region of interest (ROI) efficiently. Based on the traversability map, we propose a highly efficient frontier detection algorithm that can guarantee both reachability and safety of the extracted frontiers. To reduce the total response time of the whole robot system, a new cost function considering both the time costs of the aerial and ground robots is designed that aims to avoid back-and-forth motion behavior during aerial exploration. The performance of our approach is evaluated in both simulation and real-world experiments. The results show that the proposed method outperforms existing methods in terms of traversability estimation and frontier detection time (about one order of magnitude faster) as well as the response time (at least 13% shorter on average).