Yongliang Shi

ORCID: 0000-0003-3086-729X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Autonomous Vehicle Technology and Safety
  • Robotics and Sensor-Based Localization
  • Advanced Vision and Imaging
  • Robotic Path Planning Algorithms
  • Geographic Information Systems Studies
  • Indoor and Outdoor Localization Technologies
  • Robotics and Automated Systems
  • Traffic control and management
  • Vehicle Dynamics and Control Systems
  • Video Surveillance and Tracking Methods
  • Fuzzy Logic and Control Systems
  • Fire Detection and Safety Systems
  • Stability and Control of Uncertain Systems
  • Advanced Control Systems Design
  • Traffic and Road Safety
  • Lattice Boltzmann Simulation Studies
  • Modular Robots and Swarm Intelligence
  • Advanced Optical Imaging Technologies
  • Power Transformer Diagnostics and Insulation
  • Robotic Locomotion and Control
  • Remote Sensing and LiDAR Applications
  • Advanced Numerical Methods in Computational Mathematics
  • Neural dynamics and brain function
  • Nuclear Physics and Applications
  • Robot Manipulation and Learning

Tsinghua University
2023-2024

Beijing Institute of Technology
2024

Air University
2023

University of Pittsburgh
1987

In a paper published in 1978 Russian, Kharitonov proved that the strict Hurwitz property of set interval polynomials having complex coefficients may be established from eight extreme polynomials. The proof this significant result is advanced using elementary concepts circuit theory. approach not only provides clear and complete Kharitonov's generalized stability criterion but also has potentialities for generalization to bivariate and, subsequently, multivariate polynomial cases.

10.1109/tcs.1987.1086055 article EN IEEE Transactions on Circuits and Systems 1987-10-01

Unmanned SystemsAccepted Papers No AccessPlane-Aware Heightmap for Adaptable Footstep Planning in Discontinuous Coplanar TerrainChao Li, Yongliang Shi, Chencheng Dong, Qingqing Xuechao Chen, Zhangguo Yu, and Zhihong JiangChao Shi Search more papers by this author , Dong Li Chen Yu Jiang https://doi.org/10.1142/S2301385026500056Cited by:0 (Source: Crossref) Next AboutFiguresReferencesRelatedDetailsPDF/EPUB ToolsAdd to favoritesDownload CitationsTrack CitationsRecommend Library ShareShare...

10.1142/s2301385026500056 article EN Unmanned Systems 2025-01-22

The increasing demand for efficient last-mile delivery in smart logistics underscores the role of autonomous robots enhancing operational efficiency and reducing costs. Traditional navigation methods, which depend on high-precision maps, are resource-intensive, while learning-based approaches often struggle with generalization real-world scenarios. To address these challenges, this work proposes Openstreetmap-enhanced oPen-air sEmantic Navigation (OPEN) system that combines foundation models...

10.48550/arxiv.2502.09238 preprint EN arXiv (Cornell University) 2025-02-13

To address the practical navigation issues of rubber-tapping robots, this paper proposes an active system guided by trunk detection for a robot. A tightly coupled sliding-window-based factor graph method is proposed pose tracking, which introduces normal distribution transform (NDT) measurement factors, inertial unit (IMU) pre-integration and prior factors generated sliding window marginalization. actively pursue goals in navigation, distance-adaptive Euclidean clustering utilized...

10.3390/rs15153717 article EN cc-by Remote Sensing 2023-07-25

Abstract Particle Identification (PID) plays a central role in associating the energy depositions calorimeter cells with type of primary particle flow oriented detector system. In this paper, we propose novel PID methods based on Residual Network (ResNet) architecture which enable training very deep networks, bypass need to reconstruct feature variables, and ensure generalization ability among various geometries detectors, classify electromagnetic showers hadronic showers. Using Geant4...

10.1088/1748-0221/19/04/p04033 article EN Journal of Instrumentation 2024-04-01

Motion forecasting is an important component in autonomous driving systems. One of the most challenging problems motion interactive trajectory prediction, whose goal to jointly forecasts future trajectories interacting agents. To this end, we present a large-scale prediction dataset named INT2 for INTeractive at INTersections. includes 612,000 scenes, each lasting 1 minute, containing up 10,200 hours data. The agent are auto-labeled by high-performance offline temporal detection and fusion...

10.1109/iccv51070.2023.00784 article EN 2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2023-10-01

Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, reliance on HDMaps prevents autonomous from stepping into regions without this expensive digital infrastructure. This fact drives many researchers to study online HDMap generation algorithms, but performance these algorithms at far is still unsatisfying. We present P-MapNet, in which letter P highlights that we focus incorporating map priors improve model performance....

10.48550/arxiv.2403.10521 preprint EN arXiv (Cornell University) 2024-03-15

Robust and realistic rendering for large-scale road scenes is essential in autonomous driving simulation. Recently, 3D Gaussian Splatting (3D-GS) has made groundbreaking progress neural rendering, but the general fidelity of scene renderings often limited by input imagery, which usually a narrow field view focuses mainly on street-level local area. Intuitively, data from drone's perspective can provide complementary viewpoint ground vehicle's perspective, enhancing completeness...

10.48550/arxiv.2408.15242 preprint EN arXiv (Cornell University) 2024-08-27

Accurate localization is an essential technology for the flexible navigation of robots in large-scale environments. Both SLAM-based and map-based will increase computing load due to map size, which affect downstream tasks such as robot services. To this end, we propose a system based on Block Maps (BMs) reduce computational caused by maintaining maps. Firstly, introduce method generating block maps corresponding switching strategies, ensuring that can estimate state environments loading...

10.48550/arxiv.2404.18192 preprint EN arXiv (Cornell University) 2024-04-28

Robotic manipulation systems are urgently necessary to replace the labor generated by a avalanche of repetitive test tube operations in pharmaceutical, chemical, and biological fields. However, currently existing test-tube robot [1] have poor generality inefficiency object detection grasping reasoning. To this end, we propose robotic system for tubes arrangement harnessing geometric insights enhance efficiency. For detection, instead template matching [1], corner positioning method combining...

10.1109/robio58561.2023.10354814 article EN 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO) 2023-12-04

In the original paper, Y. Q. Shi, K. Yen, and C. M. Chen (IEEE Trans. Automat. Contr., vol. 38, no. 1, p. 125-8, 1993) present two simple necessary conditions for a polynomial with complex coefficients to be strictly Hurwitz. They claim that this is an extension refinement of result Xie (1988). Polyak Tsypkin comment second condition well known first one direct corollary Newton's test have only real roots. The authors express their appreciation certain points but state intention was point...

10.1109/9.284913 article EN IEEE Transactions on Automatic Control 1994-05-01
Coming Soon ...