Tianhai Wang

Tianhai Wang

Ph.D. Student

😃 About Me

I am currently a Ph.D. student at the Laboratory of Field Phenomics at The University of Tokyo, fully funded by the UTokyo SPRING GX Project (JST SPRING Program). My current research focuses on developing highly integrated autonomous field robots for smart orchards, with a particular emphasis on Digital Twin technologies and Sim2Real transfer.

Prior to joining UTokyo, I obtained my M.Eng. degree from China Agricultural University, where I worked on automatic perception and navigation for agricultural robots, exploring zero-shot learning and LiDAR-camera panoramic fusion. I received my B.Eng. degree from Guangxi University in 2021.

Research interest: field robotics, plant phenotyping, and smart agriculture.

🔥 News

🛠️ Current Projects - Digital Twin and Virtual Reality for Orchard Robotics

sym

The primary objective of this research is to develop a highly integrated autonomous field robot system capable of precision pruning in smart orchards, including machine vision system development, automatic navigation system development, and end-effector control system development.

Ultimately, we aim to achieve Embodied AI systems based on end-to-end Vision-Language-Action models.

At the beginning, we focus on constructing simulation environments for the training and testing of robots through Digital Twin and Virtual Reality, designing a 3D World Foundation Model for orchards, and providing a systematic and comprehensive benchmark dataset for the field of agricultural engineering.

Supervisor:

Related Support:

✅ Completed Projects

  • Multi-agent collaboration and obstacle avoidance system for wheat production

This work focuses on object detection and tracking based on multi-sensor fusion in unstructured farmland environment. Especially, I’m dedicated to realizing the detection of unknown objects in open environment via few/zero-shot learning, open set recognition, etc.

In addition, I participated in the development of multi-agent collaborative system as a main member. In this project, I am responsible for path planning and task allocation algorithms in the harvesting-unloading-transportation process of wheat production. According to constraints of plot location, task number, operation time window, and path planning, intelligent scheduling model was established based on non-dominated sorting genetic and colony algorithms.

Supervisor:

Object detection and tracking based on multi-sensor fusion

Multi-sensor
Fusion
sym

Multi-agent collaborative system for agricultural production


sym

  • Robot patrol based on Simultaneous Localization And Mapping (SLAM)

sym

This robot is designed to perform random movement indoors and real-time object detection, which can check whether there are suspicious persons in the room. In this project, I am the team leader and mainly responsible for the development of 3D modeling, object detection, and Simultaneous Localization And Mapping (SLAM). In a ministerial-level innovation competition, our team won the second prize.

  • Robot grasping for fruit picking

sym

This robot is designed to pick simulated tomatoes through narrow roads. In terms of the hardware, I am responsible for mechanical design, 3D modeling and printing of robot chassis and actuators. With regard to the software, I mainly research perception-motion coordinated control algorithm.

  • Grasping and quadruped robots

sym

These robots are designed according to the rules of a national-level innovation competition. In this project, I am the team leader and mainly responsible for the arm control of the grasping robot and the inverse kinematics analysis of the quadruped robot. In this national-level innovation competition, our team won the third prize.

  • Corn morphology detection and distribution machine

sym

This machine is designed for automatic distribution of corns according to their morphology as well as pest and disease conditions. In this project, I am the team leader and mainly responsible for corn detection, servo control, and their coordination. In a national-level innovation competition, our team won the second prize.

  • Remote sensing based on Unmanned Aerial Vehicle (UAV)

sym

This project was supported by the National Natural Science Foundation of China, which is dedicated to the early discovery and continuous monitoring of Mikania Micrantha (an invasive plant).In this project, I am the core member of algorithm development and mainly responsible for feature analysis and semantic segmentation of remote sensing images.

🎓 Education

  • Ph.D., The University of Tokyo, 04/2025 – present

  • M.Eng., China Agricultural University, 09/2021 – 06/2024

  • B.Eng., Guangxi University, 09/2017 – 06/2021

📝 Publications

  • Multimodal Feature Representation Mechanism for 3D Detection of Agricultural Obstacles with Few or Zero Samples [Available online]

    Tianhai Wang, Ning Wang, Shunda Li, Zhiwen Jin, Jianxing Xiao, Yanlong Miao, Yifan Sun, Han Li, Man Zhang*

    Engineering, 2026 (SCI, IF2025-2026=12.2, Flagship Journal of CAE, CAA-A+, Special Report: University, College, Lab, Third-party)

    sym

    To address the critical challenge of scarce labeled data in autonomous agricultural navigation, we proposed a 3D obstacle detection framework based on multimodal feature representation mechanism. Our method reduces the dependency on training samples by 30%-40% while achieving a good performance in multi-category field scenarios. Especially, it maintains a robust performance in zero-shot scenarios. This work achieves a sophisticated trade-off among detection performance, operational efficiency, and data dependency.

  • One-shot domain adaptive real-time 3D obstacle detection in farmland based on semantic-geometry-intensity fusion strategy [Available online]

    Tianhai Wang, Ning Wang, Jianxing Xiao, Yanlong Miao, Yifan Sun, Han Li, Man Zhang*

    Computers and Electronics in Agriculture, 2023 (SCI, IF2022-2023=8.3, Special Report by WeChat Public Platform)

    sym

    By introducing the concept of one-shot domain adaptation, the proposed method enables 3D obstacle detection with just one sample per category. By learning the intra-category similarity and inter-category difference, the dependence on the target domain dataset is transferred to the accessible source domain dataset, which enhances the generalization of the proposed method for different scenes and categories.

  • Zero-shot obstacle detection using panoramic vision in farmland [Available online]

    Tianhai Wang, Bin Chen, Ning Wang, Yuhan Ji, Han Li, Man Zhang*

    Journal of Field Robotics, 2023 (SCI, IF2022-2023=8.3, CAA-A, Special Report by WeChat Public Platform)

    sym

    In the absence of annotated images, the current methods cannot perform optimally. Based on the visual‐semantic mapping relationship, the proposed model not only performs the correct classification of unseen obstacles, but also improves the detection performance of both seen and unseen obstacles.

  • An efficient, scalable, and high-precision multifunctional intelligent navigation system for agricultural machinery [Available online]

    Jianxing Xiao, Qiang Sheng, Yajun An, Ning Wang, Tianhai Wang, Shunda Li, Han Li, Man Zhang*

    Computers and Electronics in Agriculture, 2026 (SCI, IF2025-2026=10.3)

    sym

    This study proposes a loosely coupled intelligent navigation system based on an edge computing platform and an Microcontroller Unit (MCU), employing a distributed computing architecture for parallel processing of obstacle detection and navigation tasks. A method based on the fusion of 3D LiDAR and RGB camera is proposed to simultaneously identify obstacles category and distance accurately. In addition, an adaptive path tracking strategy based on the Pure Pursuit algorithm with Proportional Integral Derivative (PID) algorithm is implemented, which integrates lateral error from the Stanley controller and heading error, and incorporates a fuzzy logic-based gain adjustment to improve convergence under large initial deviations.

  • An Adaptive Double Closed‐Loop Path Tracking Control Method for High‐Precision Autonomous Navigation of Agricultural Machinery [Available online]

    Jianxing Xiao, Shunda Li, Ning Wang, Qiang Sheng, Tianhai Wang, Han Li, Man Zhang*

    Journal of Field Robotics, 2026 (SCI, IF2025-2026=5.1, CAA-A)

    sym

    We proposed a path tracking control method based on a double closed-loop control that combines an improved pure pursuit algorithm with fuzzy proportional integral derivative (PID) control. The improved pure pursuit algorithm dynamically adjusts the look-ahead distance according to agricultural machinery speed, path curvature, and position deviation, modeling it as a polynomial function of these variables. Offline simulations under diverse operational conditions were performed, and the ant colony algorithm (ACA) was employed to optimize the polynomial weight parameters, ensuring fast and accurate computation of the look-ahead distance during autonomous navigation in the field. The computed front-wheel steering angle is then controlled by a fuzzy PID algorithm, enabling rapid and precise steering adjustments, thereby enhancing the responsiveness and accuracy of path tracking. Field experiments were conducted to evaluate the proposed method. Comparative experiments were performed with standard Pure Pursuit, PID, and Stanley controllers.

  • An integrated solution for collaborative scheduling of heterogeneous agricultural machines of different types in harvesting-transportation scenarios [Available online]

    Ning Wang, Zhiwen Jin, Man Zhang, Jianxing Xiao, Tianhai Wang, Qiang Sheng, Hao Wang, Han Li*

    Information Processing in Agriculture, 2025 (SCI, IF2025-2026=8.9)

    sym

    Efficient coordination of machinery fleets in regional farmland operations remains a significant challenge due to the lack of scientifically grounded scheduling management strategies, high modeling complexity, and elevated operational costs. This study proposed an integrated solution for collaborative scheduling of heterogeneous agricultural machines of different types, aiming to address the collaborative scheduling of harvesters and grain trucks in harvest-transport scenarios.

  • A collaborative scheduling and planning method for multiple machines in harvesting and transportation operations-Part Ⅰ: Harvester task allocation and sequence optimization [Available online]

  • A collaborative scheduling and planning method for multiple machines in harvesting and transportation operations-part Ⅱ: Scheduling and planning of harvesters and grain trucks [Available online]

    Ning Wang, Shunda Li, Jianxing Xiao, Tianhai Wang, Yuxiao Han, Hao Wang, Man Zhang, Han Li*

    Computers and Electronics in Agriculture, 2025 (SCI, IF2025-2026=10.3)

    sym

    In Part Ⅰ of this two-part paper, the primary focus was to address the issue of collaborative scheduling for harvesters through task allocation and whole-process path planning. In Part II, the emphasis shifts to addressing the collaborative scheduling and planning of both harvesters and grain trucks while considering the efficiency of grain trucks.

  • Hybrid path planning methods for complete coverage in harvesting operation scenarios [Available online]

    Ning Wang, Zhiwen Jin, Tianhai Wang, Jianxing Xiao, Zhang Zhao, Hao Wang, Man Zhang, Han Li*

    Computers and Electronics in Agriculture, 2025 (SCI, IF2025-2026=10.3)

    sym

    This study addresses the challenge of autonomous navigation path planning for achieving complete coverage operations using agricultural machines within harvest operation scenarios. We proposed a hybrid method mixing nested and spiral method to solve path planning problems for convex polygonal plots during harvest operations, focusing on the development of path planning models and complete coverage path planning (CCPP) method.

  • Collaborative path planning and task allocation for multiple agricultural machines [Available online]

    Ning Wang, Xi Yang, Tianhai Wang, Jianxing Xiao, Man Zhang, Han Li*

    Computers and Electronics in Agriculture, 2023 (SCI, IF2022-2023=8.3)

    sym

    The farm’s electronic map was constructed using the topological map method. The improved Dijkstra algorithm based on priority queues was combined with three different complete coverage methods: the nested method, the reciprocating method, and the combination of nested and internal spiral path methods. To solve the problem of illogical scheduling of the same type of agricultural machines, an improved ant colony method was presented based on the whole working path to minimize the path cost.

  • Applications of machine vision in agricultural robot navigation: A review [Available online]

    Tianhai Wang, Bin Chen, Zhenqian Zhang, Han Li, Man Zhang*

    Computers and Electronics in Agriculture, 2022 (SCI, IF2022-2023=8.3, ESI Highly Cited Paper, Cited by 200+, Special Report by WeChat Public Platform)

  • Research Progress of Agricultural Robot Full Coverage Operation Planning [Available online]

    Ning Wang, Yuxiao Han, Yaxuan Wang, Tianhai Wang, Man Zhang, Han Li*

    Nongye Jixie Xuebao/Transactions of the Chinese Society of Agricultural Machinery, 2022 (EI)

  • Applications of UAS in Crop Biomass Monitoring: A Review [Available online]

    Tianhai Wang, Yadong Liu, Minghui Wang, Qing Fan, Hongkun Tian, Xi Qiao*, Yanzhou Li*

    Frontiers in Plant Science, 2021 (SCI, IF2021-2022=6.627)

  • Computer vision technology in agricultural automation —A review [Available online]

    Hongkun Tian, Tianhai Wang, Yadong Liu, Xi Qiao*, Yanzhou Li*

    Information Processing in Agriculture, 2020 (EI, Cited by 500+)

💬 Presentations

  • Tianhai Wang (Presenter), Joseph R. Davidson, Haozhou Wang, James Burridge, Wei Guo*. Digital Twin Generation for Orchard Robotics Using Unsupervised Segmentation and 3D Gaussian Splatting. CIGR-EurAgEng World Congress 2026. Turin. June 2026. (Oral Presentation)

  • Tianhai Wang (Presenter), Guankang Zhang, Joseph R. Davidson, Haozhou Wang, James Burridge, Wei Guo*. 3D Reconstruction for Orchards Using a Quadruped Robot and 3D Gaussian Splatting. 2026 Annual Conference of the Japanese Society of Agricultural Informatics (JSAI2026). Osaka. May 2026. (Oral Presentation)

  • Tianhai Wang (Presenter), Haozhou Wang, James Burridge, Wei Guo*. An Unsupervised 3D Point Cloud Segmentation Method and Tool for Artificial Objects and Trees in Dense Orchards. Seventh International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2025). Tokyo. August 2025. (Oral Presentation)

  • Tianhai Wang (Presenter), Ning Wang, Jianxing Xiao, Han Li, Man Zhang*. One-shot domain adaptive obstacle detection based on semantic-geometry-intensity fusion representation. 2023 Annual Academic Conference of Chinese Society of Agricultural Engineering (CSAE2023). Chengdu. August 2023. (Oral and Poster Presentation)

🧾 Grants & Fellowships

  • Development of an Adaptive Robotic Scanning Control System for High-Fidelity Orchard Reconstruction
    UTokyo SPRING GX (JST SPRING) Self-Directed and Integrated Project Research Grant
    Role: Team Leader | Amount: JPY 1,000,000 | Period: 09/2026 – 03/2027 | Program Info

  • Development of Machine Vision System and Digital Twin Technology for Autonomous Pruning Robots in Orchards
    UTokyo SPRING GX (JST SPRING) Self-Directed and Integrated Project Research Grant
    Role: Team Leader | Amount: JPY 1,000,000 | Period: 05/2025 – 03/2026 | Program Info

  • Development of Autonomous Field Robots for Precision Pruning in Smart Orchards Using 3D Point Cloud Analysis
    UTokyo SPRING GX Project (JST SPRING Program)
    Role: Fellow | Amount: JPY 1,080,000 (Research Grant) + Full Ph.D. Stipend | Period: 04/2025 – 03/2028 | Program Info

  • Research on Monitoring Platform and Key Technologies of Mikania Micrantha based on Multi-Spectral Images
    National Innovation and Entrepreneurship Training Program for Undergraduates (Ministry of Education, China)
    Role: Team Leader | Assessment: Excellent | Amount: CNY 10,000 (approx. JPY 200,000) | Period: 05/2019 – 08/2020 | Program Info

🏅 Honors and Awards

Honors

  • 06/2024, Outstanding Master Thesis of China Agricultural University (Only one master graduate in my college that year, Special Report by University)
  • 05/2024, Honorary title of “Outstanding Graduate” of China Agricultural University
  • 12/2023, National Scholarship of China (The highest-level scholarship awarded by the Chinese government for top 0.2% students)
  • 11/2023, First Class Scholarship for Postgraduate of China Agricultural University
  • 06/2023, Honorary title of “Outstanding Postgraduate Teaching Assistant” of China Agricultural University
  • 11/2022, First Class Scholarship for Postgraduate of China Agricultural University
  • 06/2021, Honorary title of “Outstanding Graduate” of Guangxi University
  • 05/2021, Outstanding Bachelor Thesis of Guangxi University
  • 12/2020, National Encouragement Scholarship of China
  • 12/2019, Honorary title of “Outstanding Undergraduate” of Guangxi University
  • 12/2019, National Encouragement Scholarship of China

Competition Awards

  • 04/2020, Guangxi College Students Innovation Design and Production Competition, Ministerial 3rd Prize
  • 12/2019, National College Students Intelligent Agricultural Equipment Innovation Competition, National 2nd Prize
  • 11/2019, China College Students “Internet+” Innovation and Entrepreneurship Competition in Guangxi Division, Ministerial Bronze Medal
  • 10/2019, National 3D lnnovative Design Annual Competition in Guangxi Division, Ministerial 2nd Prize
  • 07/2019, National University Students Electrical Math Modeling Competition, National 3rd Prize
  • 07/2019, National 3D lnnovative Design Elite Competition in Guangxi Division, Ministerial 2nd Prize
  • 06/2019, China University Robot Competition ROBOCON, National 3rd Prize
  • 06/2018, National College Students Mechanical Innovation Design Competition in Guangxi Division, Ministerial 3rd Prize

💪 Skills

  • Programming
    • Python, Matlab, Simulink, C, C++
  • Framework
    • PyTorch, Robot Operating System (ROS)
  • 2D/3D Modeling
    • AutoCAD, Unigraphics NX, SolidWorks
  • Language
    • Chinese
    • English

👔 Service

  • Student Member, Japanese Society of Agricultural Informatics，03/2026 – present
  • Research Assistant, College of Information and Electronic Engineering, China Agricultural University，07/2024 – 03/2025
  • Student Member, Chinese Society of Agricultural Engineering，12/2022 – 12/2025
  • Teaching Assistant, Fall 2022&2023 Intelligent Guidance Technology Course (Special Report by College)