Qianyi Zhang (Kenny)
Qianyi Zhang (Kenny)

PH.D. student

Nankai University
University College London

About Me

Qianyi Zhang is a PH.D. student at Institute of Robotics and Automatic Information System of Nankai University, China (Service Robot Lab), and also a visiting PH.D. student of the Department of Computer Science of University College London (Robot Perception and Learning Lab). Recent works have been published on T-ASE, R-AL, ICRA(2023,2024,2025), IROS(2022), etc.

Interests
  • Motion planning of mobile robots
  • Decision of autonomous vehicles
  • Human-robot game theory
  • RL-based risk-aware navigation
  • Vision language navigation
Education

  • PhD in Artificial Intelligence

    Nankai University

  • Visiting PhD in Robotics Institute

    University College London

  • BSc in Automation System

    Nankai University

Experience

  1. Motion planning algorithm intern

    Huawei
    For the motion planning of unmanned delivery vehicles in complex dynamic environments, an optimization-based navigation approach, GA-TEB, has been published on ICRA2025, and a RL-based navigation approach, NavG, has been submitted on IROS2025.

  2. Decision-making algorithm intern

    Meituan
    For the decision-making of unmanned delivery vehicles in narrow roads, prediction and planning are combined to propose an explorative game theory. The related work was published on IROS2022 and deployed to real vehicles.

Education

  1. PhD in Artificial Intelligence

    Nankai University

  2. Visiting PhD in Robotics Institute

    University College London

  3. BSc in Automation System

    Nankai University
Featured Publications
GA-TEB: Goal-Adaptive Framework for Efficient Navigation Based on Goal Lines
SM-NR: Scene Modeling of Autonomous Vehicles Avoiding Stationary and Moving Objects on Narrow Roads
CG3: The Human Gaze Helps Robots Run Bravely and Efficiently in Crowds
Naivgation With Human Gaze Information

CG3: The Human Gaze Helps Robots Run Bravely and Efficiently in Crowds

In human-aware navigation, the robot tacitly games with humans, balancing safety and efficiency according to human intentions. Poor balance or bad intent recognition causes the robot to stop conservatively or advance rashly, resulting in a deadlock or even a collision respectively. To address the issue, this paper proposes an improved limit cycle for collaboratively parameterizing human intentions and planning robot motions. The human-robot interaction is modeled as a dynamic chicken game with incomplete information, where the human gaze is introduced to depict the unique characteristics of each person, allowing the robot to approach with different safety margins. Our method is tested in challenging indoor scenarios and outperforms traditional methods in both safety and efficiency. We enable robots to utilize human wisdom to solve problems that cannot be solved on their own. The robot bravely goes through oncoming crowds by getting closer to people with higher attention on it and has the foresight to stably cross in front or behind people.

Recent Publications
Qianyi Zhang (Kenny), Wentao Luo, Ziyang Zhang, Yaoyuan Wang, Jingtai Liu (2025). GA-TEB: Goal-Adaptive Framework for Efficient Navigation Based on Goal Lines. In ICRA2025.
PDF Cite Code Poster Video
Qianyi Zhang (Kenny), Wentao Luo, Boyi Liu, Ziyang Zhang, Yaoyuan Wang, Jingtai Liu (2025). NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points. In IROS2025, under review.
Zeqing Zhu, Qianyi Zhang (Kenny), Yinuo Song, Yifan Yang, Jingtai Liu (2024). STC-TEB: Spatial-Temporally Complete Trajectory Generation Based on Incremental Optimization. IEEE Robotics and Automation Letters(RAL).
PDF Cite Code DOI
Qianyi Zhang (Kenny), Jinzheng Guang, Zhenzhong Cao, Jingtai Liu (2024). SM-NR: Scene Modeling of Autonomous Vehicles Avoiding Stationary and Moving Objects on Narrow Roads. IEEE Transactions on Systems, Man and Cybernetics: Systems(SMCA, under review).
PDF Code Poster Video
Qianyi Zhang (Kenny), Zhengxi Hu, Yinuo Song, Jiayi Pei, Jingtai Liu (2023). CG3: The Human Gaze Helps Robots Run Bravely and Efficiently in Crowds. In ICRA2023.
PDF Cite Code Video
See all publications