Shiyu Feng

I am currently working toward the Ph.D. degree in mechanical engineering at Georgia Institute of Technology. I am a member of Intelligent Vision and Automation Laboratory (IVALab) supervised by Dr. Patricio A. Vela. My research focuses on vision-based hierarchical navigation using sparse representation to improve the computational efficiency and scalability. The research involves perception, motion planning, optimal control, collision avoidance, robot safety, and vehicle autonomy. Additionally, I am interested in exploring the combination of control, planning, and reinforcement learning as a prospective avenue for future research beyond the existing scope.

I am an enthusiast in robots’ software and hardware. Have a lot of hands-on experience to play with stereo and depth cameras, LiDAR, laser scanner, and multiple mobile robots. Proficient with C++, Python, MATLAB, ROS/Gazebo, and deep learning packages. I received the B.Eng. degree from Chongqing University in 2015, and the M.Eng. degree from University of California at Berkeley in 2016. In my free time, I like hiking and playing video games.

selected publications

2023

GPF-BG

GPF-BG: A Hierarchical Vision-Based Planning Framework for Safe Quadrupedal Navigation

Shiyu Feng, Ziyi Zhou, Justin S. Smith, and 3 more authors

In 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023

Bib PDF

@inproceedings{10160804,
  author = {Feng, Shiyu and Zhou, Ziyi and Smith, Justin S. and Asselmeier, Max and Zhao, Ye and Vela, Patricio A.},
  booktitle = {2023 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {GPF-BG: A Hierarchical Vision-Based Planning Framework for Safe Quadrupedal Navigation},
  year = {2023},
  volume = {},
  number = {},
  pages = {1968-1975},
  doi = {10.1109/ICRA48891.2023.10160804},
}

SaferGap

Safer Gap: A Gap-based Local Planner for Safe Navigation with Nonholonomic Mobile Robots

Shiyu Feng, Ahmad Abuaish, and Patricio A. Vela

2023

Bib PDF

@misc{feng2023safer,
  title = {Safer Gap: A Gap-based Local Planner for Safe Navigation with Nonholonomic Mobile Robots},
  author = {Feng, Shiyu and Abuaish, Ahmad and Vela, Patricio A.},
  year = {2023},
  eprint = {2303.08243},
  archiveprefix = {arXiv},
  primaryclass = {cs.RO},
}

2022

TrajServo

Image-Based Trajectory Tracking Through Unknown Environments Without Absolute Positioning

Shiyu Feng, Zixuan Wu, Yipu Zhao, and 1 more author

IEEE/ASME Transactions on Mechatronics, 2022

Bib PDF

@article{9787773,
  author = {Feng, Shiyu and Wu, Zixuan and Zhao, Yipu and Vela, Patricio A.},
  journal = {IEEE/ASME Transactions on Mechatronics},
  title = {Image-Based Trajectory Tracking Through Unknown Environments Without Absolute Positioning},
  year = {2022},
  volume = {27},
  number = {4},
  pages = {2098-2106},
  doi = {10.1109/TMECH.2022.3175819},
}

2021

PotentialGap

Potential Gap: A Gap-Informed Reactive Policy for Safe Hierarchical Navigation

Ruoyang Xu, Shiyu Feng, and Patricio A. Vela

IEEE Robotics and Automation Letters, 2021

Bib PDF

@article{pgap,
  author = {Xu, Ruoyang and Feng, Shiyu and Vela, Patricio A.},
  journal = {IEEE Robotics and Automation Letters},
  title = {Potential Gap: A Gap-Informed Reactive Policy for Safe Hierarchical Navigation},
  year = {2021},
  volume = {6},
  number = {4},
  pages = {8325-8332},
  doi = {10.1109/LRA.2021.3104623},
}

StixelNav

Ego-centric Stereo Navigation Using Stixel World

Shiyu Feng, Fanzhe Lyu, Jin Ha Hwang, and 1 more author

In 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021

Bib PDF

@inproceedings{9561385,
  author = {Feng, Shiyu and Lyu, Fanzhe and Ha Hwang, Jin and Vela, Patricio A.},
  booktitle = {2021 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {Ego-centric Stereo Navigation Using Stixel World},
  year = {2021},
  volume = {},
  number = {},
  pages = {13201-13207},
  doi = {10.1109/ICRA48506.2021.9561385},
}

2020

PiPSChapter

Real-Time Egocentric Navigation Using 3D Sensing

Justin S. Smith, Shiyu Feng, Fanzhe Lyu, and 1 more author

2020

Abs PDF

This chapter proposes a hierarchical navigation system combining the benefits of perception space local planning and allocentric global planning. Perception space permits computationally efficient 3D collision checking, enabling safe navigation in environments that do not meet the conditions assumed by traditional navigation systems based on planar laser scans. Contributions include approaches for scoring and collision checking trajectories in perception space. Benchmarking results show the advantages of perception space collision checking over popular alternatives in the context of real-time local planning. Simulated experiments with multiple robotic platforms in several environments demonstrate the importance of 3D collision checking and the utility of a mixed representation hierarchical navigation system.