About me

I received my Master’s degree at the School of Aerospace Engineering, Beijing Institute of Technology(BIT), Beijing, China. I am also a member of the Robot Vision Group at the Beijing Advanced Innovation Center for Intelligent Robots and Systems(BAICIRS). I received B.S. in Mechatronics Engineering at BIT.

I have worked on vision-based robot systems as many research projects which involve Robotic Bionic Eyes, UR Robot Arm, AGV, etc. My research interests include Robotics, Active SLAM, 3D Vision, and Reinforcement Learning. My current research interest mainly lies in perception-based control and cognitive robotics. My dream is to build a real cognitive robot prototype.

Research Experience

Head stabilization for Robotic Bionic Eyes

Sep. 2020-Now

I have designed the Disturbance Decomposition and Learning (DDL) based control system and applied it on a real robotic bionic eyes platform, which decouples the disturbance on the nonlinear bionic eyes system and realizes active disturbance compensation without complex dynamic modeling. To handle the nonlinearities, especially in the robotic bionic eyes system, a learning-based control method is combined. Compared with the state-of-the-art methods, the control accuracy is significantly improved in both the simulation and the real world. One paper has been submitted to TMECH.

Autonomous Exploration with Active Camera Control

Aug. 2021-Now

l have designed an active exploration algorithm based on multimodal sensory fusion and active camera control. Simulation results show that compared with traditional algorithms, the map coverage is improved by 10-20%, and 33% is demonstrated for the exploration efficiency. One paper has been accepted by CCDC 2022.

Gap-based Topological Mapless Maze Navigation

Nov. 2021-now

I have cooperated with the lab’s member, Zakir, on the mapless topological navigation. The paper proposed a gap-based approach for imperfect unknown mazes traversal named Follow the Nearest-to-final goal and Unvisited Gap (FNUG) for the first time. The algorithm is computationally efficient and has the ability to deal with loops and dead ends through the revisit check. One paper is published by RA-L 2022.

Reinforcement Learning based UAV control

Sep. 2019-Aug. 2020

I have co-published a paper on RL-based UAV control. The PPO algorithm of reinforcement learning is utilized in the scheme to adjust PID controller gains. The paper is published by CCC 2020.

Project Experience

UR Robot Arm based Mobile Platform for Manipulation Task (with Huawei)

Sep. 2020-now

I joined the project as one of the core members who designed the entire system framework (both hardware and ) of the robot system based on the UR robot arm and ROS. I am one of the main contributors working on modules including manipulator planning and control, object detection, pose estimation, visual servoing, and socket communication, and took the responsibility of the real robot testing. I have also built a complete corresponding simulation experiment platform based on Gazebo.

(Due to the commercial contract, the related materials can’t be presented. Here is a picture of a similar platform from the University of Nevada)

Robot SLAM

Sep. 2019-Aug. 2020, Active Mapping

I have built an active SLAM framework based on robotic bionic eyes for indoor active exploration and reconstruction. The global optimal exploration trajectory path was planned based on the Information Gain calculated from the real-time map, and the MPC controller was used for local trajectory tracking, thus realizing the complete active reconstruction of the laboratory and corridor.

Sep. 2019-Aug. 2020, Camera-IMU Time-Synchronization for Robotic Bionic Eyes based SLAM

I have developed a camera-IMU time synchronization module for improving the precision of visual-inertial SLAM based on the bionic eye platform. Hardware trigger synchronization and time error measurement of IMU and camera were implemented on the embedded development board, then synchronized images and IMU data were collected and published to improve the robustness of VI-SLAM through ROS. One related patent has been granted.

Robot Vision

Sep. 2020-Aug. 2021, Stereo Depth Estimation for Robotic Bionic Eyes

I have developed the depth estimation module for obtaining depth information from the bionic eyes’ cameras to enable its ability of 3D reconstruction. The intrinsic and extrinsic parameters are calibrated and the image acquisition program for CCD cameras is developed. Both the classic method and the learning based method are applied.

Sep. 2019-Aug. 2020, RGB-D based Indoor Dense 3D Reconstruction and Navigation

I have developed a project aimed at indoor high-precision 3D reconstruction and navigation based on an RGB-D camera. TSDF-based dense mapping algorithm was used for high-precision map reconstruction, and lidar was used for the localization and navigation of the mobile platform.

Dec. 2020-Jan. 2021, Infrared Camera based Human Body Temperature Measurement

I have built temperature measurement software based on an IR camera for a small ball-like robot.

Teaching Assistant Experience

Nov. 2020-Jan. 2021, Python & Deep Learning Basics (Undergraduate course)

This course is set by School of Mechatronical Engineering at BIT.

Publications & Patents

  1. G. Siyuan, C. Xiaopeng, Z. Weizhong, et al. “DDL: Disturbance Decomposition and Learning Based Head Stabilization for Robotic Bionic Eyes, “ (Submitted to IEEE/ASME Transactions on Mechatronics).
  2. G. Siyuan, C. Xiaopeng, Z. Weizhong, et al. “Multimodal Perception based Autonomous Exploration with Active Camera Control in Unknown Environments,” (Accepted by CCDC 2022)
  3. U. Zakir, C. Xiaopeng, G. Siyuan, Y. Xu and S. Muhammad, “FNUG: Imperfect mazes traversal based on detecting and following the nearest-to-final-goal and unvisited gaps,” in IEEE Robotics and Automation Letters, doi: 10.1109/LRA.2022.3151393.
  4. C. Xiaopeng, L. Yanyang, X. Yang, G. Siyuan, M. Siyan, U. Zakir, “Kinematic Calibration of a Laser Tracker based on Nonlinear Optimization of a Refined Geometric Error Model,” Measurement (2022): 110672.
  5. Z. Qingqing, T. Renjie, G. Siyuan, C. Xiaopeng, Z. Weizhong, “A PID Gain Adjustment Scheme Based on Reinforcement Learning Algorithm for a Quadrotor,” 2020 39th Chinese Control Conference (CCC), 2020, pp. 6756-6761.
  6. Q. Huang, C. Xiaopeng, G. Siyuan, et al. Method and Apparatus for time-synchronization of bionic eyes’ multi-channel IMUs and cameras, ZL201910777841.6 (Chinese Patent).
  7. C. Xiaopeng, Q. Huang, G. Siyuan, et al. Method and Apparatus for Pose Planar Constraining on the Basis of Planar Feature Extraction, US-2021-0192271-A1 (U.S. Patent).

Other Undergraduate Demos

Small Teaching Robot Arm with Bluetooth based Wireless Control

Four-legged Wheeled Robot