Binghong Chen

I am a first year master student in Mechanical Engineering at Carnegie Mellon University working on SafeAI Lab, advised by Prof.Ding Zhao. I am currently an Robot Learning Research Intern at Bosch, Pittsburgh, advised by Jonathan Francis.

I received my B.S. degree in Agricultural Engineering from Zhejiang University in 2025, advised by prof.Mingchuan Zhou. I also worked in Arclab, the University of Hong Kong, supervised by prof.Peng Lu. In addition, I spent several months for internship in Dessight Biomedical Company.

Research

Robot learning is the future.

	Learning Versatile Humanoid Manipulation with Touch Dreaming Yaru Niu, Zhenlong Fang, Binghong Chen, Shuai Zhou, Revanth Senthilkumaran, Hao Zhang, Bingqing Chen, Chen Qiu, H. Eric Tseng, Jonathan Francis, Ding Zhao ArXiv Preprint 2026 abstract \| webpage \| arXiv We introduce Humanoid Transformer with Touch Dreaming (HTD), which includes future hand-joint-force prediction and EMA-supervised tactile-latent prediction for versatile humanoid manipulation. We develop a whole-body humanoid manipulation system that combines VR teleoperation with an RL-based whole-body controller. We evaluate five humanoid manipulation tasks spanning insertion, rigid-object reorientation, deformable-object handling, tool use, and bimanual loco-manipulation.
	Towards Autonomous Robot-Assisted Minimally Invasive Surgery: a Dexterous Wristed Robotic Kit (DWRK) for Surgical Tasks Qiming Wu, Xinbo Chen, Binghong Chen, Fanghao Wang, Sibo Hao, Mingchuan Zhou, Limin Zeng abstract We introduce Dexterous Wristed Robotic Kit(DWRK), designed for autonomous robot-assisted minimally invasive surgery. DWRK provides a reliable modular platform with high dexterity for performing surgical manipulation tasks, enabling data-driven learning approaches toward full surgical autonomy. We implement several benchmark imitation learning algorithms based on this platform.
	STTRL-DVO: Transformer-based Reinforcement Learning for Robust Dynamic Target Tracking in Cluttered Environment Fanghao Wang, Binghong Chen, Youchao Zhang, Xiangyu Guo, Yining Lyu, Chuanjie Liu, Alois Knoll, Di Cui, Huanyu Jiang, Yibin Ying, Mingchuan Zhou IEEE Transactions on Robotics (TRO), 2026 abstract \| pdf \| code We proposed a Transformer-based RL framework to help microgripper navigate within a constrained environment with lots of dynamic obstacles and capture the dynamic target. We adopt virtual lidar information for robust perception and use Transformer to extract spatial and temporal information. We propose a deterministic velocity obstacle (DVO), an improved variant of the velocity obstacle (VO), where the sampling process is replaced with odometry-based computation to provide guidance during RL training.

Education

	Carnegie Mellon University M.S. in Mechanical Engineering Expected 2027
	University of Hongkong Visiting Student 2024.7 - 2024.10
	Zhejiang University B.Eng. in Agricultural Engineering 2021.9 - 2025.6

Working Experience

	BOSCH Robot Learning Research Intern 2026.6 - Present
	Dessight Biomedical Company Research Intern 2025.4 - 2025.7

Personal Projects

	A Fast Reinforcement Learning Approach for Fault Tolerant Control of Quadrotor abstract Trained a small drone to stabilize and track trajectory with a completely fault rotor via RLtools, a C++ RL library for accelerating the training process. It succeeded in simulation but failed in reality.
	Student Agricultural Robotics Competitions First Place Award in 2024 ASABE Student Robotics Competition, Anaheim, USA Second Prize in China Agricultural Robot Competition, Wuhan, China abstract I am mainly responsible for mechanical design of the end-effectors and building controller for navigation and specific motion.

This website is adapted from the Jon Barron website template.