Heng (Alfredo) Zhang
heng.zhang@iit.it OR zhan6025@purdue.edu

I am currently a visiting scholar at MARS lab, Purdue University, fortunately working with professor Yu She since Fall 2025. I am a third-year PhD student in Robotics and Intelligent Machines (DRIM) at Italian Institute of Technology (IIT), advised by Dr. Arash Ajoudani. Previously, I received a Master's degree in Control Engineering from Tongji University and a B.E degree in Automation from Northeast Electric Power University, China. My research envisions safe and generalizable robot learning for contact-rich robotic manipulation, which is crucial for physical interaction. I wish one day robots can safely and autonomously assist humans in various real-world scenarios, such as manufacturing, healthcare, laboratory and daily life!

CV / Google Scholar / LinkedIn / ResearchGate / Twitter / Github

Research Interests

"Contact is the heart of robotic manipulation. To understand manipulation, you must understand contact."

My research focuses on robot learning, reinforcement learning. Specifically, My current research interest focuses on: I would be happy you want to discuss my research with me. I’m open to collaborations, please feel free to send me Email!

Career Goals

Short-term:

  • Complete PhD
  • Apply for a postdoc

Long-term:

  • To be a professor or:
  • Co-found a robotics startup

Outreach

Inspired by Shuijing Liu: For junior PhD, Master's, and undergraduate students as well as potential collaborators, I offer a 30-minute mentorship session. I am especially available to support students from underrepresented groups or those in need. Topics include, but are not limited to, AI, robotics, AI4Sci research, graduate school applications, career development, and life advice. If you'd like to chat, please fill out this form to schedule a meeting.

Note: I do check my email every weekday and respond promptly. Please feel free to send a follow-up email if you haven't received a reply.


News

Research



SRL-VIC Animation
SRL-VIC: A variable stiffness-based safe reinforcement learning for contact-rich robotic tasks
Heng Zhang, Gokhan Solak, Gustavo JG Lahr, Arash Ajoudani
IEEE Robotics and Automation Letters (RA-L), 2024
Paper Video
Exploration Policy with Safety and Generalization in contact-rich tasks using Safe Reinforcement Learning and VIC.
INTENTION Animation
INTENTION: Inferring Tendencies of Humanoid Motion Through Physical Intuition and Grounded VLM
Jin Wang, Weijie Wang, Boyuan Deng, Heng Zhang, Rui Dai, Nikos Tsagarakis
IEEE-RAS International Conference on Humanoid Robots, Seoul, Korea, 2025
Paper Website
INTENTION is a framework that combines physical intuition and grounded VLM to infer humanoid motion tendencies, enabling robots to predict and adapt to human actions in dynamic environments.
OmniVIC Animation
OmniVIC: A Self-Improving Variable Impedance Controller with Vision-Language In-Context Learning for Safe Robotic Manipulation
Heng Zhang, Wei-Hsing Huang, Gokhan Solak, Arash Ajoudani
IEEE The International Conference on Robotics and Automation (ICRA), 2026, under review
Paper Website
CompliantVLA Animation
CompliantVLA-adaptor: VLM-Guided Variable Impedance Action for Safe Contact-Rich Manipulation
Heng Zhang, Wei-Hsing Huang, Qiyi Tong, Gokhan Solak, Puze Liu, Sheng Liu, Jan Peters, Arash Ajoudani
IEEE The International Conference on Robotics and Automation (ICRA), 2026, under review
Paper Website
ActivePose Animation
ActivePose: Active 6D Object Pose Estimation and Tracking for Robotic Manipulation
Sheng Liu, Zhe Li, Weiheng Wang, Han Sun, Heng Zhang, Hongpeng Chen, Yusen Qin, Arash Ajoudani, Yizhao Wang
IEEE The International Conference on Robotics and Automation (ICRA), 2026, under review
Paper
aiXiv Animation
aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists
Pengsong Zhang, Heng Zhang, et al.
The 40th Annual AAAI Conference on Artificial Intelligence, 2026, under review
Paper Code Website
aiXiv is a Preprint server for AI Scientists and Robot Scientists that leverages AI technologies to facilitate scientific discovery and collaboration among researchers.
HiBerNAC Animation
HiBerNAC: Hierarchical Brain-emulated Robotic Neural Agent Collective for Disentangling Complex Manipulation
Hongjun Wu, Heng Zhang, Pengsong Zhang, Jin Wang, Cong Wang
under review
Paper Code
HiBerNAC: a Hierarchical Brain-emulated robotic Neural Agent Collective that combines: (1) multimodal VLA planning and reasoning with (2) neuro-inspired reflection and multi-agent mechanisms, specifically designed for complex robotic manipulation tasks.
passiveRL Animation
Towards Passive Safe Reinforcement Learning: A Comparative Study on Contact-rich Robotic Manipulation
Heng Zhang, Gokhan Solak, Sebastian Hjorth, Arash Ajoudani
IEEE Robotics and Automation Letters (RA-L) under review
Paper Hugging Face
Learning to be safe and stable both in training and deployment in real world.
Bresa
Bresa: Bio-inspired Reflexive Safe Reinforcement Learning for Contact-Rich Robotic Tasks
Heng Zhang*, Gokhan Solak*, Arash Ajoudani * equal contribution
IEEE Robotics and Automation Letters (RA-L) under review
Paper Website Video
A Bio-inspired Reflexive Hierarchical Safe RL method inspired by biological reflexes operating at a higher frequency than the task solver.
AGS
Scaling Laws in Scientific Discovery with AI and Robot Scientists
Pengsong Zhang*, Heng Zhang*, Huazhe Xu, Renjun Xu, Zhenting Wang, Cong Wang, Animesh Garg, Zhibin Li, Arash Ajoudani, Xinyu Liu * equal contribution
Nature Machine Intelligence in submission
Paper Hugging Face Github
Autonomous Generalist Scientist (AGS) combines agentic AI and embodied robotics to automate the entire research lifecycle.
SVSLAM Survey
Semantic visual simultaneous localization and mapping: A survey
Kaiqi Chen, Junhao Xiao, Jialing Liu, Qiyi Tong, Heng Zhang, Ruyu Liu, Jianhua Zhang, Arash Ajoudani, Shengyong Chen
IEEE Transactions on Intelligent Transportation Systems, 2025
Paper
Semantic visual simultaneous localization and mapping (SVSLAM) is a crucial task in robotics and computer vision, aiming to simultaneously estimate the robot's location and map the environment using semantic information.

Service