Lingheng Meng 🤖

Lingheng Meng

CERC Postdoctoral Fellow

CSIRO Data61

Monash University

Professional Summary

Robotics and human-robot interaction researcher advancing human-centered robot learning through deep reinforcement learning, preference learning, and adaptive interactive systems. My work spans from foundational RL theory to real-world deployment, including a museum installation with 60,000+ public visitors.
Download CV

Education

PhD Electrical & Computer Engineering

2017-09-01
2023-05-29

University of Waterloo

M.Eng. Computer Science and Technology

2014-09-01
2017-05-29

China University of Mining and Technology

B.Eng. Computer Science and Technology

2010-09-01
2014-06-23

China University of Mining and Technology

Interests

Human-Robot Interaction Deep Reinforcement Learning Preference Learning (RLHF) Imitation Learning & Inverse RL Robot Learning for Assistive Robotics Interactive & Adaptive Robotic Systems
Research

My research advances human-centered robot learning through three interconnected themes:

Foundations of Deep Reinforcement Learning — Understanding multi-step methods, memory architectures, and value estimation in partially observable environments (Neural Networks 2025, IROS 2021, ICPR 2020).

Preference Learning for Robotics — Enabling robots to learn from human preferences rather than hand-crafted rewards, with applications to interactive systems and assistive manipulation (ACM THRI 2021, ongoing work on patchable preference learning).

Real-World Deployment & Human-Robot Interaction — Translating learning algorithms to physical robots and large-scale public installations, including the Royal Ontario Museum deployment with 60,000+ visitors and partnerships with Boeing Research and Suburban Connect.

Featured Publications
Deep Reinforcement Learning

Experimental Study on The Effect of Multi-step Deep Reinforcement Learning in POMDPs

avatar
Lingheng Meng
•
Read more
Deep Reinforcement Learning

Memory-based Deep Reinforcement Learning for POMDPs

avatar
Lingheng Meng
•
Read more
Human-Robot Interaction

Learning to Engage with Interactive Systems: A Field Study on Deep Reinforcement Learning in a Public Museum

avatar
Lingheng Meng
•
Read more
All Publications
Lingheng Meng, Rob Gorbet, Michael Burke, Dana Kulic (2025). Experimental Study on The Effect of Multi-step Deep Reinforcement Learning in POMDPs. Neural Networks, Elsevier.
PDF DOI
Mingjie Li, Ben Beck, Tharindu Rathnayake, Lingheng Meng, Zijue Chen, Akansel Cosgun, Xiaojun Chang, Dana Kulic (2025). A Benchmark for Cycling Close Pass Detection from Video Streams. Transportation Research Part C: Emerging Technologies, vol. 174, p.105112.
PDF DOI
Ben Beck, Tharindu Rathnayake, Dana Kulic, Mingjie Li, Lingheng Meng, Zijue Chen, Akansel Cosgun (2023). Detecting Near-Miss Events with Cyclists Using Computer Vision Approaches. In Australasian Road Safety Conference 2023, Cairns, QLD, Australia.
Lingheng Meng, Rob Gorbet, Dana Kulic (2021). Memory-based Deep Reinforcement Learning for POMDPs. In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021), Prague, Czech Republic.
PDF Code
Lingheng Meng, Daiwei Lin, Adam Francey, Rob Gorbet, Philip Beesley, Dana Kulic (2021). Learning to Engage with Interactive Systems: A Field Study on Deep Reinforcement Learning in a Public Museum. ACM Transactions on Human-Robot Interaction (THRI), vol. 10, no. 5, pp. 1-29.
PDF DOI
See all
Contact

Dr. Lingheng Meng

CERC Postdoctoral Fellow, CSIRO Data61 Adjunct Lecturer, Monash University

Email: lingheng.meng@data61.csiro.au

Google Scholar | GitHub | ORCID