Hello there, I’m Yan (炎)

I am a final-year PhD student at EPFL and also working as a research assistant in the Robot Learning & Interaction group at Idiap, supervised by Dr. Sylvain Calinon and Prof. Colin Jones.

Research goals

I aim to build intelligent robot assistants living together with humans at home. I am currently working on integrating task and motion planning with robot learning for multi-object manipulation tasks. My research interests include robot learning, multi-object manipulation planning, task and motion planning, and graph theory. My previous research experiences cover imitation learning, deep reinforcement learning, sim2real transfer, and variable impedacne control in robot manipulators and legged robots. See Projects for more details.

Recent News

Selected Publications

Please visit the Publications page for more details.

Whole-body rotation demo

Monte Carlo Tree Search with Tensor Factorization for Robot Optimization

Teng Xue, Yan Zhang*, Amirreza Razmjoo*, Sylvain Calinon

Under review

[paper] [website]

sym

Robustness-Aware Tool Selection and Manipulation Planning with Learned Energy-Informed Guidance

Yifei Dong*, Yan Zhang*, Sylvain Calinon, Florian T. Pokorny

In Proc. IEEE ICRA, 2026

[paper] [video]

sym

Learn2Decompose: Learning Problem Decomposition for Efficient Sequential Multi-object Manipulation Planning

Yan Zhang, Teng Xue, Amirreza Razmjoo, Sylvain Calinon

In IEEE RA-L 2025.

[paper] [website]

sym

Logic Learning from Demonstrations for Multi-step Manipulation Tasks in Dynamic Environments

Yan Zhang, Teng Xue, Amirreza Razmjoo, Sylvain Calinon

In IEEE RA-L 2024.

[paper][website] [code]

sym

Representing Robot Geometry as Distance Fields: Applications to Whole-body Manipulation

Yiming Li, Yan Zhang, Amirreza Razmjoo, Sylvain Calinon

In Proc. IEEE ICRA 2024.

[paper][website] [code]