Songyuan Zhang
— After all this time? Always.
I am a Ph.D. student at Department of Aeronautics and Astronautics, MIT. I received my Master of Science in Aeronautics and Astronautics at MIT in 2024, and Bachelor of Engineering at Tsien Excellence in Engineering Program (Tsien class, TEEP) at Tsinghua in 2021. The goal of my research is to develop real intelligent assistive robots. My research interests lie in reinforcement learning (offline/online), generative AI, safe control for robotics, neural certificates, multi-agent systems, control theories, and robotics.
I am a member of REALM lab led by Prof. Chuchu Fan. Previously in my undergraduate program, I worked on learning from suboptimal demonstrations with Prof. Yanan Sui and Prof. Dorsa Sadigh, developing clustering algorithms with Prof. Hao Wu, developing planning algorithms for autonomous driving with Prof. Masayoshi Tomizuka, as well as building medical robots with Prof. Gangtie Zheng.
Besides research, I enjoy traveling, hiking, photography, skiing, badminton, and running. I am also a Gryffindor!
News
- Jan 31, 2025: Our paper “Beyond Waypoints: Semantic-Centric Autonomy with Unreliable Maps Through Learned Abstractions” is accepted by ICRA 2026!
- Jan 26, 2025: Our papers ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation and “Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning” are accepted by ICLR 2026!
- Sep 18, 2025: Our paper HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems is accepted by NeurIPS 2025!
- Aug 29, 2025 I won the 2025-2026 Schwarzman College of Computing Amazon AI Research Innovation Fellowship!
- Jun 24, 2025 Our paper Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL wins the Best Student Paper Award of RSS 2025!
- Jun 16, 2025 Our paper Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL is selected as the Best Paper Award finalist and the Best Student Paper Award finalist of RSS 2025!
- Apr 11, 2025 Our paper Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL is accepted by RSS 2025!
- Jan 31, 2025 Our GCBF+ work is featured by MIT News!
