Melissa Greeff
Papers
4
Total Citations
714
H-Index
4
About
Melissa Greeff is a robotics and control researcher whose work sits at the intersection of safe learning-based control, reinforcement learning, and autonomous systems. She is best known for her landmark 2022 review, "Safe Learning in Robotics," which has accumulated over 650 citations and stands as one of the field's most comprehensive surveys of machine learning methods for safe real-world robotic deployment. This work synthesizes advances from both the control theory and reinforcement learning communities, providing researchers and practitioners with a unified framework for understanding safety-critical robotics. Greeff also co-developed Safe-Control-Gym, a benchmark suite that has become a valuable resource for rigorously evaluating safe learning algorithms in robotics contexts, reflecting her commitment to reproducible and standardized research infrastructure. Her work extends beyond software tools into physical systems: she has contributed to bio-inspired soft robotics, including a bistable shape memory alloy-driven aquatic robot mimicking jellyfish locomotion, and to multi-robot coordination, with research on cooperative multirotor landing on uncrewed surface vessels in dynamic maritime environments. Across these diverse domains, Greeff consistently bridges theoretical guarantees with practical deployment, making her an influential voice in the rapidly growing field of safe and autonomous robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4