Mahdis Bisheban
Papers
3
Total Citations
17
H-Index
2
About
Mahdis Bisheban is a researcher advancing the frontiers of autonomous aerial robotics, with a focus on control systems and intelligent decision-making for unmanned aerial manipulators (UAMs). Her work addresses critical challenges in dynamic environments, particularly the real-time estimation and adaptation to changing inertial properties—such as when a UAM picks up an unknown object mid-flight. Her most cited paper (2024, 11 citations) introduces an adaptive incremental nonlinear dynamic inversion (INDI) controller that enables UAMs to handle these inertia variations robustly, a key step toward practical manipulation tasks. Complementing this, her 2023 work (4 citations) develops a method for estimating time-varying inertia parameters during manipulation, laying groundwork for safer, more reliable aerial interactions. More recently, Bisheban has ventured into deep reinforcement learning, proposing a risk-sensitive exploration strategy (2025, 2 citations) that minimizes fuel consumption in unknown environments. By bridging adaptive control with learning-based autonomy, her research holds promise for applications in search-and-rescue, logistics, and infrastructure inspection. Her growing citation record reflects the timeliness and utility of her contributions to the robotics community.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3