Banafsheh Rekabdar
Papers
1
Total Citations
2
H-Index
1
About
Banafsheh Rekabdar is a leading researcher in artificial intelligence and robotics, specializing in decision-making under uncertainty and dynamic environments. Her work focuses on developing novel frameworks for robot path planning, particularly in scenarios involving visual occlusions and moving targets—challenges that have long hindered autonomous systems. Rekabdar’s major contribution, the Uncertainty Measured Markov Decision Process (UM-MDP), introduced in her highly cited 2020 paper, integrates uncertainty quantification into classical partially observable Markov decision processes. This innovation enables robots to navigate pursuit-evasion tasks more reliably by explicitly modeling and adapting to environmental unpredictability. While her work has garnered attention with over 2 citations, its true impact lies in advancing the theoretical foundations for real-world autonomous navigation. Rekabdar’s research bridges the gap between theoretical AI models and practical robotic applications, offering solutions that enhance safety and efficiency in dynamic settings. Her achievements underscore a commitment to solving complex, real-world problems, making her a notable figure in the intersection of AI, robotics, and decision science.
Research Focus
Key Achievements
Top Papers
- 1Uncertainty Measured Markov Decision Process in Dynamic Environments2 citations · 2020