Faseeh
Ahmad
PhD Candidate in Computer Science
Lund University, Sweden

Hi, My name is Faseeh Ahmad. I am a PhD candidate in the Computer Science (LTH) department. I work in the Robotics Science and Systems (RSS) group at Lund University, Sweden. My research focuses on Robotics and AI, aiming to develop autonomous robots that can efficiently handle complex industrial and daily tasks with minimal human intervention.

I work on failure recovery scenarios in robotics. While robots are increasingly common, most research focuses on their task-solving capabilities, often overlooking failure rates. My research addresses this gap by developing reliable failure recovery strategies, ensuring robots can detect, identify, and recover from both known and unknown failures, thus completing their tasks safely and successfully.
I combine robotics with AI techniques such as planning and machine learning, particularly deep learning and reinforcement learning, to create models that optimize robot performance. Recently, I’ve been exploring the integration of large language models to enhance this framework further.

I’m fortunate to conduct my research at Lund University, which is supported by funding from WASP Sweden. I collaborate closely with my supervisors, Prof. Volker Krueger, Prof. Elin Anna Topp, and Prof. Jacek Malek. My background includes extensive hands-on experience with various robots in both simulation and real-world settings, along with expertise in AI techniques like motion and task planning, machine learning, deep learning, and reinforcement learning.

publications
Adaptable Recovery Behaviors in Robotics: A Behavior Trees and Motion Generators (BTMG) Approach for Failure Management
Faseeh Ahmad, Matthias Mayr, Sulthan Suresh-Fazeela, Volker Kreuger
arXiv preprint arXiv:2404.06129
watch video
Learning to adapt the parameters of behavior trees and motion generators (btmgs) to task variations
Faseeh Ahmad, Matthias Mayr, Volker Krueger
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
watch video
Hybrid planning for challenging construction problems: An Answer Set Programming approach
Faseeh Ahmad, Volkan Patoglu, Esra Erdem
Artificial Intelligence 319, 103902
Repositories