Muhammad Sunny Nazeer
Papers
7
Total Citations
101
H-Index
6
About
Muhammad Sunny Nazeer is pioneering the use of machine learning to solve one of robotics’ most stubborn challenges: achieving precise, reliable control over soft, deformable robots. His research sits at the intersection of soft robotics and artificial intelligence, focusing on how imitation learning and reinforcement learning can overcome the inherent unpredictability of compliant materials. Nazeer’s most cited work, an RL-based adaptive controller for high-precision reaching in a soft robot arm (37 citations), directly tackles the data-hungry nature of traditional reinforcement learning. He further advanced the field with Soft DAgger (18 citations), a sample-efficient imitation learning method that enabled a soft arm to write letters in 3D space. His contributions extend to adaptive online control via regressing networks and dynamic gait controllers for repetitive tasks, collectively demonstrating how learning-based approaches can tame the nonlinear, stochastic behavior of soft manipulators. With over 100 total citations and a perspective paper on imitation and reinforcement learning for soft robots, Nazeer is establishing a foundational framework for making soft robots not just flexible, but functionally precise—a critical step toward their deployment in delicate interactions with living organisms and fragile objects.
Research Focus
Key Achievements
Top Papers
- 1RL-Based Adaptive Controller for High Precision Reaching in a Soft Robot Arm37 citations · 2024
- 2Soft DAgger: Sample-Efficient Imitation Learning for Control of Soft Robots18 citations · 2023
- 3Policy Adaptation using an Online Regressing Network in a Soft Robotic Arm13 citations · 2023
- 4
- 5Bootstrapping the Dynamic Gait Controller of the Soft Robot Arm11 citations · 2023
- 6
- 7