Yakup Demir

About

Yakup Demir is a robotics researcher whose work sits at the intersection of deep reinforcement learning (DRL), humanoid locomotion, and robotic manipulation. His most cited paper, "Efficient deep neural network model for classification of grasp types using sEMG signals" (2021, 35 citations), demonstrates his expertise in using biological signals to inform robotic control, a key contribution to the field of prosthetics and human-robot interaction. Demir has also made significant strides in advancing vision-based DRL for humanoid robots, showing that visual input—beyond traditional sensor values like IMU and gyroscope data—is critical for robots to learn complex locomotion skills. His work on "Robotic Grasping in Simulation Using Deep Reinforcement Learning" (2022) further explores how manipulators can autonomously learn to grasp objects, a fundamental challenge in industrial and service robotics. With a growing citation record, Demir’s research is shaping how robots perceive and interact with their environment, bridging the gap between simulation and real-world application. His contributions are particularly relevant for students and researchers interested in integrating computer vision, neural networks, and reinforcement learning to create more autonomous and adaptive robotic systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Efficient deep neural network model for classification of grasp types using sEMG signals

   35 citations · 2021
2. 2
   An Implementation of Vision Based Deep Reinforcement Learning for Humanoid Robot Locomotion

   14 citations · 2019
3. 3
   Robotic Grasping in Simulation Using Deep Reinforcement Learning

   3 citations · 2022

Key Collaborators

Contact & Links