Ayscgul Ucar

About

Ayscgul Ucar is a pioneering researcher in the intersection of robotics and artificial intelligence, with a primary focus on deep reinforcement learning (DRL) for humanoid robot locomotion. Her most influential work, "An Implementation of Vision Based Deep Reinforcement Learning for Humanoid Robot Locomotion" (2019), has garnered 14 citations and represents a significant breakthrough in the field. Ucar's major contribution lies in demonstrating that traditional sensor data—such as IMU, gyroscope, and GPS—is insufficient for robots to develop robust locomotion skills. By integrating vision-based inputs into DRL frameworks, she has shown that humanoid robots can learn more adaptive and complex movement patterns, effectively bridging the gap between raw sensory data and autonomous decision-making. This work has profound implications for the development of more capable, real-world robots that can navigate dynamic environments. Ucar's research not only advances the theoretical foundations of reinforcement learning but also provides practical pathways for creating humanoid robots that can see and learn from their surroundings, marking a notable achievement in the quest for truly autonomous machines.

Research Focus

Key Achievements

Top Papers

1. 1
   An Implementation of Vision Based Deep Reinforcement Learning for Humanoid Robot Locomotion

   14 citations · 2019

Key Collaborators

Contact & Links