Ali Alper Demir

About

Ali Alper Demir is a researcher advancing the frontier of autonomous mobile robotics through deep reinforcement learning. His primary research focus lies in developing unified motion planning and control systems for differential drive robots, with a particular emphasis on handling dynamic and uncertain operating conditions. Demir’s most notable contribution is his work on integrating variable payloads into robotic control, a critical challenge for real-world applications where robots must adapt to changing loads. In his 2019 study, “Motion Planning and Control with Randomized Payloads Using Deep Reinforcement Learning” (7 citations), he introduced a deep reinforcement learning agent that processes an 11-dimensional state vector to output precise wheel torques, enabling continuous control under varying payloads. This work was further validated on real hardware in a subsequent 2019 paper (3 citations). He also addressed the complex task of intersection navigation under dynamic constraints (2018, 3 citations), demonstrating robust performance with a 10-dimensional state input. Though his citation counts are modest, Demir’s research represents a practical, scalable approach to bridging simulation and real-world deployment, making him a promising voice in the integration of learning-based methods with classical robotics challenges.

Research Focus

Key Achievements

Top Papers

1. 1
   Motion Planning and Control with Randomized Payloads Using Deep Reinforcement Learning

   7 citations · 2019
2. 2
   Intersection Navigation Under Dynamic Constraints Using Deep Reinforcement Learning

   3 citations · 2018
3. 3
   Motion Planning and Control with Randomized Payloads on Real Robot Using Deep Reinforcement Learning

   3 citations · 2019

Key Collaborators

Contact & Links