Truong-Dong Do

About

Truong-Dong Do is a researcher at the forefront of autonomous aerial robotics, with a primary focus on developing intelligent control systems for quadcopters and nano drones. His most cited work, "End-to-End Deep Reinforcement Learning-based Nano Quadcopter Low-level Controller" (2024), addresses the longstanding challenges of dynamical nonlinearity, actuator saturation, and sensor noise that plague quadcopter control. Rather than relying on traditional, time-intensive modeling approaches, Do pioneers the use of deep reinforcement learning to create end-to-end controllers that directly map sensor inputs to motor commands, enabling agile and robust flight in constrained environments. This work has already garnered attention within the robotics community, with 1 citation in its first year. Do’s contributions are particularly significant for nano quadcopters—small, lightweight platforms where conventional control methods often fail due to severe hardware limitations. By demonstrating that reinforcement learning can replace hand-tuned controllers, he opens new possibilities for autonomous drones in search-and-rescue, inspection, and surveillance. His research sits at the intersection of machine learning, control theory, and embedded systems, promising to make quadcopters more adaptive and easier to deploy in real-world scenarios.

Research Focus

Key Achievements

Top Papers

1. 1
   End-to-End Deep Reinforcement Learning-based Nano Quadcopter Low-level Controller

   1 citations · 2024

Key Collaborators

Contact & Links