Colleen P. Bailey
Papers
2
Total Citations
20
H-Index
2
About
Colleen P. Bailey is a researcher specializing in robotic control and autonomous navigation, with a particular focus on applying deep reinforcement learning techniques to real-world locomotion challenges. Her most recognized contribution centers on the obstacle avoidance and navigation problem in robotics, where she proposed innovative revisions to two prominent reinforcement learning algorithms — Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO) — enhanced through an improved reward shaping technique. This work, published in 2020, has garnered 20 citations across its iterations, reflecting meaningful engagement from the robotics and machine learning communities. By refining how agents are rewarded during training, Bailey's approach addresses a fundamental bottleneck in teaching autonomous systems to navigate complex environments safely and efficiently. Her research sits at the intersection of control theory and modern deep learning, contributing practical algorithmic improvements that have relevance for applications ranging from autonomous vehicles to robotic manipulation. For students and researchers entering the field of autonomous systems, Bailey's work offers a strong methodological foundation for understanding how reward engineering can meaningfully accelerate and stabilize reinforcement learning-based navigation solutions.
Research Focus
Key Achievements
Top Papers
- 1
- 2