Max Pflueger

Papers

Total Citations

H-Index

About

Max Pflueger’s research sits at the intersection of robotic manipulation, motion planning, and reinforcement learning, with a focus on enabling robots to operate intelligently in cluttered, obstructed environments. His most influential work, “Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments” (2020, 15 citations), introduces a hybrid framework that combines the sample efficiency of motion planners with the adaptability of deep RL. This approach allows agents to learn contact-rich tasks without requiring millions of exploratory interactions, addressing a critical bottleneck in real-world robotics. Earlier, in “Multi-step planning for robotic manipulation” (2015, 4 citations), Pflueger tackled the challenge of sequential decision-making in manipulation, proposing methods to predict how early choices affect later solution quality—a problem often overlooked in ad hoc planning systems. Though his citation counts are modest, his work is notable for bridging classical planning with modern learning-based methods, offering practical pathways for robots to handle complex, long-horizon tasks. Pflueger’s contributions are particularly valuable for researchers seeking to deploy RL in physical systems where data is scarce and obstacles are abundant.