Michael K. Bowman

Papers

Total Citations

H-Index

About

Michael K. Bowman is a leading researcher in robotic manipulation, focusing on the intersection of shared autonomy, multi-agent learning, and dexterous control. His work addresses fundamental challenges in telemanipulation and in-hand manipulation, where the physical mismatch between human and robotic hands demands novel control strategies. In his highly cited 2024 paper, "Intent-based Task-Oriented Shared Control for Intuitive Telemanipulation," Bowman introduced an intuitive shared-control framework that generates robotic grasp poses tailored to fine manipulation constraints, enabling more natural and effective human-robot collaboration. This work has already garnered 7 citations, reflecting its immediate impact on the field. Earlier, his 2023 study, "A Multi-Agent Approach for Adaptive Finger Cooperation in Learning-based In-Hand Manipulation," pioneered a decentralized reinforcement learning method that treats each finger as an independent agent, overcoming the limitations of single-policy approaches for high-degree-of-freedom robotic hands. With 5 citations, this work demonstrates his ability to bridge multi-agent systems and dexterous manipulation. Bowman’s contributions are shaping the next generation of intuitive, adaptive robotic systems, making him a rising voice in human-robot interaction and autonomous manipulation.