Michael Bowman

About

Michael Bowman is a leading researcher in human-robot interaction, with a primary focus on telemanipulation and shared autonomy. His work addresses a fundamental challenge in robotics: how to seamlessly blend human intent with autonomous robot assistance. Bowman’s key contributions include developing intent-uncertainty-aware grasp planning, which allows robots to infer a human operator’s goals and provide adaptive motion support during teleoperation. His 2019 paper on this topic, with 17 citations, demonstrates how promoting robot autonomy can significantly enhance operator performance. He further advanced the field with his 2020 work on inference of manipulation intent, and his 2023 paper on dimension-specific shared autonomy tackles the critical issue of control allocation across multiple degrees of freedom, moving beyond simplistic uniform blending. Bowman has also explored real-world human-robot cooperation for general goals and dynamic pre-grasp planning for moving objects. His research has been cited over 40 times, reflecting its growing influence in shaping more intuitive and effective robotic assistance systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Intent-Uncertainty-Aware Grasp Planning for Robust Robot Assistance in Telemanipulation

   17 citations · 2019
2. 2
   Inference of Manipulation Intent in Teleoperation for Robotic Assistance

   13 citations · 2020
3. 3
   Dimension-Specific Shared Autonomy for Handling Disagreement in Telemanipulation

   5 citations · 2023
4. 4
   Forming Real-World Human-Robot Cooperation for Tasks With General Goal

   4 citations · 2021
5. 5
   WE-Filter: Adaptive Acceptance Criteria for Filter-based Shared Autonomy

   2 citations · 2023
6. 6
   Dynamic Pre-Grasp Planning when Tracing a Moving Object Through a Multi-Agent Perspective

   2 citations · 2021

Key Collaborators

Contact & Links