About

Mike Hagenow is an assistant professor in the Department of Computer Sciences at UW-Madison. His research focuses on developing methods for effective human-robot teaming, particularly in contact-rich tasks that are physically demanding on people. His main research interests include shared autonomy and robot learning. Prior to his current position, he was a postdoctoral fellow in the Aeronautics and Astronautics department and CSAIL at MIT. Hagenow holds a BS in mechanical engineering from Tufts University, obtained in 2014, and both an MS and PhD in mechanical engineering from UW-Madison, completed in 2019 and 2023 respectively.

Research topics

• Computer Science
• Artificial Intelligence
• Human–computer interaction

Selected publications

• Multi-Cycle Spatio-Temporal Adaptation in Human-Robot Teaming

  arXiv (Cornell University) · 2026-04-21

  preprintOpen access

  Effective human-robot teaming is crucial for the practical deployment of robots in human workspaces. However, optimizing joint human-robot plans remains a challenge due to the difficulty of modeling individualized human capabilities and preferences. While prior research has leveraged the multi-cycle structure of domains like manufacturing to learn an individual's tendencies and adapt plans over repeated interactions, these techniques typically consider task-level and motion-level adaptation in isolation. Task-level methods optimize allocation and scheduling but often ignore spatial interference in close-proximity scenarios; conversely, motion-level methods focus on collision avoidance while ignoring the broader task context. This paper introduces RAPIDDS, a framework that unifies these approaches by modeling an individual's spatial behavior (motion paths) and temporal behavior (time required to complete tasks) over multiple cycles. RAPIDDS then jointly adapts task schedules and steers diffusion models of robot motions to maximize efficiency and minimize proximity accounting for these individualized models. We demonstrate the importance of this dual adaptation through an ablation study in simulation and a physical robot scenario using a 7-DOF robot arm. Finally, we present a user study (n=32) showing significant plan improvement compared to non-adaptive systems across both objective metrics, such as efficiency and proximity, and subjective measures, including fluency and user preference. See this paper's companion video at: https://youtu.be/55Q3lq1fINs.

  PublisherDOI

• GeoSACS: Geometric Shared Autonomy via Canal Surfaces

  2026-03-10

  article

  Shared autonomy (SA), which combines user inputs with autonomous capabilities, presents a significant opportunity for assistive robotics. A key challenge in SA is the dimensionality gap: the mismatch between low-dimensional user inputs from familiar interfaces (e.g., 2D joysticks) and the high-dimensional control required by robot manipulators. To enhance usability and acceptance, this mapping must be as simple and intuitive as possible. We introduce GeoSACS, a geometric framework for SA. GeoSACS uses canal surfaces to encode task structure with as few as two demonstrations. While the robot moves autonomously along the canal, users can then make corrections on the 2D planar circular cross-sections orthogonal to the robot motion. By leveraging geometric structure to partition the 6D control space between the robot and the user, GeoSACS allows the intuitive mapping of 2D user inputs to 6D end-effector control. We describe GeoSACS and evaluate its underlying assumptions in a user study against two baselines. Results from the study demonstrate reduced workload and improved performance, providing insights for the design of future SA systems.

  PublisherDOI

• Multi-Cycle Spatio-Temporal Adaptation in Human-Robot Teaming

  ArXiv.org · 2026-04-21

  articleOpen access

  Effective human-robot teaming is crucial for the practical deployment of robots in human workspaces. However, optimizing joint human-robot plans remains a challenge due to the difficulty of modeling individualized human capabilities and preferences. While prior research has leveraged the multi-cycle structure of domains like manufacturing to learn an individual's tendencies and adapt plans over repeated interactions, these techniques typically consider task-level and motion-level adaptation in isolation. Task-level methods optimize allocation and scheduling but often ignore spatial interference in close-proximity scenarios; conversely, motion-level methods focus on collision avoidance while ignoring the broader task context. This paper introduces RAPIDDS, a framework that unifies these approaches by modeling an individual's spatial behavior (motion paths) and temporal behavior (time required to complete tasks) over multiple cycles. RAPIDDS then jointly adapts task schedules and steers diffusion models of robot motions to maximize efficiency and minimize proximity accounting for these individualized models. We demonstrate the importance of this dual adaptation through an ablation study in simulation and a physical robot scenario using a 7-DOF robot arm. Finally, we present a user study (n=32) showing significant plan improvement compared to non-adaptive systems across both objective metrics, such as efficiency and proximity, and subjective measures, including fluency and user preference. See this paper's companion video at: https://youtu.be/55Q3lq1fINs.

  PublisherOA PDF

• Shared Control/Autonomy: A Historical Perspective, Current Trends, and the Role of Generative AI

  2025-12-19

  preprintOpen access1st authorCorresponding

  In shared control and shared autonomy systems, humans collaborate with robot agents to achieve common goals. Research in this area dates back over 40 years, with numerous applications, such as in manufacturing, robot surgery, and assistive technologies. Shared control approaches have even seen some commercialization efforts in areas like semi-autonomous driving and automotive assembly. Recently, shared control and shared autonomy approaches have gained significant traction, with hundreds of new methods published in scientific papers each year. In this paper, we examine recent approaches and trends in these methods, investigating several crucial aspects that are underexplored in previous surveys. First, we provide descriptive statistics and trends related to human input methods, technical approaches, and applications. Second, we examine the growing role of generative artificial intelligence approaches in shared control and autonomy. Based on these insights, we offer updated recommendations for future approaches.

  PublisherOA PDFDOI

• Analyzing Reluctance to Ask for Help When Cooperating With Robots: Insights to Integrate Artificial Agents in HRC

  ArXiv.org · 2025-09-01

  preprintOpen access

  As robot technology advances, collaboration between humans and robots will become more prevalent in industrial tasks. When humans run into issues in such scenarios, a likely future involves relying on artificial agents or robots for aid. This study identifies key aspects for the design of future user-assisting agents. We analyze quantitative and qualitative data from a user study examining the impact of on-demand assistance received from a remote human in a human-robot collaboration (HRC) assembly task. We study scenarios in which users require help and we assess their experiences in requesting and receiving assistance. Additionally, we investigate participants' perceptions of future non-human assisting agents and whether assistance should be on-demand or unsolicited. Through a user study, we analyze the impact that such design decisions (human or artificial assistant, on-demand or unsolicited help) can have on elicited emotional responses, productivity, and preferences of humans engaged in HRC tasks.

  PublisherOA PDFDOI

• Versatile Demonstration Interface: Toward More Flexible Robot Demonstration Collection

  2025-10-19

  article1st authorCorresponding

  Previous methods for Learning from Demonstration leverage several approaches for a human to teach motions to a robot, including teleoperation, kinesthetic teaching, and natural demonstrations. However, little previous work has explored more general interfaces that allow for multiple demonstration types. Given the varied preferences of human demonstrators and task characteristics, a flexible tool that enables multiple demonstration types could be crucial for broader robot skill training. In this work, we propose Versatile Demonstration Interface (VDI), an attachment for collaborative robots that simplifies the collection of three common types of demonstrations. Designed for flexible deployment in industrial settings, our tool requires no additional instrumentation of the environment. Our prototype interface captures human demonstrations through a combination of vision, force sensing, and state tracking (e.g., through the robot proprioception or AprilTag tracking). Through a user study where we deployed our prototype VDI at a local manufacturing innovation center with manufacturing experts, we demonstrated VDI in representative industrial tasks. Interactions from our study highlight the practical value of VDI’s varied demonstration types, expose a range of industrial use cases for VDI, and provide insights for future tool design.

  PublisherDOI

• Analyzing Reluctance to Ask for Help When Cooperating With Robots: Insights to Integrate Artificial Agents in HRC

  2025-08-25

  article

  As robot technology advances, collaboration between humans and robots will become more prevalent in industrial tasks. When humans run into issues in such scenarios, a likely future involves relying on artificial agents or robots for aid. This study identifies key aspects for the design of future user-assisting agents. We analyze quantitative and qualitative data from a user study examining the impact of on-demand assistance received from a remote human in a human-robot collaboration (HRC) assembly task. We study scenarios in which users require help and we assess their experiences in requesting and receiving assistance. Additionally, we investigate participants’ perceptions of future non-human assisting agents and whether assistance should be on-demand or unsolicited. Through a user study, we analyze the impact that such design decisions (human or artificial assistant, on-demand or unsolicited help) can have on elicited emotional responses, productivity, and preferences of humans engaged in HRC tasks.

  PublisherDOI

• REALM: Real-Time Estimates of Assistance for Learned Models in Human-Robot Interaction

  ArXiv.org · 2025-04-12

  preprintOpen access1st authorCorresponding

  There are a variety of mechanisms (i.e., input types) for real-time human interaction that can facilitate effective human-robot teaming. For example, previous works have shown how teleoperation, corrective, and discrete (i.e., preference over a small number of choices) input can enable robots to complete complex tasks. However, few previous works have looked at combining different methods, and in particular, opportunities for a robot to estimate and elicit the most effective form of assistance given its understanding of a task. In this paper, we propose a method for estimating the value of different human assistance mechanisms based on the action uncertainty of a robot policy. Our key idea is to construct mathematical expressions for the expected post-interaction differential entropy (i.e., uncertainty) of a stochastic robot policy to compare the expected value of different interactions. As each type of human input imposes a different requirement for human involvement, we demonstrate how differential entropy estimates can be combined with a likelihood penalization approach to effectively balance feedback informational needs with the level of required input. We demonstrate evidence of how our approach interfaces with emergent learning models (e.g., a diffusion model) to produce accurate assistance value estimates through both simulation and a robot user study. Our user study results indicate that the proposed approach can enable task completion with minimal human feedback for uncertain robot behaviors.

  PublisherOA PDFDOI

• REALM: Real-Time Estimates of Assistance for Learned Models in Human-Robot Interaction

  IEEE Robotics and Automation Letters · 2025-04-14 · 2 citations

  article1st authorCorresponding

  There are a variety of mechanisms (i.e., input types) for real-time human interaction that can facilitate effective human-robot teaming. For example, previous works have shown how teleoperation, corrective, and discrete (i.e., preference over a small number of choices) input can enable robots to complete complex tasks. However, few previous works have looked at combining different methods, and in particular, opportunities for a robot to estimate and elicit the most effective form of assistance given its understanding of a task. In this paper, we propose a method for estimating the value of different human assistance mechanisms based on the action uncertainty of a robot policy. Our key idea is to construct mathematical expressions for the expected post-interaction differential entropy (i.e., uncertainty) of a stochastic robot policy to compare the expected value of different interactions. As each type of human input imposes a different requirement for human involvement, we demonstrate how differential entropy estimates can be combined with a likelihood penalization approach to effectively balance feedback informational needs with the level of required input. We demonstrate evidence of how our approach interfaces with emergent learning models (e.g., a diffusion model) to produce accurate assistance value estimates through both simulation and a robot user study. Our user study results indicate that the proposed approach can enable task completion with minimal human feedback for uncertain robot behaviors.

  PublisherDOI

• Versatile Demonstration Interface: Toward More Flexible Robot Demonstration Collection

  arXiv (Cornell University) · 2024-10-24

  preprintOpen access1st authorCorresponding

  Previous methods for Learning from Demonstration leverage several approaches for a human to teach motions to a robot, including teleoperation, kinesthetic teaching, and natural demonstrations. However, little previous work has explored more general interfaces that allow for multiple demonstration types. Given the varied preferences of human demonstrators and task characteristics, a flexible tool that enables multiple demonstration types could be crucial for broader robot skill training. In this work, we propose Versatile Demonstration Interface (VDI), an attachment for collaborative robots that simplifies the collection of three common types of demonstrations. Designed for flexible deployment in industrial settings, our tool requires no additional instrumentation of the environment. Our prototype interface captures human demonstrations through a combination of vision, force sensing, and state tracking (e.g., through the robot proprioception or AprilTag tracking). Through a user study where we deployed our prototype VDI at a local manufacturing innovation center with manufacturing experts, we demonstrated VDI in representative industrial tasks. Interactions from our study highlight the practical value of VDI's varied demonstration types, expose a range of industrial use cases for VDI, and provide insights for future tool design.

  PublisherOA PDFDOI

Frequent coauthors

• Michael Zinn

  University of Wisconsin–Madison

  23 shared

• Michael Gleicher

  University of Wisconsin–Madison

  22 shared

• Bilge Mutlu

  20 shared

• Robert G. Radwin

  University of Wisconsin–Madison

  15 shared

• Emmanuel Senft

  Idiap Research Institute

  13 shared

• Nitzan Orr

  University of Wisconsin–Madison

  4 shared

• Evan Laske

  3 shared

• Kimberly Hambuchen

  Johnson Space Center

  3 shared