Matthew B. Luebbers

Contact

Engineering Center, ECES 111
University of Colorado Boulder
Boulder, Colorado, USA
matthew.luebbers(at)colorado.edu

  Personal

I'm a PhD student in the Department of Computer Science at the University of Colorado Boulder, and a researcher in the Collaborative AI and Robotics (CAIRO) Lab, advised by Brad Hayes.

I graduated undergrad from Cornell University in 2018, where I majored in Computer Science, specializing in and conducting research into artificial intelligence and robotics in the Robot Personal Assistants Lab (RPAL).

Since 2016, I have spent six summers interning at NASA's Jet Propulsion Laboratory in Pasadena, California. I have contributed to the Instrument Data Subystem (IDS) and Rover Planning Subystem (RPS) of multiple Martian surface missions - the Curiosity rover, the InSight lander, and the Perseverance rover. Throughout my summers working on the RPS team, I have had the incredible opportunity to help drive both Curiosity and Perseverance across five solar-days worth of traverse sequencing, where I have accrued a career Martian odometry of 228 meters (86 m on Curiosity, 142 m on Perseverance)!

Some of my interests outside of work include observational astronomy, aviation and space travel, traditional animation, language learning, and distance running.

  Research

Robotics has traditionally been broken down into two distinct operational paradigms – autonomy and teleoperation. These approaches are inherently limited, however, by the respective weaknesses of autonomous systems and human operators. My research therefore focuses on a third paradigm, where human and robotic agents are treated as teammates working towards a common goal, whether the humans and robots are collocated (proximal teaming) or not (remote teaming).

Much like in human teams, demonstrating productive and collaborative behavior in these setups requires a degree of plan synchronization. Central to achieving this is establishing shared mental models between humans and robots – that is, creating formal knowledge structures that allow us to transform between robot planning spaces centered around mathematical optimization, and subjective, variable human planning spaces. This is often a challenging proposition, especially in real world domains with environmental uncertainty and time and safety constraints.

With this goal in mind, my research involves developing novel techniques for compactly communicating plan rationale and uncertainty to human collaborators through visual, natural language, and behavioral modalities, leveraging emerging technologies like augmented reality and counterfactual explanation to do so. In working to establish shared mental models interpretable by both human and robot, my work aims to improve the fluency, transparency, adaptability, and trust of human-robot teaming architectures across a variety of task types.

Asterisk (*) denotes shared first authorship

  Journal Articles

• Aaquib Tabrez, Matthew B. Luebbers, and Bradley Hayes. (2020). A Survey of Mental Modeling Techniques in Human-Robot Teaming. In Current Robotics Reports. Springer-Nature. Link.

  Conference Papers

• Matthew B. Luebbers*, Aaquib Tabrez*, Kyler Ruvane*, and Bradley Hayes. (2023). Autonomous Justification for Enabling Explainable Decision Support in Human-Robot Teaming. In Proceedings of Robotics: Science and Systems (RSS 2023). Daegu, South Korea. PDF.
  Acceptance Rate: 31%.
• Christine T. Chang, Matthew B. Luebbers, Mitchell Herbert, and Bradley Hayes. (2023). Human Non-Compliance with Robot Spatial Ownership Communicated via Augmented Reality: Implications for Human-Robot Teaming Safety. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2023). London, England, UK. PDF.
  Acceptance Rate: 43%.
• Aaquib Tabrez*, Matthew B. Luebbers*, and Bradley Hayes. (2022). Descriptive and Prescriptive Visual Guidance to Improve Shared Situational Awareness in Human-Robot Teaming. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022). Auckland, New Zealand. PDF. Video.
  Best Student Paper Runner-Up (Top 2 of 629 submissions). Acceptance Rate: 26%.
• Matthew B. Luebbers, Connor Brooks, Carl L. Mueller, Daniel Szafir, and Bradley Hayes. (2021). ARC-LfD: Using Augmented Reality for Interctive Long-Term Robot Skill Maintenance via Constrained Learning from Demonstration. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2021). Xi'an, China. PDF. Video.
  Acceptance Rate: 48%.

  Workshops, Symposia, & Posters

• Carl L. Mueller, Matthew B. Luebbers, Aaquib Tabrez, and Bradley Hayes. (2023). Augmented Reality and Proxy Grippers Improve Demonstration-based Robot Skill Learning. In Proceedings of the Workshop on Life-Long Learning with Human Help (L3H2 2023). London, England, UK. PDF.
• Breanne Crockett*, Kyler Ruvane*, Matthew B. Luebbers, and Bradley Hayes. (2023). Effective Human-in-the-loop Control Handover via Confidence-Aware Autonomy. In Proceedings of the Workshop on Life-Long Learning with Human Help (L3H2 2023). London, England, UK. PDF.
• Yi-Shiuan Tung, Matthew B. Luebbers, Alessandro Roncone, and Bradley Hayes. (2023). Improving Human Legibility in Collaborative Robot Tasks through Augmented Reality and Workspace Preparation. In Proceedings of the Workshop on Virtual, Augmented and Mixed Reality for Human-Robot Interaction (VAM-HRI 2023). Stockholm, Sweden. PDF.
• Maciej K. Wozniak*, Christine T. Chang*, Matthew B. Luebbers*, Bryce Ikeda*, Michael E. Walker*, Eric Rosen*, and Thomas Groechel*. (2023). Virtual, Augmented, and Mixed Reality for Human-Robot Interaction (VAM-HRI). In Companion for the ACM/IEEE International Conference on Human-Robot Interaction (HRI 2023). Stockholm, Sweden. PDF.
• Matthew B. Luebbers*, Aaquib Tabrez*, and Bradley Hayes. (2022). Augmented Reality-Based Explainable AI Strategies for Establishing Appropriate Reliance and Trust in Human-Robot Teaming. In Proceedings of the Workshop on Virtual, Augmented and Mixed Reality for Human-Robot Interaction (VAM-HRI 2022). Sapporo, Japan. PDF.
• Matthew B. Luebbers*, Christine T. Chang*, Aaquib Tabrez*, Jordan Dixon*, and Bradley Hayes. (2021). Emerging Autonomy Solutions for Human and Robotic Deep Space Exploration. In Proceedings of SpaceCHI: Human-Computer Interaction for Space Exploration (SpaceCHI 2021). Yokohama, Japan. PDF. Poster.
• Aaquib Tabrez*, Matthew B. Luebbers*, and Bradley Hayes. (2020). Automated Failure-Mode Clustering and Labeling for Informed Car-To-Driver Handover in Autonomous Vehicles. In Proceedings of the Workshop on Assessing, Explaining, and Conveying Robot Proficiency for Human-Robot Teaming. Cambridge, England, UK. PDF. Video.
• Matthew B. Luebbers, Connor Brooks, Minjae John Kim, Daniel Szafir, and Bradley Hayes. (2019). Augmented Reality Interface for Constrained Learning from Demonstration. In Proceedings of the Workshop on Virtual, Augmented and Mixed Reality for Human-Robot Interaction (VAM-HRI 2019). Daegu, South Korea. PDF.
• Matthew B. Luebbers, Ramchandran Muthukumar, Madeleine Udell, and Ross A. Knepper. (2017). Planning Aerial Survey Missions using Low Rank Approximation. Presented: Northeast Robotics Colloquium (NERC 2017). Boston, Massachusetts, USA.

• CSCI 5302: Advanced Robotics.
  University of Colorado Boulder, Fall '21.
• CSCI 5722: Computer Vision.
  University of Colorado Boulder, Spring '20.
• CSCI 1300: Introduction to Computer Science.
  University of Colorado Boulder, Fall '19.
• CS 4700: Foundations of Artificial Intelligence.
  Cornell University, Fall '17.
• CS 3410: Computer Systems Organization and Programming.
  Cornell University, Fall '16 - Spring '17.
• CS 2110: Object-Oriented Programming and Data Structures.
  Cornell University, Fall '15 - Spring '16.