Welcome to the Cultivating Human-Agent Interactions (CHAI) Project Page!

Description: As collaborative robots become commonplace, creating schedules for human-robot teamwork will be crucial. Our research aims to explore scheduling algorithms that have been developed for robot teams and test their effectiveness when applied to human-robot teams. We also hope to test the effect of human autonomy on these teams’ productivity and efficiency.
We are currently working with Rethink Robotics’ Sawyer platform to investigate how humans and Sawyer work together to complete simple tasks that simulate actual applications of collaborative manufacturing robots.

Read more:

• Who Takes the Lead? Automated Scheduling for Human-Robot Teams by Castro, Roberts, Mena, and Boerkoel. AI for HRI 2017 AAAI Fall Symposium.

Welcome to the Productivity and Wellness Pal (PaWPal) Project Page!

Description: College students often struggle to balance their work with personal wellness. In part, this occurs because students work when they are unable to focus. One approach to increasing both productivity and wellness is to help users achieve flow. Flow is a state in which people feel focused, motivated, and fully immersed in their activity, resulting in feelings of satisfaction and even joy.

The Experience Sampling Method (ESM), in which users are randomly surveyed throughout the day about their experiences, is a well-studied mechanism for characterizing flow. We hypothesize that we can adapt ESM to build a model of users’ efficacy and predict when they will be most likely to experience flow.

The Productivity and Wellness Pal (PaWPal) is an Android-based application that seeks to make users aware of their efficacy at various tasks as well as which courses of action are likely to lead to immersive experiences.

This project was the precursor to the campus-wide Workload and Health at Mudd (WHAM)! study about student workload and health at Harvey Mudd.

Read more:

• Predicting the Quality of User Experiences to Improve Productivity and Wellness by Donti, Rosenbloom, Gruver, and Boerkoel. AAAI 2015.
• Exploring Active and Passive Team-Based Coordination by Donti and Boerkoel. AI-HRI 2014.

Welcome to the Robot Brunch / DREAM Project Page!

Description: Temporal plans exist to provide robust directives that robots can follow to accomplish their goals, while also coordinating when these activities should occur. In general, we want temporal plans that are adaptable to events that are beyond the direct control of agents; e.g., a robot may experience slippage or sensor failures. To do this, we must answer two questions: (1) how and when do new or unexpected events arise in practice?, and (2) how "good" is the temporal plan at adapting to unexpected events that might otherwise invalidate the plan?

This project explores the usefulness of a new metric called robustness, which assesses the likelihood that a multi-robot plan succeeds. The project has proposed new, uncertainty-aware, online and offline scheduling algorithms. In particular, we've introduced a single streamlined algorithm, called DREAM (Dynamic Robust Execution Algowithm w/ Mitigation) that trades robustness for various forms of computational overhead including multi-agent communication.

Read more:

• DREAM: An Algorithm for Mitigating the Overhead of Robust Rescheduling by Abrahams, Chu, Diehl, Knittel, Lin, Lloyd, Boerkoel and Frank. ICAPS 2019.
• Robust Execution of Probabilistic Temporal Plans by Lund, Dietrich, Chow, and Boerkoel. AAAI 2017.
• Robustness in Probabilistic Temporal Planning by Brooks, Reed, Gruver, and Boerkoel. AAAI 2015.

Welcome to the Probably-in-Control Project Page!

Description: This project looks to deal with situations where scheduling uncertainty outstrips an agent’s ability to control for it. We develop new analytical tools for assessing what we coined “the degree of controllability,” which measures the likelihood that an agent (e.g., robot) can control for the presence of scheduling uncertainty (due to, e.g., slippage or localization error).

Read more:

• Quantifying Degrees of Controllability in Temporal Networks with Uncertainty by Akmal, Ammons, Li, and Boerkoel. ICAPS 2019.

Welcome to the Human-Robot Trust Project Page!

Description: Trust and cooperation are fundamental to human interactions. How much we trust other people directly influences the decisions we make and our willingness to cooperate. It thus seems natural that trust be equally important in successful human-robot interaction (HRI), since how much a human trusts a robot affects how they might interact with it.

We propose using a coin entrustment game, a variant of prisoner’s dilemma, to measure trust and cooperation as separate phenomenon between human and robot agents. We use this game along with our NAO robot to test the following hypotheses:

1. Humans will achieve and maintain higher levels of trust when interacting with what they believe to be a robot than with another human; and
2. Humans will cooperate more readily with robots and will maintain a higher level of cooperation.

Read more:

• Trust and Cooperation in Human-Robot Decision Making by Wu, Paeng, Linder, Valdesolo, and Boerkoel. AI-HRI 2016.