Computer Science Department
School of Computer Science, Carnegie Mellon University
Human-Centered Planning for
Stephanie L. Rosenthal
Increasingly available mobile devices (e.g., mobile robots, smart phones) are becoming more intelligent in their ability to autonomously perform tasks for users. However, when deployed in complex human environments, these devices still face many sensing, reasoning, and actuation limitations. To overcome limitations, we propose symbiotic relationships as those in which the device can request help from humans in the environment while it performs tasks for them. Because the devices are performing tasks for humans, humans have incentive to help the device complete its tasks effectively. However, they may not always be available or willing to help. We introduce human-centered planning to model and reason about humans in the environment in addition to their own state and goals to determine how to act and whether, who, and how to seek help.
The thesis first contributes an understanding of what and how to model humans in the environment through user studies. We first evaluate whether attributes such as availability and interruptibility affect willingness to help. Then, we contribute to the understanding of how to ask humans for help to increase the accuracy of their responses. We show that providing humans with device context, classification prediction and uncertainty, and additional feedback all increase the accuracy of human responses to device questions. Finally, we contribute algorithms to learn these models both through surveys and online while the device is performing tasks.
The thesis then introduces human-centered conditional, deliberative, and replanning algorithms that use models of humans. We contribute conditional plans that include asking actions to enable devices to perform tasks that they could not otherwise perform. We then contribute a human-centered deliberative planner for a robot to use to determine which navigational path to take that minimizes its uncertainty and maximizes the likelihood of finding available human helpers. Finally, we contribute a replanning algorithm for a robot to determine which helper to have travel to help in a particular location, such as elevators or kitchens.
Through extensive experiments and deployments, in particular with a mobile service robot, this thesis shows that human-centered algorithms trade off task performance with costs of asking and interrupting human helpers increase functionality while maintaining usability.