Spatial Tasking in Human-Robot Collaborative Exploration

Abstract

This work develops a methodology for collaborative human-robot exploration that leverages implicit coordination. Most autonomous single- and multi-robot exploration systems require a remote operator to provide explicit guidance to the robot team. Few works consider how to integrate the human partner alongside robots to provide guidance in the field. A challenge for collaborative human-robot exploration is the efficient communication of goals from the human to the robot. For applications like search and rescue, which are time-sensitive and high-stress endeavors, robot assistants must provide value for human partners to motivate deployment in the field.

In this thesis, we develop a methodology that implicitly communicates a region of interest from a helmet-mounted depth camera on the human’s head to the robot and an information gain-based exploration objective that biases motion planning within the viewpoint provided by the human. We also study the human perception of robot efficiency in a search task to better understand how to design and develop robots that explore alongside human partners. The result is an aerial system that safely accesses regions of interest that may not be immediately viewable or reachable by the human. The approach is evaluated in simulation and with hardware experiments in a motion capture arena. Our findings from the subject study suggest that users’ trust in the robot is highly dependent on mission success. Additionally, participants perceived that they had more control over the robot’s actions when the mission was successful, and the robot as being more in control when the mission failed. The results highlight the importance of designing robust robots with transparent behaviors for successful human-robot collaboration.