The Peer-to-Peer Human-Robot Interaction Project
Posted on 23. Apr, 2010 by Daryl in Blog
This research has been very inspirational for me, as the idea for my PhD came from seeing the work done on this project. The idea of viewing robots as peers instead of just tools allows for interesting issues in development and interaction systems. Particularly for Terminator movie-goers, the social context of peer robots would be a controversial idea. While robots as part of a team are not a new idea, the shift towards peer-based work introduces some solutions to autonomous problems in robot systems.
Researchers on this project have approached a complex robotic issue, but have found ways to circumvent traditional problems by utilizing humans as a resource for robots understanding of a problem (Fong et al 2005).
The Peer-to-Peer Human-Robot Interaction (P2P-HRI) project is developing techniques to improve task coordination and collaboration between human and robot partners. Our hypothesis is that peer-to-peer interaction can enable robots to collaborate in a competent, non-disruptive (i.e., natural) manner with users who have limited training, experience, or knowledge of robotics. Specifically, we believe that failures and limitations of autonomy (in planning, in execution, etc.) can be compensated for using human-robot interaction.
(Fong et al 2005)
The most interesting component for this approach is breaking the “master/slave” model for interaction between robots and humans (Fong et al 2005). However, this model presents complex problems in coordinated work including spatial reasoning, balancing autonomous work, and human-level communication (Fong et al 2005). While some of these problems remain the same in autonomous work, a peer to peer system could prevent a robot from reporting failure when it cannot solve an issue autonomously (Fong et al 2005). Instead, the robot can rely upon a human’s expertise or cognitive systems to communicate information or instructions to the robot (Fong et al 2005). Thus, researchers have utilized this social robotic architecture to reduce the complexity of robot systems for impossible or unclear tasks from the robot’s perspective.
Dr. Fong is equally optimistic about the prospects of his research as I am. He believes that these systems are “appropriate whenever humans and intelligent systems must collaborate in order to execute complex tasks” (Fong et al 2005).
Here is a video from NASA regarding the research done for this project.
References