This project, investigating formal languages as a general methodology for task transfer between distinct cyber-physical systems such as humans and robots, aims to expand the science of cyber physical systems by developing Motion Grammars that will enable task transfer between distinct systems.
Formal languages are tools for encoding, describing and transferring structured knowledge. In natural language, the latter process is called communication. Similarly, we will develop a formal language through which arbitrary cyber-physical systems communicate tasks via structured actions. This investigation of Motion Grammars will contribute to the science of human cognition and the engineering of cyber-physical algorithms. By observing human activities during manipulation we will develop a novel class of hybrid control algorithms based on linguistic representations of task execution. These algorithms will broaden the capabilities of man-made systems and provide the infrastructure for motion transfer between humans, robots and broader systems in a generic context. Furthermore, the representation in a rigorous grammatical context will enable formal verification and validation in future work.
Broader Impacts: The proposed research has direct applications to new solutions for manufacturing, medical treatments such as surgery, logistics and food processing. In turn, each of these areas has a significant impact on the efficiency and convenience of our daily lives. The PIs serve as coordinators of graduate/undergraduate programs and mentors to community schools. In order to guarantee that women and minorities have a significant role in the research, the PIs will annually invite K-12 students from Atlanta schools with primarily African American populations to the laboratories. One-day robot classes will be conducted that engage students in the excitement of hands-on science by interactively using lab equipment to transfer their manipulation skills to a robot arm.
The goal of this project has been to design and develop a context-free grammar representation of robot actions. Such a representation can be used to model human actions and transfer them to robots. Furthermore it allows for significant analysis creating guarantees of correctness of robot actions given a specification. Throughout FY13 we have focused on developing a Motion Grammar Kit that includes tools for generating grammars from tasks, verifying them with regard to desired properties such as collision safety. This is accomplished through a hierarchical decomposition of tasks and supervisory control. Intellectual Merit: Our work in FY13 has led to a publication at 4th Workshop on Formal Methods for Robotics and Automation, RSS, 2013 which automatically synthesizes LL* grammars given specifications. Furthermore the core representation has been published in IEEE Transactions on Robotics which not only describes our methods but provides significant theoretical comparisons between the Motion Grammar and existing methods in hybrid control. In a given set of domains described by this publication our approach is shown to have greater expressivity (or ability to handle a broader set of tasks), capacity to prove correctness and demonstration of applications on a 14-degree of freedom robot manipulator. Broader Impacts: Our presentations at international conferences have re-engaged the attention of the entire community to the use of grammar-based control and task transfer for humanoid robots. These include multiple workshop presentations at Robotics Science and Systems and journal publications. We have engaged MS and undergraduate students in the concept of linguistic task representations through invited lectures in the course on planning at Georgia Tech. Arash Rouhani became fascinated with the topic and worked with Neil Dantam to extend our work on the Motion Grammar Kit. The Kit itself is now an open-source BSD project that is publically available: https://github.com/golems/motion-grammar-kit While FY13 is the final year of this project, we are now engaged with researchers from the University of Maryland, Texas A&M and collaborators at Georgia Tech to continue these developments and create a joint formalism for future research.