As reported by the MIT News Office (May 26), the idea of recreating simple human actions by robots--an idea that has caught public attention for the past half century--is extremely difficult. Now, however, EECS Professors Leslie Kaelbling and Tomás Lozano-Pérez have reduced this very complex computational challenge using a hierarchical, progressive algorithm, one step at a time.
Leslie Kaelbling, the Panasonic Professor of Computer Science and Engineering, and Tomás Lozano-Pérez, the School of Engineering Professor of Teaching Excellence and co-director of MIT’s Center for Robotics, have outlined their approach in a paper titled "Hierarchical Task and Motion Planning in the Now," which they presented at the IEEE Conference on Robotics and Automation earlier this month in Shanghai.
To break the computationally burdensome goals of spatial navigation and task planning into smaller steps, Kaelbling and Lozano-Pérez have introduced a hierarchy of steps using a detailed plan for only the first few, and leaving the exact mechanisms of subsequent steps for later. "We’re introducing a hierarchy and being aggressive about breaking things up into manageable chunks," Lozano-Pérez says. Though the idea of a hierarchy is not new, the researchers are applying an incremental breakdown to create a timeline for their "in the now" approach, in which robots follow the age-old wisdom of "one step at a time."
MIT News, May 26, 2011 article by Emily Finn: "Honing household helpers. MIT computer scientists work toward improving robots’ ability to plan and perform complex actions, domestically and elsewhere."