A significant challenge of autonomous robotics lies in the area of motion planning. The overall objective is to enable robots to automatically plan the low-level motions needed to accomplish assigned high-level tasks. Toward this goal, I developed a novel multi-layered approach, termed Synergic Combination of Layers of Planning (SyCLoP), that synergically combines high-level discrete planning and low-level motion planning. High-level discrete planning, which draws from research in AI and logic, guides low-level motion planning during the search for a solution. A distinctive feature of SyCLOP is that the planning layers work in tandem to evaluate the feasibility of current plans and to compute increasingly feasible plans in future iterations. This synergic combination of high-level discrete planning and low-level motion planning allows SyCLoP to solve motion-planning problems with respect to rich models of the robot and the physical world. This facilitates the design of feedback controllers that enable the robot to execute in the physical world solutions obtained in simulation. In particular, SyCLoP effectively solves challenging motion-planning problems that incorporate discrete and continuous dynamics and physics-based simulations. In addition, SyCLoP can take into account high-level tasks specified using the expressiveness of linear temporal logic (LTL). LTL allows for complex specifications, such as sequencing, coverage, and other combinations of temporal objectives. Experiments show that SyCLoP obtains significant computational speedup of one to two orders of magnitude when compared to state-of-the-art motion planners.
Speaker Biography
Erion Plaku is a postdoctoral fellow in the Laboratory for Computational Sensing and Robotics at Johns Hopkins University. Erion received his Ph.D. in Computer Science from Rice University, Houston, TX in 2008. His research interests encompass robotics, motion planning, data mining, hybrid-system verification, and distributed computing.