Venkatesh Guru Rao

Two Approaches to Dynamic Refinement in Hierarchical Motion Planning

A common technique in robotic motion planning is to progressively refine trajectories using a hierarchical planner comprising several iteratively coupled layers. This paper presents two dynamic refinement techniques that transform the polygonal path computed by a geometric planning layer into a feasible trajectory for a specific vehicle by fitting suitable geometric primitives. This work advances the state of the art in dynamic refinement in two ways. First, we generalize the popular circular-arc-primitive methods for car-like vehicles to achieve aggressive maneuvering and higher speeds. Second, we present a preliminary analysis of minimum-time primitives for omni-directional vehicles. Results of extensive simulation experiments are presented, to demonstrate the performance characteristics of the two methods.

Patch Models and Their Applications to Multivehicle Command and Control

We introduce patch models, a computational modeling formalism for multivehicle combat domains, based on spatiotemporal abstraction methods developed in the computer science community. The framework yields models that are expressive enough to accommodate nontrivial controlled vehicle dynamics while being within the representational capabilities of common artificial intelligence techniques used in the construction of autonomous systems. The framework allows several key design requirements of next-generation network-centric command and control systems, such as maintenance of shared situation awareness, to be achieved. Major features include support for multiple situation models at each decision node and rapid mission plan adaptation. We describe the formal specification of patch models and our prototype implementation, i.e., Patchworks. The capabilities of patch models are validated through a combat mission simulation in Patchworks, which involves two defending teams protecting a camp from an enemy attacking team