Plan guided reaction

Abstract

We present a set of architectural concepts which address the needs for integrating high-level planning activities with lower-level reactive or participatory behaviors. Based on lessons learned from our experience with a hierarchical architecture for autonomous crosscountry navigation, we have come to recognize various pitfalls that may arise from the misuse of abstraction. Consequently, we have adopted a new approach which emphasizes the minimization of information loss both within and between system layers. This change in perspective has allowed us to greatly enhance the overall capabilities and performance of our system. I.

Neuroevolution of Agents Capable of Reactive and Deliberative Behaviours in Novel and Dynamic Environments

“…Unlike more traditional search based models, gradient fields can be generated efficiently, and do not suffer from the same local-minima problems as other wave based mechanisms such as potential fields [4]. However, the gradient fields approach does not deal well with changing environments and so is often coupled with a Brooks inspired [5] subsumption architecture [3]. Another issue with gradient fields is that they have to be laboriously constructed.…”

“…Payton [3] used gradient fields to represent the state-space of a problem and as an internalised plan. Unlike more traditional search based models, gradient fields can be generated efficiently, and do not suffer from the same local-minima problems as other wave based mechanisms such as potential fields [4].…”

Internalized plans for communication-sensitive robot team behaviors

“…As discussed by Payton [14], internalized plans offer an advantage in that several plans can be utilized simultaneously. We incorporate multiple plans in two ways: in parallel and in serial.…”

“…Payton also delineates a method for using information in a reactive architecture [14]. In this method, a priori knowledge becomes an enabling resource for decisionmaking.…”

An integrated system for autonomous off-road navigation

“…Detailed descriptions of its components may be found in [7] for the local map module, [12] for the planning component, and in [8] for the complete system description.…”