Hierarchical and State-based Architectures for Robot Behavior Planning and Control

TL;DR

This paper introduces two distinct behavior control architectures, one state-based and one behavior-based, implemented as cross-platform C++ frameworks for autonomous robot control, demonstrated on a humanoid soccer robot.

Contribution

The paper presents two new, independently implemented frameworks for robot behavior control that can be used together for complex autonomous agent management.

Findings

Frameworks successfully control humanoid soccer robot

Both frameworks are versatile and can be combined for multi-level behavior management

Demonstrated effectiveness in real-world robot applications

Abstract

In this paper, two behavior control architectures for autonomous agents in the form of cross-platform C++ frameworks are presented, the State Controller Library and the Behavior Control Framework. While the former is state-based and generalizes the notion of states and finite state machines to allow for multi-action planning, the latter is behavior-based and exploits a hierarchical structure and the concept of inhibitions to allow for dynamic transitioning. The two frameworks have completely independent implementations, but can be used effectively in tandem to solve behavior control problems on all levels of granularity. Both frameworks have been used to control the NimbRo-OP, a humanoid soccer robot developed by team NimbRo of the University of Bonn.