Dynamic Behavior Sequencing for Hybrid Robot Architectures |
| |
Authors: | Gilbert L Peterson Jeffrey P Duffy Daylond J Hooper |
| |
Affiliation: | (1) Honeywell International, Phoenix, USA;(2) University of Florida, Gainesville, USA; |
| |
Abstract: | Hybrid robot control architectures separate planning, coordination, and sensing and acting into separate processing layers
to provide autonomous robots both deliberative and reactive functionality. This approach results in systems that perform well
in goal-oriented and dynamic environments. Often, the interfaces and intents of each functional layer are tightly coupled
and hand coded so any system change requires several changes in the other layers. This work presents the dynamic behavior
hierarchy generation (DBHG) algorithm, which uses an abstract behavior representation to automatically build a behavior hierarchy
for meeting a task goal. The generation of the behavior hierarchy occurs without knowledge of the low-level implementation
or the high-level goals the behaviors achieve. The algorithm’s ability to automate the behavior hierarchy generation is demonstrated
on a robot task of target search, identification, and extraction. An additional simulated experiment in which deliberation
identifies which sensors to use to conserve power shows that no system modification or predefined task structures is required
for the DBHG to dynamically build different behavior hierarchies. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|