(Georgia Institute of Technology, 2005)
Likhachev, Maxim; Kaess, Michael; Kira, Zsolt; Arkin, Ronald C.
This paper presents an approach to automatic selection and
modification of behavioral assemblage parameters for
autonomous navigation tasks. The goal of this research is to make
obsolete the task of manual configuration of behavioral
parameters, which often requires significant knowledge of robot
behavior and extensive experimentation, and to increase the
efficiency of robot navigation by automatically choosing and fine-tuning
the parameters that fit the robot task-environment well in
real-time. The method is based on the Case-Based Reasoning
paradigm. Derived from incoming sensor data, this approach
computes spatial features of the environment. Based on the robot’s
performance, temporal features of the environment are then
computed. Both sets of features are then used to select and fine-tune
a set of parameters for an active behavioral assemblage. By
continuously monitoring the sensor data and performance of the
robot, the method reselects these parameters as necessary. While
a mapping from environmental features onto behavioral
parameters, i.e., the cases, can be hard-coded, a method for
learning new and optimizing existing cases is also presented. This
completely automates the process of behavioral parameterization.
The system was integrated within a hybrid robot architecture and
extensively evaluated using simulations and indoor and outdoor
real world robotic experiments in multiple environments and
sensor modalities, clearly demonstrating the benefits of the
approach.