Intelligence without representation
Artificial Intelligence
Artificial Intelligence
Specialization of perceptual processes
Specialization of perceptual processes
Adaptive action selection for cooperative agent teams
Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
Analysis of adaptation and environment
Artificial Intelligence - Special volume on computational research on interaction and agency, part 2
A layered architecture for office delivery robots
AGENTS '97 Proceedings of the first international conference on Autonomous agents
High-level planning and low-level execution: towards a complete robotic agent
AGENTS '97 Proceedings of the first international conference on Autonomous agents
Computer and Robot Vision
Direct Methods for Self-Calibration of a Moving Stereo Head
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
The Behavior Language: User''s Guide
The Behavior Language: User''s Guide
A Colony Architecture for an Artificial Creature
A Colony Architecture for an Artificial Creature
| Hi-index | 0.00 |
In this paper we present a complete control architecture for amobile robot which enables it to achieve a set of proposed goals with a highdegree of autonomy and to react to the changing environment in realtime. Autonomy and robustness are achieved through careful selectionand incremental implementation of a set of basic Motor-Behaviors thatinterpret the sensor readings (sonar, vision and odometric sensors)and actuate the motors. The plan is provided by a user, and isexpressed as a sequence of goals and a series of hints on how toachieve them. These hints are based on the user‘s knowledge of theenvironment and of the robot‘s behavioral and perceptual abilities. Anew set of behaviors, called Conductor-Behaviors, which inspect andmodify Motor-Behaviors‘ attributes, have been introduced in order tolink the robot‘s Motor-Behaviors to the user‘s plan. Finally, acanonical set of symbols, attached to the Motor-Behaviors, serves aswell grounded symbols that the user can utilize to express theplans. We also report experimental results with a real robot thatdemonstrate how plans expressed as goals and hints to achieve themimprove the robot‘s performance.