GPS, a program that simulates human thought
Computers & thought
Robotics in Practice: Management and Applications of Robotics in Industry
Robotics in Practice: Management and Applications of Robotics in Industry
Real-time navigating crowds: scalable simulation and rendering: Research Articles
Computer Animation and Virtual Worlds - CASA 2006
Robots, Reasoning, and Reification
Robots, Reasoning, and Reification
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 1
Some studies in machine learning using the game of checkers
IBM Journal of Research and Development
| Hi-index | 0.00 |
A significant problem that has plagued autonomous mobile robots is the need to reason about a complex and dynamic world in a timely fashion. Huge strides have been made in artificial intelligence systems that deal with symbolic representations, and the hardware for robotics has seen significant growth. However, autonomous robots have not seen equivalent improvement. In this paper we examine a technique to couple deliberative reasoning systems with mobile robotic platforms to enable the robot to reason about the world. Mobile autonomous robots operate under extremely tight constraints in power and computational loads, and must be responsive to the dynamic environments in which they are deployed. Since they do not have the luxury of operating in a static, controlled environment, they must be capable of quickly recognizing changes to the environment, assessing the impacts of these changes, and implementing intelligent responses to those changes. All of these requirements must be met in a real-time environment, using limited computational resources. Since living organisms also operate under these same constraints we present a design that is biologically principled. This design integrates both reactive and deliberative components using a biologically principled component called a Reification Engine. The Reification Engine acts as a bi-directional bridge between the sensor domain and the symbolic domain. It provides the ability to map the changes detected by the sensors into a symbolic representation, which is expanded by the onboard ontology to generate a semantic representation of the salient aspects of problem. This, in turn, can be analyzed by a deliberative system to generate a planned response to the changes, which can be mapped by the Reification Engine back into the sensor/effector space of the robot's hardware.