Algorithms in combinatorial geometry
Algorithms in combinatorial geometry
Plans and situated actions: the problem of human-machine communication
Plans and situated actions: the problem of human-machine communication
Coordinating Multiple Goals for a Mobile Robot
Intelligent Autonomous Systems, An International Conference
What Are Plans For?
The synthesis of digital machines with provable epistemic properties
TARK '86 Proceedings of the 1986 conference on Theoretical aspects of reasoning about knowledge
Problem-Solving Methods in Artificial Intelligence
Problem-Solving Methods in Artificial Intelligence
Universal plans for reactive robots in unpredictable environments
IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 2
Pengi: an implementation of a theory of activity
AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 1
Intelligent real-time control of robotic vehicles
Communications of the ACM
From bio-inspired vs. psycho-inspired to etho-inspired robots
Robotics and Autonomous Systems
The perception loop in CiceRobot, a museum guide robot
Neurocomputing
Pheromone robotics and the logic of virtual pheromones
SAB'04 Proceedings of the 2004 international conference on Swarm Robotics
| Hi-index | 0.02 |
In the ongoing pursuit to produce intelligent autonomous agents that can operate in real world environments, emerging concepts about the relationships between planning and action are inspiring new alternatives in plan representation. The simple yet elusive concept that plans must serve as resources for action rather than as programs for action has significant ramifications. In this paper we examine methods for compiling world knowledge into forms which serve only to enhance performance, rather than to dictate a specific course of action. We present the notion of internalized plans, which can be thought of as representations that allow the raw results of search in any abstract state space to be made available for direct use within continuous real-time decision-making processes. In the case of map-based plans, we find that by abandoning the notion that a specific path must be defined by a route plan we are free to make direct use of the map data and search results that are normally used to generate route plans. As a result of this simple change in outlook, we can more easily solve problems requiring opportunistic reaction to unexpected changes in the environment.