Declarative goals in reactive plans
Proceedings of the first international conference on Artificial intelligence planning systems
High-level planning and low-level execution: towards a complete robotic agent
AGENTS '97 Proceedings of the first international conference on Autonomous agents
Using regression-match graphs to control search in planning
Artificial Intelligence
Some contributions to the metatheory of the situation calculus
Journal of the ACM (JACM)
Reasoning about noisy sensors and effectors in the situation calculus
Artificial Intelligence
Experiences with an interactive museum tour-guide robot
Artificial Intelligence - Special issue on applications of artificial intelligence
Cognitive modeling for games and animation
Communications of the ACM
Knowlege in action: logical foundations for specifying and implementing dynamical systems
Knowlege in action: logical foundations for specifying and implementing dynamical systems
Artificial Intelligence: A New Synthesis
Artificial Intelligence: A New Synthesis
Introduction to Robotics: Mechanics and Control
Introduction to Robotics: Mechanics and Control
cc-Golog: Towards More Realistic Logic-Based Robot Controllers
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
The focussed D* algorithm for real-time replanning
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
The domestic robot—a friendly cognitive system takes care of your home
Ambient intelligence
Combining probabilities, failures and safety in robot control
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Hi-index | 0.00 |
We present a control system for autonomous mobile manipulators based on a theory of actions integrated with a theory of perception and failures. The system applies to autonomous manipulators built for simple missions like building towers of blocks, collecting balls of paper and putting them into a bin, or clearing obstacles from a path. For these application domains we have built three autonomous agents: ArmHand0, ArmHandONE and A.R.R.I.G.O. The core of the system is a high level program controlling the on-line agent behaviour: while a goal is not achieved, it selects a task from a library of possible subplans and executes it. The task, when correctly chosen, must lead to a subgoal position. At the end of each task execution, visual perception is used to monitor the coherence between the configuration of the domain and the configuration entailed as a consequence of the execution of the task. In case of a misalignment between the predicted state and the perceived one, a diagnostic procedure is activated.