Acting optimally in partially observable stochastic domains
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Forward search value iteration for POMDPs
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
A decision-theoretic approach to task assistance for persons with dementia
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Topological order planner for POMDPs
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
| Hi-index | 0.00 |
We are interested in collaboration domains between a robot and a human partner, the partners share a common mission without an explicit communication about their plans. The decision process of the robot agent should consider the presence of its human partner. Also, the robot planning should be flexible to human comfortability and all possible changes in the shared environment. To solve the problem of human-robot collaboration with no communication, we present a model that gives the robot the ability to build a belief over human intentions in order to predict his goals, this model counts mainly on observing the human actions. We integrate this prediction into a Partially Observable Markov Decision Process (POMDP) model to achieve the most appropriate and flexible decisions for the robot.