Challenges for Temporal Planning with Uncertain Durations

We investigate the problem of temporal planning with concurrent actions having stochastic durations, especially in the context of extended-state-space based planners. The problem is challenging because stochastic durations lead to an explosion in the space of possible decision-epochs, which exacerbates the familiar challenge of growth in executable action combinations caused by concurrency. We present various observations and insights into different variations of this problem that form the basis of our future research.

• Type: Conference
• Year: 2006
• Where: AIPS
• Authors: Mausam, Daniel S. Weld
• Keywords: AIPS 2006, Artificial Intelligence, Executable Action Combinations, Extended-state-space Based Planners, Stochastic Durations