Abstract
Offline reasoning techniques and online execution
strategies have made planning under uncertainty
more robust. However, the application of plans in
partially-known environments is still a difficult and
important topic. In this paper we describe our work
using Maximum-Margin Multi-Valued Regression
to predict new information about a partially-known
initial state, represented as a multigraph of relations.
We evaluate this approach in a robotics domain,
demonstrating high recall and accuracy, leading
to more robust plans.
strategies have made planning under uncertainty
more robust. However, the application of plans in
partially-known environments is still a difficult and
important topic. In this paper we describe our work
using Maximum-Margin Multi-Valued Regression
to predict new information about a partially-known
initial state, represented as a multigraph of relations.
We evaluate this approach in a robotics domain,
demonstrating high recall and accuracy, leading
to more robust plans.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 31st Workshop of the UK Planning and Scheduling Special Interest Group (PlanSIG 2016) |
| Number of pages | 5 |
| Publication status | Published - 2016 |