Learning and Verification of Safety Parameters for Airspace Deconfliction
| dc.contributor.author | Rebguns, Antons | |
| dc.contributor.author | Green, Derek | |
| dc.contributor.author | Levine, Geoffrey | |
| dc.contributor.author | Kuter, Ugur | |
| dc.contributor.author | Spears, Diana | |
| dc.date.accessioned | 2010-01-29T03:55:33Z | |
| dc.date.available | 2010-01-29T03:55:33Z | |
| dc.date.issued | 2009-11-30 | |
| dc.description.abstract | We present a Bayesian approach to learning flexible safety constraints and subsequently verifying whether plans satisfy these constraints. Our approach, called the Safety Constraint Learner/Checker (SCLC), is embedded within the Generalized Integrated Learning Architecture (GILA), which is an integrated, heterogeneous, multi-agent ensemble architecture designed for learning complex problem solving techniques from demonstration by human experts. The SCLC infers safety constraints from a single expert demonstration trace, and applies these constraints to the solutions proposed by the agents in the ensemble. Blame for constraint violations is then transmitted to the individual learning/planning/reasoning agents, thereby facilitating new problem-solving episodes. We discuss the advantages of the SCLC and demonstrate empirical results on an Airspace Planning and Deconfliction Task, which was a benchmark application in the DARPA Integrated Learning Program. | en_US |
| dc.identifier.uri | http://hdl.handle.net/1903/9803 | |
| dc.language.iso | en_US | en_US |
| dc.relation.ispartofseries | UM Computer Science Department;CS-TR-4951 | |
| dc.relation.ispartofseries | UMIACS;UMIACS-TR-2009-17 | |
| dc.title | Learning and Verification of Safety Parameters for Airspace Deconfliction | en_US |
| dc.type | Technical Report | en_US |