Difference between revisions of "Assurance for Learning Enabled Systems"

From MurrayWiki
Jump to: navigation, search
 
(7 intermediate revisions by the same user not shown)
Line 10: Line 10:
 
Additional participants:
 
Additional participants:
 
{{project additional participants}}
 
{{project additional participants}}
 +
* Yuxiao Chen (postdoc)
 
|
 
|
 
Collaborators:
 
Collaborators:
 
* Susmit Jha (SRI)
 
* Susmit Jha (SRI)
 +
* Chuchu Fan (MIT)
 
Past participants:
 
Past participants:
 
{{project past participants}}
 
{{project past participants}}
Line 26: Line 28:
 
{{project paper list}}
 
{{project paper list}}
  
[[Category:Pending project]]
+
[[Category:Active projects]]
<!-- [[Category:Subgroup projects]] -->
+
[[Category:NCS projects]]
 
{{Project
 
{{Project
 
|Title=Assurance for Learning Enabled Systems
 
|Title=Assurance for Learning Enabled Systems
 
|Agency=DARPA
 
|Agency=DARPA
|Start date=1 July 2019
+
|Grant number=FA8750-19-C-0089
 +
|Start date=1 September 2019
 
|End date=30 Jun 2021
 
|End date=30 Jun 2021
 
|Support summary=1 postdoc, 0.5 graduate student
 
|Support summary=1 postdoc, 0.5 graduate student
 +
|Reporting requirements=Monthly updates
 +
|Project ID=DARPA ALES
 +
|ack=The project or effort depicted was or is sponsored by the Defense Advanced Research Projects Agency (Agreement FA8750-19-C-0089). The content of the information does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred.
 
}}
 
}}

Latest revision as of 17:36, 10 August 2020

This project will extend previous work in automatic synthesis methods for planning and model-predictive control to address (1) real-time synthesis through efficient and incremental constraint-solving, and (2) risk-awareness by explicitly modeling uncertainty in perception and dynamics modeling. ALES includes a risk-aware planning and real-time synthesis engine to generate plans, protocols and control that are correct-by-construction. We plan to use a special class of stochastic predicates called chance constraints to express confidence in the learned component or its individual outputs. We specify the semantics of the temporal evolution of this logical model based on an underlying learning algorithm.

Current participants:

Additional participants:

  • Yuxiao Chen (postdoc)

Collaborators:

  • Susmit Jha (SRI)
  • Chuchu Fan (MIT)

Past participants:

  • Sumanth Dathathri (Alumni, CMS)
  • Chuchu Fan (Alumni, CMS)

Objectives

Assured-autonomy.png

SRI and Caltech shall develop algorithms for correct-by-construction synthesis from high- level contracts, and planning in presence of uncertainty. Caltech's primary objectives are to support the following milestones:

  • Year 1: Develop algorithms for correct-by-construction synthesis with probabilistic notion of safety
  • Year 2: Extend the approaches to incorporate risk measures such as Conditional Value-at-Risk.

References



The project or effort depicted was or is sponsored by the Defense Advanced Research Projects Agency (Agreement FA8750-19-C-0089). The content of the information does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred.

  • Agency: DARPA
  • Grant number: FA8750-19-C-0089
  • Start date: 1 September 2019
  • End date: 30 Jun 2021
  • Support: 1 postdoc, 0.5 graduate student
  • Reporting: Monthly updates