Layered T&E for Safety-Critical Autonomous Systems - Revision history

Murray at 20:14, 30 November 2025

2025-11-30T20:14:35Z

← Older revision		Revision as of 20:14, 30 November 2025
Line 9:		Line 9:
	Additional participants:		Additional participants:
	{{project additional participants}}		{{project additional participants}}
	* Max Cohen (MCE)
	\|		\|
	Collaborators:		Collaborators:
Line 16:		Line 15:
	Past participants:		Past participants:
	{{project past participants}}		{{project past participants}}
			* Max Cohen (MCE)
	\|}		\|}

Murray at 22:36, 8 December 2024

2024-12-08T22:36:36Z

← Older revision		Revision as of 22:36, 8 December 2024
Line 1:		Line 1:
	{{righttoc}}		{{righttoc}}
	The overall goal of this project is to develop a layered safety-critical framework for test and evaluation (T&E) with a focus on (semi-) autonomous systems. We leverage the structure of layered architectures to design tests that evaluate the safety-critical nature of next generation systems, specifically the multiple time scales present in modern day systems: the planning layer (minutes), the trajectory generation layer (seconds), and the real-time control layer (milliseconds). We exploit models present at these different levels, and the interactions between the layers, to design tests that evaluate system specifications in a provably safe manner. This will be achieved through the use of safety filters around autonomy features —- including AI driven controllers —- the guarantee safe T&E. Additionally, we exploit the layered layered structure of software for autonomous systems to allow for computationally efficient approaches to T&E that facilitate the integration of data-driven methods in uncertain environments. The methods developed are being deployed experimentally on a wide-variety of robotic systems: from legged robots, to flying robots, to multi-robot systems with legged and flying robots.		The overall goal of this project is to develop a layered safety-critical framework for test and evaluation (T&E) with a focus on (semi-) autonomous systems. We leverage the structure of layered architectures to design tests that evaluate the safety-critical nature of next generation systems, specifically the multiple time scales present in modern day systems: the planning layer (minutes), the trajectory generation layer (seconds), and the real-time control layer (milliseconds). We exploit models present at these different levels, and the interactions between the layers, to design tests that evaluate system specifications in a provably safe manner. This will be achieved through the use of safety filters around autonomy features -- including AI driven controllers -- the guarantee safe T&E. Additionally, we exploit the layered layered structure of software for autonomous systems to allow for computationally efficient approaches to T&E that facilitate the integration of data-driven methods in uncertain environments. The methods developed are being deployed experimentally on a wide-variety of robotic systems: from legged robots, to flying robots, to multi-robot systems with legged and flying robots.

	{\| cellpadding=0 cellspacing=0 width=80%		{\| cellpadding=0 cellspacing=0 width=80%

Murray at 00:48, 13 October 2024

2024-10-13T00:48:25Z

← Older revision		Revision as of 00:48, 13 October 2024
Line 9:		Line 9:
	Additional participants:		Additional participants:
	{{project additional participants}}		{{project additional participants}}
			* Max Cohen (MCE)
	\|		\|
	Collaborators:		Collaborators:

Murray at 22:47, 18 December 2022

2022-12-18T22:47:54Z

← Older revision		Revision as of 22:47, 18 December 2022
Line 1:		Line 1:
	{{righttoc}}		{{righttoc}}
	The overall goal of this project is to develop a layered safety-critical framework for test and evaluation (T&E) with a focus on (semi-) autonomous systems. We leverage the structure of layered architectures to design tests that evaluate the safety-critical nature of next generation systems, specifically the multiple time scales present in modern day systems: the planning layer (minutes), the trajectory generation layer (seconds), and the real-time control layer (milliseconds). We exploit models present at these different levels, and the interactions between the layers, to design tests that evaluate system specifications in a provably safe manner. This will be achieved through the use of safety filters around autonomy ~~features—including~~ AI driven ~~controllers—the~~ guarantee safe T&E. Additionally, we exploit the layered layered structure of software for autonomous systems to allow for computationally ~~effecient approach~~ to T&E that facilitate the integration of data-driven methods in uncertain environments. The methods developed are being deployed experimentally on a wide-variety of robotic systems: from legged robots, to flying robots, to multi-robot systems with legged and flying robots.		The overall goal of this project is to develop a layered safety-critical framework for test and evaluation (T&E) with a focus on (semi-) autonomous systems. We leverage the structure of layered architectures to design tests that evaluate the safety-critical nature of next generation systems, specifically the multiple time scales present in modern day systems: the planning layer (minutes), the trajectory generation layer (seconds), and the real-time control layer (milliseconds). We exploit models present at these different levels, and the interactions between the layers, to design tests that evaluate system specifications in a provably safe manner. This will be achieved through the use of safety filters around autonomy features —- including AI driven controllers —- the guarantee safe T&E. Additionally, we exploit the layered layered structure of software for autonomous systems to allow for computationally efficient approaches to T&E that facilitate the integration of data-driven methods in uncertain environments. The methods developed are being deployed experimentally on a wide-variety of robotic systems: from legged robots, to flying robots, to multi-robot systems with legged and flying robots.

	{\| cellpadding=0 cellspacing=0 width=80%		{\| cellpadding=0 cellspacing=0 width=80%

Murray at 22:46, 18 December 2022

2022-12-18T22:46:02Z

← Older revision		Revision as of 22:46, 18 December 2022
Line 11:		Line 11:
	\|		\|
	Collaborators:		Collaborators:
			{{project collaborators}}

	Past participants:		Past participants:

Murray at 22:45, 18 December 2022

2022-12-18T22:45:29Z

← Older revision		Revision as of 22:45, 18 December 2022
Line 25:		Line 25:
	{{project paper list}}		{{project paper list}}

	[[Category:~~Current project~~]]		[[Category:Active projects]]
	[[Category:NCS projects]]		[[Category:NCS projects]]
	{{Project		{{Project

Murray: /* Objectives */

2022-12-18T22:43:58Z

Objectives

← Older revision		Revision as of 22:43, 18 December 2022
Line 17:		Line 17:

	=== Objectives ===		=== Objectives ===
	[[Image:~~project~~-~~name~~.png\|right\|400px]]		[[Image:afosr-t&e2.png\|right\|400px]]
	My groups goals under this project are focused on the following objectives:		My groups goals under this project are focused on the following objectives:
	* ''Data-driven T&E'': Exploitation of data logging and data-in-the-loop testing in conjunction with the layered architecture to validate simulation- and regression-based elements of the certification process.		* ''Data-driven T&E'': Exploitation of data logging and data-in-the-loop testing in conjunction with the layered architecture to validate simulation- and regression-based elements of the certification process.

Murray at 22:42, 18 December 2022

2022-12-18T22:42:49Z

← Older revision		Revision as of 22:42, 18 December 2022
Line 1:		Line 1:
	{{righttoc}}		{{righttoc}}
	~~Project description~~ (~~typically about~~ a ~~paragraph~~)		The overall goal of this project is to develop a layered safety-critical framework for test and evaluation (T&E) with a focus on (semi-) autonomous systems. We leverage the structure of layered architectures to design tests that evaluate the safety-critical nature of next generation systems, specifically the multiple time scales present in modern day systems: the planning layer (minutes), the trajectory generation layer (seconds), and the real-time control layer (milliseconds). We exploit models present at these different levels, and the interactions between the layers, to design tests that evaluate system specifications in a provably safe manner. This will be achieved through the use of safety filters around autonomy features—including AI driven controllers—the guarantee safe T&E. Additionally, we exploit the layered layered structure of software for autonomous systems to allow for computationally effecient approach to T&E that facilitate the integration of data-driven methods in uncertain environments. The methods developed are being deployed experimentally on a wide-variety of robotic systems: from legged robots, to flying robots, to multi-robot systems with legged and flying robots.

	{\| cellpadding=0 cellspacing=0 width=80%		{\| cellpadding=0 cellspacing=0 width=80%
Line 18:		Line 18:
	=== Objectives ===		=== Objectives ===
	[[Image:project-name.png\|right\|400px]]		[[Image:project-name.png\|right\|400px]]
	~~Description~~ of the ~~main objectives~~ of the ~~project~~		My groups goals under this project are focused on the following objectives:
			* ''Data-driven T&E'': Exploitation of data logging and data-in-the-loop testing in conjunction with the layered architecture to validate simulation- and regression-based elements of the certification process.
			* ''Compositional T&E'': Development of compositional approaches to T&E allowing a smaller number of more comprehensive tests to validate system specifications.

	=== References ===		=== References ===
	{{project paper list}}		{{project paper list}}

	[[Category:Current ~~projects~~]]		[[Category:Current project]]
	[[Category:NCS projects]] ~~-->~~		[[Category:NCS projects]]
	{{Project		{{Project
	\|Title=Layered T&E for Safety-Critical Autonomous Systems		\|Title=Layered T&E for Safety-Critical Autonomous Systems

Murray at 22:37, 18 December 2022

2022-12-18T22:37:05Z

← Older revision		Revision as of 22:37, 18 December 2022
Line 23:		Line 23:
	{{project paper list}}		{{project paper list}}

	[[Category:~~Pending project~~]]		[[Category:Current projects]]
	~~<!--~~ [[Category:~~Subgroup~~ projects]] -->		[[Category:NCS projects]] -->
	{{Project		{{Project
	\|Title=Layered T&E for Safety-Critical Autonomous Systems		\|Title=Layered T&E for Safety-Critical Autonomous Systems

Murray: Created page with "{{subst:project boilerplate}} {{Project |Title=Layered T&E for Safety-Critical Autonomous Systems |Agency=AFOSR |Grant number=FA9550-22-1-0333 |Start date=30 Sep 2022 |End date=29 Sep 2025 |Support summary=1 postdoc, 1-2 graduate students |Reporting requirements=Annual program review + report |Project ID=AFOSR T&E2 |ack=Research supported by the AFOSR Test and Evaluation program, grant FA9550-22-1-0333 }}"

2022-12-18T22:34:20Z

Created page with "{{subst:project boilerplate}} {{Project |Title=Layered T&E for Safety-Critical Autonomous Systems |Agency=AFOSR |Grant number=FA9550-22-1-0333 |Start date=30 Sep 2022 |End date=29 Sep 2025 |Support summary=1 postdoc, 1-2 graduate students |Reporting requirements=Annual program review + report |Project ID=AFOSR T&E2 |ack=Research supported by the AFOSR Test and Evaluation program, grant FA9550-22-1-0333 }}"

New page

{{righttoc}}
Project description (typically about a paragraph)

{| cellpadding=0 cellspacing=0 width=80%
|- valign=top
|
Current participants:
{{project current participants}}
Additional participants:
{{project additional participants}}
|
Collaborators:

Past participants:
{{project past participants}}
|}

=== Objectives ===
[[Image:project-name.png|right|400px]]
Description of the main objectives of the project

=== References ===
{{project paper list}}

[[Category:Pending project]]

{{Project
|Title=Layered T&E for Safety-Critical Autonomous Systems
|Agency=AFOSR
|Grant number=FA9550-22-1-0333
|Start date=30 Sep 2022
|End date=29 Sep 2025
|Support summary=1 postdoc, 1-2 graduate students
|Reporting requirements=Annual program review + report
|Project ID=AFOSR T&E2
|ack=Research supported by the AFOSR Test and Evaluation program, grant FA9550-22-1-0333
}}