The Autonomy Research Pilot Initiative (ARPI) seeks to promote the development of innovative, cross-cutting science and technology for autonomous systems able to meet future DOD system and mission requirements. The focus is on those projects with the potential to radically advance capabilities 5, 10 or more years in the future in important warfare areas. Envisioned technology will allow military systems to complete complex military missions in dynamic environments with the right balance of warfighter involvement. The ARPI is a pilot test of an OSD-sponsored
innovation program, directed by ASD (R&E), and executed by the Services, with support from the DOD Priority Steering Council (PSC) for Autonomy.
US Department of Defense Directive
November 21, 2012
SUBJECT: Autonomy in Weapon Systems
1. PURPOSE. This Directive:
a. Establishes DoD policy and assigns responsibilities for the development and use of autonomous and semi-autonomous functions in weapon systems, including manned and unmanned platforms.
b. Establishes guidelines designed to minimize the probability and consequences of failures in autonomous and semi-autonomous weapon systems that could lead to unintended engagements.
The Task Force has concluded that, while currently fielded unmanned systems are making positive contributions across DoD operations, autonomy technology is being underutilized as a result of material obstacles within the Department that are inhibiting the broad acceptance of autonomy and its ability to more fully realize the benefits of unmanned systems.
Key among these obstacles identified by the Task Force are poor design, lack of effective coordination of research and development (R&D) efforts across the Military Services, and operational challenges created by the urgent deployment of unmanned systems to theater without adequate resources or time to refine concepts of operations and training.
To address the issues that are limiting more extensive use of autonomy in DoD systems, the Task Force recommends a crosscutting approach that includes the following key elements:
• The DoD should embrace a three-facet (cognitive echelon, mission timelines and human-machine system trade spaces) autonomous systems framework to assist program managers in shaping technology programs, as well as to assist acquisition officers and developers in making key decisions related to the design and evaluation of future systems.
• The Assistant Secretary of Defense for Research and Engineering (ASD(R&E)) should work with the Military Services to establish a coordinated science and technology (S&T) program guided by feedback from operational experience and evolving mission requirements.
• The Under Secretary of Defense for Acquisition, Technology and Logistics (USD(AT&L)) should create developmental and operational test and evaluation (T&E) techniques that focus on the unique challenges of autonomy (to include developing operational training techniques that explicitly build trust in autonomous
• The Joint Staff and the Military Services should improve the requirements process to develop a mission capability pull for autonomous systems to identify missed opportunities and desirable future system capabilities.
Overall, the Task Force found that unmanned systems are making a significant, positive impact on DoD objectives worldwide. However, the true value of these systems is not to provide a direct human replacement, but rather to extend and complement human capability by providing potentially unlimited persistent capabilities, reducing human exposure to life threatening tasks, and with proper design, reducing the high cognitive load currently placed on
Presentation to 10th International MIW Technology Symposium Moneterey CA, 7 May 2012More
The ENDURANCE autonomous underwater vehicle was developed and deployed to explore and map a unique environment: the waters of Lake Bonney in Taylor Valley, one of the McMurdo Dry Valleys of Antarctica. This permanently ice-covered lake presented several unique challenges and opportunities for exploration and mapping with an AUV. ENDURANCE was successfully deployed in the west lobe of Lake Bonney in the 2008-2009 and 2009-2010 austral summer seasons, completing the rst full synoptic 3-D chemical prole and high-resolution 3-D geometric mapping of such a body of water. ENDURANCE successfully traversed the entire 1 km x 2 km lobe of the lake, including successful automated spooling of a science payload and automated docking into a deployment/recovery melt hole 0.25 m larger in diameter than the vehicle.More
Networks of autonomous robots will someday transform warfare, but significant hurdles remain
Why haven't we seen a fully autonomous robot that can sense for itself, decide for itself, and seamlessly interact with people and other machines? Unmanned systems still fall short in three key areas: sensing, testing, and interoperability. Although the most advanced robots these days may gather data from an expansive array of cameras, microphones, and other sensors, they lack the ability to process all that information in real time and then intelligently act on the results. Likewise, testing poses a problem, because there is no accepted way to subject an autonomous system to every conceivable situation it might encounter in the real world. And interoperability becomes an issue when robots of different types must interact; even more difficult is getting manned and unmanned systems to interact.More
In this paper we describe an integrated goal-oriented control architecture for onboard decision-making for AUVs. Onboard planning and execution is augmented by state estimation of perceived features of interest in the coastal ocean, to drive platform adaptation. The partitioned architecture is a collection of coordinated control loops, with a recurring sense, plan, act cycle and which allows for plan failures to be localized within a control loop and ensures a divide-and-conquer approach to problem solving in dynamic environments.More
Command fusion is a fundamental problem in Robotics and has received considerable attention in the research
community. Several methods have been proposed that have been shown to be effective under certain conditions. This paper presents a novel method of combining multiple low-level behaviors while maintaining the high-level mission. In this approach, charts are created for each domain and the command fuser combines them in a fashion that is responsive to the immediate need (low-level behaviors) while continuing to maintain a high-level view. The
approach has been tested on simulators and the results are presented.
In January of 2003, the Autonomous Undersea Systems Institute (AUSI) joined with Falmouth Scientific, Inc. (FSI) and Technology Systems Inc. (TSI) to develop the second generation Solar powered Autonomous Underwater Vehicle (SAUV) II. The first generation SAUV was developed by AUSI along with the Institute of Marine Technology Problems (IMTP) [Ageev et. al., 2001] and served as a proof of concept for solar re-powering of an AUV.
The SAUV II development effort has been a team based program, where FSI focused on the vehicle hardware and its associated low level subsystem software, TSI focused on the user interface, and AUSI focused on program management and the development of the onboard high level mission/system software. In this manner, a diverse set of talents was brought together to realize the SAUV II design.
This paper will describe what we have named the SAUV “production” architecture, which has evolved during the past two and a half years. It will describe the various software modules and identify the functional components of the system that are controlled by the high level vehicle software. The paper will also describe the insights that resulted from in water testing and the impact that those insights have had on the overall system architecture.More