A deliberative architecture for AUV control

McGann, Conor; Py, Frédéric; Rajan, Kanna; Thomas, Hans; Henthorn, R.; McEwen, R.

doi:10.1109/robot.2008.4543343

Cited by 123 publications

(72 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Including time has allowed some planning systems to perform continuous planning, i.e., continuously synthesize plans as new goals and contingencies become known. Execution monitoring techniques have been developed which leverage the explicit temporal representation of these plans [48][49][50], thus effectively providing a few examples of planning for real robots. Although these constitute important steps towards obtaining planners that are appropriate for robots, they address only partially (i.e., in the temporal dimension) requirements 1 and 2.…”

Section: Planningmentioning

confidence: 99%

Robotic Ubiquitous Cognitive Ecology for Smart Homes

Amato

Bacciu

Broxvall

et al. 2015

J Intell Robot Syst

View full text Add to dashboard Cite

Robotic ecologies are networks of heterogeneous robotic devices pervasively embedded in everyday environments, where they cooperate to perform complex tasks. While their potential makes them increasingly popular, one fundamental problem is how to make them both autonomous and adaptive, so as to reduce the amount of preparation, pre-programming and human supervision that they require in real world applications. The project RUBICON develops learning solutions which yield cheaper, adaptive and efficient coordination of robotic ecologies. The approach we pursue builds upon a unique combination of methods from cognitive robotics, machine learning, planning and agentbased control, and wireless sensor networks. This paper illustrates the innovations advanced by RUBICON in each of these fronts before describing how the resulting techniques have been integrated and applied to a smart home scenario. The resulting system is able to provide useful services and pro-actively assist the users in their activities. RUBICON learns through an incremental and progressive approach driven by the feedback received from its own activities and from the user, while also self-organizing the manner in which it uses available sensors, actuators and other functional components in the process. This paper summarises some of the lessons learned by adopting such an approach and outlines promising directions for future work.

show abstract

Section: Planningmentioning

confidence: 99%

Robotic Ubiquitous Cognitive Ecology for Smart Homes

Amato

Bacciu

Broxvall

et al. 2015

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…Some well known frameworks are: MOOSIvP [16], TREX [17], ORCA [18], and ROS [19]. The predominantly implemented frameworks are T-REX and the MOOS-IvP.…”

Section: Review Of Mission Adaptive Systemsmentioning

confidence: 99%

The Role of adaptive mission planning and control in persistent autonomous underwater vehicles presence

Brito

Bose

Lewis

et al. 2012

2012 IEEE/OES Autonomous Underwater Vehicles (AUV)

View full text Add to dashboard Cite

Abstract-The Autonomous Underwater Vehicle (AUV) community has for many years recognized the potential benefits made by adapting mission planning on-the-fly. Over the years there has been some degree of success in applying adaptive mission planning to very specific problems. Examples of applications include capabilities for a vehicle to search for, and then modify its trajectory to follow, a feature such as a plume or a thermocline, or to modify its trajectory to avoid an obstacle, or to find and follow a feature such as a pipeline. Despite an evident increase in the number of applications, the use of adaptive mission planning is still in its infancy. There is no doubt that adaptive mission planning will play a pivotal role in future AUV persistent presence. So what is delaying this technology from making the leap towards wider industry acceptance? This paper reviews the literature in adaptive mission planning and uses a failure analysis technique to identify key obstacles for the integration of this technique in wider AUV applications. We use our failure analysis to help devise recommendations for mitigating these obstacles. The complexity of the mathematical approaches used by adaptive techniques is one key obstacle. Perhaps of more importance is that the AUV community is increasingly requiring quantitative assessment of risk associated with the use of AUVs. We propose that probability is the appropriate measure for quantifying the risk of adaptive systems and their uncertainty. The work here presented is a collective endeavor of the Engineering Committee on Oceanic Resources Specialist Panel on Underwater Vehicles.

show abstract

“…However, in the case where more than one response is received, the Captain agent identifies one of the BD agents as the mission point generator according to a specific preference. This preference can be determined by simple priority look-up table (adopted in this paper) or more sophisticated approaches like the market-based approach [10] and automated planning approach like T-REX [11]. Once selected, the assigned BD agent is notified with an agreement and contracted as the mission point generator.…”

Section: Backseat Driver Design Paradigmmentioning

confidence: 99%

Hierarchical multi-agent command and control system for autonomous underwater vehicles

Teck

2012

2012 IEEE/OES Autonomous Underwater Vehicles (AUV)

View full text Add to dashboard Cite

Abstract-Inspired by the command structure of a manned submarine, we have developed a Command and Control (C2) system for autonomous underwater vehicles (AUVs) that allocates mission, navigation and vehicle tasks to individual self-contained agents, each with their own responsibilities and behaviors. These agents are distributed over different levels of control hierarchies where they behave deliberately at the supervisory level and reactively at the vehicle and navigational level. The collective interactions among the pool of agents enables the AUV to achieve its mission objectives autonomously.The mission supervisory level adopts a backseat driver paradigm where mission-level decisions are made based on the inputs provided by a pool of backseat driver (BD) agents. Each BD agent is responsible for handling different aspects of a mission and provides input in the form of mission points to achieve specific mission sub-tasks. This approach offers several advantages. Firstly, complex mission objectives can be divided into simpler mission sub-tasks and handled by different BD agents. Secondly, the C2 system's capabilities in coping with new mission scenarios can be easily extended through the introduction of new BD agents that generates the required maneuvering patterns. New mission behaviors may emerge from the cooperation and/or competition among the BD agents. These complex behaviors increase the level of mission autonomy.The C2 system described above is being used in the STARFISH AUVs and has been used to perform single AUV surveying missions as well as multi-AUV cooperative positioning missions.

show abstract

A deliberative architecture for AUV control

Cited by 123 publications

References 11 publications

Robotic Ubiquitous Cognitive Ecology for Smart Homes

Robotic Ubiquitous Cognitive Ecology for Smart Homes

The Role of adaptive mission planning and control in persistent autonomous underwater vehicles presence

Hierarchical multi-agent command and control system for autonomous underwater vehicles

Contact Info

Product

Resources

About