Arjuna Balasuriya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Arjuna Balasuriya has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Henrik Schmidt
Department of Anesthesiology and Intensive Care, Odense University Hospital , Odense
5 shared publications Michael B. Benjamin
MIT, 77 Mass Ave, 5-204, Cambridge, MA 02139, USA
2 shared publications- Subhash Challa
Faculty of Engineering, University of Technology, Sydney, NSW, Australia
2 shared publications - Zhen Jia
United Technologies Research Center, No. 3239, Shenjiang Road, Shanghai 201206, P.R. China
2 shared publications - Bharath Kalyan
School of Electrical and Electronic Engg., Nanyang Technological University, Singapore 639798
1 shared publication - David Battle
Dept. of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge MA 02139
1 shared publication
Latest Publications
- 30 September 2012
- Published by Defense Technical Information Center (DTIC)
Multistatic, Concurrent Detection, Classification and Localization Concepts for Autonomous, Shallow Water Mine Counter Measures
The objective of SWAMSI is the development and demonstration of robust multi-static detection and classification of proud- and buried seabed objects using cooperative networks of autonomous vehicles with acoustic sources and receiving arrays. The emphasis of the MIT SWAMSI effort has focused on utilizing high fidelity acoustic modeling of both scatterers and shallow-water environments to better understand and bound the limits of detectability for mine-like objects via autonomous networks of sensors, and the assess the performance of time-reversal processing for concurrent detection, classification, localization and Tracking (DCLT) of seabed objects. The analysis s supported by series of experiments using multiple sonar-equipped AUVs in shallow water and then cross-validate the results obtained with high precision modeling and visualization. Another, related objective is to better understand the problems of cooperative autonomous vehicle interaction to define the base-line infrastructure requirements for cooperative detection, classification and navigation, an understanding which may lead to guidelines for optimal collaborative configuration control of the underwater sonar platforms.
- 30 September 2012
- Published by Defense Technical Information Center (DTIC)
Multistatic, Concurrent Detection, Classification and Localization Concepts for Autonomous, Shallow Water Mine Counter Measures
The objective of SWAMSI is the development and demonstration of robust multi-static detection and classification of proud- and buried seabed objects using cooperative networks of autonomous vehicles with acoustic sources and receiving arrays. The emphasis of the MIT SWAMSI effort has focused on utilizing high fidelity acoustic modeling of both scatterers and shallow-water environments to better understand and bound the limits of detectability for mine-like objects via autonomous networks of sensors, and the assess the performance of time-reversal processing for concurrent detection, classification, localization and Tracking (DCLT) of seabed objects. The analysis s supported by series of experiments using multiple sonar-equipped AUVs in shallow water and then cross-validate the results obtained with high precision modeling and visualization. Another, related objective is to better understand the problems of cooperative autonomous vehicle interaction to define the base-line infrastructure requirements for cooperative detection, classification and navigation, an understanding which may lead to guidelines for optimal collaborative configuration control of the underwater sonar platforms.
- 16 January 2009
- Published by Bentham Science Publishers Ltd. in Recent Patents on Computer Science
- Vol. 2 (1) , 32-42
Vision Based Target Tracking for Autonomous Land Vehicle Navigation: A Brief Survey
- 16 January 2009
- Published by Bentham Science Publishers Ltd. in Recent Patents on Computer Science
- Vol. 2 (1) , 32-42
Vision Based Target Tracking for Autonomous Land Vehicle Navigation: A Brief Survey
- Open Access
- 15 December 2008
- Published by MDPI AG in Algorithms
- Vol. 1 (2) , 153-182
Autonomous Vehicles Navigation with Visual Target Tracking: Technical Approaches
This paper surveys the developments of last 10 years in the area of vision based target tracking for autonomous vehicles navigation. First, the motivations and applications of using vision based target tracking for autonomous vehicles navigation are presented in the introduction section. It can be concluded that it is very necessary to develop robust visual target tracking based navigation algorithms for the broad applications of autonomous vehicles. Then this paper reviews the recent techniques in three different categories: vision based target tracking for the applications of land, underwater and aerial vehicles navigation. Next, the increasing trends of using data fusion for visual target tracking based autonomous vehicles navigation are discussed. Through data fusion the tracking performance is improved and becomes more robust. Based on the review, the remaining research challenges are summarized and future research directions are investigated.
- 15 December 2008
- Published by MDPI AG in Algorithms
- Vol. 1 (2) , 153-182
Open AccessAutonomous Vehicles Navigation with Visual Target Tracking: Technical Approaches
This paper surveys the developments of last 10 years in the area of vision based target tracking for autonomous vehicles navigation. First, the motivations and applications of using vision based target tracking for autonomous vehicles navigation are presented in the introduction section. It can be concluded that it is very necessary to develop robust visual target tracking based navigation algorithms for the broad applications of autonomous vehicles. Then this paper reviews the recent techniques in three different categories: vision based target tracking for the applications of land, underwater and aerial vehicles navigation. Next, the increasing trends of using data fusion for visual target tracking based autonomous vehicles navigation are discussed. Through data fusion the tracking performance is improved and becomes more robust. Based on the review, the remaining research challenges are summarized and future research directions are investigated.
- 1 May 2008
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 123 (5_Suppleme) , 3905
Nested Autonomy - Adaptive and collaborative sensing with hybrid sensing networks
Control of undersea sensing networks is restricted by the limited acoustic communication capacity and the need for surfacing “data‐mules” for communicating with the operators. Adaptive sampling of episodic events must therefore be performed fully autonomously. Similarly, collaboration between nodes is limited by the communication horizon. These constraints favor the use of a nested operational paradigm, with clusters of highly autonomous nodes capable of detecting, classifying, and localizing episodic events, if possible collaborating with neighboring nodes without operator intervention. Such a Nested Autonomy operational paradigm is being developed for capturing episodic oceanographic events by AUVs and gliders in the NSF ORION ocean observatory. Based on the portable, open‐source MOOS‐IvP autonomous control framework, the same paradigm is being applied for distributed acoustic surveillance networks in the ONR PLUSNet program. In either case the nested autonomy enables the autononomous exploitation of the environmental and tactical situation, and collaborative tracking of targets or oceanographic events. The operator control is limited to very simple deploy and prosecute commands. The performance of the nested autonomy paradigm is demonstrated by examples using a high‐fidelity simulation environment, and by results from recent field experiments. [Work supported by ONR.]
- 1 May 2008
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 123 (5_Suppleme) , 3905
Nested Autonomy - Adaptive and collaborative sensing with hybrid sensing networks
Control of undersea sensing networks is restricted by the limited acoustic communication capacity and the need for surfacing “data‐mules” for communicating with the operators. Adaptive sampling of episodic events must therefore be performed fully autonomously. Similarly, collaboration between nodes is limited by the communication horizon. These constraints favor the use of a nested operational paradigm, with clusters of highly autonomous nodes capable of detecting, classifying, and localizing episodic events, if possible collaborating with neighboring nodes without operator intervention. Such a Nested Autonomy operational paradigm is being developed for capturing episodic oceanographic events by AUVs and gliders in the NSF ORION ocean observatory. Based on the portable, open‐source MOOS‐IvP autonomous control framework, the same paradigm is being applied for distributed acoustic surveillance networks in the ONR PLUSNet program. In either case the nested autonomy enables the autononomous exploitation of the environmental and tactical situation, and collaborative tracking of targets or oceanographic events. The operator control is limited to very simple deploy and prosecute commands. The performance of the nested autonomy paradigm is demonstrated by examples using a high‐fidelity simulation environment, and by results from recent field experiments. [Work supported by ONR.]
- 1 May 2008
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 123 (5_Suppleme) , 3007
Integrated sensing, modeling, and control in undersea sensor networks
The way forward in adaptively sampling the vast ocean environment is by deploying a network of sensors with different capabilities. Due to the complex nature of the environment, covering such an area cannot be achieved by simply deploying underwater sensor nodes at predefined locations. The undersea network topology should dynamically adapt to the events and changes in the environment. However, the main challenge for undersea network autonomy is due to the limitations in underwater acoustic communication. In order to overcome such limitations, Nested Autonomy architecture is being developed and demonstrated in programs such as PLUSNet and Ocean Observatories. This paper looks into the implementation of such autonomy architecture in different sensor nodes with different capabilities. This is achieved by separating the "low‐level" tasks of a sensor node with its "high‐level" tasks. Low‐level tasks will be sensor specific while the high‐level tasks looks into the autonomy required for the adaptive sampling applications, which here refers to as the "Backseat‐driver paradigm". The "backseat" carries the on‐board intelligence required for the mission at hand. Behavior‐based autonomy architecture which is used in the back‐seat significantly improves the sensor performance by selecting the best behavior for the given state of the vehicle, mission at hand and the observations being made.
- 1 May 2008
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 123 (5_Suppleme) , 3007
Integrated sensing, modeling, and control in undersea sensor networks
The way forward in adaptively sampling the vast ocean environment is by deploying a network of sensors with different capabilities. Due to the complex nature of the environment, covering such an area cannot be achieved by simply deploying underwater sensor nodes at predefined locations. The undersea network topology should dynamically adapt to the events and changes in the environment. However, the main challenge for undersea network autonomy is due to the limitations in underwater acoustic communication. In order to overcome such limitations, Nested Autonomy architecture is being developed and demonstrated in programs such as PLUSNet and Ocean Observatories. This paper looks into the implementation of such autonomy architecture in different sensor nodes with different capabilities. This is achieved by separating the "low‐level" tasks of a sensor node with its "high‐level" tasks. Low‐level tasks will be sensor specific while the high‐level tasks looks into the autonomy required for the adaptive sampling applications, which here refers to as the "Backseat‐driver paradigm". The "backseat" carries the on‐board intelligence required for the mission at hand. Behavior‐based autonomy architecture which is used in the back‐seat significantly improves the sensor performance by selecting the best behavior for the given state of the vehicle, mission at hand and the observations being made.
- 1 April 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Nested Distributed Autonomy Architecture for Undersea Sensor Networks
Underwater surveillance is experiencing a paradigm shift from platform-centric to distributed networks of autonomous underwater vehicles (AUVs). In order to achieve the performance goals with smaller apertures carried by single platforms, new concepts of operations must be developed, which exploit platform mobility to adapt to the changing environmental conditions. Unlike the network of sensor nodes used in air/land, underwater networks cannot rely on the low channel capacity of the acoustic communication available. The operation of such an underwater sensor network requires a much higher level of autonomous, distributed command and control architecture. This paper discusses the proposed nested autonomy architecture developed at MIT for command and control of AUVs.
- 1 April 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Nested Distributed Autonomy Architecture for Undersea Sensor Networks
Underwater surveillance is experiencing a paradigm shift from platform-centric to distributed networks of autonomous underwater vehicles (AUVs). In order to achieve the performance goals with smaller apertures carried by single platforms, new concepts of operations must be developed, which exploit platform mobility to adapt to the changing environmental conditions. Unlike the network of sensor nodes used in air/land, underwater networks cannot rely on the low channel capacity of the acoustic communication available. The operation of such an underwater sensor network requires a much higher level of autonomous, distributed command and control architecture. This paper discusses the proposed nested autonomy architecture developed at MIT for command and control of AUVs.
- 1 November 2007
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 122 (5_Suppleme) , 2998
Nested autonomy—A paradigm for distributed, undersea acoustic sensing and surveillance
Undersea surveillance networks using acoustic communication between nodes are severely bandwidth‐limited. Equally critical, operational constraints often require a gateway vehicle to surface and quickly relay messages to and from the operator, with typical latencies of 10–30 min. Therefore, in contrast to above‐sea systems, the data processing and control of the underwater assets cannot be performed centrally but must be distributed, and the individual and clusters of assets must be capable of autonomously exploiting the environmental acoustics and completing the mission objectives, such as detecting, classifying, localizing, and tracking (DCLT) of a target. The resulting target solution must be assembled in a track report, which must be transmitted back to the operators within the constraint of the communication system. Constrained by small individual acoustic apertures, the net‐centric systems may exploit adaptive and collaborative sensing and control for enhancing system performance. Under the ONR PLUSNet program, a nested, autonomous command and control architecture is being developed, with fully integrated sensing, modeling, and control within each autonomous node and clusters of nodes. It enables autonomous adaptation to the environmental and tactical situation, and collaborative target tracking by multiple platforms. The operator controls the autonomous mission behaviors by very simple commands tailored to the limited communication bandwidth. The performance of the nested autonomy paradigm will be demonstrated by examples using a high‐fidelity simulation environment, and by results from the PN07 field experiment. [Work supported by ONR.]
- 1 November 2007
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 122 (5_Suppleme) , 2998
Nested autonomy—A paradigm for distributed, undersea acoustic sensing and surveillance
Undersea surveillance networks using acoustic communication between nodes are severely bandwidth‐limited. Equally critical, operational constraints often require a gateway vehicle to surface and quickly relay messages to and from the operator, with typical latencies of 10–30 min. Therefore, in contrast to above‐sea systems, the data processing and control of the underwater assets cannot be performed centrally but must be distributed, and the individual and clusters of assets must be capable of autonomously exploiting the environmental acoustics and completing the mission objectives, such as detecting, classifying, localizing, and tracking (DCLT) of a target. The resulting target solution must be assembled in a track report, which must be transmitted back to the operators within the constraint of the communication system. Constrained by small individual acoustic apertures, the net‐centric systems may exploit adaptive and collaborative sensing and control for enhancing system performance. Under the ONR PLUSNet program, a nested, autonomous command and control architecture is being developed, with fully integrated sensing, modeling, and control within each autonomous node and clusters of nodes. It enables autonomous adaptation to the environmental and tactical situation, and collaborative target tracking by multiple platforms. The operator controls the autonomous mission behaviors by very simple commands tailored to the limited communication bandwidth. The performance of the nested autonomy paradigm will be demonstrated by examples using a high‐fidelity simulation environment, and by results from the PN07 field experiment. [Work supported by ONR.]
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 4562-4569
Autonomous Control of an Autonomous Underwater Vehicle Towing a Vector Sensor Array
This paper is about the autonomous control of an autonomous underwater vehicle (AUV), and the particular considerations required to allow proper control while towing a 100-meter vector sensor array. Mission related objectives are tempered by the need to consider the effect of a sequence of maneuvers on the motion of the towed array which is thought not to tolerate sharp bends or twists in sensitive material. We describe and motivate an architecture for autonomy structured on the behavior-based control model augmented with a novel approach for performing behavior coordination using multi-objective optimization. We provide detailed in-field experimental results from recent exercises with two 21-inch AUVs in Monterey Bay California.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 4562-4569
Autonomous Control of an Autonomous Underwater Vehicle Towing a Vector Sensor Array
This paper is about the autonomous control of an autonomous underwater vehicle (AUV), and the particular considerations required to allow proper control while towing a 100-meter vector sensor array. Mission related objectives are tempered by the need to consider the effect of a sequence of maneuvers on the motion of the towed array which is thought not to tolerate sharp bends or twists in sensitive material. We describe and motivate an architecture for autonomy structured on the behavior-based control model augmented with a novel approach for performing behavior coordination using multi-objective optimization. We provide detailed in-field experimental results from recent exercises with two 21-inch AUVs in Monterey Bay California.
- 1 May 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 39, 1-5
Multiple target tracking in Underwater Sonar Images using Particle-PHD filter
A multiple feature tracking algorithm for Sector Scan Sonar images is presented. The underlying framework that is employed is the Random Finite Sets (RFS) approach which is the natural representation of the multi-target states and observations. There has been a strong mathematical foundation laid to this approach using Finite Set Statistic(FISST). However, the propagation of the full multi-target posterior distribution using the optimal Bayesian approach is not yet practical due to computational hurdles. A practical alternative to the optimal Bayesian multi-target filter based on RFS is the probability hypothesis density (PHD) filter. PHD is a first order statistical moment of the full multi-target posterior distribution. This paper deals with feature detection and estimation techniques using the particle-PHD filter. The ability to track features in heavy clutter is demonstrated first using the simulated data and then with the real sector scan sonar data.
- 1 May 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 39, 1-5
Multiple target tracking in Underwater Sonar Images using Particle-PHD filter
A multiple feature tracking algorithm for Sector Scan Sonar images is presented. The underlying framework that is employed is the Random Finite Sets (RFS) approach which is the natural representation of the multi-target states and observations. There has been a strong mathematical foundation laid to this approach using Finite Set Statistic(FISST). However, the propagation of the full multi-target posterior distribution using the optimal Bayesian approach is not yet practical due to computational hurdles. A practical alternative to the optimal Bayesian multi-target filter based on RFS is the probability hypothesis density (PHD) filter. PHD is a first order statistical moment of the full multi-target posterior distribution. This paper deals with feature detection and estimation techniques using the particle-PHD filter. The ability to track features in heavy clutter is demonstrated first using the simulated data and then with the real sector scan sonar data.