Vikram Manikonda - Academia.edu (original) (raw)

Papers by Vikram Manikonda

This paper describes the approach for creating a prototype modeling and simulation syste m that c... more This paper describes the approach for creating a prototype modeling and simulation syste m that captures the interactions between key participants within the National Airspace System. The current operational paradigm for the National Airspace System has nearly reached its limits and cannot accommodate the projected increases in air travel dema nd. As a result, systems -engineering practices are being used to develop and evaluate candidate operational concepts for air traffic control. As these new concepts are considered, it is imperative that adequate and credible models are available to: 1) perf orm conceptual trade evaluations covering many issues and metrics; 2) provide detailed evaluations from many viewpoints of changes to the system prior to their implementation; and 3) conduct real -time and non -real -time analyses of system -wide performance. It is planned that an effective modeling and simulation capability , known as the Airspace Concept Evaluation System, will be achieve...

Real-world applications for unmanned and autonomous systems (UAS) teams continue to grow, and the... more Real-world applications for unmanned and autonomous systems (UAS) teams continue to grow, and the scale and complexity of the teams are continually increasing. To reduce life cycle costs and improve test and evaluation (T&E), we increasingly need to develop a generalized framework that can support the design and development of T&E approaches for multi-UAS teams and validate the feasibility of the concepts, architectures, and algorithms. This challenge is most significant in the cognitive–social domains, where the development of test approaches and methodologies are difficult because of the emergent nature of behaviors in response to dynamic changes in the battlespace. Today much of the initial validation effort is done using simulations, which unfortunately rarely capture the complexity of real world effects related to net-centric communications, vehicle dynamics, distributed sensors, physical environment (terrain), external disturbances, etc. Furthermore, very often high fidelity s...

A major task in information extraction is to extract relations between named entities. Relation e... more A major task in information extraction is to extract relations between named entities. Relation extraction not only builds and extends knowledge bases and ontologies but also supports downstream application processing such as graph mining. In this paper, we report a relation extraction framework based on the natural language theory of link grammar. Our methodology uses and extends Akbik and Broß’s Wanderlust approach, where linguistic paths that are defined over the dependency grammar of sentences guide the relation extraction process. In particular, our framework splits a document into sentences, creates a dependency tree of each sentence, tags and categorizes entities, and extract relations between these entities. The accuracy of our framework is parametrized with the choice of linguistic paths, and accuracy scores as high as 95% precision, 36% recall, and 44% f-score are obtained. We also envision natural extensions of our work, where cross-sentence references are resolved and/or...

: The primary focus is on providing a formal basis for behavior-based robotics using techniques t... more : The primary focus is on providing a formal basis for behavior-based robotics using techniques that have been successful in control-based approaches for steering and stabilizing robots that are subject to nonholonomic constraints. In particular, behaviors for robots are formalized in terms of kinetic state machines, a motion description language and the interaction of the kinetic state machine with information coming in from (limited range) sensors. This allows us to create a mathematical basis for discussing these systems, including techniques for integrating sets of behaviors. In addition we suggest optimality criteria for comparing both atomic and compound behaviors in various environments. A hybrid architecture for the implementation of path planners that use the motion description language is presented. The design and implementation of a planner for path planning and examples of obstacle avoidance with nonholonomic robots are discussed.

The proceedings, working notes, or technical report will be printed directly from camera-ready co... more The proceedings, working notes, or technical report will be printed directly from camera-ready copy furnished by the authors. To ensure that all papers in the publication have a uniform appearance, authors should adhere to the following instructions. (Authors who are only writing an extended abstract need not include an abstract of their

This paper describes the architecture of the Simulation-based Intelligent Training and Assessment... more This paper describes the architecture of the Simulation-based Intelligent Training and Assessment (SITA) system. SITA is a prototype system that integrates HLA compliant simulation with SCORM compliant instruction to provide a more robust and realistic virtual training environment. The SITA architecture is designed to address issues related to SCORMHLA standards interoperability, cross domain execution, code reusability and integration ease. The overall architecture and implementation details of the prototype system are presented in this paper. Air Traffic Management is adopted as the domain of instruction, and an HLA compliant Collaborative Regional Flow Control Decision Support Tool, integrated with a LMS and SCORM compliant instruction, is used to demonstrate the features of the architecture.

In this paper we discuss the dynamics of a planar rigid body with a thruster. We identify the pos... more In this paper we discuss the dynamics of a planar rigid body with a thruster. We identify the position and orientation of the planar rigid body with an element of the Lie group SE(2). The invariance of the kinetic energy Lagrangian and the forcing term (thrust) under the SE(2) action of translations and rotations is used to obtain a set of Poisson-reduced equations on T SE(2)=SE(2) which is isomorphic to se(2) , the dual of the Lie algebra of SE(2). Depending on the control authority available, we distinguish two versions of the problem which we call the \jet-puck" problem and the \hovercraft" problem respectively. In the jet-puck problem the control enters linearly, and we show that, using only a scalar control we have controllability over se(2). In the hovercraft problem the controls enter nonlinearly. In the equations of motion of the above cases the drift vectorreld is periodic (and hence trivially weakly positively Poisson stable). This, along with the fact that the L...

Proceedings 2000 Icra Millennium Conference Ieee International Conference on Robotics and Automation Symposia Proceedings, Feb 1, 2000

ABSTRACT We present some new results in controller design for spacecraft attitude trajectory trac... more ABSTRACT We present some new results in controller design for spacecraft attitude trajectory tracking. A model-based nonlinear controller and a controller gain switching strategy are presented. The nonlinear controller together with the switching strategy result in exponential convergence and also provide a near method to overcome problems associated with closed loop behavior near an unstable equilibrium that are inherent to controllers with quaternion feedback. Bounds of convergence rates and “turn around time” to the stable equilibrium are explicitly calculated. A “time-scaling” approach for partial reference trajectory redesign is then presented to achieve tracking when constraints on the magnitude of the available input torques are present

Conference on Information Sciences and Systems, 1996

In this paper we discuss the dynamics of a planar rigidbody with a thruster. We identify the posi... more In this paper we discuss the dynamics of a planar rigidbody with a thruster. We identify the position and orientationof the planar rigid body with an element ofthe Lie group SE(2). The invariance of the kineticenergy Lagrangian and the forcing term (thrust) underthe SE(2) action of translations and rotations isused to obtain a set of Poisson-reduced equations onTSE(2)=SE(2) which is

International Joint Conference on Artificial Intelligence, 1995

In this paper we present a formalization of behavior-base d planning for nonholonomic robotic sys... more In this paper we present a formalization of behavior-base d planning for nonholonomic robotic systems. This work provides a frame- work that integrates features of reactive plan ning models with modern control-theory-based robotic approaches in the area of path-planning for nonholonomic robots. In particular, we in troduce a motion description language, MDLe, that provides a formal basis for robot program

Page 1. An HLA Compliant Agent-Based Fast-Time Simulation Architecture For Analysis Of Civil Avia... more Page 1. An HLA Compliant Agent-Based Fast-Time Simulation Architecture For Analysis Of Civil Aviation Concepts Jesse Aronson, Vikram Manikonda*, Wilbur Peng*, Renato Levy* and Karlin Roth Science Applications International Corporation ...

In this paper we discuss the use of predictors as a means to improve the robustness of a multi-ag... more In this paper we discuss the use of predictors as a means to improve the robustness of a multi-agent system in the event of information attacks that might result in a communication loss between agents. We focus on an adaptive logistics application developed under DARPA's Ultralog program using the Cougaar Agent infrastructure. The objective of the predictors is to estimate key "state variables" such as demand, inventory etc. in the absence of communication, and allow logistics planning and execution to continue when communication resources are limited or lost. Prediction schemes based on a model-based linear state estimation and moving averages are discussed. A generalized software implementation of the predictors as plugins within a Cougaar agent, and approaches to reconcile any errors between the "estimated" and "actual" states when communication is restored is also discussed. Experimental results based on the implementation of the predictors in a...

This paper presents an innovative shared intelligence framework for flexible human-agent collabor... more This paper presents an innovative shared intelligence framework for flexible human-agent collaboration. By 'flexible', we mean the level of collaboration is selected through a negotiated and iterative human-agent collaboration (HAC) process, which ensures that the needs of a system user are balanced with the availability of suitable experts to form and maintain an expert team that supports the user's decision-making. To enable flexible human-agent collaboration to develop expert teams, our framework suitably represents team members' roles and capabilities, represents tasks and environments, reasons simultaneously about task decomposition and team formation, and coordinates human experts and software agents. We describe our prototype implementation as it applies to a military medical service scenario.1

Proceedings 2000 Icra Millennium Conference Ieee International Conference on Robotics and Automation Symposia Proceedings, Feb 1, 2000

Conference on Information Sciences and Systems, 1996

International Joint Conference on Artificial Intelligence, 1995