Manish Kumar - Academia.edu (original) (raw)

Papers by Manish Kumar

Volume 2: Legged Locomotion; Mechatronic Systems; Mechatronics; Mechatronics for Aquatic Environments; MEMS Control; Model Predictive Control; Modeling and Model-Based Control of Advanced IC Engines;, 2012

ASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control, Volume 1, 2011

ABSTRACT

ASME 2009 Dynamic Systems and Control Conference, Volume 1, 2009

Allocation of a large number of resources to tasks in a complex environment is often a very chall... more Allocation of a large number of resources to tasks in a complex environment is often a very challenging problem. This is primarily due to the fact that a large number of resources to be allocated results into an optimization problem that involves a large number of decision variables. Most of the optimization algorithms suffer from this issue of non-scalability. Further, the uncertainties and dynamic nature of environment make the optimization problem quite challenging. One of the techniques to overcome the issue of scalability that have been considered recently is to carry out the optimization in a distributed or decentralized manner. Such techniques make use of local information to carry out global optimization. However, such techniques tend to get stuck in local minima. Further, the connectivity graph that governs the sharing of information plays a role in the performance of algorithms in terms of time taken to obtain the solution, and quality of the solution with respect to the global solution. In this paper, we propose a distributed greedy algorithm inspired by market based concepts to optimize a cost function. This paper studies the effectiveness of the proposed distributed algorithm in obtaining global solutions and the phase transition phenomenon with regard to the connectivity metrics of the graph that underlies the network of information exchange. A case study involving resource allocation in wildland firefighting is provided to demonstrate our algorithm.

51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition, 2013

There are a growing number of applications demonstrating the effectiveness of emulating human dec... more There are a growing number of applications demonstrating the effectiveness of emulating human decision making using fuzzy logic. Main research challenges include situational awareness and decision making in an uncertain spatio-temporal environment. In this effort, a MATLAB simulation of a surveillance environment was created that placed targets in random areas on a map, with each target having a circular area imposed around it. In the simulation, a fuzzy robot was to find the shortest path around the environment, where it touched each target area at least once (meaning the areas can be passed through) before returning to its starting position. Through fuzzy optimization of a path produced through a genetic algorithm, this task was completed and it was shown that a shorter path could be found through the fuzzy optimization.

51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition, 2013

This paper proposes implementing fuzzy logic to improve upon the decision-making and resource all... more This paper proposes implementing fuzzy logic to improve upon the decision-making and resource allocation during a wildland fire. The problem is based on previous work of implementing neural dynamic programming in the theater-missile defense problem. The scenario was modified to the parameters of a wildland fire and extended to include multiple layers of defense. Three key areas were studied to evaluate the performance of the algorithm: sensitivity to engagement probability, uncertainty analysis, and scalability. The control methodologies were critiqued by the remaining health of the assets and the execution time. The neuro-fuzzy dynamic programming showed improved results in the uncertainty cases while being robust to system complexity.

Infotech@Aerospace 2011, 2011

When an individual enters a room, he/she knows how to plan his/her path to a desired point in the... more When an individual enters a room, he/she knows how to plan his/her path to a desired point in the room, avoiding any obstacles on the way. The individual generates a mental map of the room, based on his or her sensing of the environment, and uses this map to find the optimal path. This task is not trivial for a robot. Even if the map of the environment is somehow made available for the robot, the robot is still required to plan its path. The general problem of path planning for autonomous robots is defined as the search for a path which a robot (with specified geometry) has to follow in a described environment, in order to reach a particular position and orientation B, given an initial position and orientation A. Our approach is to use genetic algorithms to search for a viable and preferably the optimal solution to the problem. We use chromosomes that encode the entire path using a set of discrete steps taken in directions encoded by 3-bit genes. This unique approach requires us to make some modifications to the general genetic algorithms technique, such as varying mutation probability and variable chromosome length. Our approach allows us to plan a path for any amount of obstacles and works particularly well in cases where the number of obstacles is small.

48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition, 2010

This effort explores the effectiveness of adding a layer of fuzzy logic to a group of swarming mu... more This effort explores the effectiveness of adding a layer of fuzzy logic to a group of swarming multi agent robots for exploration and exploitation of an unknown obstacle rich environment represented by a 2D maze problem. The generalized maze problem has been considered as an interesting test bed by various researchers in AI and neural networks. Using a cooperative multi agent robot system reduces the convergence time considerably as compared to a single agent. For the multi agent case, a robust and effective decision making technique is required that prevents a robot from moving to a region already explored by some other robot. In this paper, we present a counter ant algorithm (modified ant colony optimization algorithm) based on a fuzzy inference system which enables multiple agents in path planning along the unexplored regions of a maze in order to find a solution rapidly. Simulation results demonstrate the effectiveness of this approach.

Unmanned Systems, 2014

This paper focuses on the development of control and guidance laws for quadrotor Unmanned Aerial ... more This paper focuses on the development of control and guidance laws for quadrotor Unmanned Aerial Vehicles (UAVs) to track maneuvering ground targets. Proportional Derivative (PD) control law is a popular choice to be used as a tracking controller for quadrotors, but it is often inefficient due to practical acceleration constraints and a number of parameters that need to be tuned. The paper proposes a Proportional Navigation (PN)-based switching strategy to address the problem of mobile target tracking. The experiments and numerical simulations performed using nonmaneuvering and maneuvering targets show that the proposed PN-based switching strategy not only carries out effective tracking but also results into smaller oscillations and errors when compared to the widely used PD tracking method. The proposed PN-based switching strategy presents an important question with regard to when the switching should happen that would minimize the positional error between the UAV and the target. A...

AIAA Infotech@Aerospace (I@A) Conference, 2013

We formulate the Min-Max Multiple Depots, Multiple Traveling Salesmen Problem (MMMDMTSP) as a Bin... more We formulate the Min-Max Multiple Depots, Multiple Traveling Salesmen Problem (MMMDMTSP) as a Binary Programming Problem. The MMMDMTSP is an extension of the classical Traveling Salesman Problem (TSP), in the sense that there are several salesmen, whose routes may originate at several depot locations, and where the goal is to minimize the longest tour by any single salesman. This problem is of particular interest in cases where the time required to complete a set of tasks is of the greatest importance, e.g., military missions or civilian relief efforts. Using our formulation, we develop an algorithm that is capable of finding a near optimal solution to the MMMDMTSP, with a bound on the optimal cost. Some sample solutions are shown for randomly generated instances of the problem, and the scalability properties of the solution are discussed.

AIAA Infotech@Aerospace Conference, 2009

Volume 2: Legged Locomotion; Mechatronic Systems; Mechatronics; Mechatronics for Aquatic Environments; MEMS Control; Model Predictive Control; Modeling and Model-Based Control of Advanced IC Engines;, 2012

ASME 2010 Dynamic Systems and Control Conference, Volume 2, 2010

Abstract This work focuses on the use of a swarm of unmanned aerial vehicles (UAVs) for fire fron... more Abstract This work focuses on the use of a swarm of unmanned aerial vehicles (UAVs) for fire front monitoring applications. Typically, fire monitoring relies on satellite imagery or manned aircraft missions for tracking fire spread. However, both methods have limitations ...

Proceedings of the 2003 IEEE International Symposium on Intelligent Control ISIC-03, 2003

sControI of multiple robots presents numerous challenges, some of which include synchronization i... more sControI of multiple robots presents numerous challenges, some of which include synchronization in terms of position, motion, force, load sharing and intemal force minimization. This paper presents formulation and application of a fuzzy logic based strategy for control of two six degree-of-keedom robots carrying an object in a cooperative mode. The paper focuses on control of intemal forces which get generated when two or more robots cany an object in coordination. Forceltorque sensors mounted on wrist of each robot provide the force and torque data in six dimensions. A fuzzy logic controller has been designed to use these Forcenorque (Fm) data to achieve a cooperating movement in which one robot acts as leader and the other robot follows. Matlab's Fuzzy logic, Simulink, and State Flow toolboxes are used for achieving real-time, autonomous and intelligent behavior of the two robots. Simulation results from three experiments show that the above strategy was able to constrain the intemal forces and provide a smooth movement of the manipulators.

ASME 2011 5th International Conference on Energy Sustainability, Parts A, B, and C, 2011

ABSTRACT

Modern Physics Letters B, 2014

In this paper, we present a generic theoretical chemotactic model that accounts for certain emerg... more In this paper, we present a generic theoretical chemotactic model that accounts for certain emergent behaviors observed in ant foraging. The model does not have many of the constraints and limitations of existing models for ants colony dynamics and takes into account the distinctly different behaviors exhibited in nature by ant foragers in search of food and food ferrying ants. Numerical simulations based on the model show trail formation in foraging ant colonies to be an emergent phenomenon and, in particular, replicate behavior observed in experiments involving the species P. megacephala. The results have broader implications for the study of randomness in chemotactic models. Potential applications include the developments of novel algorithms for stochastic search in engineered complex systems such as robotic swarms.

Dynamic Systems and Control, Parts A and B, 2005

... IMECE2005-80972 INTELLIGENT SENSOR MODELING AND DATA FUSION VIA NEURAL NETWORK AND MAXIMUM LI... more ... IMECE2005-80972 INTELLIGENT SENSOR MODELING AND DATA FUSION VIA NEURAL NETWORK AND MAXIMUM LIKELIHOOD ESTIMATION Manish Kumar NRC Associate Army Research Office Duke University, Durham, NC manish@duke.edu ...

Infotech@Aerospace 2011, 2011

Infotech@Aerospace 2011, 2011

This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency R... more This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency Response Robotic Aircraft (SIERRA) Team of The University of Cincinnati in supporting continued development of technology for Emergency Management Operations. Provided are the background and mission objectives of the current wildland fire support mission in the areas of Unmanned Aerial System (UAS) support and Emergency Management task optimization support. The paper discusses the pre-demonstration aspects of the team's UAS wildland fire demonstration test program, and the intelligent algorithms and techniques utilized for this mission. I. Introduction The SIERRA Project is an organization operated by the University of Cincinnati faculty, graduate and undergraduate students, Marcus UAV and the West Virginia Division of Forestry focusing on Unmanned Aerial Vehicles and Intelligent Systems. The group's primary focus is utilizing the Systems Engineering process and related methods to support emergency management organizations by developing and deploying software and aerial platforms. SIERRA's mission is to develop a tactical sized UAS for use in the Mid-Atlantic state fire region as a wildland fire test platform. The team is currently preparing for a 2011 demonstration event at a live wildfire, which will allow for operational fire units from the State of West Virginia Department of Forestry to review the technology and provide feedback to researchers. The team has formed a relationship between industry, customers, and government, which has allowed for a unique approach to the development of next generation technology. An essential aspect of supporting the development of wildland fire technology is understanding the basics of wildland fire science. The group has focused on understanding the areas of wildland fire behavior and wildland fire organization operational components. The team conducted several years of research on both fire response capabilities and understanding the various fire characteristics in different parts of the country. Teaming with The State of West Virginia Forestry, the team identified several technologies that can support this mission. The technologies improve situational awareness, and fire response measures. Conducting testing with the State of West Virginia Department of Forestry allows operational units to provide feedback based on experience and expectations. To support the missions required by the wildland fire organizations, a robust background of Unmanned Aerial Systems was required. Currently, in the United States, this technology is utilized primarily by the military , related law enforcement, and civilian agencies, such as NASA. Civilian agencies are beginning to operate these systems in experimental and emergency management roles. UAS vary greatly in size, capability, cost, and resource

Infotech@Aerospace 2012, 2012

This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency R... more This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency Response Robotic Aircraft (SIERRA) Team of The University of Cincinnati in supporting continued development of technology for Emergency Management Operations. This paper represents the experimental and post flight analysis of the SIERRA program during the late 2011 time frame in which the team flew 2 successful demonstrations in West Virginia. This paper is the conclusion of "Intelligent Integration of UAV Systems for WildlandFire Management: Towards Concept Demonstration" from AIAA Infotech 2011.

In this paper the use of support vector machines (SVM) for path planning has been investigated th... more In this paper the use of support vector machines (SVM) for path planning has been investigated through a Player/Stage simulation for various case studies. SVMs are maximum margin classifiers that obtain a non-linear class boundary between the data sets. In order to apply SVM to the path planning problem, the entire obstacle course is divided in to two classes of data sets and a separating class boundary is obtained using SVM. This non-linear class boundary line determines the heading of the robot for a collision-free path. Complex obstacles and maps have been created in the simulation environment of Player/Stage. The effectiveness of SVM for path planning on unknown tracks has been studied and the results have been presented. For the classification of newly detected data points in the unknown environment, the k-nearest neighbors algorithm has been studied and implemented.

Volume 2: Legged Locomotion; Mechatronic Systems; Mechatronics; Mechatronics for Aquatic Environments; MEMS Control; Model Predictive Control; Modeling and Model-Based Control of Advanced IC Engines;, 2012

ASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control, Volume 1, 2011

ABSTRACT

ASME 2009 Dynamic Systems and Control Conference, Volume 1, 2009

Allocation of a large number of resources to tasks in a complex environment is often a very chall... more Allocation of a large number of resources to tasks in a complex environment is often a very challenging problem. This is primarily due to the fact that a large number of resources to be allocated results into an optimization problem that involves a large number of decision variables. Most of the optimization algorithms suffer from this issue of non-scalability. Further, the uncertainties and dynamic nature of environment make the optimization problem quite challenging. One of the techniques to overcome the issue of scalability that have been considered recently is to carry out the optimization in a distributed or decentralized manner. Such techniques make use of local information to carry out global optimization. However, such techniques tend to get stuck in local minima. Further, the connectivity graph that governs the sharing of information plays a role in the performance of algorithms in terms of time taken to obtain the solution, and quality of the solution with respect to the global solution. In this paper, we propose a distributed greedy algorithm inspired by market based concepts to optimize a cost function. This paper studies the effectiveness of the proposed distributed algorithm in obtaining global solutions and the phase transition phenomenon with regard to the connectivity metrics of the graph that underlies the network of information exchange. A case study involving resource allocation in wildland firefighting is provided to demonstrate our algorithm.

51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition, 2013

There are a growing number of applications demonstrating the effectiveness of emulating human dec... more There are a growing number of applications demonstrating the effectiveness of emulating human decision making using fuzzy logic. Main research challenges include situational awareness and decision making in an uncertain spatio-temporal environment. In this effort, a MATLAB simulation of a surveillance environment was created that placed targets in random areas on a map, with each target having a circular area imposed around it. In the simulation, a fuzzy robot was to find the shortest path around the environment, where it touched each target area at least once (meaning the areas can be passed through) before returning to its starting position. Through fuzzy optimization of a path produced through a genetic algorithm, this task was completed and it was shown that a shorter path could be found through the fuzzy optimization.

51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition, 2013

This paper proposes implementing fuzzy logic to improve upon the decision-making and resource all... more This paper proposes implementing fuzzy logic to improve upon the decision-making and resource allocation during a wildland fire. The problem is based on previous work of implementing neural dynamic programming in the theater-missile defense problem. The scenario was modified to the parameters of a wildland fire and extended to include multiple layers of defense. Three key areas were studied to evaluate the performance of the algorithm: sensitivity to engagement probability, uncertainty analysis, and scalability. The control methodologies were critiqued by the remaining health of the assets and the execution time. The neuro-fuzzy dynamic programming showed improved results in the uncertainty cases while being robust to system complexity.

Infotech@Aerospace 2011, 2011

When an individual enters a room, he/she knows how to plan his/her path to a desired point in the... more When an individual enters a room, he/she knows how to plan his/her path to a desired point in the room, avoiding any obstacles on the way. The individual generates a mental map of the room, based on his or her sensing of the environment, and uses this map to find the optimal path. This task is not trivial for a robot. Even if the map of the environment is somehow made available for the robot, the robot is still required to plan its path. The general problem of path planning for autonomous robots is defined as the search for a path which a robot (with specified geometry) has to follow in a described environment, in order to reach a particular position and orientation B, given an initial position and orientation A. Our approach is to use genetic algorithms to search for a viable and preferably the optimal solution to the problem. We use chromosomes that encode the entire path using a set of discrete steps taken in directions encoded by 3-bit genes. This unique approach requires us to make some modifications to the general genetic algorithms technique, such as varying mutation probability and variable chromosome length. Our approach allows us to plan a path for any amount of obstacles and works particularly well in cases where the number of obstacles is small.

48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition, 2010

This effort explores the effectiveness of adding a layer of fuzzy logic to a group of swarming mu... more This effort explores the effectiveness of adding a layer of fuzzy logic to a group of swarming multi agent robots for exploration and exploitation of an unknown obstacle rich environment represented by a 2D maze problem. The generalized maze problem has been considered as an interesting test bed by various researchers in AI and neural networks. Using a cooperative multi agent robot system reduces the convergence time considerably as compared to a single agent. For the multi agent case, a robust and effective decision making technique is required that prevents a robot from moving to a region already explored by some other robot. In this paper, we present a counter ant algorithm (modified ant colony optimization algorithm) based on a fuzzy inference system which enables multiple agents in path planning along the unexplored regions of a maze in order to find a solution rapidly. Simulation results demonstrate the effectiveness of this approach.

Unmanned Systems, 2014

This paper focuses on the development of control and guidance laws for quadrotor Unmanned Aerial ... more This paper focuses on the development of control and guidance laws for quadrotor Unmanned Aerial Vehicles (UAVs) to track maneuvering ground targets. Proportional Derivative (PD) control law is a popular choice to be used as a tracking controller for quadrotors, but it is often inefficient due to practical acceleration constraints and a number of parameters that need to be tuned. The paper proposes a Proportional Navigation (PN)-based switching strategy to address the problem of mobile target tracking. The experiments and numerical simulations performed using nonmaneuvering and maneuvering targets show that the proposed PN-based switching strategy not only carries out effective tracking but also results into smaller oscillations and errors when compared to the widely used PD tracking method. The proposed PN-based switching strategy presents an important question with regard to when the switching should happen that would minimize the positional error between the UAV and the target. A...

AIAA Infotech@Aerospace (I@A) Conference, 2013

We formulate the Min-Max Multiple Depots, Multiple Traveling Salesmen Problem (MMMDMTSP) as a Bin... more We formulate the Min-Max Multiple Depots, Multiple Traveling Salesmen Problem (MMMDMTSP) as a Binary Programming Problem. The MMMDMTSP is an extension of the classical Traveling Salesman Problem (TSP), in the sense that there are several salesmen, whose routes may originate at several depot locations, and where the goal is to minimize the longest tour by any single salesman. This problem is of particular interest in cases where the time required to complete a set of tasks is of the greatest importance, e.g., military missions or civilian relief efforts. Using our formulation, we develop an algorithm that is capable of finding a near optimal solution to the MMMDMTSP, with a bound on the optimal cost. Some sample solutions are shown for randomly generated instances of the problem, and the scalability properties of the solution are discussed.

AIAA Infotech@Aerospace Conference, 2009

Volume 2: Legged Locomotion; Mechatronic Systems; Mechatronics; Mechatronics for Aquatic Environments; MEMS Control; Model Predictive Control; Modeling and Model-Based Control of Advanced IC Engines;, 2012

ASME 2010 Dynamic Systems and Control Conference, Volume 2, 2010

Abstract This work focuses on the use of a swarm of unmanned aerial vehicles (UAVs) for fire fron... more Abstract This work focuses on the use of a swarm of unmanned aerial vehicles (UAVs) for fire front monitoring applications. Typically, fire monitoring relies on satellite imagery or manned aircraft missions for tracking fire spread. However, both methods have limitations ...

Proceedings of the 2003 IEEE International Symposium on Intelligent Control ISIC-03, 2003

sControI of multiple robots presents numerous challenges, some of which include synchronization i... more sControI of multiple robots presents numerous challenges, some of which include synchronization in terms of position, motion, force, load sharing and intemal force minimization. This paper presents formulation and application of a fuzzy logic based strategy for control of two six degree-of-keedom robots carrying an object in a cooperative mode. The paper focuses on control of intemal forces which get generated when two or more robots cany an object in coordination. Forceltorque sensors mounted on wrist of each robot provide the force and torque data in six dimensions. A fuzzy logic controller has been designed to use these Forcenorque (Fm) data to achieve a cooperating movement in which one robot acts as leader and the other robot follows. Matlab's Fuzzy logic, Simulink, and State Flow toolboxes are used for achieving real-time, autonomous and intelligent behavior of the two robots. Simulation results from three experiments show that the above strategy was able to constrain the intemal forces and provide a smooth movement of the manipulators.

ASME 2011 5th International Conference on Energy Sustainability, Parts A, B, and C, 2011

ABSTRACT

Modern Physics Letters B, 2014

In this paper, we present a generic theoretical chemotactic model that accounts for certain emerg... more In this paper, we present a generic theoretical chemotactic model that accounts for certain emergent behaviors observed in ant foraging. The model does not have many of the constraints and limitations of existing models for ants colony dynamics and takes into account the distinctly different behaviors exhibited in nature by ant foragers in search of food and food ferrying ants. Numerical simulations based on the model show trail formation in foraging ant colonies to be an emergent phenomenon and, in particular, replicate behavior observed in experiments involving the species P. megacephala. The results have broader implications for the study of randomness in chemotactic models. Potential applications include the developments of novel algorithms for stochastic search in engineered complex systems such as robotic swarms.

Dynamic Systems and Control, Parts A and B, 2005

... IMECE2005-80972 INTELLIGENT SENSOR MODELING AND DATA FUSION VIA NEURAL NETWORK AND MAXIMUM LI... more ... IMECE2005-80972 INTELLIGENT SENSOR MODELING AND DATA FUSION VIA NEURAL NETWORK AND MAXIMUM LIKELIHOOD ESTIMATION Manish Kumar NRC Associate Army Research Office Duke University, Durham, NC manish@duke.edu ...

Infotech@Aerospace 2011, 2011

Infotech@Aerospace 2011, 2011

This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency R... more This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency Response Robotic Aircraft (SIERRA) Team of The University of Cincinnati in supporting continued development of technology for Emergency Management Operations. Provided are the background and mission objectives of the current wildland fire support mission in the areas of Unmanned Aerial System (UAS) support and Emergency Management task optimization support. The paper discusses the pre-demonstration aspects of the team's UAS wildland fire demonstration test program, and the intelligent algorithms and techniques utilized for this mission. I. Introduction The SIERRA Project is an organization operated by the University of Cincinnati faculty, graduate and undergraduate students, Marcus UAV and the West Virginia Division of Forestry focusing on Unmanned Aerial Vehicles and Intelligent Systems. The group's primary focus is utilizing the Systems Engineering process and related methods to support emergency management organizations by developing and deploying software and aerial platforms. SIERRA's mission is to develop a tactical sized UAS for use in the Mid-Atlantic state fire region as a wildland fire test platform. The team is currently preparing for a 2011 demonstration event at a live wildfire, which will allow for operational fire units from the State of West Virginia Department of Forestry to review the technology and provide feedback to researchers. The team has formed a relationship between industry, customers, and government, which has allowed for a unique approach to the development of next generation technology. An essential aspect of supporting the development of wildland fire technology is understanding the basics of wildland fire science. The group has focused on understanding the areas of wildland fire behavior and wildland fire organization operational components. The team conducted several years of research on both fire response capabilities and understanding the various fire characteristics in different parts of the country. Teaming with The State of West Virginia Forestry, the team identified several technologies that can support this mission. The technologies improve situational awareness, and fire response measures. Conducting testing with the State of West Virginia Department of Forestry allows operational units to provide feedback based on experience and expectations. To support the missions required by the wildland fire organizations, a robust background of Unmanned Aerial Systems was required. Currently, in the United States, this technology is utilized primarily by the military , related law enforcement, and civilian agencies, such as NASA. Civilian agencies are beginning to operate these systems in experimental and emergency management roles. UAS vary greatly in size, capability, cost, and resource

Infotech@Aerospace 2012, 2012

This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency R... more This paper discusses the Systems Engineering plan of the Surveillance for Intelligent Emergency Response Robotic Aircraft (SIERRA) Team of The University of Cincinnati in supporting continued development of technology for Emergency Management Operations. This paper represents the experimental and post flight analysis of the SIERRA program during the late 2011 time frame in which the team flew 2 successful demonstrations in West Virginia. This paper is the conclusion of "Intelligent Integration of UAV Systems for WildlandFire Management: Towards Concept Demonstration" from AIAA Infotech 2011.

In this paper the use of support vector machines (SVM) for path planning has been investigated th... more In this paper the use of support vector machines (SVM) for path planning has been investigated through a Player/Stage simulation for various case studies. SVMs are maximum margin classifiers that obtain a non-linear class boundary between the data sets. In order to apply SVM to the path planning problem, the entire obstacle course is divided in to two classes of data sets and a separating class boundary is obtained using SVM. This non-linear class boundary line determines the heading of the robot for a collision-free path. Complex obstacles and maps have been created in the simulation environment of Player/Stage. The effectiveness of SVM for path planning on unknown tracks has been studied and the results have been presented. For the classification of newly detected data points in the unknown environment, the k-nearest neighbors algorithm has been studied and implemented.