Changing the way you work online.
Responsible for providing engaging, functional, highly useful collaboration solutions for game producers, artists and developers across PlayStation’s studios in the US, EU and Japan. Heavily engaged in researching new technology and determining specific business process solutions for Sony game studios around the world, with the mission to increase revenue and slash costs.
Map-driven guide to local businesses and event listings with reviews and ratings. Written in Ruby on Rails, deployed on worry-free hosting from Heroku, the application integrates with a variety of publicly available APIs, such as Google Maps, address geocoding, IP geocoding, Amazon S3, Facebook Connect and Social Plugins, MailChimp, and more. Based on SEO that works, and relying on zero marketing, The Indian List sees increasing visitors every week. Check it out at theindianlist.com.
Conceived and developed this cross-platform, full-featured instant messenger with a specific co-browsing feature set. Wrote XMPP Server extensions, browser add-ons for IE and Firefox, client installation scripts and an auto-updating platform. Heylos went through a controlled beta, primarily by word-of-mouth, and was in use by a few hundred users. Met with Tech Coast Angels to raise an angel round, however, I ultimately shut it down due to unavailability of a suitable entrepreneur VISA.
Developed a plugin for Eclipse to perform source control actions (e.g. checkin, checkout, etc) for the SourceJammer version control system. Now, developers can avoid switching between the IDE and the SourceJammer client to manage their code. More information can be found on the product homepage. Binaries, screenshots, documentation and source available at SourceForge.
Developed Java web-applications that form an integral part of tolling solutions installed worldwide, such as FasTrak, EZ-Pass, Salik etc. Introduced open-source software alternatives, multiple DB support, server clustering, Java job-scheduling, and efficient scripts providing 100x improvement in build and deploy times. TransCore is the largest global manufacturer of transportation-based RFID technology and operates as a unit of the $6+ billion Roper Industries (NYSE: ROP).
Second employee in a high-tech, demanding startup environment, developing advanced TinyOS mesh sensor networks and Java scheduling applications for the restaurant and hospitality industry. Also developed an interrupt-driven standards-compliant I²C library for TI’s MSP430 processors without hardware support. A highly educational experience, where I worked extensively on various technologies as a Senior Engineer and Server Administrator.
I was a Research Assistant in the AI Robotics Lab at TTU for most of my Masters, with guidance from Dr. Larry Pyeatt, and heavily influenced by Sebastian Thrun and Dr. Robin Murphy. Research Localization and Mapping solutions for robots and to apply concepts of Reinforcement Learning to Robotics. Carried out several projects during this time, exercising mechanical skills towards robot construction and algorithmic skills for intelligence.
Dead Reckoning & Time Based Navigation Robot
Designed a robot which would move on a specific path and return as close as possible to its starting position in the shortest amount of time. Used a Lego Mindstorms Kit to model and the NotQuiteC programming language. The dead-reckoning version involved counting the number of rotations of a wheel to measure how far the robot has moved, when its moving straight or turning. No matter how good a programmer you may be, you have no control over the dirt on the floor in a robot’s path, which will make it change course. Nor do you have control over the wear-and-tear of the robot’s joints, and rubber on the wheels: everything needs to be factored into the algorithm. The time-based version required measuring the amount of time taken for one unit rotation of the wheel, and using that measure to move the robot a certain distance. A lot of mechanical and electrical engineering also went into this project to reduce the effects of the environment as much as possible. After near perfect runs, with near perfect 90 degree turns, the robot was a mere 2 inches from its starting location.
Line Follower Robot
Project to design the most accurate and fastest line-follower robot. The robot was made using the Lego Mindstorms Kit and the NotQuiteC programming language. The goal was to use light-sensors to detect and follow a line made using black-electrical tape on the floor. Since the line crisscrossed over itself, and the room was filled with fluorescent light, it was purposely difficult for the light-sensors to detect the lines. Completed the run in 56secs (under one minute, everytime). The first runner-up’s run took more than 4 minutes. Employing some smart engineering, after 3-4 prototypes, moved the RCX Brick onto a trailer, to reduce the weight (front-wheel drive). So the front moved/turned really fast, and the trailer with the heavy RCX brick simply followed it.
|Line Follower Report (pdf)||Line Follower (nqc)|
Mapping & Obstacle Avoidance Wandering Simulation
Designed a navigational and mapping obstacle-avoidance algorithm, experimenting on a simulator. I based my implementation on the HIMM algorithm proposed by Borenstein and Koren. The simulation was run on the Nomadic Technologies Super Scout II Simulator. Written entirely in C++ on a Linux machine, utilizing the Scout API extensively. This application was to achieve two goals: wander in the environment without hitting any obstacles that may be in the robot’s path, and to make a map of the environment as the robot sees it. The map was to be made using Occupancy grids.
|HIMM Report (pdf)||HIMM Source (zip)|
Water Management System
Developed a Java Swing application, using JFreeChart and JFreeReport to interface with physical ORP, Pressure and pH sensors for data collection, report generation and control. Developed a PHP web interface to provide users ability to view data collected in the Oracle database.
Master’s Thesis: Monte Carlo Localization for Robots using Dynamically Expanding Occupancy Grids
The past few years have seen tremendous growth in the research areas of Mobile Robotics. While growth has been fast and several problems have been very splendidly solved most mobile roboticists are faced with two primary challenges: how will the robot gather information about its environment and how will it know where it is? These two problems are referred to as:
i. Mapping and
Mapping is the process whereby a robot can extract relevant information from its environment allowing it to “remember” it. Localization is the problem of estimating a robot’s pose relative to a map of its environment. However, both these problems are computationally intensive to solve and furthermore, limitations on a robot’s on board computational abilities and inaccuracies in sensor hardware and motor effectors make it even harder. Most mapping techniques are limited by memory and hence a robot has a limitation on the area that it can directly map. Also, if the mapped area is extended, most mapping implementations require that the mapping parameters be changed and the entire mapping algorithm be executed again. However, in recent times a new mapping technique was explored which is that of using Dynamically Expanding Occupancy Grids (Ellore 2002), and of using a Centralized Storage System (Barnes, Quasny, Garcia, and Pyeatt 2004). By using this approach, the robot has virtually unlimited storage space, limited only by the hard drive space, and a small initial map which grows as the robots explores its environment.
Localization has not yet been attempted using Dynamically Expanding Occupancy Grids and a Centralized Storage System. This research was geared towards implementing Monte-Carlo Localization methods (Fox, Burgard, Dellaert, and Thrun 1999; Dellaert, Fox, Burgard, and Thrun; Thrun, Fox, Burgard, and Dellaert 2001; Fox, Thrun, Burgard, and Dellaert 2001) for robots using Dynamically Expanding Occupancy Grids. By using this approach this research aimed to provide a complete mapping and localization implementation for robots using dynamically expanding occupancy grids and a centralized storage system.
Mapping and Localization
Monte Carlo Localization
President of Computer Society and initiated and developed first official college website, circa 2000.
Visit this old projects page to see my work over the years.