The Computing Research Association (CRA) is a coalition of more than 200 organizations with the mission of enhancing innovation by joining with industry, government and academia to strengthen research and advanced education in computing. Every year, they recognize North American students who show phenomenal research potential with their Outstanding Undergraduate Researcher Award, and last year, Brown University's Department of Computer Science (Brown CS) made one of the strongest showings in the Honorable Mentions category. Out of forty-seven students who received Honorable Mentions, three of them are Brown CS students: Siddharth Karamcheti, Sorawee Porncharoenwase, and Eric Rosen.
Asked about his work, Siddharth says, "My primary areas of research are natural language processing and machine learning – I specifically focus on problems dealing with how we use language to interact with and understand the world around us. I have two big projects that I’ve worked on the last couple of years, under the supervision of Professor Charniak and Professor Tellex. The first is in human-robot interaction: how do we get robots to follow natural language instructions? The second big project is focused on question-answering: how do we develop models that can read and understand short stories, perform reasoning, and answer complex questions? Outside of natural language, I also work on problems on combining machine learning with automated program testing, or 'fuzzing'. The idea here is to use methods from reinforcement learning in conjunction with existing tools for program analysis and testing to find inputs that crash or unearth bugs in the programs under test, in a manner that is faster and more efficient than existing fuzzers."
"My work (with Tim Nelson and Shriram Krishnamurthi)," says Sorawee, "improves model finders, which are programs producing a set of models that satisfy input constraints. Commonly used in software engineering to explore and verify systems' behavior, model finders however could inundate users with models that don't offer more useful information. We explored using syntax to evaluate how 'interesting' a model is, and investigated how to find a set of these interesting models. The result is a model finder that produces a more concise and useful set of models."
Eric wanted to share some links to four different blog posts about his research. The first three, he explains, are paper publications, and the fourth is an introductory research project from his first year at Brown:
- Communicating Robot Arm Motion Intent Through Mixed Reality Head-mounted Displays
- Comparing Robot Grasping Teleoperation across Desktop and Virtual Reality with ROS Reality
- Reducing Errors in Object-Fetching Interactions through Social Feedback
- Grippers On The Robot!
You can see the full list of Outstanding Undergraduate Researcher winners here. Congratulations, Siddharth, Sorawee, and Eric!
For more information, click the link that follows to contact Brown CS Communication Outreach Specialist Jesse C. Polhemus.