"The goal of this project is to allow robots to learn to understand spoken instructions and information about the world directly from speech with end users. Modern robots are small and capable, but not adaptable enough to perform the variety of tasks people may require. Meanwhile, too many machine learning systems work poorly for people from under-represented groups. The research will use physical, real-world context to enable learning directly from speech, including constructing a data set that is large, realistic, and inclusive of speakers from diverse backgrounds.

As robots become more capable and ubiquitous, they are increasingly moving into traditionally human-centric environments such as health care, education, and eldercare. As robots engage in tasks as diverse as helping with household work, deploying medication, and tutoring students, it becomes increasingly critical for them to interact naturally with the people around them. Key to this progress is the development of robots that acquire an understanding of goals and objects from natural communications with a diverse set of end-users. One way to address this is using language to build systems that learn from people they are interacting with. Algorithms and systems developed in this project will allow robots to learn about the world around them from linguistic interactions. This research will focus on understanding spoken language about the physical world from diverse groups of people, resulting in systems that are more able to robustly handle a wide variety of real-world interactions. Ultimately, the project will increase the usability and fairness of robots deployed in human spaces.

This CAREER project will study how robots can learn about noisy, unpredictable human environments from spoken language combined with perception, using context derived from sensors to constrain the learning problem. Grounded language refers to language that occurs in and refers to the physical world in which robots operate. Human interactions are fundamentally contextual: when learning about the world, we focus on learning by considering not only direct communication but also the context of that interaction. This work will focus on learning semantics directly from perceptual inputs combined with speech from diverse sources. The goal is to develop learning infrastructure, algorithms, and approaches to enable robots to learn to understand task instructions and object descriptions from spoken communication with end users. The project will develop new methods of efficiently learning from multi-modal data inputs, with the ultimate goal of enabling robots to efficiently and naturally learn about their world and the tasks they should perform."

WILL+ is working with the organization Comfort Cases on a book drive to donate new books to kids in the foster system. Please donate new books at our collection boxes in the AOK Library or Harbor Hall lobby. You can also shop our Wish List at Amazon and have books delivered directly to the GWST department. 

The Drive runs from Monday, March 7-Sunday, March 20.

Or, buy from your favorite local bookstore and have books sent to: Kate Drabinski, 1000 Hilltop Circle, 417 Fine Arts, Baltimore, MD 21250.

Help us help kids get their hands on new books!

Madan’s work has received a phase 1 award from the Maryland Innovation Initiative (MII). The MII is a partnership between the State of Maryland and five academic research institutions in Maryland, including UMBC, which promotes the commercialization of research conducted at the universities involved. It helps to get innovative products to consumers more quickly.

The goal of this work is to develop a flexible, rechargeable zinc battery (RZB) prototype that can be used in wearable devices such as watches, wireless headphones, and health devices. “By demonstrating the unique advantages of safety and design flexibility—which enables larger battery footprint and, hence, better performance—we expect to enable RZB commercialization and gain market share for wearable health monitoring devices,” Madan explains.

Enhanced durability is an additional benefit of the RZB technology. These batteries can continue to safely generate power even if they are punctured, bent, or cut. 

During testing, Madan and her students poked six holes in the plastic that contained the battery. They found that the holes reduced the power generated from 100 percent to about 88 percent. The remaining power was still enough to power a small light.

Read more here.

Please consider nominating a fellow student you think personifies our values, a faculty or industry mentor who has made a difference for you, a UMBC staff person who has played a special role, or another partner of CWIT that you think is amazing, or an outstanding member of the CWIT community who helps us fulfill our mission.

Link to form - https://docs.google.com/forms/d/e/1FAIpQLSf13wMauHpM8TFKptWILxjKa3pfSjkGs7-yhNn3GKAnmhIt7w/viewform

Cross-promotion from this original event link. Please mark as going in person on this event to RSVP.

Hello OCSS,

Today's event for Starbucks with OCSS is moved to Commons OCSS lounge at 1pm due to the tent being put up outside.

Thank you for your cooperation.

Name: Olivia Hutchinson

Internship, Co-op, or Research Site: Maryland Psychiatric Research Center 

Position Title: Undergraduate Research Assistant

Major or Program: Psychology

Current Class Level: Sophomore

Work Term: Spring 2022

My internship is with the Maryland Psychiatric Research Center, I am working on two research studies that focus on patients with schizophrenia. The tasks I am doing change from day to day; some days I am helping with data collection during trials and setting up the computer to collect data from the MRI and sometimes I am entering information into the database and excel sheets. There is something new I learn how to do everyday like screening patients on the phone or mailing biological samples to labs to be processed. Everyday is exciting, wondering what new skill I will be learning. 

I heard about the position through an email sent out by the Psychology department in the middle of last December. I submitted my application as soon as I read the email by emailing back my resume. I wrote my resume last year and have been adding on to it since, but when I first wrote it I went to a Resume Rescue session to get it reviewed and I was helped with phrasing and consistency throughout my resume.

Everyone at the Maryland Psychiatric Research Center has been very welcoming and helpful but especially the research assistant I work with on a day to day basis. I have learned so much about data entry, collecting data using an MRI machine as well as the practical process of recording data and how the data we are recording is important to the study.

The work I am doing helps to add to the body of knowledge about schizophrenia. Every discovery starts with data collection.

Apply for anything and everything you're interested in. Don't be intimidated by the amount of work you may have to put in. When you love what you're doing it doesn't feel like work.

By working with the Career Center I get to receive college credits (that I do not have to pay for) while doing something that I would have done for free, something I thoroughly enjoy and care deeply about.

Check out this post on our social media platforms!

Like the Career Center on Facebook

Follow us on Twitter and Instagram

Want to be the next Intern of the Week? Make sure to fill out this form and stay tuned. New interns are announced every Monday!