The GAMMA group has recently developed a new deep learning model that can identify people’s emotions based on their walking styles. The approach works by extracting an individual’s gait from an RGB video of him/her walking, then analyzing it and classifying it as one of four emotions: happy, sad, angry or neutral.
“Emotions play a significant role in our lives, defining our experiences, and shaping how we view the world and interact with other humans,” Tanmay Randhavane, one of the primary researchers in this project and a graduate student at UNC, told TechXplore.
The march of progress is a gradual movement. We’re well on our way to a future where humans and robots routinely interact as effortlessly as on the show Futurama. Laying the groundwork for a new social infrastructure is the start of a new societal paradigm, and it begins with developing emotionally intelligent robots such as Pepper.
Members of the GAMMA group — University of North Carolina graduate student Tanmay Randhavane, computer science professors Aniket Bera and Dinesh Manocha, are three of the team members who work with Pepper, along with Rohan Prinja, Kyra Kapsaskis, Austin Wang, Kurt Gray.
Dinesh Manocha has been named to the 2019 SIGGRAPH Academy.
The SIGGRAPH Academy, established last year, recognizes individuals who have made substantial contributions to computer graphics and interactive techniques. Only eight researches were selected this year.
Criteria for election to the Academy includes: cumulative contributions to the field of computer graphics and interactive techniques; impact on the field through development of new research directions and/or innovations; and influence on the work of others.
The growth of the computer science curriculum in the University of Maryland has already triggered the addition of new programs moving from other universities to join the University in its ambition project. Research Assistant Professor Aniket Bera will be bringing his robotics program and graphics research from the University of North Carolina, Chapel Hill to College Park after learning more about the enhanced possibilities.
Bera will be joining the GAMMA group as well as bringing his latest work of an “emotionally intelligent” robot that can read one’s facial and real-time emotions in order to best help a person during a difficult time.
Dinesh Manocha has developed a photo-realistic simulation system for training and validating self-driving vehicles. The new system provides a richer, more authentic simulation than current systems that use game engines or high-fidelity computer graphics and mathematically rendered traffic patterns.
The system was developed in collaboration with a team of colleagues from Baidu Research and the University of Hong Kong. It is called Augmented Autonomous Driving Simulation (AADS), and could make self-driving technology easier to evaluate in the lab while also ensuring more reliable safety before expensive road testing begins.
After Carl Schissler of the GAMMA group finished his doctorate on the room acoustics problem for real-time VR applications in summer 2017, he joined the Facebook Reality Labs Audio Research Team led by Research Science Manager Philip Robinson. Initially working on creating a system that could simulate all the complex room acoustics in real time, his work subsequently found its way into the Oculus Audio SDK.
Read the full news release here.
Dinesh Manocha joins the University of Maryland’s Department of Computer Science in May 2018 as the inaugural Paul Chrisman Iribe Endowed E-Nnovate Professor. He also holds joint appointments in the University of Maryland Institute for Advanced Computer Studies (UMIACS) and the Department of Electrical and Computer Engineering.
“I am truly honored to join the University of Maryland with appointments in two top-ranked departments. With very strong research groups in virtual reality, computer vision and graphics, and robotics, the University of Maryland is regarded as the world leader in these areas,” Manocha said.