- Divya Srivastava
- Ph.D. Student (ME)
- Montgomery Knight Building270 Ferst DriveAtlanta, GA 30332United States
Divya is a third-year Mechanical Engineering Ph.D. student in the Cognitive Engineering Center at Georgia Tech. She is researching how human factors can be incorporated as design parameters when creating machine learning algorithms. Her research interests are in HRI and user-centric product design.
Previously, Divya has worked for Amazon Robotics as a Software Development Research Intern. For two summers, Divya worked as a Systems Engineer (research intern) in the Robotic Systems Estimation, Decision, and Control Group at NASA’s Jet Propulsion Laboratory. She led a 4-person team to create an Adaptable UAV Swarm Autonomy and Formation Platform and developed a swarm of quadrotors that executes formations and maneuvers in response to user command. She developed a communication system to control the swarm via direct user input into command line. She also worked on the rapid prototyping of a reusable high altitude balloon system for researchers at JPL to conduct near-space experiments. She led the sub-team responsible for the avionics systems and payload integration section of the project, performing Arduino programming, sensor and circuit wiring, and incorporating the electronics within the payload systems.
Divya received her B.S. degree in Mechanical Engineering (Honors) with thesis option and concentration in Aerospace along with a minor degree in Computer Science from Rutgers University.
"Effect of Interaction Design of Reinforcement Learning Agents on Human Satisfaction in Partially Observable Domains"; International Conference on Human Computer Interaction Theory and Applications 2021, on February 10, 2021.
“Case-Based Gesture Interface for Multiagent Formation Control"; International Conference on Case-Based Reasoning 2020, on June 10th, 2020.
“Adaptable UAV Swarm Autonomy and Formation Platform"; International IEEE Aerospace Conference 2019, on March 4th, 2019.
“Project Zephyrus: Developing a Rapidly Reusable High-Altitude Flight Test Platform"; International IEEE Aerospace Conference 2018, on March 5th, 2018.
“Impact of Interaction Design on Human Satisfaction Teaching Reinforcement Learning Agents in Partially Observable Domains"; Workshop on Interactive Robot Learning at the 2020 International Conference on Robotics and Automation, on June 5th, 2020.
“Gesture-Based Interface for Multi-Agent and Swarm Formation Control"; SWARM 2019: The 3rd International Symposium on Swarm Behavior and Bio-Inspired Robotics, on November 20th, 2019.
We are interested in machines that can learn new things from people who are not Machine Learning (ML) experts. We propose a research agenda framed around the human factors (HF) and ML research questions of teaching an agent via demonstration and critique. Ultimately, we will develop a training simulation game with several nonplayer characters, all of which can be easily taught new behaviors by an end-user.