Ravi Pandya
Date:
Speaker
Ravi Pandya is a PhD Candidate in the Robotics Institute at Carnegie Mellon University advised by Prof. Changliu Liu and Prof. Andrea Bajcsy. His work is at the intersection of safe control, robot learning, and human modeling, focusing specifically on enabling AI and robots to understand the influence they have on people in order to stay safe while interacting with humans. He is a recipient of the National Science Foundation Graduate Research Fellowship. Prior to his PhD, he was a data scientist at Ericsson working on multi-agent reinforcement learning. He received a BS in Electrical Engineering and Computer Science from UC Berkeley in 2019.
Speaker Links: Google Scholar
Abstract
In recent years, we have seen through chatbots and recommendation algorithms on social media just how influential AI can be in our lives, sometimes creating polarization and potentially even unsafe behavior. Now that robots are also growing more common in the real world, we must be careful to ensure that they are aware of the influence they will have on people, especially when it comes to safety—we do not want robots to cause any harm. In this talk, I will focus on the problem of influence-aware safe control for human-robot interaction. After introducing the overall problem, I will dive into multiple instantiations and discuss how this novel problem formulation can enable robots to intentionally and positively influence people to make their interactions with robots safer and more efficient. I believe that the explicit modeling of both influence and safety is key to enabling autonomous agents to act in the real world around people, and I believe this problem formulation will be a useful building block for a broad set of robotics and AI systems in the future.