The robotic future that wasn鈥檛

EAISI lecture of visiting Professor Sarath Sreedharan

Datum
donderdag 21 november 2024 vanaf 3:30 PM tot 4:30 PM
Locatie
Neuron 0.262
Prijs
free
Delen
professor

On November 21, Hendrik Baier will host professor Sarath Sreedharan of Colorado State University (USA).

Abstract:

We are living through a revolutionary moment in AI history. We are seeing the development of impressive new AI systems at a rate that was unimaginable just a few years ago. However, AI's true potential to transform society remains unrealized, in no small part due to the inability of current systems to work effectively with people. A major hurdle to achieving such coordination is the inherent asymmetry between the AI system and its users.

In this talk, I will discuss how the framework of Human-Aware AI (HAAI) provides us with the tools required to bridge this gap and support fluent and intuitive coordination between the AI system and its users. We will discuss how, HAAI, a framework originally developed to model explanatory dialogue has since been shown to be capable of modeling and addressing diverse challenges associated with human-AI Interaction. In particular, we will look at how HAAI could be used to achieve value-alignment, calibrate user trust, provide effective assistance, and even generate deceptive behavior.

Bio:

Sarath Sreedharan is an Assistant Professor at Colorado State University. His core research interests include designing human-aware decision-making systems to generate behaviors that align with human expectations. He completed his Ph.D. at Arizona State University, where his doctoral dissertation received one of the 2022 Dean鈥檚 Dissertation Awards for Ira A. Fulton Schools of Engineering and was an Honorable mention for the ICAPS-23 Outstanding Dissertation Award.

His research has been published in various premier research conferences, including AAAI, ICAPS, IJCAI, AAMAS, IROS, HRI, ICRA, ICML, ICLR, and NeurIPS, and journals like AIJ, and in AI Magazine. He has presented tutorials on his research at various forums and is the lead author of a Morgan Claypool monograph on explainable human-AI interactions. He was selected as a DARPA Riser Scholar for 2022 and a Highlighted New Faculty at AAAI-23.

His research has won multiple awards, including the Best System's Demo and Exhibit Award at ICAPS-20 and the Best Paper Award at Bridging Planning & RL workshop at ICAPS 2022. He was also recognized as a AAAI-20 Outstanding Program Committee Member, Highlighted Reviewer at ICLR 22, IJCAI 2022 and 2023 Distinguished Program Committee Member, and Top Reviewer at NeurIPS 22.

(This lecture has been rescheduled due to the Education protests in Utrecht on November 14).

title=Designer
Organisator

Industrial Engineering and Innovation Sciences