Integrating Cognitive Modeling in Engineering Analysis and Design

December 19, 2014, Webb 1100

Vaibhav Srivastava

Princeton University, Department of Mechanical and Aerospace Engineering


SHared autonomy is becoming increasingly important in complex and information rich systems. THe purpose of shared autonomy is to exploit the human cognitive abilities in complex missions. It has been evident that the information overload in these complex missions has a detrimental effect on the human performance. THe focus of this talk is the design of efficient shared autonomy. It is imperative for such designs to efficiently handle information overload and to effectively integrate human cognition into shared autonomy. In this talk, I will focus on three important aspects of these designs. First, I will focus on modeling human decision-making in tasks involving exploration-exploitation trade-off using the context of multiarmed bandit problems. I will present a model for decision-making in such tasks that captures behavioral data and has provable performance. I will show how the model can be leveraged in engineering design. Second, I will discuss how cognitive models can be integrated in engineering analysis and design. I will integrate a model of human decision making in tasks involving speed-accuracy trade-off and integrate it with a popular model for information assimilation in social networks to analyze decision-making in so-called socio-cognitive networks. I will identify influence of network structure in decision-making performance. Finally, I will focus on information-overload problem in shared autonomy. I will show that optimization problems associated with handling information overload problem are non-convex and will design efficient algorithms for these problems.

Speaker's Bio

Vaibhav Srivastava was born in Lucknow, Uttar Pradesh, India. He received the B.Tech. degree in mechanical engineering from the Indian Institute of Technology Bombay,Mumbai, India, in 2007, the M.S. degree in mechanical engineering and the M.A. degree in statistics from the University of California at Santa Barbara, Santa Barbara, CA, USA, in 2011 and 2012,respectively, and the Ph.D. degree in mechanical engineering from the University of California at Santa Barbara in 2012.

He is currently a Lecturer and Postdoctoral Research Associate with the Mechanical and Aerospace Engineering Department, Princeton University, Princeton, NJ, USA. His research interests include modeling, analysis, and design of mixed human-robot networks, robotic/mobile sensor networks, and computational networks.