Electrical and Computer Engineering
Dean of Engineering
ECE Seminar Series: Towards Socially-aware AI (698/699)
Wednesday, February 15, 2017
to 5:00 PM
1064 Duncan Hall
6100 Main St
Houston, Texas, USA
Artificial Intelligence (AI) is reshaping the future of many industries ranging from healthcare, energy supply chain, building controls to legal services. Transportation systems will undergo a similar transformation; self-driving vehicles, delivery robots, and smart environments will be ubiquitous. To realize this future, we have to develop machines that can not only perform intelligent tasks, but do so while co-existing with humans in the open world - without negatively perturbing their habits. Self-driving vehicles will navigate the streets alongside human drivers, and delivery robots will share sidewalks with pedestrians. Consequently, machines need to learn unwritten common sense rules and comply with social conventions. For instance, delivery robots should respect personal space, yield right-of-way, and “read” the behavior of others to predict future actions. In this talk, I will present my work towards these goals. I propose to empower machines with a type of cognition I call socially-aware AI, i.e., systems equipped with perception and social intelligence. In other words, I aim to develop systems that have the capacity to i) understand human behavior and ii) effectively navigate complex social interactions. I will present our large-scale multi-modal data collection campaign on human mobility. We have collected massive volumes of data (more than 20 petabytes), which have been processed to analyze the behavior of more than 100 million individuals in crowded urban spaces. Then, I will present a new deep learning framework that can learn to forecast these behaviors in a fully data-driven fashion, without specifying hand-crafted rules. Based on a Recurrent Neural Network, the proposed framework is capable of jointly forecasting multiple correlated sequences, i.e., human walking trajectories in crowds. Finally, I will conclude my talk by showing some ongoing works in applying these techniques to social robots and smart environments.
Biography of Alexandre Alahi:
Alexandre Alahi is currently a research scientist at Stanford University and received his Ph.D. from EPFL (nominated for the EPFL Ph.D. prize in 2011). His research enables machines to perceive the world and make decisions in the context of transportation problems and smart environments. He has worked on the theoretical challenges and practical applications of socially-aware Artificial Intelligence, i.e., systems equipped with perception and social intelligence. He was awarded the Swiss NSF early and advanced researcher grants for his work on predicting human social behavior. He won the CVPR Open Source Award (2012) for his work on Retina-inspired image descriptors, and the ICDSC Challenge Prize (2009) for his sparsity-driven algorithm that has tracked more than 100 million pedestrians to date. His research has been covered internationally by BBC, abc, PBS, Euronews, Wall street journal, and other national news outlets around the world. Alexandre has also co-founded multiple startups such as Visiosafe, and won several startup competitions. He was elected as one of the Top 20 Swiss Venture leaders in 2010.