Safety Challenges for Automated Vehicles in the Absence of Connectivity
TECoSA Seminar with Dr Akhil Shetty, UC Berkeley, Department of Mechanical Systems
All are welcome to this seminar! See the Zoom link below.
Time: Thu 2023-09-07 16.00 - 17.00
Video link: https://kth-se.zoom.us/j/66857695267
Language: English
ABSTRACT: Automated vehicles (AVs) are expected to create a future with effortless driving and virtually no traffic accidents. AV companies claim that, when fully developed, the technology will eliminate all crashes caused due to human error. Indeed, AVs will likely avoid the large number of crashes caused by impaired, distracted or reckless drivers. But there remains a significant proportion of crashes for which no driver is directly responsible. In particular, the absence of connectivity of an AV with its neighboring vehicles (V2V) and the infrastructure (I2V) leads to a lack of information that can induce such crashes. In this talk, I will present prototypical examples motivated by the NHTSA pre-crash scenario typology to show that fully autonomous vehicles cannot guarantee safety in the absence of connectivity. Since AV designs today do not require such connectivity, these crashes would persist in the future. Combining theoretical models and empirical data, I will also argue why such hazardous scenarios would occur with a significantly high probability. Our work suggests that incorporating connectivity is a prerequisite for a safe AV future.
BIO: Akhil Shetty is a postdoctoral researcher in the Department of Mechanical Engineering at UC Berkeley. He completed his Ph.D. in Electrical Engineering and Computer Sciences at UC Berkeley advised by Prof. Kameshwar Poolla and Prof. Pravin Varaiya. He received his B.Tech and M.Tech degrees in Electrical Engineering from IIT Bombay. Akhil is a recipient of the Berkeley Graduate Fellowship for doctoral studies at UC Berkeley. He received the Best Student Paper Award at ITSC 2020, and was a finalist for Best Student Paper at ECC 2018 and SPCOM 2014. He is interested in applying tools from optimization, control, and statistics to tackle problems in the fields of energy and intelligent transportation systems.