Presented By: Aerospace Engineering
Aerospace Department Seminar Series: Building Trust in Autonomy - Driving at the Limits of Handling and Interacting with Pedestrians
Nitin Kapania Postdoctoral Fellow Stanford University and University of California, Berkeley
Nitin Kapania
Postdoctoral Fellow
Stanford University and University of California, Berkeley
Autonomy has become a dominant theme across many transportation domains, from automobiles to aircraft to ships. However, the interaction of these autonomous systems with humans remains an open challenge. Several examples of this challenge include the interaction between the pilot and autonomous system in transport aircraft and the interaction between autonomous cars and pedestrians. The interaction challenge arises for a number of reasons, including a lack of mathematical models for human behavior and the need for a massive amount of data required to safely account for all potential interactions. The first half of this talk focuses on one aspect of this challenge, developing a mathematical model for a pedestrian's behavior and studying its interaction with an automated vehicle at a mid-block, unsignalized intersection. By modeling pedestrian behavior through the concept of gap acceptance, we show that a hybrid controller with just four distinct modes allows an autonomous vehicle to successfully interact with a pedestrian across a continuous spectrum of possible crosswalk entry behaviors. The controller is validated through extensive simulation and compared to an alternate POMDP solution, with experimental results provided on a Hyundai research vehicle for a virtual pedestrian. The second half of this talk will focus on another contribution related to automated driving - a feedback-feedforward steering algorithm that enables an autonomous vehicle to accurately follow a specified trajectory at the friction limits while preserving robust stability margins. Experimental data collected from an Audi TTS driving at the handling limits (0.95 g) on a full length race circuit will demonstrate the performance of the controller design.
About the Speaker...
Dr. Nitin Kapania is a postdoctoral fellow with joint appointments at Stanford University and the University of California, Berkeley. His research interests are centered on the planning and control of automated vehicles, with an emphasis on building trust in autonomy by developing algorithms that match or even exceed the performance of the best human drivers. He completed his PhD from Stanford University in 2016, after which he served as a lecturer at Stanford, teaching Vehicle Dynamics and Control. Prior to his postdoctoral appointment, he served as a management consultant at Bain and Company, developing broad expertise in commercial applications for autonomous driving, Internet of Things, and Artificial Intelligence.
Postdoctoral Fellow
Stanford University and University of California, Berkeley
Autonomy has become a dominant theme across many transportation domains, from automobiles to aircraft to ships. However, the interaction of these autonomous systems with humans remains an open challenge. Several examples of this challenge include the interaction between the pilot and autonomous system in transport aircraft and the interaction between autonomous cars and pedestrians. The interaction challenge arises for a number of reasons, including a lack of mathematical models for human behavior and the need for a massive amount of data required to safely account for all potential interactions. The first half of this talk focuses on one aspect of this challenge, developing a mathematical model for a pedestrian's behavior and studying its interaction with an automated vehicle at a mid-block, unsignalized intersection. By modeling pedestrian behavior through the concept of gap acceptance, we show that a hybrid controller with just four distinct modes allows an autonomous vehicle to successfully interact with a pedestrian across a continuous spectrum of possible crosswalk entry behaviors. The controller is validated through extensive simulation and compared to an alternate POMDP solution, with experimental results provided on a Hyundai research vehicle for a virtual pedestrian. The second half of this talk will focus on another contribution related to automated driving - a feedback-feedforward steering algorithm that enables an autonomous vehicle to accurately follow a specified trajectory at the friction limits while preserving robust stability margins. Experimental data collected from an Audi TTS driving at the handling limits (0.95 g) on a full length race circuit will demonstrate the performance of the controller design.
About the Speaker...
Dr. Nitin Kapania is a postdoctoral fellow with joint appointments at Stanford University and the University of California, Berkeley. His research interests are centered on the planning and control of automated vehicles, with an emphasis on building trust in autonomy by developing algorithms that match or even exceed the performance of the best human drivers. He completed his PhD from Stanford University in 2016, after which he served as a lecturer at Stanford, teaching Vehicle Dynamics and Control. Prior to his postdoctoral appointment, he served as a management consultant at Bain and Company, developing broad expertise in commercial applications for autonomous driving, Internet of Things, and Artificial Intelligence.
Explore Similar Events
-
Loading Similar Events...
