Browsing by Author "Gopalswamy, Swaminathan"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Formalizing Human Machine Communication in the Context of Autonomous Vehicles
    Gopalswamy, Swaminathan; Saripalli, Srikanth; Shell, Dylan; Hickman, Jeffrey S.; Hsu, Ya-Chuan (SAFE-D: Safety Through Disruption National University Transportation Center, 2020-05)
    There are many situations where tacit communication between drivers and pedestrians governs and enhances safety. The goal of this study was to formalize this communication and apply it to the driving strategy of an autonomous vehicle. Toward this, we performed a field study of the interaction between drivers and pedestrians. Vehicles were instrumented to capture behavioral information on a driver as well as passengers and the traffic scenario in general. The data captured were reduced by data analysts to provide insights into the communication and driving patterns. The categorical reduction on driver, pedestrian, and environmental variables was captured. A domain specific language (DSL) was developed to precisely describe the driver-pedestrian behavior, toward the development of a behavioral model for generating autonomous vehicle controls. Specifically, interaction was formalized through a probabilistic model, namely a partially observable Markov decision process (POMDP). This enabled study of what-if scenarios with different risk averseness characteristics. One particular strategy was implemented on an autonomous vehicle and experimental observations were made. Future work will consider (i) richer DSLs to better quantify the driver-human communication, (ii) faster POMDP solvers for real-time operation, and (iii) further applications.
  • Thumbnail Image
    Response of Autonomous Vehicles to Emergency Response Vehicles (RAVEV)
    Nayak, Abhishek; Rathinam, Sivakumar; Gopalswamy, Swaminathan (SAFE-D: Safety Through Disruption National University Transportation Center, 2020-06)
    The objective of this project was to explore how an autonomous vehicle identifies and safely responds to emergency vehicles using visual and other onboard sensors. Emergency vehicles can include police, fire, hospital and other responders’ vehicles. An autonomous vehicle in the presence of an emergency vehicle must have the ability to accurately sense its surroundings in real-time and be able to safely yield to the emergency vehicle. This project used machine learning algorithms to identify the presence of emergency vehicles, mainly through onboard vision, and then maneuver an in-path non-emergency autonomous vehicle to a stop on the curbside. Two image processing frameworks were tested to identify the best combination of vision-based detection algorithms, and a novel lateral control algorithm was developed for maneuvering the autonomous vehicle.