Large Scale Retrieval Models for Multi-Sensor Data Search

Autonomous Vehicles (AVs) are expected to have the potential to impact urban mobility by providing increased safety, reducing traffic congestion, mitigating accidents and reducing emissions. Since AVs operate with little or no human intervention, it is very essential to perceive the external world and understand different objects and their relationships in the scene, and respond appropriately. For doing this effectively, AVs need to be trained on a variety of traffic situations and appropriate responses to them. Behavior of vehicular traffic varies widely from one part of the world to another. An AV trained for traffic conditions in one part of the world may not be effective, or worse, even be risky in some other part of the world. There is hence a need to create datasets of vehicular traffic scenarios and design mechanisms to query, retrieve and reason about dynamic traffic scenarios. The primary focus of our work is to create a scenario database comprising of diverse Indian traffic scenarios and develop a method for vector based semantic scenario search using a natural language interface.

Funding Agency:

Siemens Technologies and Services Private Limited(STSPL)

Publications:

Bhoomika, A. P., Srinath Srinivasa, Vijaya Sarathi Indla, and Saikat Mukherjee. “Vector Based Semantic Scenario Search for Vehicular Traffic.” InĀ International Conference on Big Data Analytics, pp. 160-171. Cham: Springer Nature Switzerland, 2023.

Team Details:

  • Bhoomika A P (PhD Research Scholar)
  • Prof. Srinath Srinivasa (PI)

Project Students:

  • Vidish Trivedi
  • Sasank Karamsetty
  • Dhanvi Medha Beechu
  • Swetha Murali

Interns:

  • Yashasvi Virani
  • Nayan Radadiya