Skip to main content Skip to secondary navigation

Verifiable Perception and Navigation

Main content start

Research Question: How to Safely Plan the Vehicle Paths with Sensing Uncertainty? 

Autonomous vehicles often operate in complex environ-ments with various sensing uncertainties. For example, GPS signals can be blocked or reflected by buildings. Additionally, camera sensor measurements are susceptible to lighting conditions and yield poor vision performance in environments which lack distinguishing features. We aim to provide safe vehicle path-planning against sensing errors and uncertainties. We not only monitor sensing uncertainties, but also predict the characteristics of these uncertainties based on vehicle dynamics as well as environmental information, such as 3D maps. We apply formal methods, such as stochasticreachability to provide provable navigation safety guarantees.

Research Team: 

  • Sriramya Bhamidipati
  • Adam Dai
  • Tara Mina
  • Akshay Shetty
  • Alexandros Tzikas

Related Works: 

  • Tara Mina, Ashwin V. Kanhere, Shreyas Kousik and Grace Gao, Continuous GPS Authentication with Chimera Using Stochastic Reachability AnalysisNavigation: Journal of the Institute of Navigation.Submitted. [paper]

  • Tara Mina, Ashwin V. Kanhere, Shreyas Kousik and Grace Gao, Continuous GPS Authentication with Chimera using Stochastic Reachability AnalysisProceedings of the Institute of Navigation GNSS+ conference (ION GNSS+ 2021), St. Louis, MO, Sep 2021. [paper] [slides] [video]

  • Sriramya Bhamidipati and Grace Gao, Networked Timing Risk Analysis Against GPS Spoofing via Stochastic Reachability in PMUs, Navigation: Journal of the Institute of Navigation. Submitted. [paper]

  • Shreyas Kousik, Adam Dai and Grace Gao, Ellipsotopes: Combining Ellipsoids and Zonotopes for Reachability Analysis and Fault DetectionIEEE Transactions on Automatic Control. Submitted. [paper]

  • Long Kiu Chung*, Adam Dai*, Derek Knowles, Shreyas Kousik, and Grace X. Gao, Constrained Feedforward Neural Network Training via Reachability AnalysisRobotics: Science and Systems (RSS 2021) Robotics for People (R4P) Workshop, Jul 2021. [paper]

  • Akshay Shetty and Grace X. Gao, Predicting State Uncertainty Bounds Using Non-linear Stochastic Reachability Analysis for Urban GNSS-based UAS NavigationIEEE Intelligent Transportation Systems, doi: 10.1109/TITS.2020.3040517. [paper]

  • Akshay Shetty and Grace X. Gao, Trajectory Planning Under Stochastic and Bounded Sensing Uncertainties Using Reachability AnalysisProceedings of the Institute of Navigation GNSS+ conference (ION GNSS+ 2020), St. Louis, MO, Sep 2020. [paper] [slides] [video]

  • Sriramya Bhamidipati and Grace X. Gao, Integrity-driven Landmark Attention for GPS-Vision Navigation Via Stochastic ReachabilityProceedings of the Institute of Navigation GNSS+ conference (ION GNSS+ 2020), St. Louis, MO, Sep 2020. [paper] [slides] [video]
  • Akshay Shetty and Grace X. Gao, Predicting State Uncertainty for GNSS-based UAV Path Planning Using Stochastic Reachability, Proceedings of the Institute of Navigation GNSS+ conference (ION GNSS+ 2019), Miami, FL, Sep 2019. [paper] [slides]