Low-cost Real-Time Learning-based Localization for Autonomous Systems

Robot localization is the problem of finding a robot’s pose using a map and sensor measurements, like LiDAR scans or camera images. It is crucial for any moving autonomous vehicle to interact with the physical world correctly. However, finding injective mappings between measurements and poses is difficult because sensor measurements from multiple distant poses can be similar. To solve this ambiguity, Monte Carlo Localization (MCL), the widely adopted method, uses random hypothesis sampling and sensor measurement updates to infer the pose. Other common approaches are to use Bayesian filtering or to find better-distinguishable global descriptors on the map. Recent developments in localization research usually propose better measurement models or feature extractors within these frameworks. On contrary, this project the research team proposes a radically new approach to frame the localization problem as an ambiguous inverse problem and solve it with an invertible neural network (INN). The team claims that INN is naturally suitable for the localization problem with many benefits, in terms of high accuracy (within 0.25m for city-scale maps), high-speed operation (>150Hz) and operates on low-cost embedded system hardware. The team will demonstrate this on point-cloud and camera datasets with evaluation on indoor and outdoor localization benchmarks, and also deploy it on 1/10th scale and 1/2 scale autonomous vehicles to show real-time and scalable operation.

• Record URL:
  https://ppms.cit.cmu.edu/projects/detail/441

Language

• English

Project

• Status: Active
• Funding: $100000
• Contract Numbers:

  69A3552344811

• Sponsor Organizations:

  Carnegie Mellon University

  Safety21 National UTC for Promoting Safety
  Pittsburgh, PA  United States  15213

  Office of the Assistant Secretary for Research and Technology

  University Transportation Center Program
  ,    
• Managing Organizations:

  Carnegie Mellon University

  Safety21 National UTC for Promoting Safety
  Pittsburgh, PA  United States  15213
• Project Managers:

  Stearns, Amy

• Performing Organizations:

  University of Pennsylvania

  ,    
• Principal Investigators:

  Mangharam, Rahul

• Start Date: 20230701
• Expected Completion Date: 20240630
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Location; Neural networks
• Subject Areas: Data and Information Technology; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01900244
• Record Type: Research project
• Source Agency: Safety21
• Contract Numbers: 69A3552344811
• Files: UTC, RIP
• Created Date: Nov 20 2023 8:51PM