AstroLoc2: Fast Sequential Depth-Enhanced Localization for Free-Flying Robots

We present AstroLoc2, a monocular and time-offlight (ToF) visual-inertial graph-based localizer used by the Astrobee free-flying robots on the International Space Station (ISS). AstroLoc2 sequentially performs odometry and absolute localization in a single process to decouple map noise from velocity and IMU bias estimation and run efficiently on resource constrained platforms. It improves monocular visual-inertial odometry robustness by adding ToF correspondence factors and uses adaptive map-matching to increase image registration reliability in dynamic environments while preserving fast matching in static ones. We evaluate the performance of AstroLoc2 on a public dataset of 10 ISS activities and show that it improves localization accuracy by 16 % and success rates by 5. 5 % while maintaining a faster runtime than leading methods. AstroLoc2 has enabled the Astrobee robots to perform higher precision maneuvers in changing environments on the ISS. It can be configured for other limited computation platforms and we release the source code to the public.

Authors

• Ryan Soussan
• Marina Moreira 0001
• Brian Coltin
• Trey Smith

Keywords

• Location awareness
• Surveys
• Accuracy
• Simultaneous localization and mapping
• Runtime
• Source coding
• Noise
• Robustness
• Odometry
• Robots
• Matching Model
• Localizer
• Absolute Position
• Computational Platform
• International Space Station
• Static Ones
• Improve Localization Accuracy
• Visual-inertial Odometry
• Image Features
• Number Of Images
• Similar Images
• Optical Flow
• Core Processes
• Normal Approximation
• Feature Matching
• Pose Estimation
• Adaptive Threshold
• Matching Score
• Microgravity
• Feature Tracking
• Time-of-flight Sensors
• Factor Graph
• Bundle Adjustment
• Relative Pose
• Monocular Images
• Cross-covariance
• Visual Simultaneous Localization And Mapping