Learnable Spatio-Temporal Map Embeddings for Deep Inertial Localization

Indoor localization systems often fuse inertial odometry with map information via hand-defined methods to reduce odometry drift, but such methods are sensitive to noise and struggle to generalize across odometry sources. To address the robustness problem in map utilization, we propose a data-driven prior on possible user locations in a map by combining learned spatial map embeddings and temporal odometry embeddings. Our prior learns to encode which map regions are feasible locations for a user more accurately than previous hand-defined methods. This prior leads to a 49% improvement in inertial-only localization accuracy when used in a particle filter. This result is significant, as it shows that our relative positioning method can match the performance of absolute positioning using bluetooth beacons. To show the gen-eralizability of our method, we also show similar improvements using wheel encoder odometry. Our code will be made publicly available † 1 project page: https://rebrand.ly/learned-map-prior.

Authors

• Dennis Melamed
• Karnik Ram
• Vivek Roy
• Kris Kitani

Keywords

• Location awareness
• Performance evaluation
• Fuses
• Wheels
• Robot sensing systems
• Particle filters
• Robustness
• Localization Accuracy
• Particle Filter
• Map Information
• User Location
• Absolute Position
• Indoor Localization
• Improve Localization Accuracy
• Deep Network
• Hidden Markov Model
• Long Short-term Memory
• Kalman Filter
• Local Map
• Inertial Measurement Unit
• Mapping Process
• Heuristic Method
• Extended Kalman Filter
• Conditional Random Field
• Prior Methods
• Bluetooth Low Energy
• Simultaneous Localization And Mapping
• Inertial Measurement Unit Data
• Occupancy Map
• Likelihood Score
• Smartphone
• Functional Graph
• Ground Truth Trajectory
• Feasible Set
• Mean Square Error