Map-Based Object Localization Using Neural Motion Trajectories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing localization technologies, such as GPS and IPS, face challenges in accuracy and reliability, especially in environments where satellite signals are degraded or unavailable, leading to high maintenance costs and inefficiencies in object positioning and navigation.
Innovation Solution
A method using a neural network to map motion trajectories on geospatial maps, employing a topological map-based approach with sensor fusion and neural networks like RNN and GNN to learn object motion patterns, enabling accurate localization through relative position signals and trajectory analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GPS technology is used for object localization, then positioning can be achieved in outdoor environments, but accuracy is insufficient and reliability deteriorates in GPS-degraded areas such as urban canyons, tunnels, and indoors
Solution Approach 1:
The patent introduces map data and motion-based relative position signals as intermediary elements between the object and the localization system. Instead of directly relying on GPS satellite signals, the system uses pre-stored map information combined with relative motion measurements to infer absolute position, thereby mediating the localization process and maintaining reliability in GPS-denied environments
Solution Approach 2:
The patent creates a virtual copy of the physical environment through map data representation. By maintaining a digital map that mirrors the real-world geography and using it in conjunction with relative position signals, the system can localize objects without direct satellite signal input, effectively copying environmental information to compensate for GPS unavailability
2Measurement precision
If Indoor Positioning Systems (IPS) using infrastructure like WiFi, Bluetooth, or UWB are deployed, then localization accuracy can be improved, but device complexity and maintenance cost increase due to large investment requirements
Solution Approach 1:
The patent makes the localization system universal by using map data and motion sensors that can function across diverse environments (outdoors, urban canyons, tunnels, indoors) without requiring environment-specific infrastructure. The same system architecture and algorithm process apply universally, eliminating the need for separate IPS deployments for different locations
Solution Approach 2:
The patent enables the localization system to be self-sufficient by using only the object's own motion sensors and pre-existing public map data. The system does not require external infrastructure installation, maintenance, or coordination with other devices, making it self-service and eliminating the complexity and costs associated with deployed IPS infrastructure
Data Source
AI summary
An object of initial unknown position on a map may be determined by traversing through moving and turning to establish motion trajectory to reduce its spatial uncertainty to a single location that would fit only to a certain map trajectory. An artificial neural network model learns from object motion on different map topologies may establish the object's end-to-end positioning from embedding map topologies and object motion. The proposed method includes learning potential motion patterns from the map and perform trajectory classification in the map's edge-space. Two different trajectory representations, namely angle representation and augmented angle representation (incorporates distance traversed) are considered and both a Graph Neural Network and an RNN are trained from the map for each representation to compare their performances. The results from the actual visual-inertial odometry have shown that the proposed approach is able to learn the map and localize the object based on its motion trajectories.