On the Application of Efficient Neural Mapping to Real-Time Indoor Localisation for Unmanned Ground Vehicles
This work addresses indoor localization for robotics, but it is incremental as it builds on prior neural mapping methods by focusing on 2D constraints and increased data.
The authors tackled real-time indoor localization for unmanned ground vehicles by applying a neural mapping approach, achieving a mean accuracy of 9cm at 6fps on an onboard CPU and releasing a new dataset with tens of thousands of samples.
Global localisation from visual data is a challenging problem applicable to many robotics domains. Prior works have shown that neural networks can be trained to map images of an environment to absolute camera pose within that environment, learning an implicit neural mapping in the process. In this work we evaluate the applicability of such an approach to real-world robotics scenarios, demonstrating that by constraining the problem to 2-dimensions and significantly increasing the quantity of training data, a compact model capable of real-time inference on embedded platforms can be used to achieve localisation accuracy of several centimetres. We deploy our trained model onboard a UGV platform, demonstrating its effectiveness in a waypoint navigation task, wherein it is able to localise with a mean accuracy of 9cm at a rate of 6fps running on the UGV onboard CPU, 35fps on an embedded GPU, or 220fps on a desktop GPU. Along with this work we will release a novel localisation dataset comprising simulated and real environments, each with training samples numbering in the tens of thousands.