Distance Invariant Sparse Autoencoder for Wireless Signal Strength Mapping
This work addresses the challenge of efficient localization for robots using inexpensive sensors in environments with many access points, representing an incremental improvement through a novel method for a known bottleneck.
The paper tackles the problem of high dimensionality in wireless signal strength mapping for robot localization by proposing a distance-invariant sparse autoencoder that learns compact latent representations, demonstrating feasibility in outdoor experiments with precise data reconstruction and low impact on localization performance.
Wireless signal strength based localization can enable robust localization for robots using inexpensive sensors. For this, a location-to-signal-strength map has to be learned for each access point in the environment. Due to the ubiquity of Wireless networks in most environments, this can result in tens or hundreds of maps. To reduce the dimensionality of this problem, we employ autoencoders, which are a popular unsupervised approach for feature extraction and data compression. In particular, we propose the use of sparse autoencoders that learn latent spaces that preserve the relative distance between inputs. Distance invariance between input and latent spaces allows our system to successfully learn compact representations that allow precise data reconstruction but also have a low impact on localization performance when using maps from the latent space rather than the input space. We demonstrate the feasibility of our approach by performing experiments in outdoor environments.