Towards bio-inspired unsupervised representation learning for indoor aerial navigation
This addresses the problem of enabling drones to navigate indoors without GPS, which is incremental as it builds on existing SLAM methods with a bio-inspired twist.
The paper tackled indoor aerial navigation in GPS-denied environments by proposing a biologically inspired unsupervised representation learning method for SLAM, which achieved feasibility for robust navigation as shown in initial results on a warehouse dataset.
Aerial navigation in GPS-denied, indoor environments, is still an open challenge. Drones can perceive the environment from a richer set of viewpoints, while having more stringent compute and energy constraints than other autonomous platforms. To tackle that problem, this research displays a biologically inspired deep-learning algorithm for simultaneous localization and mapping (SLAM) and its application in a drone navigation system. We propose an unsupervised representation learning method that yields low-dimensional latent state descriptors, that mitigates the sensitivity to perceptual aliasing, and works on power-efficient, embedded hardware. The designed algorithm is evaluated on a dataset collected in an indoor warehouse environment, and initial results show the feasibility for robust indoor aerial navigation.