In this work we propose i) a robust multi-category (non-)localizability detection module, and ii) a localizability-aware constrained ICP optimization module, and couple both in a unified manner. The proposed localizability detection is achieved by utilizing the correspondences between the scan and the map to analyze the alignment strength against the principal directions of the optimization as part of its multi-category LiDAR localizability analysis. In the second part, this localizability analysis is then tightly integrated into the scan-to-map point cloud registration to generate drift-free pose updates along well-constrained directions.

This article presents a team of legged robots for exploration missions in challenging planetary analog environments. We equipped the robots with an efficient locomotion controller, a mapping pipeline for online and post-mission visualization, semantic and instance segmentation to highlight scientific targets, and advanced payloads for remote and in-situ scientific investigation.

In this work, we present Simulation and prediction focuced DNNs for non-linear system identification problem. Furthermore, we provide recommendations on how deep AEs and LSTMs should be utilized to end up with efficient Prediction-focused (Pf) and Simulation-focused (Sf) DNNs for time series and system identification problems.

In this work, we extend the design principles of previously established a unique self foldable and self deployable autonomous quadcopter, FOLLY, for volume limited applications and fast steady deployment. We thoroughly explain the design principles and mechanics that drive FOLLY.

In this work, we propose a unique self foldable and self deployable autonomous quadcopter for search and rescue deployment.