Semantically-enhanced Deep Collision Prediction for Autonomous Navigation using Aerial Robots This work contributes a novel and modularized learning-based method for aerial robots navigating cluttered environments containing hard-to-perceive thin obstacles without assuming access to a map or the full pose estimation of the robot. The proposed solution builds upon a semantically-enhanced Variational Autoencoder that is trained with both real-world and simulated depth images to compress the input

Autonomous boat with independent decision-making, efficient control, and long-range navigation capabilities to improve bathymetric surveys. Researchers from the University of Texas, El Paso construct a fully autonomous vessel to carry out reliable and economical bathymetric surveys, which involves mapping the depth and terrain of water bodies. The researchers’ main objective being to provide a methodological framework for other researchers to build their own autonomous boat which will assist wit