Safe Landing
Safe landing, encompassing both aerial and terrestrial vehicles, focuses on developing robust and reliable methods for controlled descent and touchdown in diverse and often unpredictable environments. Current research emphasizes autonomous systems using computer vision (including deep learning models like convolutional neural networks and semantic segmentation), reinforcement learning, and advanced control algorithms (such as model predictive control) to perceive and react to dynamic obstacles and environmental uncertainties. These advancements are crucial for expanding the operational capabilities of drones, robots, and spacecraft in various sectors, including search and rescue, delivery, exploration, and space missions, by improving safety and efficiency.
Papers
Towards Safe Landing of Falling Quadruped Robots Using a 3-DoF Morphable Inertial Tail
Yunxi Tang, Jiajun An, Xiangyu Chu, Shengzhi Wang, Ching Yan Wong, K. W. Samuel Au
Towards a Fully Autonomous UAV Controller for Moving Platform Detection and Landing
Michalis Piponidis, Panayiotis Aristodemou, Theocharis Theocharides