Without image processing: Drone autonomously hangs onto branches with a gripper A drone from TU Delft manages without image recognition to grasp branches of a tree and land on them. It feels the branches. A research team from Delft University of Technology (TU Delft) has developed a drone that can hang onto branches with a gripper to pause during a mission. The gripping function is triggered by tactile sensors, so no visual recognition systems need to be used, which would not function reliably in cluttered treetops anyway. When monitoring ecosystems, drones sometimes need to remain in one place to collect data. However, hovering is noisy and consumes a lot of energy. In such cases, it is better if the drone can switch off its motors and remain in a waiting position. This saves energy, and the battery lasts longer, as the scientists write in the study “Aerial tactile perching via an anthropomorphic hand with embodied soft tactile receptors,” which was published in Nature npj Robotics. The researchers therefore want to let the drone land on a branch without using complicated landing systems that rely on visual recognition and, by calculating the flight path and landing, would again consume a lot of energy. The TU Delft drone is intended to hang onto a branch with a simple tactile gripper, switch off its motors, and then collect data. Empfohlener redaktioneller Inhalt Mit Ihrer Zustimmung wird hier ein externes YouTube-Video (Google Ireland Limited) geladen. Ich bin damit einverstanden, dass mir externe Inhalte angezeigt werden. Damit können personenbezogene Daten an Drittplattformen (Google Ireland Limited) übermittelt werden. Mehr dazu in unserer Datenschutzerklärung. In cluttered treetops, visual systems with cameras for landing calculations would be overwhelmed, the scientists write. Foliage and small branches restrict visibility, impairing landing calculations. Such systems are therefore not practical. Branch recognition