02307nam 2200481 450 991071742100332120230801215441.09783031272882(electronic bk.)978303127287510.1007/978-3-031-27288-2(MiAaPQ)EBC7240908(Au-PeEL)EBL7240908(DE-He213)978-3-031-27288-2(OCoLC)1378391944(PPN)26965545X(EXLCZ)992651639580004120230801d2023 uy 0engurcnu||||||||txtrdacontentcrdamediacrrdacarrierAgile autonomy learning high-speed vision-based flight /Antonio Loquercio1st ed. 2023.Cham, Switzerland :Springer,[2023]©20231 online resource (69 pages)Springer Tracts in Advanced Robotics,1610-742X ;153Print version: Loquercio, Antonio Agile Autonomy: Learning High-Speed Vision-Based Flight Cham : Springer International Publishing AG,c2023 9783031272875 Includes bibliographical references.1: Introduction -- 2: Contribution -- 3: Future Directions.This book presents the astonishing potential of deep sensorimotor policies for agile vision-based quadrotor flight. Quadrotors are among the most agile and dynamic machines ever created. However, developing fully autonomous quadrotors that can approach or even outperform the agility of birds or human drone pilots with only onboard sensing and computing is challenging and still unsolved. Deep sensorimotor policies, generally trained in simulation, enable autonomous quadrotors to fly faster and more agile than what was possible before. While humans and birds still have the advantage over drones, the author shows the current research gaps and discusses possible future solutions.Springer Tracts in Advanced Robotics,1610-742X ;153Autonomous robotsAutonomous robots.050Loquercio Antonio1354687MiAaPQMiAaPQMiAaPQ9910717421003321Agile autonomy3419284UNINA