Filters








206 Hits in 4.9 sec

Deep Drone Acrobatics (Extended Abstract)

Elia Kaufmann, Antonio Loquercio, Rene Ranftl, Matthias Müller, Vladlen Koltun, Davide Scaramuzza
2021 Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence   unpublished
Acrobatic flight with quadrotors is extremely challenging.  ...  Human drone pilots require years of practice to safely master such maneuvers. Yet, a tiny mistake could make the platform lose control, and brutally crash.  ...  Introduction Acrobatic flight with quadrotors is extremely challenging. Human drone pilots require many years of practice to safely master maneuvers such as power loops and barrel rolls 1 .  ... 
doi:10.24963/ijcai.2021/650 fatcat:wxfa42pburhcdcm5napmy3yfyq

Agile Autonomy: High-Speed Flight with On-Board Sensing and Computing

Antonio Loquercio, Davide Scaramuzza
2020 Zenodo  
In this extended abstract, we present our latest research in learning deep sensorimotor policies for agile visionbased quadrotor flight.  ...  In addition, we discuss the open research questions that still need to be answered to improve the agility and robustness of autonomous drones.  ...  In this extended abstract, we summarize our latest research in learning deep sensorimotor policies for agile vision-based quadrotor flight.  ... 
doi:10.5281/zenodo.4781012 fatcat:uo3kr3flbzcrxgwmqkt5fpohcq

Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents [article]

Christian Pfeiffer, Simon Wengeler, Antonio Loquercio, Davide Scaramuzza
2022 arXiv   pre-print
We compare the drone racing performance of the attention-prediction controller to those using raw image inputs and image-based abstractions (i.e., feature tracks).  ...  We test this hypothesis using eye gaze and flight trajectory data from 18 human drone pilots to train a visual attention prediction model.  ...  is adapted from the "Deep Drone Acrobatics" (DDA) architecture proposed in [11] .  ... 
arXiv:2201.02569v2 fatcat:scc33lp2ovcrdkov6uris2w7fy

Visual attention prediction improves performance of autonomous drone racing agents

Christian Pfeiffer, Simon Wengeler, Antonio Loquercio, Davide Scaramuzza, Sathishkumar V E
2022 PLoS ONE  
We compare the drone racing performance of the attention-prediction controller to those using raw image inputs and image-based abstractions (i.e., feature tracks).  ...  We test this hypothesis using eye gaze and flight trajectory data from 18 human drone pilots to train a visual attention prediction model.  ...  The architecture is adapted from the "Deep Drone Acrobatics" (DDA) architecture proposed in [11] .  ... 
doi:10.1371/journal.pone.0264471 pmid:35231038 pmcid:PMC8887736 fatcat:h2slgyjxq5bs7koyibvda4gil4

Companion Unmanned Aerial Vehicles: A Survey [article]

Chun Fui Liew, Takehisa Yairi
2020 arXiv   pre-print
We tackle two major challenges towards these goals, where we first use a coordinated way to gather top-quality human-drone interaction (HDI) papers from three sources, and then propose to use a perceptual  ...  Table 1 1 35 keywords used to search drone papers systematically from the collected titles and abstracts. acrobatic bat flight rotor aerial bee fly rotorcraft aero bird flying soar aeroplane  ...  titles and abstracts collected in the first step.  ... 
arXiv:2001.04637v1 fatcat:shhen6kkwzfhznp2ecgbuti5ii

UAV Autonomous Target Search Based on Deep Reinforcement Learning in Complex Disaster Scene

Chunxue Wu, Bobo Ju, Yan Wu, Xiao Lin, Neal N. Xiong, Guangquan Xu, Hongyan Li, Xuefeng Liang
2019 IEEE Access  
INDEX TERMS Deep reinforcement learning, Markov decision, Monte Carlo, Q-learning.  ...  Current drones are quite mature in terms of automation control, but current drones require manual control.  ...  Some drone companies use cloud services to support multiple drones for aerial collaboration. The multi-UAV work together currently the most widely used area is Aerial acrobatics.  ... 
doi:10.1109/access.2019.2933002 fatcat:ys4niqndlbhzphwko2way46are

Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents [article]

Christian Pfeiffer, Simon Wengeler, Antonio Loquercio, Davide Scaramuzza
2022
We compare the drone racing performance of the attention-prediction controller to those using raw image inputs and image-based abstractions (i.e., feature tracks).  ...  We test this hypothesis using eye gaze and flight trajectory data from 18 human drone pilots to train a visual attention prediction model.  ...  is adapted from the "Deep Drone Acrobatics" (DDA) architecture proposed in [11] .  ... 
doi:10.48550/arxiv.2201.02569 fatcat:yzzpneoaxrhktl6xx7jrpeavfi

Visual attention prediction improves performance of autonomous drone racing agents

Christian Pfeiffer, Simon Wengeler, Antonio Loquercio, Davide Scaramuzza
2022
We compare the drone racing performance of the attention-prediction controller to those using raw image inputs and imagebased abstractions (i.e., feature tracks).  ...  We test this hypothesis using eye gaze and flight trajectory data from 18 human drone pilots to train a visual attention prediction model.  ...  The architecture is adapted from the "Deep Drone Acrobatics" (DDA) architecture proposed in [11] .  ... 
doi:10.3929/ethz-b-000536703 fatcat:clly6j644vdptgceciy42ip3m4

Listening to Capoeira: Phenomenology, Embodiment, and the Materiality of Music

Greg Downey
2002 Ethnomusicology  
University of Illinois Press and Society for Ethnomusicology are collaborating with JSTOR to digitize, preserve and extend access to Ethnomusicology. •W r hat does this music sound like?"  ...  He could not remember the whole extended metaphor.  ...  He describes how the sound of a Russian cantor's voice was, "brought to your ears in one and the same movement from deep down in the cavities, the muscles, the membranes, the cartilages, and from deep  ... 
doi:10.2307/852720 fatcat:2opk2wjiergw5mf2pzw6m32yp4

Alucinação transensorial

Johannes Birringer
2018 Texto Digital  
warehouse space, attached to aerial wires that allow the fabrics to fly, I watched how dancer Yoko Ishiguro slowly emerged, like an amphibian creature, from under the fabrics, still shrouded by them, then extending  ...  Examples from the recent history of music and sonic art are too numerous to cite, ranging from Xenakis, Paik, Lucier, and Stockhausen to drone and noise artists (Niblock, Fusinato, Ikeda) and sound installation  ... 
doi:10.5007/1807-9288.2018v14n1p52 fatcat:nazqjqwjrjamxlbcezezlxdcci

From Athens to Atlanta and Beyond: Reshaping Ourselves for a New World Through King's Living Legacy

Myron Moses Jackson
2020 Eidos  
Moral Acrobatics and Conscientious Citizens In her chapter "From Anger to Love," Martha Nussbaum emphasizes how this perfectionism should not be equated with either stoicism nor Gandhi's asceticism and  ...  (SNW, 76) Challenging the conventional wisdom that King's "I Have a Dream" speech is merely extending the original vision of the American republic during the founding, rooted in liberty, equality, and  ... 
doi:10.14394/eidos.jpc.2020.0036 fatcat:s3545kyaofa3hd5czqoxjofidq

A System-of-Systems Bio-Inspired Design Process: Conceptual Design and Physical Prototype of a Reconfigurable Robot Capable of Multi-Modal Locomotion

Ning Tan, Zhenglong Sun, Rajesh Elara Mohan, Nishann Brahmananthan, Srinivasan Venkataraman, Ricardo Sosa, Kristin Wood
2019 Frontiers in Neurorobotics  
Step 7: Problem Definition The problem definition plays an important role in the SoS-BID process, involving deep and higher level understanding and interpretation of the searched problem.  ...  For example, they use friction to climb steeper surfaces where part of the body has a grip on the surface of interest climbed and the other part extends forward.  ... 
doi:10.3389/fnbot.2019.00078 pmid:31616275 pmcid:PMC6763944 fatcat:o64bk4kg3feixekp6znzj2u57y

Agile autonomy: learning tightly-coupled perception-action for high-speed quadrotor flight in the wild

Antonio Loquercio
2021
"Deep Drone Acrobatics".  ...  Therefore, if we change the task, e.g. from drone racing to acrobatics, the abstraction will have to be adjusted accordingly.  ...  We provide the drone with a straight reference trajectory of 40 m length.  ... 
doi:10.5167/uzh-206048 fatcat:n2nvlyrztrhafmo447vsysamye

Fabrication and Evaluation of the Inshore Fishing UAV Gripper

Mbaitiga Zacharie
2018 Zenodo  
Keywords: UAV; UAS; Gripper; Drone; Seashore; twe-litle.  ...  Abstract: UAV is defined as Unmanned Aerial Vehicle with some greater or lesser degree of 'automatic intelligence' part of an unmanned aircraft systems.  ...  It is an extended task, requiring the location of suspected vessels and their intent.  ... 
doi:10.5281/zenodo.4280140 fatcat:kdr22wtp3ndldbqkrx2stw5fxe

An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots [article]

Marcos V. Conde
2021 arXiv   pre-print
robots are currently one of the most popular Artificial Intelligence problems, having experienced significant advances in the last decade, from Self-driving cars and humanoids to delivery robots and drones  ...  with other robots, acrobatic movements, etc.  ...  last decade, from Self-driving cars and humanoids to delivery robots and drones.  ... 
arXiv:2112.05534v2 fatcat:3drhsxelvvdwvpsq5rvfpnukam
« Previous Showing results 1 — 15 out of 206 results