Website - rpg.ifi.uzh.ch
youtube.com/ailabRPG
Director - Davide Scaramuzza
Website - rpg.ifi.uzh.ch
youtube.com/ailabRPG
Director - Davide Scaramuzza
https://youtu.be/C5I190lzDdQ
Aerial-guided Navigation of a Ground Robot among Movable Obstacles
Published on Oct 24, 2014
Quote:
We demonstrate the fully autonomous collaboration of an aerial and a ground robot in a mock-up disaster scenario. Within this collaboration, we make use of the individual capabilities and strengths of both robots. The aerial robot ?rst maps an area of interest, then it computes the fastest mission for the ground robot to reach a spotted victim and deliver a ?rst-aid kit. Such a mission includes driving and removing obstacles in the way while being constantly monitored and commanded by the aerial robot. Our mission- planning algorithm distinguishes between movable and ?xed obstacles and considers both the time for driving and removing obstacles. The entire mission is executed without any human interaction once the aerial robot is launched and requires a minimal amount of communication between the robots. We describe both the hardware and software of our system and detail our mission-planning algorithm. We present exhaustive results of both simulation and real experiments. Our system was successfully demonstrated more than 20 times at Automatica and was awarded the KUKA Innovation Award.
"Aerial-guided Navigation of a Ground Robot among Movable Obstacles"
IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Toyako-cho, 2014.
Elias Mueggler, Matthias Faessler, Flavio Fontana and Davide Scaramuzza
Robotics and Perception Group, University of Zurich
https://youtu.be/KOi_YZlPva8
Three-Year Anniversary of the Robotics and Perception Group!
Published on Feb 5, 2015
Quote:
The Robotics and Perception Group celebrates its 3-year anniversary! In this clip, we summarize our main achievements, projects, awards, exhibitions, and upcoming videos! But it wasn’t all work! We also had lots of fun! I am very thankful and proud of having such a great team! It has been an amazing adventure, greatly rewarded by numerous grants and awards, such as the recent ERC Starting Grant, Google, KUKA, and IEEE RAS awards! Congrats and thanks to all that have been part of it!
https://youtu.be/ZcJcsoGGqbA
Information gain metrics for active 3D object reconstruction
Published on Mar 8, 2016
Quote:
Video accompanying the paper:
Jeffrey Delmerico, Stefan Isler, Pavel Vechersky, Reza Sabzevari, Davide Scaramuzza, "Information Gain Metrics for Active 3D Object Reconstruction", Autonomous Robots, 2016.
https://youtu.be/VbvJGQFCvGs
Event-based vision for autonomous high-speed robotics
Published on May 8, 2017
Quote:
This video summarizes the research carried out by the Robotics and Perception Group of the University of Zurich on Event-based Vision between 2013 and 2017. Event-based sensors enable the design of very agile low powered robots that respond within microseconds to changes in the environment, faster than robots based on standard cameras, which have a latency of 200 ms or more. We investigate new methods to make our robots perceive and understand the environment using neuromorphic sensors. In our work, we strive to demonstrate the capabilities of these sensors to tackle real-world robotics problems that are out of reach with traditional cameras, namely in high speed and/or high dynamic range (HDR) conditions.
https://youtu.be/2N_wKXQ6MXA
Deep Drone Acrobatics (RSS 2020)
Jun 11, 2020
Quote:
Performing acrobatic maneuvers with quadrotors is extremely challenging. Acrobatic flight requires high thrust and extreme angular accelerations that push the platform to its physical limits. Professional drone pilots often measure their level of mastery by flying such maneuvers in competitions. In this work, we propose to learn a sensorimotor policy that enables an autonomous quadrotor to fly extreme acrobatic maneuvers with only onboard sensing and computation. We train the policy entirely in simulation by leveraging demonstrations from an optimal controller that has access to privileged information. We use appropriate abstractions of the visual input to enable transfer to a real quadrotor. We show that the resulting policy can be directly deployed in the physical world without any fine-tuning on real data. Our methodology has several favorable properties: it does not require a human expert to provide demonstrations, it cannot harm the physical system during training, and it can be used to learn maneuvers that are challenging even for the best human pilots. Our approach enables a physical quadrotor to fly maneuvers such as the Power Loop, the Barrel Roll, and the Matty Flip, during which it incurs accelerations of up to 3g.
Reference:
E. Kaufmann, A. Loquercio, R. Ranftl, M. Müller, V. Koltun, D. Scaramuzza
"Deep Drone Acrobatics",
Robotics: Science and Systems (RSS), 2020
PDF: rpg.ifi.uzh.ch/docs/RSS20_Kaufmann.pdf
https://youtu.be/bONhhFRVRgU
10-Year Anniversary of the UZH Robotics and Perception Group
Nov 30, 2022
Quote:
This video celebrates the 10-year anniversary of the University of Zurich's Robotics and Perception Group, led by Prof. Davide Scaramuzza. The lab was founded in 2012. More than 300 people worked in our lab as Bsc/Msc/Ph.D. students, postdocs, and visiting researchers. We thank all of them for contributing to our research. The lab made important contributions to autonomous, agile vision-based navigation of micro aerial vehicles and event cameras for mobile robotics and computer vision. Three startups and entrepreneurial projects came out of the lab: the first one, Zurich Eye, became Facebook-Meta Zurich, which contributed to the development of the VR headset Oculus Quest; the second one, Fotokite, makes tethered drones for first responders; the third one, SUIND, makes vision-based drones for precision agriculture. Our researchers won over 50 awards, including four-time finalists and one-time winner of the Georges Giralt Best Ph.D. Thesis Award, two SNSF and ERC grants, Facebook, Kuka, Qualcomm, Intel awards, two NASA TechBrief Awards, and many paper awards. Our lab members have published more than 100 scientific articles, which have been cited more than 35 thousand times, and have been featured in many media, including The New York Times, Forbes, and The Economist. We have also released more than 85 open-source software packages, datasets, and toolboxes to further accelerate science advancement and our research's reproducibility. Our algorithms have inspired and have been transferred to many products and companies, including NASA, DJI, Bosch, Nikon, Magic Leap, Meta-Facebook, Huawei, Sony, and Hilti. Thank you for following our research!
All our research papers, videos, media coverage, software, datasets, and awards can be found on our website: https://rpg.ifi.uzh.ch