- 138
- 941 043
DLR RM
Germany
Приєднався 12 лип 2013
Institut für Robotik und Mechatronik am DLR in Oberpfaffenhofen
Entwickelt werden derzeit einerseits hoch autonome Robotersysteme, insbesondere für die Erkundung ferner Planeten, Monde und anderer Himmelskörper, die aufgrund ihrer Entfernung oder der lebensfeindlichen Bedingungen für Menschen in naher Zukunft nicht zugänglich sein werden. Andererseits setzt das Institut für Aufgaben im erdnahen Orbit sowohl auf Autonomie als auch auf Methoden der Telepräsenz und Mensch-Roboterkooperation. Über die Raumfahrt hinaus, haben die robotischen Technologien direkte Anwendung in den DLR-Schwerpunkten Luftfahrt und Verkehr, aber auch gleichermaßen in der Medizintechnik, der Fabrik der Zukunft und Industrie 4.0, der Katastrophenhilfe, bis hin zur persönlichen robotischen Assistenz.
Der wechselseitige Technologietransfer zwischen den terrestrischen und den raumfahrtbezogenen Anwendungen ist eine besondere Stärke unseres Instituts.
Impressum: www.dlr.de/rmc/desktopdefault.aspx/tabid-11937/
Entwickelt werden derzeit einerseits hoch autonome Robotersysteme, insbesondere für die Erkundung ferner Planeten, Monde und anderer Himmelskörper, die aufgrund ihrer Entfernung oder der lebensfeindlichen Bedingungen für Menschen in naher Zukunft nicht zugänglich sein werden. Andererseits setzt das Institut für Aufgaben im erdnahen Orbit sowohl auf Autonomie als auch auf Methoden der Telepräsenz und Mensch-Roboterkooperation. Über die Raumfahrt hinaus, haben die robotischen Technologien direkte Anwendung in den DLR-Schwerpunkten Luftfahrt und Verkehr, aber auch gleichermaßen in der Medizintechnik, der Fabrik der Zukunft und Industrie 4.0, der Katastrophenhilfe, bis hin zur persönlichen robotischen Assistenz.
Der wechselseitige Technologietransfer zwischen den terrestrischen und den raumfahrtbezogenen Anwendungen ist eine besondere Stärke unseres Instituts.
Impressum: www.dlr.de/rmc/desktopdefault.aspx/tabid-11937/
Bipedal Running: Bioinspired Fundamentals for Versatile Humanoid Robot Locomotion
This presentation was held on the IEEE-RAS Humanoids Conference 2023 in Austin, Texas.
The according paper can be found on IEEE Xplore: ieeexplore.ieee.org/document/10375238
Abstract:
The field of humanoid robots has grown in recent years with several companies and research laboratories developing new humanoid systems. However, the number of running robots did not noticeably rise. Despite the need for fast locomotion to quickly serve given tasks, which require traversing complex terrain by running and jumping over obstacles. To provide an overview of the design of humanoid robots with bioinspired mechanisms, this paper introduces the fundamental functions of the human running gait. The paper surveys multiple concepts, i.e. to protect the system against impacts, store kinetic energy at touchdown, use natural dynamics, and transfer energy between joints through couplings. The understanding of the fundamental functions can support engineers to design versatile humanoid robots, without sacrificing versatility against capability.
Structure:
0:00 Introduction & Motivation 1:13 Impacts 2:50 Energy Storage 4:59 Natural Dynamics 5:34 Couplings 7:09 Design Guideline & Conclusion
The according paper can be found on IEEE Xplore: ieeexplore.ieee.org/document/10375238
Abstract:
The field of humanoid robots has grown in recent years with several companies and research laboratories developing new humanoid systems. However, the number of running robots did not noticeably rise. Despite the need for fast locomotion to quickly serve given tasks, which require traversing complex terrain by running and jumping over obstacles. To provide an overview of the design of humanoid robots with bioinspired mechanisms, this paper introduces the fundamental functions of the human running gait. The paper surveys multiple concepts, i.e. to protect the system against impacts, store kinetic energy at touchdown, use natural dynamics, and transfer energy between joints through couplings. The understanding of the fundamental functions can support engineers to design versatile humanoid robots, without sacrificing versatility against capability.
Structure:
0:00 Introduction & Motivation 1:13 Impacts 2:50 Energy Storage 4:59 Natural Dynamics 5:34 Couplings 7:09 Design Guideline & Conclusion
Переглядів: 543
Відео
Humanoid Robot neoDavid: Your Future Dexterous Assistant
Переглядів 10 тис.3 місяці тому
neoDavid is a Robust Humanoid with Dexterous Manipulation Skills, developed at DLR. The main focus in the development of neoDavid is to get as close to human capabilities as possible − especially in terms of dynamics, dexterity and robustness. The robot will operate in an environment designed for humans. neoDavid has a range of motion and size similar to that of a human. Its human-like shape en...
OOS experimental facility
Переглядів 1,1 тис.3 місяці тому
The OOS-SIM (On-Orbit Servicing Simulator) is a simulator for on-orbit servicing tasks such as repair, maintenance and assembly that have to be carried out on satellites orbiting the earth. It simulates the operational conditions in orbit, such as the felt weightlessness and the harsh illuminaton. Robotic technologies in the areas of robot autonomy and teleoperation are tested with this simulat...
Research Project ION
Переглядів 2163 місяці тому
The ION project of the DLR aims to preserve and expand the space ecosystem. By pooling expertise from the fields of aerospace, aviation, and security, new operational procedures are being developed to make a significant contribution to orbital sustainability. www.dlr.de/rm/en/ION
Space technology in the operating room - medical robotics at DLR (MIRO Innovation Lab)
Переглядів 1,3 тис.4 місяці тому
Find out how a bold vision became a success story! The DLR Institute of Robotics and Mechatronics has been researching robotic arms since the 1990s - originally for use in space. It was a long and ambitious journey before these lightweight robotic arms could be used on earth and finally in operating theaters, a journey that required concentrated robotics expertise, interdisciplinary cooperation...
MIRO Innovation Lab - competence center for medical robotics
Переглядів 3474 місяці тому
Welcome to the MIRO Innovation Lab! We are your experienced research partner when it comes to robotic assistance systems in medicine. We work closely with renowned clinics and industrial companies on an interdisciplinary basis. Join us and get to know our expertise, services and our modular research system! Find out more here: www.miroinnovationlab.de
ARCHES crater exploration
Переглядів 8435 місяців тому
We present the collaborative crater exploration of two planetary rover prototypes with an experiment during the ARCHES Moon analogue campaign on the volcano Mt. Etna, Italy, in 2022. On the volcano, the rovers successfully access the Cisternazza crater, a crater of approximately 150m in width and 30m in depth, featuring steep flanks of partially compacted and partially loose volcanic soil. The ...
Robotic surface finishing using automatic trajectory generation
Переглядів 1,2 тис.5 місяців тому
The video shows a novel approach on robotic surface finishing as developed in the project LEROSH (lerosh.de/) . The surface is segmented automatically according to the part geometry and feasible execution strategies are selected. The planning result can be inspected intuitively by the user through augmented reality. The automatically generated trajectories are executed by the DLR SARA (www.dlr....
Accuracy meets Safety: PID and ESP Control in Elastic Robots
Переглядів 6278 місяців тому
This work addresses the problem of global set-point control of elastic joint robots by combining elastic structure preserving (ESP) control with non-collocated integral action. Despite the popularity and extensive research on PID control for rigid joint robots, such schemes largely evaded adoption to elastic joint robots. This is mainly due to the underactuation inherent to these systems, which...
Shape Completion and Grasp Prediction for Fast and Versatile Grasping with a Multi-Fingered Hand
Переглядів 1,5 тис.11 місяців тому
Grasping objects with limited or no prior knowl- edge about them is a highly relevant skill in assistive robotics. Still, in this general setting, it has remained an open problem. Strong challenges arise from object shape diversity with only partial visibility. To address these challenges, we present a deep learning pipeline consisting of a shape completion module that is based on a single dept...
Estimator-Coupled Reinforcement Learning for Robust Purely Tactile In-Hand Manipulation
Переглядів 3,8 тис.11 місяців тому
This paper identifies the culprits of naively com- bining learning-based controllers and state estimators for robotic in-hand manipulation. Specifically, we tackle the chal- lenging task of purely tactile, goal-conditioned dextrous in- hand reorientation with the hand pointing downwards. Here, we observe that due to the limited sensing available, many control strategies that are feasible in sim...
EmPReSs - Empowerment in tomorrows`s production
Переглядів 40911 місяців тому
This video provides an overview of our recently concluded interdisciplinary research project EmPReSs that aimed at integrating human labor and AI-assisted robots in industrial assembly lines. It features the development of our Mixed-Skill concept, detailing its application in creating more adaptable and people-focused production environments. The video further outlines our efforts in assessing ...
Hybrid Force-Impedance Control for Fast End-Effector Motions
Переглядів 4,7 тис.Рік тому
This video presents a unified hybrid force-impedance framework for highly dynamic end-effector motions. The unified framework features compliant behavior in the free (motion) task directions and explicit force tracking in the constrained directions. Advantageously, the involved force subspace in contact direction is fully dynamically decoupled from dynamics in the motion subspace. Further detai...
Learning Fluid Flow Visualizations from In-Flight Images with Tufts
Переглядів 612Рік тому
To better understand fluid flows around aerial systems, strips of wire or rope, widely known as tufts, are often used to visualize the local flow direction. This paper presents a computer vision system that automatically extracts the shape of tufts from images, which have been collected during real flights of a helicopter and an unmanned aerial vehicle (UAV). As images from these aerial systems...
Mattias and EDAN winning at CYBATHLON Challenges March 2023
Переглядів 1,1 тис.Рік тому
CYBATHLON, a non-profit project of ETH Zurich, acts as a platform that challenges teams from all over the world to develop assistive technologies suitable for everyday use with and for people with disabilities. In 2023 CYBATHLON Challenges, DLR’s EDAN team won the assistant robot race with pilot Mattias Atzenhofer. #CYBATHLONChallenges #CYBATHLON #MovingPeopleAndTechnology #ForAWorldWithoutBarr...
Fusing Visual Appearance and Geometry for Multi-Modality 6DoF Object Tracking
Переглядів 2,3 тис.Рік тому
Fusing Visual Appearance and Geometry for Multi-Modality 6DoF Object Tracking
Successful Teleoperation of the Sherp-Vehicle (Demonstration of A.H.E.A.D./KI4HE/MAISHU Projects)
Переглядів 895Рік тому
Successful Teleoperation of the Sherp-Vehicle (Demonstration of A.H.E.A.D./KI4HE/MAISHU Projects)
A VR-based telepresence robot with aerial manipulation capabilities
Переглядів 2,1 тис.Рік тому
A VR-based telepresence robot with aerial manipulation capabilities
RECALL: Rehearsal-free Continual Learning for Object Classification (IROS 2022)
Переглядів 537Рік тому
RECALL: Rehearsal-free Continual Learning for Object Classification (IROS 2022)
A Multi-body Tracking Framework - From Rigid Objects to Kinematic Structures
Переглядів 6 тис.Рік тому
A Multi-body Tracking Framework - From Rigid Objects to Kinematic Structures
Iterative Corresponding Geometry - Presentation CVPR 2022
Переглядів 1,8 тис.Рік тому
Iterative Corresponding Geometry - Presentation CVPR 2022
Live Stream on 29/0622: ARCHES experiment. Analogue planetary exploration experiment on Mount Etna.
Переглядів 623Рік тому
Live Stream on 29/0622: ARCHES experiment. Analogue planetary exploration experiment on Mount Etna.
Humanoid robot David shows in-hand manipulation skills
Переглядів 8 тис.2 роки тому
Humanoid robot David shows in-hand manipulation skills
The Time Domain Passivity Approach for High Delays (TDPA-HD): Experiments with 3s Roundtrip-Delay
Переглядів 7132 роки тому
The Time Domain Passivity Approach for High Delays (TDPA-HD): Experiments with 3s Roundtrip-Delay
Iterative Corresponding Geometry (ICG) - Highly Efficient 3D Object Tracking - CVPR 2022
Переглядів 4,5 тис.2 роки тому
Iterative Corresponding Geometry (ICG) - Highly Efficient 3D Object Tracking - CVPR 2022
A Model for Multi-View Residual Covariances based on Perspective Deformation
Переглядів 4212 роки тому
A Model for Multi-View Residual Covariances based on Perspective Deformation
IROS 2021 Analyzing the Performance Limits of Articulated Soft Robots based on the ESPi Framework
Переглядів 1,8 тис.2 роки тому
IROS 2021 Analyzing the Performance Limits of Articulated Soft Robots based on the ESPi Framework
Christmas Special: 'The Common Justin' (Mockumentary)
Переглядів 3,8 тис.2 роки тому
Christmas Special: 'The Common Justin' (Mockumentary)
Das Institut für Robotik und Mechatronik am DLR
Переглядів 2,4 тис.2 роки тому
Das Institut für Robotik und Mechatronik am DLR
as cool as this is, wouldn't it be easier to build bespoke tools for robots vs. building robots to use human tools?
Im sorry Dave. Im afraid i cant do that.
E eu pensando que ele iria demolir o bloco com um soco...
Esse e zica hein 😅😅😅 Onde compra ?😅😅😅
Been a few years, DLR doing anything new?
This guy is soooo slooow ... also precision is not sufficient, driller is put to one spot at the beginning and when the drill beginns the driller scratches a little bit over the surface ( an error that humans also do in the beginning ) ...but a robot should be more precise just like automotive production robot arms! Naahh ..... but thank you for your demo. Personally i prefer Teslabot , or Boston Dynmamics Atlas, or Sanctuary AI, etc, etc...
We're all SCREWED!🪛
Whow. That robot looks SO complicated - compared to what we have now ready to be sold.
slower than my grandma
They took our jobs!!!
Slower than a dead human. Must try harder.
Grandfather of the new Atlas 🙂
Will fuzzy logic or something similar work ? May be an enhanced. modified or mixed fuzzy logic ?
tfw a robot 6 years ago could do something you feel incapable of doing.
here comes the yt algorithm. robot takeover
he's so gentle
He?
Fantastic engineering work !
America goes for the full monty, American adquisition 🇦🇷
old techno ... obsolete
It's amazing to me that animals including ourselves have an intuitive sense of COM and Balance, through learned behavior as a result of both trial and error in our lives (growing up, falling down) but also as a species evolutionarily. Whats even more fascinating is how we've learned to simulation fluid movement through inverted kinematic models, solving for an end effector; essentially bypassing the millions of years it took to build up that muscle mind intuition that we have. I presume more advanced robots will use machine learning and complex neural algorithms for movement instead... But we shall see! Incredible work.
Hanzhen harmonic drive gear , strain wave reducer, robot joint, over 30 years experience
Hanzhen harmonic drive gear , strain wave reducer, robot joint , over 30 years experience
Anyone who can code our robots to balance like this is HIRED!
Next FEM bot
Wonderful work of the DLR! Congratulations.
is the variable stiffness implemented in the software ?
No, it's realized in hardware...
.
.
2:59...lol
This is proof that robots are so far from being better than human labor.
Well, look at all the automated factories. Most of the things that are repeatable and need to be done in large numbers are already automated. More and more more sophisticated jobs will be automated at some point as well. If you look at something like dall-e, art could be one of the next areas that will be more automated.
Now make the drill weigh 200 kg , find a place like a mine where a humanoid body type is needed because of its manoeuvring skill , suddenly the droid may save the day , our bodies cannot drill endlessly
@@IONACOMPUTERS Autonomous robots vs Human Controlled **
@@renanmonteirobarbosa5761 I do not think so 😂 from now on we are really damn fast in optimization of these kind of problems give them 8years the world we know of will be upside down
Three years later and every week it seems there's a new humanoid robot company releasing jaw dropping videos of autonomous operation. See 1x, figure ai, astribot, and sanctuary to name just a few.
Could i use this footage for a video promoting the futur jobs of telesurgery ?
bullshit, this robot is a shame, lot of money and a millionare budget just for this crap? just take a look to the channel of Dr Guero, he work alone, with his own resources, and make a robot QUITE GOOD THAN THIS CRAP, is a small robot that WALK LIKE A REAL HUMAN, LIFT LOTTT OF WEIGHT, MAKE GYMNASTIC EXCERCICES, DANCE CLASIC BALLET LIKE BARISHNIKHOV, EVEN DANCE A VALS WITH A BARBIE DOLL, just take a look to the work of Dr Guero, IS AWESOME, this robots and the robots of honda or other clown are just crap
My mother would shit herself if she would See that robot comeing around the corner
I'm a bit confused. The name says the device is autonomous, but the description says it is remote controlled, and the video shows drivers inside the vehicle. Which one is it? Looks cool though.
The video shows drivers inside the vehicle because it was taken as part of driver training. The device is not autonomous yet, the development of the tele-operation is the goal of the project which was launched 21st October.
He dresses better than I do
What type of algorithm do they use to keep it balancing properly?
ua-cam.com/video/AxbokJO2pMI/v-deo.html
Thanks for the information, may be useful for my designs ua-cam.com/video/1SGB_tFqUgw/v-deo.html
That is one expensive hole..
Looks like Baymax lost weight and has the blues.
80% similar to Atlas, Good job!
110th Approved !!!
What model of robot arm is that? I like the moving base.
Let me know, How you fix shoulder rotation in 3 axis. ?
Can you explain /why/ camera are not a solution?
Pretty cool!
So you guys need to build the 3D model of the target scenario every single time, right? What about having cameras strategically pointing to the target, fixed or mounted on the manipulator, and a master-slave wireless chain between two twin robots, master for the operator (holding the grasp) and the slave doing the work? Joysticks are kind of ..mmm.. difficult..and need training.
What if he took his pilot? ua-cam.com/video/Z392_rf26HY/v-deo.html