NimbRo-OP2X: Adult-Sized Open-Source 3D Printed Humanoid Robot

@article{Ficht2018NimbRoOP2XAO,
  title={NimbRo-OP2X: Adult-Sized Open-Source 3D Printed Humanoid Robot},
  author={Grzegorz Ficht and Hafez Farazi and Andr{\'e} Brandenburger and Diego Rodriguez and Dmytro Pavlichenko and Philipp Allgeuer and Mojtaba Hosseini and Sven Behnke},
  journal={2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)},
  year={2018},
  pages={1-9}
}
  • G. Ficht, H. Farazi, +5 authors Sven Behnke
  • Published 19 October 2018
  • Computer Science
  • 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)
Humanoid robotics research depends on capable robot platforms, but recently developed advanced platforms are often not available to other research groups, expensive, dangerous to operate, or closed-source. [...] Key Method Our robot is equipped with a fast onboard computer and a GPU to accelerate parallel computations. We extend our already open-source software by a deep-learning based vision system and gait parameter optimisation. The NimbRo-OP2X was evaluated during RoboCup 2018 in Montreál, Canada, where it…Expand
NimbRo-OP2X: Affordable Adult-sized 3D-printed Open-Source Humanoid Robot for Research
TLDR
The NimbRo-OP2X is presented, a capable and affordable adult-sized humanoid platform aiming to significantly lower the entry barrier for humanoid robot research and won all possible awards at RoboCup 2018.
Real-time Pose Estimation from Images for Multiple Humanoid Robots
TLDR
This paper examines different state of the art pose estimation models and proposes a lightweight model that can work in real-time on humanoid robots in the RoboCup Humanoid League environment and presents a novel dataset called the HumanoidRobotPose dataset.
DeepWalk: Omnidirectional Bipedal Gait by Deep Reinforcement Learning
TLDR
This paper proposes a novel DRL approach that enables an agent to learn omnidirectional locomotion for humanoid (bipedal) robots by introducing a new curriculum learning method that gradually increases the task difficulty by scheduling target velocities.
A comprehensive survey on humanoid robot development
TLDR
This review paper is presented to show variations in the requirements, design, and development process and also proposes a taxonomy of existing humanoid robots, aimed at demonstrating a general perspective ofexisting humanoid robots’ characteristics and applications.
Mapless Humanoid Navigation Using Learned Latent Dynamics
TLDR
A novel Deep Reinforcement Learning approach to address the mapless navigation problem, in which the locomotion actions of a humanoid robot are taken online based on the knowledge encoded in learned models.
NimbRo Robots Winning RoboCup 2018 Humanoid AdultSize Soccer Competitions
TLDR
This paper presents the software and hardware designs that led the team NimbRo to win the competitions in the AdultSize league—including the soccer tournament, the drop-in games, and the technical challenges at RoboCup 2018 in Montreal, and describes the deep-learning approaches for visual perception and the new fully 3D printed robot Nimb Ro-OP2X.
A Review Study of the 3-D Printing Techniques utilized in Developing Humanoid Robot
Research in the field of 3-D printing in humanoid robot is trending. Ranging from the designing of the structure of the robot, stability of the structure, material to be used, actuators, sensors,
RoboCup 2019 AdultSize Winner NimbRo: Deep Learning Perception, In-Walk Kick, Push Recovery, and Team Play Capabilities
TLDR
The latest developments that lead team NimbRo to win the soccer tournament, drop-in games, technical challenges and the Best Humanoid Award of the RoboCup Humanoid League 2019 in Sydney are presented.
RoboCup 2019 AdultSize Winner NimbRo: Deep Learning Perception, In-Walk Kick, Push Recovery, and Team Play Capabilities
TLDR
The latest developments that lead team NimbRo to win the soccer tournament, drop-in games, technical challenges and the Best Humanoid Award of the RoboCup Humanoid League 2019 in Sydney are presented.
RoboCup: A Treasure Trove of Rich Diversity for Research Issues and Interdisciplinary Connections [TC Spotlight]
TLDR
The challenging goal of RoboCup has been expanded to include teams of rescue robots, those that service humans at home or in manufacturing tasks, and robotics soccer, rescue, and dancing motion challenges for educating children.
...
1
2
3
...

References

SHOWING 1-10 OF 35 REFERENCES
NimbRo-OP2: Grown-up 3D printed open humanoid platform for research
TLDR
This work introduces NimbRo-OP2, an affordable, fully open-source platform in terms of both hardware and software that is not only capable of interacting in an environment meant for humans, but also easy and safe to operate and does not require a gantry when doing so.
Child-sized 3D printed igus humanoid open platform
TLDR
The igus® Humanoid Open Platform is presented - a new, affordable, versatile and easily customisable standard platform for humanoid robots in the child-sized range, equipped with enough torque and computing power to foster research in many possible directions.
Humanoid TeenSize Open Platform NimbRo-OP
TLDR
The NimbRo-OP robot was designed to be easily manufactured, assembled, repaired, and modified, and is equipped with a wide-angle camera, ample computing power, and enough torque to enable full-body motions, such as dynamic bipedal locomotion, kicking, and getting up.
Deep visual foresight for planning robot motion
TLDR
This work develops a method for combining deep action-conditioned video prediction models with model-predictive control that uses entirely unlabeled training data and enables a real robot to perform nonprehensile manipulation — pushing objects — and can handle novel objects not seen during training.
A ROS-based Software Framework for the NimbRo-OP Humanoid Open Platform
TLDR
A software framework for the NimbRo-OP that is based on the Robot Operating System (ROS) middleware is described, which provides functionality for hardware abstraction, visual perception, and behavior generation, and has been used to implement basic soccer skills.
Grown-Up NimbRo Robots Winning RoboCup 2017 Humanoid AdultSize Soccer Competitions
TLDR
The mechatronic design of the upgraded robot Copedo and the newly developed NimbRo-OP2 is presented, including improved approaches to visual perception of the game situation, including compassless localization on a soccer field with symmetric appearance, and the generation of soccer behaviors.
Valkyrie: NASA's First Bipedal Humanoid Robot
TLDR
A brief system overview is presented, detailing Valkyrie's mechatronic subsystems, followed by a summarization of the inverse kinematics-based walking algorithm employed at the Trials, and some closing remarks are given about the competition.
Humanoid robotics platforms developed in HRP
Humanoid robots learning to walk faster: from the real world to simulation and back
TLDR
GSL is introduced, an iterative optimization framework for speeding up robot learning using an imperfect simulator, and is fully implemented and validated on the task of learning to walk using an Aldebaran Nao humanoid robot.
Detection and Localization of Features on a Soccer Field with Feedforward Fully Convolutional Neural Networks ( FCNN ) for the Adult-Size Humanoid Robot Sweaty
For the RoboCup Soccer AdultSize League the humanoid robot Sweaty uses a single fully convolutional neural network to detect and localize the ball, opponents and other features on the field of play.
...
1
2
3
4
...