1,065 Hits in 6.6 sec

Humanoid Robot Motion Recognition and Reproduction

Rawichote Chalodhorn, Karl F. MacDorman, Minoru Asada
2009 Advanced Robotics  
Thus, an important goal is to develop a humanoid robot that can learn to perform complex tasks by itself. This paper proposes a method to recognize and regenerate motion in a humanoid robot.  ...  Humanoid robots have become appealing to the research community because of their potential versatility. However, traditional programming approaches may not reveal their full capabilities.  ...  Recently, robotics researchers have succeeded in developing mechanical platforms for humanoid robots. These robots can walk and perform simple tasks.  ... 
doi:10.1163/156855308x397569 fatcat:aqae2thevnhudmnnksrx2irbxu

Robust Biped Locomotion Using Deep Reinforcement Learning on Top of an Analytical Control Approach [article]

Mohammadreza Kasaei, Miguel Abreu, Nuno Lau, Artur Pereira, Luis Paulo Reis
2021 arXiv   pre-print
Furthermore, a learning framework is developed based on Genetic Algorithm (GA) and Proximal Policy Optimization (PPO) to find the optimum parameters and to learn how to improve the stability of the robot  ...  This paper proposes a modular framework to generate robust biped locomotion using a tight coupling between an analytical walking approach and deep reinforcement learning.  ...  [30] developed a hybrid CPG-ZMP controller to generate stable locomotion for humanoid robots.  ... 
arXiv:2104.10592v1 fatcat:ulkxmgotivdsrjdnysqimer7b4

Dynamic Walking: Toward Agile and Efficient Bipedal Robots [article]

Jenna Reher, Aaron D. Ames
2020 arXiv   pre-print
Dynamic walking on bipedal robots has evolved from an idea in science fiction to a practical reality.  ...  In this context, this review article outlines the end-to-end process of methods which have proven effective in the literature for achieving dynamic walking on bipedal robots.  ...  ACKNOWLEDGMENTS The authors would like to thank the members of AMBER Lab whom have contributed to the understanding of robotic walking summarized in this paper.  ... 
arXiv:2010.07451v1 fatcat:rdnhz65amne3hbqvew6pd7qtd4

Imitation of Dynamic Walking with BSN for a Humanoid Robot

Krittameth Teachasrisaksakul, Zhiqiang Zhang, Guang-Zhong Yang, Benny Lo
2015 IEEE journal of biomedical and health informatics  
This paper proposes a strategy for imitating dynamic walking gait for a humanoid robot by formulating the problem as an optimization process.  ...  The method is validated using a NAO humanoid robot, with results demonstrating the effectiveness of the proposed strategy for dynamic walking.  ...  Therefore, the optimization framework is able to reproduce robot walking that is similar to human walking.  ... 
doi:10.1109/jbhi.2015.2425221 pmid:25935051 fatcat:2fdp4idurjaf5iwy5w24gu6jyy

Stochastic optimization of bipedal walking using gyro feedback and phase resetting

Felix Faber, Sven Behnke
2007 2007 7th IEEE-RAS International Conference on Humanoid Robots  
We present a method to optimize the walking pattern of a humanoid robot for forward speed using suitable metaheuristics.  ...  We selected the extended PGRL algorithm to optimize the gait of a real robot. After optimization, the robot is able to walk significantly faster.  ...  INTRODUCTION Enabling a humanoid robot to walk fast and stable is nontrivial. Such robots are highly complex, non-linear dynamical systems that are hard to control.  ... 
doi:10.1109/ichr.2007.4813869 dblp:conf/humanoids/FaberB07 fatcat:cupjvaqidbalxaic542vpmu6ji

Efficient Walking Speed Optimization of a Humanoid Robot

T. Hemker, M. Stelzer, O. von Stryk, H. Sakamoto
2009 The international journal of robotics research  
The development of optimized motions of humanoid robots that guarantee a fast and also stable walking is an important task especially in the context of autonomous soccer playing robots in RoboCup.  ...  quadratic programming to search for a fast and stable walking motion.  ...  Conclusion For the newly developed, 55 cm tall autonomous humanoid robot prototype HR18 a hardware-in-the-loop walking optimization approach has been presented.  ... 
doi:10.1177/0278364908095171 fatcat:zz2eyscm3nht7mhcis4jt3qusi

Using eigenposes for lossless periodic human motion imitation

Rawichote Chalodhorn, Rajesh P. N. Rao
2009 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Programming a humanoid robot to perform an action that takes the robot's complex dynamics into account is a challenging problem.  ...  Training using human motion capture is an intuitive and flexible approach to programming a robot but directly applying motion capture data to a robot usually results in dynamically unstable motion.  ...  Our previous work [18] demonstrated that the proposed approach allows a humanoid robot to learn to walk based solely on human motion capture without the need for a detailed physical model of the robot  ... 
doi:10.1109/iros.2009.5354391 dblp:conf/iros/ChalodhornR09 fatcat:zhg3b7a23bca7auxi6gqdlfmdu

Humanoids [chapter]

Paul Fitzpatrick, Kensuke Harada, Charles C. Kemp, Yoshio Matsumoto, Kazuhito Yokoi, Eiichi Yoshida
2016 Springer Handbook of Robotics  
Researchers have also developed specialized methods for generating stable robot motion while an object is being manipulated [67.46, 65, 68-70] .  ...  The ZMP can be used to plan walking patterns that make the robot dynamically stable while walking.  ... 
doi:10.1007/978-3-319-32552-1_67 fatcat:xgkavbgzmbae7mo4wjdrmivkdu

Modular software architecture for teams of cooperating, heterogeneous robots

Martin Friedmann, Jutta Kiener, Sebastian Petters, Dirk Thhomas, Oskar von Stryk
2006 2006 IEEE International Conference on Robotics and Biomimetics  
The application to teams of cooperating small and medium size humanoid robots is investigated in this paper. Scenarios for inter robot communication and cooperative task accomplishment are described.  ...  For teams of cooperating autonomous lightweight robots with challenging dynamical locomotion properties a platform independent modular software architecture and platform independent modules for sensor  ...  The walking motions have been optimized regarding to stability and walking speed by varying the controlling parameters, e.g. step length and pitch angle in the upper body etc., in a hardware-in-the-loop  ... 
doi:10.1109/robio.2006.340270 dblp:conf/robio/FriedmannKPTS06 fatcat:mwxpovkjwfeuhi74mph24rtoky

Automatic task-specific model reduction for humanoid robots

Umashankar Nagarajan, Katsu Yamane
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
It also presents an optimization framework that uses the auto-generated taskspecific reduced models to control humanoid robots.  ...  This paper presents an automatic model reduction procedure for humanoid robots, which is task-specific.  ...  Moreover, an optimization framework was presented that empowers the reduced models to be used for control of humanoid robots.  ... 
doi:10.1109/iros.2013.6696720 dblp:conf/iros/NagarajanY13 fatcat:qfk6zftnvrguffbonyy45gvlou

Bio-Inspired Optimal Control Framework to Generate Walking Motions for the Humanoid Robot iCub Using Whole Body Models

Yue Hu, Katja Mombaur
2018 Applied Sciences  
In an approach that is situated between whole-body optimization and motion generation by reduced models, optimization of template models has been used for generating walking motion of humanoid robots in  ...  As motions in nature are often considered as optimal with respect to certain criteria, in this work, we present an optimal control-based approach that allows us to generate optimized walking motions using  ...  We wish to thank the Simulation and Optimization group of H. G. Bock at the Heidelberg University for providing the optimal control code MUSCOD.  ... 
doi:10.3390/app8020278 fatcat:7hdc33mrmfdtpm4frne5zes37u

Learning to Imitate Human Actions through Eigenposes [chapter]

Rawichote Chalodhorn, Rajesh P. N. Rao
2010 Studies in Computational Intelligence  
Programming a humanoid robot to perform an action that takes into account the robot's complex dynamics is a challenging problem.  ...  An inverse mapping that maps optimized eigenpose data from the low-dimensional subspace back to the original joint space is then used to generate motion on the robot.  ...  This work was supported by National Science Foundation (NSF) grant 0622252, the Office of Naval Research (ONR) Cognitive Science program, and a Packard Fellowship to RPNR.  ... 
doi:10.1007/978-3-642-05181-4_15 fatcat:bcmdujf5araurmavhi5sq3aem4

Special issue on whole-body control of contacts and dynamics for humanoid robots

Serena Ivaldi, Jan Babič, Michael Mistry, Robin Murphy
2016 Autonomous Robots  
Sometimes, like when reaching for a distant object or standing inside a moving bus that suddenly brakes, humans plan intentionally new contacts to preserve their balance and avoid falling.  ...  Whether you are walking on a concrete floor, standing on a carpet, or sitting on a soft chair, your entire body continuously controls the posture and the contact forces that are produced by acting on rigid  ...  He is broadly interested in human motion and humanoid robotics.  ... 
doi:10.1007/s10514-016-9545-5 fatcat:svbsz5d5obe5fossx6fkymb57a

Passivity-Based Full-Body Force Control for Humanoids and Application to Dynamic Balancing and Locomotion

Sang-ho Hyon, Gordon Cheng
2006 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems  
With this framework, we introduce gravity compensation at the lowest layer of the controller that makes the closed-loop system passive with respect to additional inputs as well as external forces.  ...  This paper proposes a passivity-based hierarchical full-body motion controller for force-controllable multi-DOF humanoid robots.  ...  The robot does not fall, but walks to the direction of the external force. This is an externally-driven-walking, demonstrating the passivity of the closed-loop system.  ... 
doi:10.1109/iros.2006.282450 dblp:conf/iros/HyonC06 fatcat:g7u3hwzrtjfxbfbqydms3gqprq

Humanoid Robot Balance Control Using the Spherical Inverted Pendulum Mode

Ahmed Elhasairi, Alexandre Pechev
2015 Frontiers in Robotics and AI  
However, biped humanoid robots are far from exhibiting similar skills. This is mainly due to the limitations in the current control and modeling techniques used in humanoid robots.  ...  the humanoid robot.  ...  Table 1 shows the parameters of the humanoid robot used in the simulations. Figure 3 shows the closed-loop system response for the different disturbances.  ... 
doi:10.3389/frobt.2015.00021 fatcat:yduuxhcghffzjfeupuketzwrly
« Previous Showing results 1 — 15 out of 1,065 results