Filters








341 Hits in 2.9 sec

Reinforcement Learning Algorithms in Humanoid Robotics [chapter]

Dusko Katic, Miomir Vukobratovic
2007 Humanoid Robots: New Developments  
In spite of a significant progress and accomplishments achieved in the design of a hardware platform of humanoid robot and synthesis of advanced intelligent control of humanoid robots, a lot of work has  ...  Finally, one ought to point out that the problem of motion of humanoid robots is a very complex control task, especially when the real environment is taken into account, requiring as a minimum, its integration  ...  Aleksandar Rodi for generation of experimental data and realization of humanoid robot modeling and trajectory generation software.  ... 
doi:10.5772/4878 fatcat:brp43tnj35c2lmalaawtv5gv6u

Benchmarking Deep Reinforcement Learning for Continuous Control [article]

Yan Duan, Xi Chen, Rein Houthooft, John Schulman, Pieter Abbeel
2016 arXiv   pre-print
We report novel findings based on the systematic evaluation of a range of implemented reinforcement learning algorithms.  ...  Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning.  ...  Acknowledgements We thank Emo Todorov and Yuval Tassa for providing the MuJoCo simulator, and Sergey Levine, Aviv Tamar, Chelsea Finn, and the anonymous ICML reviewers for insightful comments.  ... 
arXiv:1604.06778v3 fatcat:lceiaesdbvallnt57nbxp7b42q

Emergence of human-comparable balancing behaviours by deep reinforcement learning

Chuanyu Yang, Taku Komura, Zhibin Li
2017 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)  
This paper presents a hierarchical framework based on deep reinforcement learning that learns a diversity of policies for humanoid balance control.  ...  The successful emergence of humanlike behaviors through deep reinforcement learning proves the feasibility of using an AI-based approach for learning humanoid balancing control in a unified framework.  ...  Researchers in the computer science and robotics community have published a few papers on using deep reinforcement learning for humanoid motion control.  ... 
doi:10.1109/humanoids.2017.8246900 dblp:conf/humanoids/YangKL17 fatcat:zak7o5wsfvbujk6tflxawqqnee

SURVEY OF INTELLIGENT CONTROL ALGORITHMS FOR HUMANOID ROBOTS

Dusko Katić, Miomir Vukobratović
2005 IFAC Proceedings Volumes  
algorithms) in the area of humanoid robotic systems.  ...  This paper focusses on the application of intelligent control techniques (neural networks, fuzzy logic and genetic algorithms) and their hybrid forms (neuro-fuzzy networks, neuro-genetic and fuzzy-genetic  ...  In this case, the gait synthesizer with reinforcement learning is based on a modified GARIC (Generalized Approximate Reasoning for Intelligent Control) method.  ... 
doi:10.3182/20050703-6-cz-1902.01276 fatcat:wrzes2vitbf4rkkfn3c6evxuxe

Emergence of Human-comparable Balancing Behaviors by Deep Reinforcement Learning [article]

Chuanyu Yang, Taku Komura, Zhibin Li
2018 arXiv   pre-print
This paper presents a hierarchical framework based on deep reinforcement learning that learns a diversity of policies for humanoid balance control.  ...  The successful emergence of human-like behaviors through deep reinforcement learning proves the feasibility of using an AI-based approach for learning humanoid balancing control in a unified framework.  ...  Researchers in the computer science and robotics community have published a few papers on using deep reinforcement learning for humanoid motion control.  ... 
arXiv:1809.02074v1 fatcat:255popwpubgubocofmlakqrzve

Obtaining Humanoid Robot Controller Using Reinforcement Learning [chapter]

Masayoshi Kanoh, Hidenori Itoh
2007 Humanoid Robots: New Developments  
We therefore apply reinforcement learning for the control of humanoid robots because this process resembles a human's trial and error learning process.  ...  They are suitable for off-line learning, but not adequate for on-line learning.  ...  Obtaining Humanoid Robot Controller Using Reinforcement Learning, Humanoid Robots: New Developments, Armando Carlos de Pina Filho (Ed.), ISBN: 978-3-902613-00-4, InTech, Available from: http://www.intechopen.com  ... 
doi:10.5772/4877 fatcat:riaschf3rzbb3n3t55zw7mdzfy

Recent Advances in Deep Reinforcement Learning Applications for Solving Partially Observable Markov Decision Processes (POMDP) Problems: Part 1—Fundamentals and Applications in Games, Robotics and Natural Language Processing

Xuanchen Xiang, Simon Foo
2021 Machine Learning and Knowledge Extraction  
The first part of a two-part series of papers provides a survey on recent advances in Deep Reinforcement Learning (DRL) applications for solving partially observable Markov decision processes (POMDP) problems  ...  In this overview, we introduce Markov Decision Processes (MDP) problems and Reinforcement Learning and applications of DRL for solving POMDP problems in games, robotics, and natural language processing  ...  [114] presented a comprehensive survey for learning control in robotics from reinforce to imitation in 2018.  ... 
doi:10.3390/make3030029 fatcat:u3y7bqkoljac5not2eq5konnnm

ADHERENT: Learning Human-like Trajectory Generators for Whole-body Control of Humanoid Robots

Paolo Maria Viceconte, Raffaello Camoriano, Giulio Romualdi, Diego Ferigo, Stefano Dafarra, Silvio Traversaro, Giuseppe Oriolo, Lorenzo Rosasco, Daniele Pucci
2022 IEEE Robotics and Automation Letters  
trajectories for humanoid robots.  ...  Recently, research in computer graphics investigated machinelearning methods for character animation based on training human-like models directly on motion capture data.  ...  Another recent research stream focuses on reinforcement learning (RL) for dynamic character control.  ... 
doi:10.1109/lra.2022.3141658 fatcat:275cp35vtbeezau3iwa3nwtoey

Practical bipedal walking control on uneven terrain using surface learning and push recovery

Seung-Joon Yi, Byoung-Tak Zhang, D. Hong, D. D. Lee
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We use a physically realistic simulation with an articulated robot model and reinforcement learning algorithm to train the push recovery controller, and implement the learned controller on a commercial  ...  DARwIn-OP small humanoid robot.  ...  In our former works, we have suggested practical methods to handle each problems for generic humanoid robots [20] , [21] .  ... 
doi:10.1109/iros.2011.6048731 fatcat:yymaa7qtznhv3lhm33jfxlnxkq

Practical bipedal walking control on uneven terrain using surface learning and push recovery

Seung-Joon Yi, Byoung-Tak Zhang, Dennis Hong, Daniel D. Lee
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We use a physically realistic simulation with an articulated robot model and reinforcement learning algorithm to train the push recovery controller, and implement the learned controller on a commercial  ...  DARwIn-OP small humanoid robot.  ...  In our former works, we have suggested practical methods to handle each problems for generic humanoid robots [20] , [21] .  ... 
doi:10.1109/iros.2011.6095131 dblp:conf/iros/YiZHL11 fatcat:zlylppy6nze6ddpc3emn3syn4a

Robust Dynamic Locomotion via Reinforcement Learning and Novel Whole Body Controller [article]

Donghyun Kim, Jaemin Lee, Luis Sentis
2017 arXiv   pre-print
Our locomotion strategy relies on devising a reinforcement learning (RL) approach for robust walking.  ...  We propose a robust dynamic walking controller consisting of a dynamic locomotion planner, a reinforcement learning process for robustness, and a novel whole-body locomotion controller (WBLC).  ...  ACKNOWLEDGMENT The authors would like to thank the members of the Human Centered Robotics Laboratory at The University of Texas at Austin for their great help and support.  ... 
arXiv:1708.02205v1 fatcat:w3ltjoku6fg6nkul35263iq3o4

Hierarchical Skills for Efficient Exploration [article]

Jonas Gehring, Gabriel Synnaeve, Andreas Krause, Nicolas Usunier
2021 arXiv   pre-print
In previous work on continuous control, the sensitivity of methods to this trade-off has not been addressed explicitly, as locomotion provides a suitable prior for navigation tasks, which have been of  ...  In our experiments, we show that our approach performs this trade-off effectively and achieves better results than current state-of-the-art methods for end- to-end hierarchical reinforcement learning and  ...  Acknowledgements: We thank Alessandro Lazaric for insightful discussions, and Franziska Meier, Ludovic Denoyer, and Kevin Lu for helpful feedback on early versions of this paper.  ... 
arXiv:2110.10809v1 fatcat:26d3laqcrzc45k6omuoskbzife

Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion [article]

Changxin Huang, Guangrun Wang, Zhibo Zhou, Ronghui Zhang, Liang Lin
2021 arXiv   pre-print
In this work, we propose a novel reward-adaptive reinforcement learning for biped locomotion, allowing the control policy to be simultaneously optimized by multiple criteria using a dynamic mechanism.  ...  Recent works have demonstrated the effectiveness of deep reinforcement learning (DRL) for simulation and physical robots.  ...  control for biped robot via ddpg-based deep reinforcement learning,” in [9] K. Zhang, Z. Hou, C. W. de Silva, H. Yu, and C.  ... 
arXiv:2107.01908v2 fatcat:ey2t3vncprayzmvh2h3otk7hru

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.  ...  Combination of CPG-ZMP based walking and ML algorithms Massah et al. [30] developed a hybrid CPG-ZMP controller to generate stable locomotion for humanoid robots.  ... 
arXiv:2104.10592v1 fatcat:ulkxmgotivdsrjdnysqimer7b4

Special Feature on Bio-Inspired Robotics

Toshio Fukuda, Fei Chen, Qing Shi
2018 Applied Sciences  
Acknowledgments: This special issue receives technical support by IEEE Robotics and Automation Society (RAS) Technical Committee on Neuro-Robotics Systems, and Technical Committee on Cyborg and Bionic  ...  Systems and IEEE Systems, Man, and Cybernetics Society (SMC) Technical Committee on Bio-Mechatronics and Bio-Robotics Systems.  ...  They develop an angular momentum control method based on human motion for a humanoid upper body.  ... 
doi:10.3390/app8050817 fatcat:umcpvvryxbfnvlmwvlcmsynj3q
« Previous Showing results 1 — 15 out of 341 results