2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)最新文献_第3页

Teaching robots the use of human tools from demonstration with non-dexterous end-effectors 通过演示非灵巧末端执行器，教机器人使用人类工具

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363586

Wenbin Li, Mario Fritz

引用次数: 18

Differential dynamic programming with temporally decomposed dynamics 具有时间分解动力学的微分动态规划

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363430

Akihiko Yamaguchi, C. Atkeson

{"title":"Differential dynamic programming with temporally decomposed dynamics","authors":"Akihiko Yamaguchi, C. Atkeson","doi":"10.1109/HUMANOIDS.2015.7363430","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363430","url":null,"abstract":"We explore a temporal decomposition of dynamics in order to enhance policy learning with unknown dynamics. There are model-free methods and model-based methods for policy learning with unknown dynamics, but both approaches have problems: in general, model-free methods have less generalization ability, while model-based methods are often limited by the assumed model structure or need to gather many samples to make models. We consider a temporal decomposition of dynamics to make learning models easier. To obtain a policy, we apply differential dynamic programming (DDP). A feature of our method is that we consider decomposed dynamics even when there is no action to be taken, which allows us to decompose dynamics more flexibly. Consequently learned dynamics become more accurate. Our DDP is a first-order gradient descent algorithm with a stochastic evaluation function. In DDP with learned models, typically there are many local maxima. In order to avoid them, we consider multiple criteria evaluation functions. In addition to the stochastic evaluation function, we use a reference value function. This method was verified with pouring simulation experiments where we created complicated dynamics. The results show that we can optimize actions with DDP while learning dynamics models.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116322958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 31

A robust linear MPC approach to online generation of 3D biped walking motion 三维双足行走运动在线生成的鲁棒线性MPC方法

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363423

C. Brasseur, Alexander Sherikov, C. Collette, Dimitar Dimitrov, Pierre-Brice Wieber

{"title":"A robust linear MPC approach to online generation of 3D biped walking motion","authors":"C. Brasseur, Alexander Sherikov, C. Collette, Dimitar Dimitrov, Pierre-Brice Wieber","doi":"10.1109/HUMANOIDS.2015.7363423","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363423","url":null,"abstract":"A crucial part in biped walking motion generation is to ensure dynamic feasibility, which takes the form of a nonlinear constraint in the general case. Our proposition is to bound the nonlinear part of the dynamic feasibility constraint between some properly chosen extreme values. Making sure that this constraint is satisfied for the extreme values guarantees its satisfaction for all possible values in between. This follows a classical approach from robust nonlinear control theory, which is to consider a nonlinear dynamical system as a specific selection of a time-invariant Linear Differential Inclusion. As a result, dynamic feasibility can be imposed by using only linear constraints, which can be included in an efficient linear MPC scheme, to generate 3D walking motions online. Our simulation results show two major achievements: 1) walking motions over uneven ground such as stairs can be generated online, with guaranteed kinematic and dynamic feasibility, 2) walking on flat ground is significantly improved, with a 3D motion of the CoM closely resembling the one observed in humans.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"2674 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121934410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 94

IK-Map: An enhanced workspace representation to support inverse kinematics solvers IK-Map:一个增强的工作空间表示，以支持逆运动学求解器

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363443

N. Vahrenkamp, D. Muth, P. Kaiser, T. Asfour

引用次数: 13

Design & evaluation of a sensor minimal gait phase and situation detection Algorithm of Human Walking 人类步行传感器最小步态相位与态势检测算法的设计与评价

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363517

J. Schuy, T. Mielke, M. Steinhausen, P. Beckerle, S. Rinderknecht

引用次数: 5

Online impedance parameter tuning for compliant biped balancing 柔性双足平衡的在线阻抗参数调谐

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363553

Emmanouil Spyrakos-Papastavridis, Navvab Kashiri, Jinoh Lee, N. Tsagarakis, D. Caldwell

{"title":"Online impedance parameter tuning for compliant biped balancing","authors":"Emmanouil Spyrakos-Papastavridis, Navvab Kashiri, Jinoh Lee, N. Tsagarakis, D. Caldwell","doi":"10.1109/HUMANOIDS.2015.7363553","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363553","url":null,"abstract":"This paper describes a technique aimed at the online active impedance regulation of compliant humanoid robots, for the purpose of maintaining balance. The presence of passive elastic elements in their drives leads to under-actuation, thereby rendering the control of compliant robots a rather intricate task. Consequently, the impedance regulation procedure proposed in this paper accounts for these elastic elements. In order to acquire an indication of the robot's state of balance in an online fashion, an energy (Lyapunov) function is introduced, whose sign then allows one to determine whether the robot is converging to or diverging from, a desired equilibrium position. This function's derivative reveals the energy-injecting nature of the active stiffness regulation, while it attests to the fact that active damping regulation has no effect on the system's stability properties. Furthermore, the notion of the velocity margin is described as a velocity beyond which the system might lose its balance, or below which it will be guaranteed to remain stable. As a result, the impedance optimization procedure's functionality relies upon the use of bounds that have been defined based on the energy function's derivative, in addition to the velocity margin. A series of experiments carried out using the COmpliant huMANoid (COMAN), demonstrates the superior balancing results acquired when using the proposed scheme, as compared to utilizing controllers possessing constant impedance parameters.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125836436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Base position planning for dual-arm mobile manipulators performing a sequence of pick-and-place tasks 执行一系列取放任务的双臂移动机械臂基座位置规划

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363551

K. Harada, Tokuo Tsuji, K. Kikuchi, K. Nagata, H. Onda, Y. Kawai

引用次数: 14

A comparison of contact distribution representations for learning to predict object interactions 用于学习预测物体相互作用的接触分布表示的比较

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363435

Simon Leischnig, Stefan Luettgen, Oliver Kroemer, Jan Peters

引用次数: 5

MuJoCo HAPTIX: A virtual reality system for hand manipulation MuJoCo HAPTIX:用于手部操作的虚拟现实系统

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363441

Vikash Kumar, E. Todorov

引用次数: 91

Configurable autonomy applicable to humanoid manipulation in unstructured and communication-limited environment 可配置的自主性适用于非结构化和通信受限环境下的类人操作

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) Pub Date : 2015-12-28 DOI: 10.1109/HUMANOIDS.2015.7363577

Yu Ohara, Masaki Murooka, Ryohei Ueda, Shunichi Nozawa, Youhei Kakiuchi, K. Okada, M. Inaba

引用次数: 8