2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)最新文献_第2页

A Standardized Benchmark for Humanoid Whole-Body Manipulation 仿人全身操作的标准化基准

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000141

William Thibault, Francisco Javier Andrade Chavez, K. Mombaur

{"title":"A Standardized Benchmark for Humanoid Whole-Body Manipulation","authors":"William Thibault, Francisco Javier Andrade Chavez, K. Mombaur","doi":"10.1109/Humanoids53995.2022.10000141","DOIUrl":"https://doi.org/10.1109/Humanoids53995.2022.10000141","url":null,"abstract":"In this paper we focus on the evaluation of humanoid manipulation skills while balancing on two feet. This involves manipulation while standing and loco-manipulation where the object is being manipulated while taking steps. With this objective in mind, an initial study of whole-body manipulation in a box manipulation scenario with two dif-ferent motions using the University of Waterloo's REEM-C, “Seven”, is investigated to provide insight into a valuable setup, comprehensive test protocols and useful performance metrics based on real world data. The contribution of this paper is a proposed benchmark for whole-body manipulation consisting of the design of a test bed inspired by real use cases for humanoid whole-body manipulation tasks, the definition of a set of protocols to standardize the testing procedure and insightful key performance indicators (KPIs) based on this initial study with the real robot. The proposed benchmark for humanoid whole-body manipulation is part of the EUROBENCH project that aims at creating a benchmarking framework for robotic systems performing locomotion related tasks.","PeriodicalId":180816,"journal":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133750994","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: 0

Development of Amphibious Humanoid Platform for Sensor-based Behavior Acquisition of Whole-body Manipulation Tasks 基于传感器的全身操作任务行为采集两栖仿人平台的研制

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000091

Tasuku Makabe, J. Oh, T. Anzai, Yuta Kojio, Shintaro Noda, Youhei Kakiuchi, K. Okada, M. Inaba

{"title":"Development of Amphibious Humanoid Platform for Sensor-based Behavior Acquisition of Whole-body Manipulation Tasks","authors":"Tasuku Makabe, J. Oh, T. Anzai, Yuta Kojio, Shintaro Noda, Youhei Kakiuchi, K. Okada, M. Inaba","doi":"10.1109/Humanoids53995.2022.10000091","DOIUrl":"https://doi.org/10.1109/Humanoids53995.2022.10000091","url":null,"abstract":"To build a software platform for research on control and simulation methods for robots that can operate in multiple environments, we need a robot platform that we can use to verify behavior in real diverse surroundings such as land and water. Even though robots need much freedom and perception to work and move around in diverse environments, the more challenging the environment to adapt to, such as underwater or outer space, the more limited the resources we can bring to the environment. In this study, we propose a humanoid robot system that we can use to study the acquisition of whole-body manipulation tasks based on sensor information in water as well as on land by constructing the humanoid with force, vision, and posture perception and multiple degrees of freedom that can use its limbs in various ways such as walking, swimming, and working depending on the condition. As examples of sensor-based whole-body manipulation tasks, we conducted walking experiments, box carrying experiments, remote-control-based wiping experiments in the water, and swimming experiments with object tracking on the water's surface. We discussed the effects of the underwater environment, compared the experimental results between the land and underwater environments, and showed that we could use the proposed robot system to study the acquisition of whole-body manipulation movements in multiple conditions.","PeriodicalId":180816,"journal":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114767831","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: 0

Fast Multi-Contact Motion Planning Based on Best-Neighbor Search of Contact Sequences 基于接触序列最近邻搜索的快速多接触运动规划

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000158

Y. Tazaki

引用次数: 1

Shell Gripper Inspired by Human Finger Structure for Automatically Packaging Agricultural Product 受人体手指结构启发的贝壳夹持器用于农产品自动包装

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000125

Hiroki Aoyama, Zhongkui Wang, S. Hirai

{"title":"Shell Gripper Inspired by Human Finger Structure for Automatically Packaging Agricultural Product","authors":"Hiroki Aoyama, Zhongkui Wang, S. Hirai","doi":"10.1109/Humanoids53995.2022.10000125","DOIUrl":"https://doi.org/10.1109/Humanoids53995.2022.10000125","url":null,"abstract":"Soft robotic end-effectors have been developed for grasping food and agricultural products. However, end-effectors that can package multiple agricultural products simultaneously in a clustered scenario have not been studied frequently so far. In this paper, we propose a robotic end-effector capable of performing such packaging task on multiple cucumbers. The end-effector consists of multiple thin shell grippers and each of them can grasp one cucumber. The shell gripper is composed of a rigid shell and a soft membrane. Upon pressurization, the soft membrane can be inflated to realize a grasping motion. This hybrid (rigid and soft) structure was inspired by human finger structure, which consists of rigid bone or nail and soft tissue. For fabricating the shell gripper, we proposed a demolding-free casting method that eliminates the need of removing silicone rubber from mold. Thanks to this new fabrication method, we are able to minimize the thickness of the shell gripper. The membrane inflation displacement was experimentally measured to confirm the grasping ability. Finally, field tests on packaging nine cucumbers were conducted and results validated that the proposed robotic end-effector can stably package multiple cucumbers simultaneously.","PeriodicalId":180816,"journal":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125346839","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: 0

Hardware Design and Learning-Based Software Architecture of Musculoskeletal Wheeled Robot Musashi-W for Real-World Applications 肌肉骨骼轮式机器人武藏- w的硬件设计和基于学习的软件体系结构

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000123

Kento Kawaharazuka, Akihiro Miki, Masahiro Bando, Temma Suzuki, Yoshimoto Ribayashi, Yasunori Toshimitsu, Yuya Nagamatsu, K. Okada, M. Inaba

引用次数: 0

Integrated Bi-Manual Motion Generation and Control shaped for Probabilistic Movement Primitives 集成双手运动生成和控制的概率运动基元

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000149

Jonathan Vorndamme, João Carvalho, Riddhiman Laha, Dorothea Koert, Luis F. C. Figueredo, Jan Peters, S. Haddadin

{"title":"Integrated Bi-Manual Motion Generation and Control shaped for Probabilistic Movement Primitives","authors":"Jonathan Vorndamme, João Carvalho, Riddhiman Laha, Dorothea Koert, Luis F. C. Figueredo, Jan Peters, S. Haddadin","doi":"10.1109/Humanoids53995.2022.10000149","DOIUrl":"https://doi.org/10.1109/Humanoids53995.2022.10000149","url":null,"abstract":"This work introduces a novel cooperative control framework that allows for real-time reactiveness and adaptation whilst satisfying implicit constraints stemming from proba-bilistic/stochastic trajectories. Stemming from task-oriented sampling and/or task-oriented demonstrations, e.g., learning based on motion primitives, such trajectories carry additional information often neglected during real-time control deployment. In particular, methods such as probabilistic movement primitives offer the advantage to capture the inherent stochasticity in human demonstrations - which in turn reflects human's understanding about task-variability and adaption possibilities. This information, however, is often poorly exploited and, mostly, used during offline trajectory planning stage. Our work instead introduces a novel real-time motion-generation strategy that explicitly exploits such information to improve trajectories according to changes in the environmental condition and robot task-space topology. The proposed solution is particularly well-suited for bi-manual and coordinated systems where the increased kinematic complexity, tightly-coupled constraints and reduced workspace have detrimental effects on the manipula-bility, joint-limits, and are even capable of causing unstable behavior and task-failure. Our methodology addresses these challenges, and improves performance and task-execution by taking the confidence range region explicitly into account whilst maneuvering towards better configurations. Furthermore, it can directly cope with different closed-chain kinematics and task-space topologies, resulting for instance from different grasps. Experimental evaluations on a bi-manual Franka panda robot show that the method can run in the inner control loop of the robot and enables successful execution of highly constrained tasks.","PeriodicalId":180816,"journal":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125142347","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: 1

Synthesis of Lower-Body Human Walking using Trigonometric Spline Method 用三角样条法合成人体下体行走

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000253

Altay Zhakatayev, Yuri V. Rogovchenko, M. Pätzold

引用次数: 0

Harnessing Long-term Memory for Personalized Human-Robot Interactions 利用长期记忆进行个性化人机交互

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000213

S. Paplu, Raúl Fernández Navarro, K. Berns

{"title":"Harnessing Long-term Memory for Personalized Human-Robot Interactions","authors":"S. Paplu, Raúl Fernández Navarro, K. Berns","doi":"10.1109/Humanoids53995.2022.10000213","DOIUrl":"https://doi.org/10.1109/Humanoids53995.2022.10000213","url":null,"abstract":"Long-term memory system along with a working memory paves the way for a personalized human-robot interaction. Memorability based on visual and auditory cues can potentially enhance the simple stimulus-driven interaction process towards a more human-like and natural one. Most of the existing interactive humanoids, to some extent, utilize the short-term or working memory for the robot to establish interaction. This work incorporates a stable long-term memory system for the socially interactive robot ROBIN, triggering a notion of episodic memory. A MySQL database system has been integrated into the existing robot behavior control system in order to store and retrieve essential information e.g., name, age, occupation etc. of an interaction partner. The proposed personalized interaction system utilizes the interlocutors' past events / experiences in different interaction scenarios. Realistic robot behaviour in the form of speech, gesture / posture and facial expressions has been generated. The user experiences collected with a questionnaire-based evaluation process indicate a notion of fluid and realistic human-robot interaction.","PeriodicalId":180816,"journal":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133975822","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: 0

Bimanual Manipulation Workspace Analysis of Humanoid Robots with Object Specific Coupling Constraints 具有特定对象耦合约束的仿人机器人双手操作工作空间分析

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000183

William Thibault, Vidyasagar Rajendran, K. Mombaur

{"title":"Bimanual Manipulation Workspace Analysis of Humanoid Robots with Object Specific Coupling Constraints","authors":"William Thibault, Vidyasagar Rajendran, K. Mombaur","doi":"10.1109/Humanoids53995.2022.10000183","DOIUrl":"https://doi.org/10.1109/Humanoids53995.2022.10000183","url":null,"abstract":"In this work, a bimanual manipulation workspace analysis for humanoid robots is developed. This analysis con-siders manipulability and whole-body stability for a workspace where constraints exist between the hands of the humanoid for varying hand positions and object grasps. With this goal in mind, a combined manipulability-stability metric based on the volume of the manipulability ellipsoid and the distance of the capture point from the edge of the support polygon is proposed. This metric is visualized in a variety of workspace scenarios including those where the humanoid's center of mass is moving at a certain velocity and where it is grasping and carrying objects of different masses and shapes. With a focus on tightly coupled bimanual manipulation of varying symmetry, objects studied include boxes, a broom and a rolling pin. A general workspace and a box manipulation workspace are visualized for both the REEM-C and TALOS humanoids showing differences in the generated workspace volumes due to the varying topologies of the humanoids. These visualizations aim to provide insights into how manipulability and whole-body stability are affected by bimanual manipulation scenarios and to inform complex manipulation applications in areas such as control and cost-based planning.","PeriodicalId":180816,"journal":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114656505","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: 0

A Framework for Recognizing Industrial Actions via Joint Angles 通过联合角度识别工业行动的框架

2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids) Pub Date : 2022-11-28 DOI: 10.1109/Humanoids53995.2022.10000226

Ashutosh Kumar Singh, Mohamed Adjel, Vincent Bonnet, R. Passama, A. Cherubini

{"title":"A Framework for Recognizing Industrial Actions via Joint Angles","authors":"Ashutosh Kumar Singh, Mohamed Adjel, Vincent Bonnet, R. Passama, A. Cherubini","doi":"10.1109/Humanoids53995.2022.10000226","DOIUrl":"https://doi.org/10.1109/Humanoids53995.2022.10000226","url":null,"abstract":"This paper proposes a novel framework for recognizing industrial actions, in the perspective of human-robot collaboration. Given a one second long measure of the human's motion, the framework can determine his/her action. The originality lies in the use of joint angles, instead of Cartesian coordinates. This design choice makes the framework sensor agnostic and invariant to affine transformations and to anthropometric differences. On AnDy dataset, we outperform the state of art classifier. Furthermore, we show that our framework is effective with limited training data, that it is subject independent, and that it is compatible with robotic real-time constraints. In terms of methodology, the framework is an original synergy of two antithetical schools of thought: model-based and data-based algorithms. Indeed, it is the cascade of an inverse kinematics estimator compliant with the International Society of Biomechanics recommendations, followed by a deep learning architecture based on Bidirectional Long Short Term Memory. We believe our work may pave the way to successful and fast action recognition with standard depth cameras, embedded on moving collaborative robots.","PeriodicalId":180816,"journal":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115737171","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: 1