V. Wank, A. Fischer, K. Bös, I. Boesnach, J. Moldenhauer, T. Beth
{"title":"Similarities and varieties in human motion trajectories of predefined grasping and disposing movements","authors":"V. Wank, A. Fischer, K. Bös, I. Boesnach, J. Moldenhauer, T. Beth","doi":"10.1109/ICHR.2004.1442129","DOIUrl":"https://doi.org/10.1109/ICHR.2004.1442129","url":null,"abstract":"Human movement is characterized by smoothed trajectories and individual solutions relating to joint angle configuration. For the transformation of human movement characteristics into humanoid robots knowledge about basic strategies and the nature of human motion is necessary. The objective of this study is the inter-individual and intra-individual comparison of movement trajectories and time series of joint angles for several predefined object manipulations. For that purpose the kinematics of arm, hand and finger motion was measured via 3D video motion capturing and analyzed. Graphs of object trajectories, joint angles and finger tip distances (grasp state) were displayed for an example motion: moving to a cuboid, grasping the object and putting it to a heightened target position. The varieties in motion of different subjects and within repeated motion cycles of one and the same subject are presented. Besides this we show, how test subjects with different body height solve the motion task.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124134675","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}
Dimitris Pongas, F. Guenter, A. Guignard, A. Billard
{"title":"Development of a miniature pair of eyes with camera for the humanoid robot Robota","authors":"Dimitris Pongas, F. Guenter, A. Guignard, A. Billard","doi":"10.1109/ICHR.2004.1442693","DOIUrl":"https://doi.org/10.1109/ICHR.2004.1442693","url":null,"abstract":"A growing trend in humanoid robotics tend at reducing the size of humanoids in order to lower their building costs. While growing small has its advantages, it also has drawbacks. In particular, providing miniature humanoids with the same sensorimotor capabilities as their grown-up peers is a challenge, both in terms of mechanics, electronics and control. The Robota project creates humanoids, whose size should match that of a commercial doll, so that they can be used as part of experiments with autistic children. Because these experiments measure the child's ability to socially interact with others, it is fundamental to provide the robot with sensory capabilities, such as speech and vision, that are at the basis of these interactions. This paper presents the creation of a miniature pair of mobile eyes, mounted with miniature cameras to provide Robota with binocular and mobile vision. The system allows the robot to blink, to direct its gaze toward or away from its user and to track the user's face.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128601110","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}
{"title":"Sensor-based biped gait generation scheme for humanoid - implementation and evaluation","authors":"K. Toda, M. Sagara, K. Tomiyama","doi":"10.1109/ICHR.2004.1442677","DOIUrl":"https://doi.org/10.1109/ICHR.2004.1442677","url":null,"abstract":"A new gait generation method, called sensor-based biped gait generation, for humanoids is proposed here. The proposed method chooses a gait generating method from a set of prepared ones according to sensor measurements of robot's environment and to its behavior state. A gait generator that is based on the proposed method is designed and implemented onto an original humanoid to demonstrate its effectiveness.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122645999","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}
{"title":"A tiered planning strategy for biped navigation","authors":"Joel E. Chestnutt, J. Kuffner","doi":"10.1109/ICHR.2004.1442135","DOIUrl":"https://doi.org/10.1109/ICHR.2004.1442135","url":null,"abstract":"This paper presents a three-tiered planner for biped navigation over large distances through complex environments where conventional 2D planning algorithms designed for wheeled robots fail to find a solution. The lowest tier is a footstep planner which can plan sequences of footholds for navigating through obstacles or over rough terrain. The second tier is a mobile robot planner, which plans outward from the goal to the robot's initial state, building a heuristic to aid the lowest level planner in directing the footholds toward a likely path. The highest tier chooses a long-term path to follow, ignoring the details of how it will be implemented, and directs the lower levels during execution to provide footstep sequences for the robot and notification of when re-planning is necessary. Results are demonstrated with simulated environments and execution.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122688086","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}
T. Harada, S. Taoka, Taketoshi Mori, Tomomasa Sato
{"title":"Quantitative evaluation method for pose and motion similarity based on human perception","authors":"T. Harada, S. Taoka, Taketoshi Mori, Tomomasa Sato","doi":"10.1109/ICHR.2004.1442140","DOIUrl":"https://doi.org/10.1109/ICHR.2004.1442140","url":null,"abstract":"In the imitation research, \"how much similar two motions are\" is an essential problem. This paper tries to clarify the criterion by which human evaluates the similarity of poses and motions. First we proposed the quantitative pose similarity evaluation which follows human's intuition. This proposed evaluation uses the optimized parameters such as attention to each human's region and the nonlinearity of the distance perception from questionnaires of similarities for many pairs of human poses. Secondly by comparing the conventional similarity evaluation, we confirmed the validity of the quantitative pose similarity evaluation among different pairs of human poses. Lastly the quantitative pose similarity evaluation was applied to the motion similarity evaluation. Verification of that appropriateness revealed that the quantitative pose similarity evaluation is also useful for the motion similarity evaluation. Since the quantitative pose similarity evaluation reflects the human's perception, this evaluation clarifies the criterions by which human evaluates the pose or motion similarity. The clarified criterions for pose or motion similarity evaluation are as follows: 1) the distance perception is processed in three dimensional positions, 2) the relationship between the similarity and the sum of the Euclidean distances for each region is nonlinear, 3) human fixates poses symmetrically, 4) fingertips are paid particular attention, 5) human pays more attention to further regions from the hip in the upper half of the body, and 6) human pays more attention to nearer regions from the hip in the lower half of the body.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125325979","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}
K. Nishiwaki, M. Kuga, S. Kagami, M. Inaba, H. Inoue
{"title":"Whole-body cooperative balanced motion generation for reaching","authors":"K. Nishiwaki, M. Kuga, S. Kagami, M. Inaba, H. Inoue","doi":"10.1142/S0219843605000624","DOIUrl":"https://doi.org/10.1142/S0219843605000624","url":null,"abstract":"This paper addresses a constructing method of a system that realizes whole body reaching motion of humanoids. Humanoids have many redundant DOFs for reaching, and even the base can be moved by making the robot step. Therefore there are infinite postures as solutions of final reaching posture, and there are also infinite solutions for reaching trajectory that realizes a final reaching posture. It is, however, difficult to find an appropriate solution because of the constraint of dynamical balance, relatively narrow movabIe range for each angle. We prepared basic postures heuristically, and a final reaching posture is generated by modifying one of them. This method enables to implement heuristics easily, such as, kneeling down is suitable for reaching near the ground. Methods that compose the reaching system, such as, basic posture selection, modification of posture for generating final reaching posture, balance compensation, footstep planning to realize desired feet position, and generation and execution of whole body motion to final reaching posture are described. Reaching to manually set position, and picking up a bat at various posture using visual information are shown as experiments to show the performance of the system.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116158796","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}
{"title":"A full body human motion capture system using particle filtering and on-the-fly edge detection","authors":"P. Azad, A. Ude, R. Dillmann, G. Cheng","doi":"10.1109/ICHR.2004.1442696","DOIUrl":"https://doi.org/10.1109/ICHR.2004.1442696","url":null,"abstract":"In this paper we present a full body human motion capture system based on particle filtering operating on monocular image sequences. Distinguishing our approach from others is that edge detection is not carried out globally on the whole picture in a preprocess manner, but is done locally on-the-fly during the calculation of the likelihood function. This approach is effective and flexible at the same time, allowing the use of various edge detection algorithms with only small modifications. Another special feature of our system is a highly optimized occlusion test based on a fast point-in-triangIe test. Our system has been designed carefully with respect to serve as a basis for various research activities in the near future, including the incorporation of stereo vision. A general framework architecture for particle filters and an extension for appliance to edge tracking has been developed with which it is possible to test a whole range of search space decomposition variants with minimum implementation effort.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116453656","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}
{"title":"Acquisition of a biped walking pattern using a Poincare map","authors":"J. Morimoto, J. Nakanishi, G. Endo, G. Cheng","doi":"10.1109/ICHR.2004.1442694","DOIUrl":"https://doi.org/10.1109/ICHR.2004.1442694","url":null,"abstract":"We propose a model-based reinforcement learning algorithm for biped walking in which the robot learns to appropriately place the swing leg. This decision is based on a learned model of the Poincare map of the periodic walking pattern. The model maps from a state at a single support phase and foot placement to a state at the next single support phase. We applied this approach to both a simulated robot model and an actual biped robot. We show that successful walking patterns are acquired.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127958126","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}
{"title":"Building an adaptive spoken language interface for perceptually grounded human-robot interaction","authors":"Peter Ford Dominey, Jean-David Boucher, T. Inui","doi":"10.1109/ICHR.2004.1442121","DOIUrl":"https://doi.org/10.1109/ICHR.2004.1442121","url":null,"abstract":"In previous research, we developed an integrated platform that combined visual scene interpretation with speech processing to provide input to a language-learning model. The system was demonstrated to learn a rich set of sentence-meaning mappings that could allow it to construct the appropriate meanings for new sentences in a generalization task. While this demonstrated potential promise, it fell short in several aspects of providing a useful human-robot interaction system. The current research addresses three of these shortcomings, demonstrating the natural extensibility of the platform architecture. First, the system must be able not only to understand what it hears, but also to describe what it sees and to interact with the human user. This is a natural extension of the knowledge of sentence-to-meaning mappings that is now applied in the inverse scene-to-sentence sense. Secondly, we extend the system's ontology from physical events to include spatial relations. We show that spatial relations are naturally accommodated in the predicate argument representations for events. Finally, because the robot community is international the robot should be able to speak multiple languages, we thus demonstrate that the language model extends naturally to include both English and Japanese. Concrete results from a working interactive system are presented and future directions for adaptive human-robot interaction systems are outlined.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124995320","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}
Ill-Woo Park, Jung-Yup Kim, Seo-Wook Park, Jun-Ho Oh
{"title":"Development of humanoid robot platform KHR-2 (KAIST humanoid robot-2)","authors":"Ill-Woo Park, Jung-Yup Kim, Seo-Wook Park, Jun-Ho Oh","doi":"10.1142/S0219843605000612","DOIUrl":"https://doi.org/10.1142/S0219843605000612","url":null,"abstract":"We are presenting the mechanical and electrical system design and system integration of controllers including sensory devices of the humanoid, KHR-2 in this paper. The concept and the objective of the design will be described. We have developed KHR-2 since 2003 which has 41 DOF (degree of freedom). Each arm including a hand and a wrist has 11 DOF (5+2 DOF/hand (finger + wrist), 4 DOF/arm) and each leg has 6 DOF. Head and trunk have 6 DOF (2 DOF/eye and 2 DOF/neck) and 1 DOF respectively. The mechanical part of the robot is designed to have human friendly appearance and wide movable angle range. Joint actuators are designed to have negligible uncertainties such as backlash. To control all axes, distributed control architecture is adopted to reduce the computation burden of the main controller (PC) and to expand the devices easily. We developed a sub-controller which is a servo motor controller and sensor interfacing devices using microprocessor. The main controller (PC) attached on the back of the robot communicates with sub-controllers in real-time by using CAN (controller area network). Windows XP is used for OS (operating system) for fast development of main control program. RTX (real time extension) HAL extension software is used to realize the real-time control in Windows XP environment. KHR-2 has several sensor types, which are 3-axis F/T (force/torque) sensors at foot and wrist, inertia sensor system (accelerometer and rate gyro) and CCD camera. The F/T sensor at the foot is the most fundamental sensor for stable walking. The inertia sensor system is essential for determining the inclination between the ground and the robot. Finally, we used the CCD camera for navigation and stabilization of the robot in the future. We described the details of the KHR-2 in this paper.","PeriodicalId":367693,"journal":{"name":"4th IEEE/RAS International Conference on Humanoid Robots, 2004.","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121363800","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}