Jonathan Maycock, Tobias Röhlig, Matthias Schröder, M. Botsch, H. Ritter
{"title":"Fully automatic optical motion tracking using an inverse kinematics approach","authors":"Jonathan Maycock, Tobias Röhlig, Matthias Schröder, M. Botsch, H. Ritter","doi":"10.1109/HUMANOIDS.2015.7363590","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363590","url":null,"abstract":"Optical motion tracking systems often require a lot of manual work to generate clean labeled trajectories. This can be a deterrent if the goal is the creation of large motion tracking datasets. Especially in the case of hand tracking, issues of occlusion (often self-occlusion by other fingers) make the post-processing task very difficult and time intensive. We introduce a fully automatic optical motion tracking method that utilizes a model based inverse kinematics approach. The Hungarian method is used to efficiently calculate associations between model markers and motion capture markers and we demonstrate an elegant solution to the problem of occlusions using a posture interpolation step.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"53 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":"121288344","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}
Hyunchul Choi, Sukwon Lee, Taeil Jin, Sung-Hee Lee
{"title":"Trajectory-free reactive stepping of humanoid robots using momentum control","authors":"Hyunchul Choi, Sukwon Lee, Taeil Jin, Sung-Hee Lee","doi":"10.1109/HUMANOIDS.2015.7363511","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363511","url":null,"abstract":"Momentum control approaches have been successfully applied to balance controllers for humanoid robots due to their integrated controllability of ground reaction force and the center of pressure. In this paper, we introduce a trajectory-free reactive stepping controller using momentum control. The controller is characterized by moving passively in the direction of external pushes without attempting to follow some prescribed trajectory, thereby achieving a natural reactive stepping behavior adaptive to various perturbations. Constructed on top of momentum control, our stepping controller is realized straightforwardly by setting a set of suitable inputs such as the desired momentum rate change and the target swing foot position to the momentum controller for each phase of stepping. We demonstrate the effectiveness of our approach through various simulation experiments on a humanoid robot model.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"22 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":"122538291","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":"Fusion of force-torque sensors, inertial measurements units and proprioception for a humanoid kinematics-dynamics observation","authors":"M. Benallegue, Alexis Mifsud, F. Lamiraux","doi":"10.1109/HUMANOIDS.2015.7363425","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363425","url":null,"abstract":"We present a scheme where the measurements obtained through inertial measurement units (IMU), contact-force sensors and proprioception (joint encoders) are merged in order to observe humanoid unactuated floating-base dynamics. The sensor data fusion is implemented using an Extended Kalman Filter. The prediction part is constituted by viscoelastic contacts assumption and a model expressing at the origin the full body dynamics. The correction is achieved using embedded IMU and force sensor. Simulation and experimentation on HRP-2 robot show a state observation with improves inter-sensor consistency but also increased reconstruction accuracy.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"26 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":"123118628","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":"Biologically inspired deadbeat control for running on 3D stepping stones","authors":"Johannes Englsberger, P. Kozłowski, C. Ott","doi":"10.1109/HUMANOIDS.2015.7363501","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363501","url":null,"abstract":"This paper enhances the Biologically Inspired Dead-beat (BID) controller from [1], to not only enable three-dimensional bipedal running on a horizontal plane but also on 3D stepping-stones. Further contributions of the paper are explicit foot step targeting during running, leg cross-over avoidance and the embedding of the BID controller into a QP-based whole-body controller. The BID controller is based on the encoding of leg forces and CoM trajectories during stance as polynomial splines, allowing for intuitive and primarily analytical controller design. It allows a real-time implementation, is highly robust against perturbations and enables versatile running patterns. The performance of the control framework is tested in various simulations for a bipedal point-mass model and an articulated multi-body model of the humanoid robot Toro.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"24 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":"125163017","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":"Task-specific grasping of simiiar objects by probabiiistic fusion of vision and tactiie measurements","authors":"E. Kolycheva, V. Kyrki","doi":"10.1109/HUMANOIDS.2015.7363431","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363431","url":null,"abstract":"This paper presents a probabilistic approach for task-specific grasping of novel objects from a known category. RGB-D imaging is used to establish an initial estimate of the target object's shape and pose, which is used to plan an optimal grasp over the uncertain estimate. Tactile information is then used for incrementally improving the estimate and sequentially replanning better grasps. The resulting grasp is maximally likely to be task compatible and stable taking into account shape uncertainty in a probabilistic context. Experimental results in simulation and on a real platform show that tactile information can be used for improving the stability of grasps for objects which belong to a known category even if they vary considerably in shape.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"23 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":"122525821","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}
H. V. Hoof, Tucker Hermans, G. Neumann, Jan Peters
{"title":"Learning robot in-hand manipulation with tactile features","authors":"H. V. Hoof, Tucker Hermans, G. Neumann, Jan Peters","doi":"10.1109/HUMANOIDS.2015.7363524","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363524","url":null,"abstract":"Dexterous manipulation enables repositioning of objects and tools within a robot's hand. When applying dexterous manipulation to unknown objects, exact object models are not available. Instead of relying on models, compliance and tactile feedback can be exploited to adapt to unknown objects. However, compliant hands and tactile sensors add complexity and are themselves difficult to model. Hence, we propose acquiring in-hand manipulation skills through reinforcement learning, which does not require analytic dynamics or kinematics models. In this paper, we show that this approach successfully acquires a tactile manipulation skill using a passively compliant hand. Additionally, we show that the learned tactile skill generalizes to novel objects.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"3 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132731999","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}
L. Osuna-Ibarra, H. Caballero-Barragán, A. Loukianov, O. Carbajal-Espinosa, E. Bayro-Corrochano
{"title":"Continuous and discrete time robust control for bipedal robot assuming minimal knowledge of the plant","authors":"L. Osuna-Ibarra, H. Caballero-Barragán, A. Loukianov, O. Carbajal-Espinosa, E. Bayro-Corrochano","doi":"10.1109/HUMANOIDS.2015.7363485","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363485","url":null,"abstract":"In this paper, a control approach in continuous and discrete time, for the robust tracking of walking patterns in a bipedal robot, is proposed. A discrete time model of the robot is obtained using the symplectic Euler method, in order to define a comparison between the proposed continuous and discrete time controllers in presence of parametric variations. Two robust controllers are designed using the Sliding Mode approach, one is based on the discrete time model and the other one on the continuous time model of the bipedal robot. The performance and robustness with respect to external disturbances and parametric variations of the proposed controllers, are demonstrated via Lyapunov stability analysis and simulations. By means of a discrete event model, the switching logic is simulated to represent the switching in the walking phases of the robot.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"74 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":"134458294","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":"Simultaneous kinesthetic teaching of positional and force requirements for sequential in-contact tasks","authors":"Franz Steinmetz, Alberto Montebelli, V. Kyrki","doi":"10.1109/HUMANOIDS.2015.7363552","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363552","url":null,"abstract":"This paper demonstrates a method for simultaneous transfer of positional and force requirements for in-contact tasks from a human instructor to a robotic arm through kinesthetic teaching. This is achieved by a specific use of the sensory configuration, where a force/torque sensor is mounted between the tool and the flange of a robotic arm endowed with integrated torque sensors at each joint. The human demonstration is modeled using Dynamic Movement Primitives. Following human demonstration, the robot arm is provided with the capacity to perform sequential in-contact tasks, for example writing on a notepad a previously demonstrated sequence of characters. During the reenactment of the task, the system is not only able to imitate and generalize from demonstrated trajectories, but also from their associated force profiles. In fact, the implemented framework is extended to successfully recover from perturbations of the trajectory during reenactment and to cope with dynamic environments.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"8 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":"134070982","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}
Russ Tedrake, S. Kuindersma, Robin Deits, K. Miura
{"title":"A closed-form solution for real-time ZMP gait generation and feedback stabilization","authors":"Russ Tedrake, S. Kuindersma, Robin Deits, K. Miura","doi":"10.1109/HUMANOIDS.2015.7363473","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363473","url":null,"abstract":"Here we present a closed-form solution to the continuous time-varying linear-quadratic regulator problem for zero-moment point (ZMP) tracking. This generalizes previous analytical solutions for gait generation by allowing \"soft\" tracking (with a quadratic cost) of the desired ZMP, and by providing the feedback gains for the resulting time-varying optimal controller. This enables very fast O(n) computation, with n the number of piecewise polynomial segments in the desired ZMP trajectory. Results are presented using the Atlas humanoid robot where dynamic walking is achieved by recomputing the optimal controller online.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"33 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":"115024091","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":"Multi-layered real-time controllers for humanoid's manipulation and locomotion tasks with emergency stop","authors":"Shunichi Nozawa, Eisoku Kuroiwa, Kunio Kojima, Ryohei Ueda, Masaki Murooka, Shintaro Noda, Iori Kumagai, Yu Ohara, Youhei Kakiuchi, K. Okada, M. Inaba","doi":"10.1109/HUMANOIDS.2015.7363578","DOIUrl":"https://doi.org/10.1109/HUMANOIDS.2015.7363578","url":null,"abstract":"This paper describes a practical method to construct real-time controllers to achieve locomotion and manipulation tasks with a humanoid robot. We propose a method to insert emergency stop functionality to each layer to avoid robot's falling down and joint overloads even if recognition and planning error exist. We explain implementation of multi-layered real-time controllers on HRP2 robot and application to several manipulation and locomotion tasks. Finally, we evaluate emergency stop functionality in several manipulation tasks.","PeriodicalId":417686,"journal":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","volume":"378 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":"122863544","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}