{"title":"Broadening applicability of swarm-robotic foraging through constraint relaxation","authors":"John Harwell, Maria L. Gini","doi":"10.1109/SIMPAR.2018.8376280","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376280","url":null,"abstract":"Swarm robotics (SR) offers promising solutions to real-world problems that can be modeled as foraging tasks, e.g. disaster/trash cleanup or object gathering for construction. Yet current SR foraging approaches make limiting assumptions that restrict their applicability to selected real-world environments. We propose an improved self-organized task allocation method based on task partitioning that removes restrictions such as: (1) a priori knowledge of foraging environment, and (2) strict limitations on intermediate drop/pickup site behavior. With experiments in simulation, we show that under the proposed constraint relaxation, our approach still provides performance increases when compared to an unpartitioned strategy within some combinations of swarm sizes, robot capabilities, and environmental conditions. This work broadens the applicability of SR foraging approaches, showing that they can be effective under ideal conditions while continuing to perform robustly in more volatile/challenging environments.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125256803","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":"Learning from outside the viability kernel: Why we should build robots that can fall with grace","authors":"Steve Heim, Alexander Spröwitz","doi":"10.1109/SIMPAR.2018.8376271","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376271","url":null,"abstract":"Despite impressive results using reinforcement learning to solve complex problems from scratch, in robotics this has still been largely limited to model-based learning with very informative reward functions. One of the major challenges is that the reward landscape often has large patches with no gradient, making it difficult to sample gradients effectively. We show here that the robot state-initialization can have a more important effect on the reward landscape than is generally expected. In particular, we show the counter-intuitive benefit of including initializations that are unviable, in other words initializing in states that are doomed to fail.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131744611","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":"Modeling human-likeness in approaching motions of dual-arm autonomous robots","authors":"N. García, J. Rosell, R. Suárez","doi":"10.1109/SIMPAR.2018.8376269","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376269","url":null,"abstract":"This paper addresses the problem of obtaining human-like motions with an anthropomorphic dual-arm torso assembled on a mobile platform. The focus is set on the coordinated movements of the robotic arms and the robot base while approaching a table to subsequently perform a bimanual manipulation task. For this, human movements are captured and mapped to the robot in order to compute the human dual-arm synergies. Since the demonstrated synergies change depending on the robot position, a recursive Cartesian-space discretization is presented based on these differences. Thereby, different movements of the arms are assigned to different regions of the Cartesian space. As an application example, a motion-planning algorithm exploiting this information is proposed and used.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114238403","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":"Online eye-robot self-calibration","authors":"Arnaud Tanguy, A. Kheddar, Andrew I. Comport","doi":"10.1109/SIMPAR.2018.8376273","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376273","url":null,"abstract":"We present a new approach that extends the well known Eye-Hand calibration to the online whole-body calibration of the kinematic tree geometric parameters. Only on-board RGB-D sensor and joint encoders are required. Online calibration allows to estimate the state of the kinematic tree at any time, and thus account for inaccurate models, passive joints, mechanical wear, unexpected damages, etc. One major challenge in achieving such an online self-calibration procedure with the available sensors is that the observability of the calibrated parameters cannot always be guaranteed. In this work, we determine the effect of joint degrees of freedom on observability. From this, we propose a novel Eye-Robot calibration method that determines the geometric transformations between joints. Conditions on joint motion are further used to improve upon existing kinematic tree parameters when observability is incomplete. In practice a dense SLAM algorithm is used for online pose estimation and the results are demonstrated with an HRP-4 humanoid robot.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114915745","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}
S. Dutta, T. Maiti, Y. Ochi, M. Miura-Mattausch, S. Bhattacharya, D. Navarro, N. Yorino, H. Mattausch
{"title":"Self-controlled walking robot with gyro sensor network for stable movement on non-smooth surfaces","authors":"S. Dutta, T. Maiti, Y. Ochi, M. Miura-Mattausch, S. Bhattacharya, D. Navarro, N. Yorino, H. Mattausch","doi":"10.1109/SIMPAR.2018.8376283","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376283","url":null,"abstract":"In this paper a gyro-sensor control for improved walking-robot stability is presented, which applies a new control algorithm to drive the servo motors in response to the transmitted signals from the gyro sensor. Modelling of gyro-sensor and servo-motor for electro-mechanical system simulation is undertaken to facilitate improvements of the walking robot's gyro-sensor-driven self-controlled balancing. The robot's pitch motion on non-smooth ground surfaces is verified experimentally and also theoretically with use of the developed system simulation tool.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121378720","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}
Y. Wu, Hu Cheng, Adam Fingrut, K. Crolla, Y. Yam, Darwin Lau
{"title":"CU-brick cable-driven robot for automated construction of complex brick structures: From simulation to hardware realisation","authors":"Y. Wu, Hu Cheng, Adam Fingrut, K. Crolla, Y. Yam, Darwin Lau","doi":"10.1109/SIMPAR.2018.8376287","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376287","url":null,"abstract":"Robotic building construction has had significant advances in the recent decades, but also has various limitations. In particular, construction typically requires a robot to operate within a large space for long hours and be able to transport between sites. Cable-driven parallel robots (CDPRs) show strong potentials within the automation of construction due to its desirable characteristics, such as high payload-to-weight ratio, transportability, scalability and reconfigurability. This paper proposes a simulation-based analysis, design and pre-execution verification for a cable-driven brick structure building system (CU-Brick), among which a way to determine the buildable workspace where the construction could be constructed is proposed. Simulations are used to do the workspace analysis, design of the brick structure within the workspace and also verification that the motions can be executed. Using this simulation approach, real demonstrations have been performed to show that indeed the system is able to construct the brick structures safely and consistently.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127469653","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":"Dynamics simulation for an upper-limb human-exoskeleton assistance system in a latent-space controlled tool manipulation task","authors":"J. Kuehn, Tingli Hu, M. Schappler, S. Haddadin","doi":"10.1109/SIMPAR.2018.8376286","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376286","url":null,"abstract":"This paper introduces a more complete and complex dynamics simulation tool for an exoskeletal human upper limb assistant system. This heterogeneous simulation model couples the articulated dynamics of a 6 degree-of-freedom (DoF) wearable exoskeleton with an upper-limb human neu-romechanics model of 12 skeletal and 42 muscular DoFs with corresponding controls. Furthermore, the process forces of toolmediated manipulation tasks can be fed into the overall system. This simulation tool can be used for various purposes such as 1) design and evaluation of human-centered exoskeleton controllers 2) evaluating human motor control hypotheses during exoskeleton use and 3) investigating various properties and the performance on exoskeleton systems and manipulation tasks. This framework is used exemplary in designing and implementing a human kinematic latent-space controller for a power drilling manipulation task under exoskeletal assistance.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"289 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117294419","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":"Investigating heterogeneous planning spaces","authors":"Aakriti Upadhyay, Chinwe Ekenna","doi":"10.1109/SIMPAR.2018.8376279","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376279","url":null,"abstract":"With the continuous improvement of the capabilities of robots and the increasing complexity of the environments they successfully traverse, this paper presents useful concepts and definitions about the heterogeneous nature of planning spaces within the context of motion planning. Our methodology uses the property of visibility, expansiveness and homotopy class to develop algorithms that represent the heterogeneity of the planning space. Our algorithm also include a machine learning technique that identifies sub regions and then intelligently applies necessary existing strategies to create well connected maps in that sub region. We make comparisons with two other machine learning methods in a variety of simulated robot environments ranging from simple homogeneous rooms to complicated maze environments. Our method outperforms the other two methods in terms of time to build a roadmap, the number of nodes needed and the number of connected components generated.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117295326","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":"Analysis of a simple model for post-impact dynamics active compliance in humanoids falls with nonlinear optimization","authors":"V. Samy, Karim Bouyarmane, A. Kheddar","doi":"10.1109/SIMPAR.2018.8376272","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376272","url":null,"abstract":"We analyse a mass-spring-damper model as an active compliance steering controller to adaptively comply with post-impact dynamics in humanoid falls. We use it as a one degree of freedom virtual link that can be attached between a point at impact and a given limb point (e.g. torso or waist of the humanoid). By mapping position and torque limits of the robot joints into corresponding position and force limits in the virtual link, we formulate a nonlinear optimization problem to find its admissible stiffness and damping that prevents violating the constraints before reaching a steady state rest. The nonlinear constraints are analytically derived using symbolic computation and then numerically solved with off-the-shelf nonlinear optimization solver. The virtual model trajectories are then mapped back on the full body of the humanoid robot and illustrated on the HRP-4 robot in simulation.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"47 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120847895","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":"Hybrid map mosaicing: A novel approach for large area mapping","authors":"Brice Renaudeau, O. Labbani-Igbida, G. Mourioux","doi":"10.1109/SIMPAR.2018.8376266","DOIUrl":"https://doi.org/10.1109/SIMPAR.2018.8376266","url":null,"abstract":"In this paper, we propose a new approach to global mapping of ground free spaces from aerial views in structured outdoor environments. The presented approach makes a topological mosaicing based on free space skeletonization and graph matching. The obtained environment model is a ground traversability map represented as a hybrid topological/metrical graph, which is a very suitable representation for ground navigation and planing. To validate this approach, the proposed algorithm is applied on aerial views provided by a UAV evolving over an experimental site and is compared with a recent state-of-the-art mosaicing solution.","PeriodicalId":156498,"journal":{"name":"2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124811689","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}