TechTalks from event: Technical session talks from ICRA 2012

Conference registration code to access these videos can be accessed by visiting this link: PaperPlaza. Step-by-step to access these videos are here: step-by-step process .
Why some of the videos are missing? If you had provided your consent form for your video to be published and still it is missing, please contact

Sensing for manipulation

  • Using Depth and Appearance Features for Informed Robot Grasping of Highly Wrinkled Clothes Authors: Ramisa, Arnau; Alenyà, Guillem; Moreno-Noguer, Francesc; Torras, Carme
    Detecting grasping points is a key problem in cloth manipulation. Most current approaches follow a multiple re-grasp strategy for this purpose, in which clothes are sequentially grasped from different points until one of them yields to a desired configuration. In this paper, by contrast, we circumvent the need for multiple re-graspings by building a robust detector that identifies the grasping points, generally in one single step, even when clothes are highly wrinkled. In order to handle the large variability a deformed cloth may have, we build a Bag of Features based detector that combines appearance and 3D geometry features. An image is scanned using a sliding window with a linear classifier, and the candidate windows are refined using a non-linear SVM and a "grasp goodness" criterion to select the best grasping point. We demonstrate our approach detecting collars in deformed polo shirts, using a Kinect camera. Experimental results show a good performance of the proposed method not only in identifying the same trained textile object part under severe deformations and occlusions, but also the corresponding part in other clothes, exhibiting a degree of generalization.
  • Integrating surface-based hypotheses and manipulation for autonomous segmentation and learning of object representations Authors: Ude, Ales; Schiebener, David; Morimoto, Jun
    Learning about new objects that a robot sees for the first time is a difficult problem because it is not clear how to define the concept of object in general terms. In this paper we consider as objects those physical entities that are comprised of features which move consistently when the robot acts upon them. Among the possible actions that a robot could apply to a hypothetical object, pushing seems to be the most suitable one due to its relative simplicity and general applicability. We propose a methodology to generate and apply pushing actions to hypothetical objects. A probing push causes visual features to move, which enables the robot to either confirm or reject the initial hypothesis about existence of the object. Furthermore, the robot can discriminate the object from the background and accumulate visual features that are useful for training of state of the art statistical classifiers such as bag of features.
  • From Object Categories to Grasp Transfer Using Probabilistic Reasoning Authors: Madry, Marianna; Song, Dan; Kragic, Danica
    In this paper we address the problem of grasp generation and grasp transfer between objects using categorical knowledge. The system is built upon an i)~active scene segmentation module, able of generating object hypotheses and segmenting them from the background in real time, ii)~object categorization system using integration of 2D and 3D cues, and iii)~probabilistic grasp reasoning system. Individual object hypotheses are first generated, categorized and then used as the input to a grasp generation and transfer system that encodes task, object and action properties. The experimental evaluation compares individual 2D and 3D categorization approaches with the integrated system, and it demonstrates the usefulness of the categorization in task-based grasping and grasp transfer.
  • Voting-Based Pose Estimation for Robotic Assembly Using a 3D Sensor Authors: Choi, Changhyun; Taguchi, Yuichi; Tuzel, Oncel; Liu, Ming-Yu; Ramalingam, Srikumar
    We propose a voting-based pose estimation algorithm applicable to 3D sensors, which are fast replacing their 2D counterparts in many robotics, computer vision, and gaming applications. It was recently shown that a pair of oriented 3D points, which are points on the object surface with normals, in a voting framework enables fast and robust pose estimation. Although oriented surface points are discriminative for objects with sufficient curvature changes, they are not compact and discriminative enough for many industrial and real-world objects that are mostly planar. As edges play the key role in 2D registration, depth discontinuities are crucial in 3D. In this paper, we investigate and develop a family of pose estimation algorithms that better exploit this boundary information. In addition to oriented surface points, we use two other primitives: boundary points with directions and boundary line segments. Our experiments show that these carefully chosen primitives encode more information compactly and thereby provide higher accuracy for a wide class of industrial parts and enable faster computation. We demonstrate a practical robotic bin-picking system using the proposed algorithm and a 3D sensor.
  • Supervised Learning of Hidden and Non-Hidden 0-Order Affordances and Detection in Real Scenes Authors: Aldoma, Aitor; Tombari, Federico; Vincze, Markus
    The ability to perceive possible interactions with the environment is a key capability of task-guided robotic agents. An important subset of possible interactions depends solely on the objects of interest and their position and orientation in the scene. We call these object-based interactions $0$-order affordances and divide them among non-hidden and hidden whether the current configuration of an object in the scene renders its affordance directly usable or not. Conversely to other works, we propose that detecting affordances that are not directly perceivable increase the usefulness of robotic agents with manipulation capabilities, so that by appropriate manipulation they can modify the object configuration until the seeked affordance becomes available. In this paper we show how $0$-order affordances depending on the geometry of the objects and their pose can be learned using a supervised learning strategy on 3D mesh representations of the objects allowing the use of the whole object geometry. Moreover, we show how the learned affordances can be detected in real scenes obtained with a low-cost depth sensor like the Microsoft Kinect through object recognition and 6D0F pose estimation and present results for both learning on meshes and detection on real scenes to demonstrate the practical application of the presented approach.
  • Estimating Object Grasp Sliding Via Pressure Array Sensing Authors: Alcazar, Javier Adolfo; Barajas, Leandro
    Advances in design and fabrication technologies are enabling the production and commercialization of sensor-rich robotic hands with skin-like sensor arrays. Robotic skin is poised to become a crucial interface between the robot embodied intelligence and the external world. The need to fuse and make sense out of data extracted from skin-like sensors is readily apparent. This paper presents a real-time sensor fusion algorithm that can be used to accurately estimate object position, translation and rotation during grasping. When an object being grasped moves across the sensor array, it creates a sliding sensation; the spatial-temporal sensations are estimated by computing localized slid vectors using an optical flow approach. These results were benchmarked against an L-inf Norm approach using a nominal known object trajectory generated by sliding and rotating an object over the sensor array using a second, high accuracy, industrial robot. Rotation and slid estimation can later be used to improve grasping quality and dexterity

Sampling-Based Motion Planning

  • A Scalable Method for Parallelizing Sampling-Based Motion Planning Algorithms Authors: Jacobs, Sam Ade; Burgos, Juan; Manavi, Kasra; Denny, Jory; Thomas, Shawna; Amato, Nancy
    This paper describes a scalable method for parallelizing sampling-based motion planning algorithms. It subdivides configuration space (C-space) into (possibly overlapping) regions and independently, in parallel, uses standard (sequential) sampling-based planners to construct roadmaps in each region. Next, in parallel, regional roadmaps in adjacent regions are connected to form a global roadmap. By subdividing the space and restricting the locality of connection attempts, we reduce the work and inter-processor communication associated with nearest neighbor calculation, a critical bottleneck for scalability in existing parallel motion planning methods. We show that our method is general enough to handle a variety of planning schemes, including the widely used Probabilistic Roadmap (PRM) and Rapidly-exploring Random Trees (RRT) algorithms.We compare our approach to two other existing parallel algorithms and demonstrate that our approach achieves better and more scalable performance. Our approach achieves almost linear scalability on a 2400 core LINUX cluster and on a 153,216 core Cray XE6 petascale machine.
  • LQR-RRT*: Optimal Sampling-Based Motion Planning with Automatically Derived Extension Heuristics Authors: Perez, Alejandro; Platt, Robert; Konidaris, George Dimitri; Kaelbling, Leslie; Lozano-Perez, Tomas
    The RRT* algorithm has recently been proposed as an optimal extension to the standard RRT algorithm [1]. However, like RRT, RRT* is difficult to apply in problems with complicated or underactuated dynamics because it requires the design of a two domain-specific extension heuristics: a distance metric and node extension method. We propose automatically deriving these two heuristics for RRT* by locally linearizing the domain dynamics and applying linear quadratic regulation (LQR). The resulting algorithm, LQR-RRT*, finds optimal plans in domains with complex or underactuated dynamics without requiring domain-specific design choices. We demonstrate its application in domains that are successively torquelimited, underactuated, and in belief space.
  • SR-RRT: Selective Retraction-Based RRT Planner Authors: Lee, Junghwan; Kwon, Osung; Zhang, Liangjun; Yoon, Sung-eui
    We present a novel retraction-based planner, selective retraction-based RRT, for efficiently handling a wide variety of environments that have different characteristics. We first present a bridge line-test that can identify regions around narrow passages, and then perform an optimizationbased retraction operation selectively only at those regions. We also propose a non-colliding line-test, a dual operator to the bridge line-test, as a culling method to avoid generating samples near wide-open free spaces and thus to generate more samples around narrow passages. These two tests are performed with a small computational overhead and are integrated with a retraction-based RRT. In order to demonstrate benefits of our method, we have tested our method with different benchmarks that have varying amounts of narrow passages. Our method achieves up to 21 times and 3.5 times performance improvements over a basic RRT and an optimizationbased retraction RRT, respectively. Furthermore, our method consistently improves the performances of other tested methods across all the tested benchmarks that have or do not have narrow passages.
  • Sampling-Based Motion Planning with Dynamic Intermediate State Objectives: Application to Throwing Authors: Zhang, Yajia; Luo, Jingru; Hauser, Kris
    Dynamic manipulations require attaining high velocities at specified configurations, all the while obeying geometric and dynamic constraints. This paper presents a motion planner that constructs a trajectory that passes at an intermediate state through a dynamic objective region, which is comprised of a certain lower dimensional submanifold in the configuration/velocity state space, and then returns to rest. Planning speed and reliability is greatly improved using optimizations based on the fact that ramp-up and ramp-down subproblems are coupled by the choice of intermediate state, and that very few (often less than 1%) intermediate states yield feasible solution trajectories. Simulation experiments demonstrate that our method quickly generates trajectories for a 6-DOF industrial manipulator throwing a small object.
  • Towards Small Asymptotically Near-Optimal Roadmaps Authors: Marble, James; Bekris, Kostas E.
    An exciting recent development is the definition of sampling-based motion planners which guarantee asymptotic optimality. Nevertheless, roadmaps with this property may grow too large and lead to longer query resolution times. If optimality requirements are relaxed, existing asymptotically near-optimal solutions produce sparser graphs by removing redundant edges. Even these alternatives, however, include all sampled configurations as nodes in the roadmap. This work proposes a method, which can reject redundant samples but does provide asymptotic coverage and connectivity guarantees, while keeping local path costs low. Not adding every sample can significantly reduce the size of the final roadmap. An additional advantage is that it is possible to define a reasonable stopping criterion for the approach inspired by previous methods. To achieve these objectives, the proposed method maintains a dense graph that is used for evaluating the performance of the roadmap with regards to local path costs. Experimental results show that the method indeed provides small roadmaps, allowing for shorter query resolution times. Furthermore, smoothing the final paths results in an even more advantageous comparison against alternatives with regards to path quality.
  • Proving Path Non-Existence Using Sampling and Alpha Shapes Authors: McCarthy, Zoe; Bretl, Timothy; Hutchinson, Seth
    In this paper, we address the problem determining the connectivity of a robot's free configuration space. Our method iteratively builds a constructive proof that two configurations lie in disjoint components of the free configuration space. Our algorithm first generates samples that correspond to configurations for which the robot is in collision with an obstacle. These samples are then weighted by their generalized penetration distance, and used to construct alpha shapes. The alpha shape defines a collection of simplices that are fully contained within the configuration space obstacle region. These simplices can be used to quickly solve connectivity queries, which in turn can be used to define termination conditions for sampling-based planners. Such planners, while typically either resolution complete or probabilistically complete, are not able to determine when a path does not exist, and therefore would otherwise rely on heuristics to determine when the search for a free path should be abandoned. An implementation of the algorithm is provided for the case of a 3D Euclidean configuration space, and a proof of correctness is provided.

Minimally Invasive Interventions II

  • Configuration Comparison for Surgical Robotic Systems Using a Single Access Port and Continuum Mechanisms Authors: Zheng, Xidian; Xu, Kai
    Research on robot-assisted laparoscopic SPA (Single Port Access) surgery and N.O.T.E.S (Natural Orifice Translumenal Endoscopic Surgery) have thrived in the past a few years. A configuration similarity between these surgical robotic slaves is that two robotic arms are extended from the same access port (either a laparoscope or an endoscope) for surgical interventions. However, upon designing such a surgical robotic slave, the structure of the extended robotic arms has not been explored thoroughly based on evaluation of their distal dexterity. This paper presents a simulation-based comparison among three different structures which could be used to form these extended robotic arms. Results presented in this paper could serve as a design reference for surgical robotic slaves which use a single access port and continuum mechanisms.
  • Control of Untethered Magnetically Actuated Tools Using a Rotating Permanent Magnet in Any Position Authors: Mahoney, Arthur; Cowan, Daniel Lewis; Miller, Katie; Abbott, Jake
    It has been shown that when a magnetic dipole, such as a permanent magnet, is rotated around a fixed axis such that the dipole is perpendicular to the axis of rotation, the magnetic field vector at every point in space also rotates around a fixed axis. In this paper, we reformulate this phenomenon using linear algebraic techniques, which enables us to find the necessary dipole rotation axis to make the magnetic field at any desired point in space rotate about any desired axis. To date, untethered magnetically actuated tools (e.g., capsule endoscopes, rolling spheres, and helical-propeller microswimmers) controlled with a single rotating permanent magnet have been constrained to operate in positions where the rotating field behavior is simple and easy to visualize. We experimentally demonstrate that the results of this paper can be used to control a variety of untethered, rotating magnetic devices in any position even while the rotating permanent magnet follows trajectories independent of the devices themselves. This method constitutes a substantial step toward making a great deal of prior laboratory research regarding rotating magnetic microrobots and capsule endoscopes clinically feasible.
  • Integration and Preliminary Evaluation of an Insertable Robotic Effectors Platform for Single Port Access Surgery Authors: Bajo, Andrea; Goldman, Roger E.; Wang, Long; Fowler, Dennis; Simaan, Nabil
    In this paper, we present the integration and preliminary evaluation of a novel Insertable Robotic Effectors Platform (IREP) for Single Port Access Surgery (SPAS). The unique design of the IREP includes planar parallel mechanisms, continuum snake-like arms, wire-actuated wrists, and passive flexible components. While this design has advantages, it presents challenges in terms of modeling, control, and telemanipulation. The complete master-slave resolved-rates telemanipulation framework of the IREP along with its actuation compensation is presented. Experimental evaluation of the capabilities of this new surgical system include bi-manual exchange of rings, pick-and-place tasks, suture passing and knot tying. Results show that the IREP meets the minimal workspace and dexterity requirements specified for laparoscopic surgery, it allows for dual-arm operations such as tool exchange and knot tying in confined spaces. Although it was possible to tie a surgeon's knot with minimal training, suture passing was difficult due to the limited axial rotation of the distal wrists.
  • Constrained Filtering with Contact Detection Data for the Localization and Registration of Continuum Robots in Flexible Environments Authors: Tully, Stephen; Bajo, Andrea; Kantor, George; Choset, Howie; Simaan, Nabil
    This paper presents a novel filtering technique that uses contact detection data and environmental stiffness estimates to register and localize a robot with respect to an a priori 3D surface model. The algorithm leverages geometric constraints within a Kalman filter framework and relies on two distinct update procedures: 1) an equality constrained step for when the robot is forcefully contacting the environment, and 2) an inequality constrained step for when the robot lies in the freespace of the environment. This filtering procedure registers the robot by incrementally eliminating probabilistically infeasible state space regions until a high likelihood solution emerges. In addition to registration and localization, the algorithm can estimate the deformation of the surface model and can detect false positives with respect to contact estimation. This method is experimentally evaluated with an experiment involving a continuum robot interacting with a bench-top flexible structure. The presented algorithm produces an experimental error in registration (with respect to the end-effector position) of 1.1 mm, which is less than 0.8 percent of the robot length.
  • Real-Time Control Architecture of a Novel Single-Port Laparoscopy Bimanual Robot (SPRINT) Authors: Niccolini, Marta; Petroni, Gianluigi; Menciassi, Arianna; Dario, Paolo
    This paper presents a novel master-slave teleoperated robotic platform designed for Single Port Laparoscopy. The SPRINT (Single-Port lapaRoscopy bimaNual roboT) is composed of two high-dexterity 6 Degrees of Freedom (DOFs) robotic arms, a stereoscopic camera and a dedicated console for the robot control by the surgeon. Along with a short summary of the hardware features of the system, this paper describes the real-time control architecture of the SPRINT. Particular attention was given to the kinematic coupling between the master and the slave manipulators, as well as to the inverse kinematics algorithm. Tests performed to validate the performance of the robot in terms of accuracy are satisfactory, thus positioning the SPRINT as a candidate for the next generation of robots for Single Port Laparoscopy.
  • Remote Centre-Of-Motion Control Algorithms of 6-RRCRR Parallel Robot Assisted Surgery System (PRAMiSS) Authors: Moradi Dalvand, Mohsen; Shirinzadeh, Bijan
    In this paper a 6-RRCRR parallel robot assisted minimally invasive surgery/microsurgery system (PRAMiSS) is introduced. Remote centre-of-motion (RCM) control algorithms of PRAMiSS suitable for minimally invasive surgery and microsurgery are also presented. The programmable RCM approach is implemented in order to achieve manipulation under the constraint of moving through the fixed penetration point. Having minimised the displacements of the mobile platform of the parallel micropositioning robot, the algorithms also apply orientation constraint to the instrument and prevent the tool tip to orient due to the robot movements during the manipulation. Experimental results are provided to verify accuracy and effectiveness of the proposed RCM control algorithms for minimally invasive surgery.