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 support@techtalks.tv

Planning and Navigation of Biped Walking

  • Real-Time Footstep Planning for Humanoid Robots among 3D Obstacles Using a Hybrid Bounding Box Authors: Perrin, Nicolas Yves; Stasse, Olivier; Lamiraux, Florent; Kim, Young J.; Manocha, Dinesh
    In this paper we introduce a new bounding box method for footstep planning for humanoid robots. Similar to the classic bounding box method (which uses a single rectangular box to encompass the robot) it is computationally efficient, easy to implement and can be combined with any rigid body motion planning library. However, unlike the classic bounding box method, our method takes into account the stepping over capabilities of the robot, and generates precise leg trajectories to avoid obstacles on the ground. We demonstrate that this method is well suited for footstep planning in cluttered environments.
  • Foot Placement for Planar Bipeds with Point Feet Authors: van Zutven, Pieter; Kostic, Dragan; Nijmeijer, Hendrik
    When humanoid robots are going to be used in society, they should be capable to maintain the balance. Knowing where to step appears to be crucially important to remain balanced. This paper contributes the foot placement indicator (FPI), an extension to the foot placement estimator (FPE) for planar bipeds with point feet and an arbitrary number of non-massless links. The method uses conservation of energy to determine where the planar biped needs to step to remain in balance. Simulations of the FPI show improved foot placement for balance with respect to the FPE.
  • A Framework for Extreme Locomotion Planning Authors: Dellin, Christopher; Srinivasa, Siddhartha
    A person practicing parkour is an incredible display of intelligent planning; he must reason carefully about his velocity and contact placement far into the future in order to locomote quickly through an environment. We seek to develop planners that will enable robotic systems to replicate this performance. An ideal planner can learn from examples and formulate feasible full-body plans to traverse a new environment. The proposed approach uses momentum equivalence to reduce the full-body system into a simplified one. Low-dimensional trajectory primitives are then composed by a sampling planner called Sampled Composition A* to produce candidate solutions that are adjusted by a trajectory optimizer and mapped to a full-body robot. Using primitives collected from a variety of sources, this technique is able to produce solutions to an assortment of simulated locomotion problems.
  • Adaptive Level-of-Detail Planning for Efficient Humanoid Navigation Authors: Hornung, Armin; Bennewitz, Maren
    In this paper, we consider the problem of efficient path planning for humanoid robots by combining grid-based 2D planning with footstep planning. In this way, we exploit the advantages of both frameworks, namely fast planning on grids and the ability to find solutions in situations where grid-based planning fails. Our method computes a global solution by adaptively switching between fast grid-based planning in open spaces and footstep planning in the vicinity of obstacles. To decide which planning framework to use, our approach classifies the environment into regions of different complexity with respect to the traversability. Experiments carried out in a simulated office environment and with a Nao humanoid show that (i) our approach significantly reduces the planning time compared to pure footstep planning and (ii) the resulting plans are almost as good as globally computed optimal footstep paths.
  • Dominant Sources of Variability in Passive Walking Authors: Nanayakkara, Thrishantha; Byl, Katie; Liu, Hongbin; Song, Xiaojing; Villabona, Tim
    This paper investigates possible sources of variability in the dynamics of legged locomotion, even in its most idealized form. The rimless wheel model is a seemingly deterministic legged dynamic system, popular within the legged locomotion community for understanding basic collision dynamics and energetics during passive phases of walking. Despite the simplicity of this legged model, however, experimental motion capture data recording the passive step-to-step dynamics of a rimless wheel down a constant-slope terrain actually demonstrates significant variability, providing strong evidence that stochasticity is an intrinsic-and thus unavoidable-property of legged locomotion that should be modeled with care when designing reliable walking machines. We present numerical comparisons of several hypotheses as to the dominant source(s) of this variability: 1) the initial distribution of the angular velocity, 2) the uneven profile of the leg lengths and 3) the distribution of the coefficients of friction and restitution across collisions. Our analysis shows that the 3rd hypothesis most accurately predicts the noise characteristics observed in our experimental data while the 1st hypothesis is also valid for certain contexts of terrain friction. These findings suggest that variability due to ground contact dynamics, and not simply due to geometric variations more typically modeled in terrain, is important in determining the stochasticity and resulting stability of walking robots. Althou
  • First Steps Toward Underactuated Human-Inspired Bipedal Robotic Walking Authors: Ames, Aaron
    This paper presents the first steps toward going from human data to formal controller design to experimental realization in the context of underactuated bipedal robots. Specifically, by studying experimental human walking data, we find that specific outputs of the human, i.e., functions of the kinematics, appear to be canonical to walking and are all characterized by a single function of time, termed a human walking function. Using the human outputs and walking function, we design a human-inspired controller that drives the output of the robot to the output of the human as represented by the walking function. The main result of the paper is an optimization problem that determines the parameters of this controller so as to guarantee stable underactuated walking that is as "close" as possible to human walking. This result is demonstrated through the simulation of a physical underactuated 2D bipedal robot, AMBER. Experimentally implementing this control on AMBER through "feed-forward" control, i.e., trajectory tracking, repeatedly results in 5-10 steps.

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.