List of all recorded talks

  • Place Representation in Topological Maps Based on Bubble Space Authors: Erkent, Ozgur; Bozma, Isil
    Place representation is a key element in topological maps. This paper presents bubble space - a novel representation for "places" (nodes) in topological maps. The novelties of this model are two-fold: First, a mathematical formalism that defines bubble space is presented. This formalism extends previously proposed bubble memory to accommodate two new variables -- varying robot pose and multiple features. Each bubble surface preserves the local $S^2-$metric relations of the incoming sensory data from the robot's viewpoint. Secondly, for learning and recognition, bubble surfaces can be transformed into bubble descriptors that are compact and rotationally invariant, while being computable in an incremental manner. The proposed model is evaluated with support vector machine based decision making in two different settings: first with a mobile robot placed in a variety of locations and secondly using benchmark visual data.
  • DP-FACT: Towards Topological Mapping and Scene Recognition with Color for Omnidirectional Camera Authors: Liu, Ming; Siegwart, Roland
    Topological mapping and scene recognition problems are still challenging, especially for online realtime vision-based applications. We develop a hierarchical probabilistic model to tackle them using color information. This work is stimulated by our previous work [1] which defined a lightweight descriptor using color and geometry information from segmented panoramic images. Our novel model uses a Dirichlet Process Mixture Model to combine color and geometry features which are extracted from omnidirectional images. The inference of the model is based on an approximation of conditional probabilities of observations given estimated models. It allows online inference of the mixture model in real-time (at 50Hz), which outperforms other existing approaches. A real experiment is carried out on a mobile robot equipped with an omnidirectional camera. The results show the competence against the state-of-art.
  • Acquiring Semantics Induced Topology in Urban Environments Authors: Singh, Gautam; Kosecka, Jana
    Methods for acquisition and maintenance of an environment model are central to a broad class of mobility and navigation problems. Towards this end, various metric, topological or hybrid models have been proposed. Due to recent advances in sensing and recognition, acquisition of semantic models of the environments have gained increased interest in the community. In this work, we will demonstrate a capability of using weak semantic models of the environment to induce different topological models, capturing the spatial semantics of the environment at different levels. In the first stage of the model acquisition, we propose to compute semantic layout of the street scenes imagery by recognizing and segmenting buildings, roads, sky, cars and trees. Given such semantic layout, we propose an informative feature characterizing the layout and train a classifier to recognize street intersections in challenging urban inner city scenes. We also show how the evidence of different semantic concepts can induce useful topological representation of the environment, which can aid navigation and localization tasks. To demonstrate the approach, we carry out experiments on a challenging dataset of omnidirectional inner city street views and report the performance of both semantic segmentation and intersection classification.
  • Large-scale Semantic Mapping and Reasoning with Heterogeneous Modalities Authors: Pronobis, Andrzej; Jensfelt, Patric
    This paper presents a probabilistic framework combining heterogeneous, uncertain, information such as object observations, shape, size, appearance of rooms and human input for semantic mapping. It abstracts multi-modal sensory information and integrates it with conceptual common-sense knowledge in a fully probabilistic fashion. It relies on the concept of spatial properties which make the semantic map more descriptive, and the system more scalable and better adapted for human interaction. A probabilistic graphical model, a chain-graph, is used to represent the conceptual information and perform spatial reasoning. Experimental results from online system tests in a large unstructured office environment highlight the system's ability to infer semantic room categories, predict existence of objects and values of other spatial properties as well as reason about unexplored space.
  • Robotic Finger Mechanism Equipped Omnidirectional Driving Roller with Two Active Rotational Axes Authors: Tadakuma, Kenjiro; Tadakuma, Riichiro; Higashimori, Mitsuru; Kaneko, Makoto
    This paper describes the finger mechanism with omnidirectional driving roller to realize the two active rotational axes on the surface of the grasped object. As the omnidirectional driving roller, we adopt the Omni-Crawler we developed: the crawler mechanism with circular cross section. This cylinderical tracked unit can be used as the roller and the fingers with this roller can manipulate the grasped object in the arbitrary axes. The basic concept of this finger is proposed.
  • Indoor and Outdoor Parametrized Gait Execution with Modular Snake Robots Authors: Melo, Kamilo; Paez, Laura; parra, carlos
    This video shows the mechanical structure, module length possibilities, skin options and some of the locomotion capabilities, including indoor and outdoor demonstrations of parametrized gaits for a modular snake robot, used to research at Pontificia Universidad Javeriana by the Systems, Intelligence, Robotics and Perception Research group (SIRP).
  • Quick Slip-Turn of HRP-4C on Its Toes Authors: Miura, Kanako; Kanehiro, Fumio; Kaneko, Kenji; Kajita, Shuuji; Yokoi, Kazuhito
    In this video, we present the realization of quick turning motion of a humanoid robot on its toes via slipping between its feet and the floor. A rotation model is described on the basis of our hypothesis that turning via slip occurs as a result of minimizing the power caused by floor friction. Using the model, the trajectory of the center of the foot can be generated to realize the desired rotational angle. Toe joints are used to realize quicker turning motion, while avoiding excessive motor load due to frictional torque. Quick slip-turn motion with toe support is successfully demonstrated using a humanoid robot HRP-4C.
  • Flight Stability in Aerial Redundant Manipulators Authors: Korpela, Christopher M.; Danko, Todd; McNeil, Clayton; Pisch, Robert; Oh, Paul Y.
    Ongoing efforts toward mobile manipulation from an aerial vehicle are presented. Recent tests and results from a prototype rotorcraft have shown that our hybrid structure increases stability during flight and manipulation. Since UAVs require significant setup time, suitable testing locations, and have tendencies to crash, we developed an aerial manipulation test and evaluation environment that provides controllable and repeatable experiments. By using force feedback techniques, we have designed multiple, dexterous, redundant manipulators that can grasp objects such as tools and small objects. These manipulators are controlled in concert with an emulated aerial platform to provide hovering stability. The manipulator and aircraft flight control are tightly coupled to facilitate grasping without large perturbations in the end-effector.
  • Study on the Omnidirectional Driving Gear Mechanism Authors: Tadakuma, Kenjiro; Tadakuma, Riichiro; Ioka, Kyohei; Kudo, Takeshi; Takagi, Minoru; Tsumaki, Yuichi; Higashimori, Mitsuru; Kaneko, Makoto
    As ordinary dual-axis driving mechanisms in X-Y directions, for example, commercially available X-Y stages with ball screws are familiar. However, such driving mechanisms have two stages, namely both upper and lower linear actuators, the latter of which must generate sufficient thrust to carry large weights, including that of the upper actuator mechanism, which has hampered efforts to achieve suitably fast and smooth driving motion due to the inertial force effect. It is also difficult to achieve a small and slimline driving mechanism with such overlapping two-stage structure. In these ordinary two-stage driving mechanisms, the motion of the X-Y stage can be disturbed by the cords of the upper actuator. In this research, we have considered the abovementioned problems, and propose a new omnidirectional driving gear mechanism that enhances its driving area from the normal X-Y plane to convex and concave curved surfaces respectively, and even various combinations of both. The smoothness of basic omnidirectional motion and effectiveness of the driving method of this proposed omnidirectional driving gear mechanism have been confirmed with several experiments involving our setups.
  • Over-Tube Apparatus for Increasing the Capabilities of an Articulated Robotic Probe Authors: Degani, Amir; Tully, Stephen; Zubiate, Brett; Choset, Howie
    This video elaborates on a new active and controllable over-tube addition to the highly articulated robotic probe; the HARP. This over-tube allows the current HARP mechanism to double its overall length and allows it to perform more complex tasks. We explain the design concept of the current HARP and the novel over-tube mechanism and show two proof-of-concept experiments demonstrating the use of the active over-tube.