Rosen Diankov's research while affiliated with Carnegie Mellon University and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (15)
![Fig. 1. OpenRAVE Architecture (Picture reproduced from [22])](profile/Beatriz-Leon/publication/233910780/figure/fig1/AS:299963448872966@1448528267880/OpenRAVE-Architecture-Picture-reproduced-from-22_Q320.jpg)
Abstract One of the challenges in developing real-world autonomous,robots is the need for integrating and rigorously test- ing high-level scripting, motion planning, perception, and control algorithms. For this purpose, we introduce an open-source cross-platform software architecture called OpenRAVE, the Open Robotics and Animation Virtual Envi- ro...
Simulation is essential for different robotic research fields such as mobile robotics, motion planning and grasp planning.
For grasping in particular, there are no software simulation packages, which provide a holistic environment that can deal
with the variety of aspects associated with this problem. These aspects include development and testing o...
This paper evaluates the dynamic and kinematic properties of a prismatic mechanism and shows its capabilities in performing home manipulation tasks when integrated into a robotic arm. Our design is motivated from the observation that human hand motions often follow a linear trajectory when manipulating everyday objects. We present the mechanical de...
We present a vision-centric manipulation framework for reliably performing reach-and-grasp tasks in everyday environments. By combining grasp planning and visual feedback algorithms, and constantly considering sensor visibility, the framework can recover from sensor calibration errors and unexpected changes in the environment. Although many current...
In this paper we present a comprehensive perception system with applications to mobile manipulation and grasping for personal robotics. Our approach makes use of dense 3D point cloud data acquired using stereo vision cameras by projecting textured light onto the scene. To create models suitable for grasping, we extract the supporting planes and mod...
We describe the architecture, algorithms, and experiments with HERB, an autonomous mobile manipulator that performs useful manipulation tasks in the home. We present new algorithms for searching
for objects, learning to navigate in cluttered dynamic indoor scenes, recognizing and registering objects accurately in high
clutter using vision, manipula...
State-of-the-art robotics research on such topics as manipulation, motion planning, micro-robotics, distributed systems, autonomous navigation, and mapping.
Robotics: Science and Systems IV spans a wide spectrum of robotics, bringing together researchers working on the foundations of robotics, robotics applications, and analysis of robotics systems...
We present a planning algorithm called BiSpace that produces fast plans to complex high-dimensional problems by simultaneously exploring multiple spaces. We specifically focus on finding robust solutions to manipulation and grasp planning problems by using BiSpace's special characteristics to explore the work and configuration spaces of the environ...
We present a novel motion planning algorithm for performing constrained tasks such as opening doors and drawers by robots such as humanoid robots or mobile manip-ulators. Previous work on constrained manipulation transfers rigid constraints imposed by the target object motion directly into the robot configuration space. This often unnecessarily res...
This paper combines grasp analysis and manipulation planning techniques to perform fast grasp planning in complex scenes. In much previous work on grasping, the object being grasped is assumed to be the only object in the environment. Hence the grasp quality metrics and grasping strategies developed do not perform well when the object is close to o...
This paper explores the use of statical learning methods on randomized path planning algorithms. A continuous, randomized version of A* is presented along with an empirical analysis showing planning time convergence rates in the robotic manipulation domain. The algorithm relies on several heuristics that capture a manipulator's kinematic feasibilit...
1. Why COLLADA? The robotics industry is overflowing with open and proprietary robot file formats. It seems that every major program and library has its own format and own set of quirks. Furthermore, no matter how hard a developer attempts to unify the robotics information, there will always be information that another devel-oper wants to insert. A...
We present an autonomous multi-robot system that can collect objects from indoor environments and load them into a dishwasher rack. We discuss each component of the system in detail and highlight the perception, navigation, and ma- nipulation algorithms employed. We present results from several public demonstra- tions, including one in which the sy...
1. Abstract Using the OpenRAVE motion planning system, we show the minimal number of steps to get the JSK Kitchen Assistant Robot to autonomously pick-up cups and dishes from the sink and place them in a dishwasher (Figure 2). Starting from just the basic CAD and kinematics models of the robot and target objects, it took a total of 9 hours of devel...
Citations
![[object Object]](https://i1.rgstatic.net/ii/profile.image/445070081040385-1483124384051_Q64/Siddhartha-Srinivasa.jpg)
... COLLADA has not been developed for robotic applications. However, it was shown how the format could be modified to work with robots and translate scenes between different simulators [20]. The authors identified two main features of COLLADA: ...
... Constructive approaches successfully tried to overcome a few of these issues by performing random or heuristic restarts from random initial configurations [6]. Although algebraic [7,8] approaches are very convincing and have high acceptance rates due to their extremely low computational cost but encounter problems by highly articulated, constrained and increasingly complex kinematic models and thus lack in scalability. Same drawback holds for solutions that rely on expensive precomputation and reachability analysis [9] so therefore are restricted to a lower-dimensional degree of freedom. ...
... The tactile feedback enables some local reactivity in grasping to account for sensor error or small grasp-target perturbances. Similar approaches are used on the Intel HERB platform in [6], [7]. Additionally, [8] uses a similar approach on the ARMAR-III robot for dual-arm grasping. ...
... Other widely used methods for numerical inverse kinematics solvers include Rosen Diankov's Open Robotics Automation Virtual Environment (OpenRave)'s IKFast [15] and Orocos Kinematics Dynamics Library (KDL) 2 . IKFast is fast but can have infinite solutions in solving some iterations of the inverse kinematics problem, as it cannot be used for arms of more than six degrees of freedom. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/282155050651649-1444282414411_Q64/James-Kuffner.jpg)
... The work begins in simulation and culminates in the development and testing of a novel spatial manipulator called the Model B. This hand has four fingers, each consisting of fully actuated two link serial chains; two opposing fingers on prismatic bases and two on a rotary base for abduction about an axis orthogonal to the palm. The hand was designed to perform manipulation while maintaining a cage on the object (Makita and Maeda, 2008a;Diankov et al., 2008;Rodriguez et al., 2012), allowing contact constraints to be relaxed and helping to enable more adventurous manipulation primitives without increasing the risk of object ejection. ...
... Early works focused on modeling robot dynamics and physical forces for parameter identification and controller modelling [31,53]. Several works then developed accurate physics engines for improving robot design and motion planning [7,13,15,28,33], and for specific domains such as grasping [36], soft robotics [27], and SDVs [88]. But to enable end-to-end testing of full autonomy systems, we must also simulate realistic sensor observations of the 3D environment for the robot to perceive, interact with its surroundings, and plan accordingly [19]. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/627652058689539-1526655320891_Q64/Beatriz-Leon.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/278783077699586-1443478473807_Q64/Stefan-Ulbrich-2.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/821923579695104-1572973260708_Q64/Ruediger-Dillmann.jpg)
... Once a goal point in the building is set, then the robot needs to move until it reaches the goal point. This scenario is important for the operation of many indoor robots, such as home robots [1,2], service robots [3,4] or nursing robots [5,6]. ...
... 3) Integrated Grasp and Motion Planning: The integrated grasp and motion planning provides automatic control for [168]. They then used a path planning method to filter collision-free grasps. ...
... Humans visually perceive the world with passive RGB views and are able to perform sophisticated interactions with objects even if the objects are unseen previously, translucent, reflective, or transparent. Robotic grasping primarily relies on RGB cameras [1], or active depth sensors such as ToF [2], LiDAR [3], and active stereo [4], to perform arbitrary object grasping using the simplified grasping representation in SE (2) or SE (3) with no prior knowledge such as explicit object models or category information. Existing learning-based approaches can be categorized in two directions, namely planar grasping and 6-DoF grasping. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/279553206439955-1443662086643_Q64/Andreas-Holzbach.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/272666749829125-1442020227314_Q64/Gary-Bradski-4.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/393868135682048-1470916889033_Q64/Michael-Beetz.jpg)
