The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform

Dinesh Manocha - One of the best experts on this subject based on the ideXlab platform.

  • efficient probabilistic Collision Detection for non gaussian noise distributions
    International Conference on Robotics and Automation, 2020
    Co-Authors: Jae Sung Park, Dinesh Manocha
    Abstract:

    We present an efficient algorithm to compute tight upper bounds of Collision probability between two objects with positional uncertainties, whose error distributions are represented with non-Gaussian forms. Our approach can handle noisy datasets from depth sensors, whose distributions may correspond to Truncated Gaussian, Weighted Samples, or Truncated Gaussian Mixture Model. We derive tight probability bounds for convex shapes and extend them to non-convex shapes using hierarchical representations. We highlight the benefits of our approach over prior probabilistic Collision Detection algorithms in terms of tighter bounds (10x) and improved running time (3x). Moreover, we use our tight bounds to design an efficient and accurate motion planning algorithm for a 7-DOF robot arm operating in tight scenarios with sensor and motion uncertainties.

  • probabilistic Collision Detection between noisy point clouds using robust classification
    International Symposium on Robotics, 2017
    Co-Authors: Jia Pan, Sachin Chitta, Dinesh Manocha
    Abstract:

    We present a new Collision Detection algorithm to perform contact computations between noisy point cloud data. Our approach takes into account the uncertainty that arises due to discretization error and noise, and formulates Collision checking as a two-class classification problem. We use techniques from machine learning to compute the Collision probability for each point in the input data and accelerate the computation using stochastic traversal of bounding volume hierarchies. We highlight the performance of our algorithm on point clouds captured using PR2 sensors as well as synthetic data sets, and show that our approach can provide a fast and robust solution for handling uncertainty in contact computations.

  • fast continuous Collision Detection using deforming non penetration filters
    SI3D, 2010
    Co-Authors: Min Tang, Dinesh Manocha, Ruofeng Tong
    Abstract:

    We present a novel culling algorithm that uses deforming non-penetration filters to improve the performance of continuous Collision Detection (CCD) algorithms. The underlying idea is to use a simple and effective filter that reduces both the number of false positives and the elementary tests between the primitives. This filter is derived from the coplanarity condition and can be easily combined with other methods used to accelerate CCD. We have implemented the algorithm and tested its performance on many non-rigid simulations. In practice, we can reduce the number of false positives significantly and improve the overall performance of CCD algorithms by 1.5--8.2x.

  • iccd interactive continuous Collision Detection between deformable models using connectivity based culling
    IEEE Transactions on Visualization and Computer Graphics, 2009
    Co-Authors: Min Tang, Sean Curtis, Sungeui Yoon, Dinesh Manocha
    Abstract:

    We present an interactive algorithm for continuous Collision Detection between deformable models. We introduce multiple techniques to improve the culling efficiency and the overall performance of continuous Collision Detection. First, we present a novel formulation for continuous normal cones and use these normal cones to efficiently cull large regions of the mesh as part of self-Collision tests. Second, we introduce the concept of ldquoprocedural representative trianglesrdquo to remove all redundant elementary tests between nonadjacent triangles. Finally, we exploit the mesh connectivity and introduce the concept of ldquoorphan setsrdquo to eliminate redundant elementary tests between adjacent triangle primitives. In practice, we can reduce the number of elementary tests by two orders of magnitude. These culling techniques have been combined with bounding volume hierarchies and can result in one order of magnitude performance improvement as compared to prior Collision Detection algorithms for deformable models. We highlight the performance of our algorithm on several benchmarks, including cloth simulations, N-body simulations, and breaking objects.

  • fast Collision Detection for deformable models using representative triangles
    Interactive 3D Graphics and Games, 2008
    Co-Authors: Sean Curtis, Rasmus Tamstorf, Dinesh Manocha
    Abstract:

    We present a new approach to accelerate Collision Detection for deformable models. Our formulation applies to all triangulated models and significantly reduces the number of elementary tests between features of the mesh, i.e., vertices, edges and faces. We introduce the notion of Representative-Triangles, standard geometric triangles augmented with mesh feature information and use this representation to achieve better Collision query performance. The resulting approach can be combined with bounding volume hierarchies and works well for both inter-object and self-Collision Detection. We demonstrate the benefit of Representative-Triangles on continuous Collision Detection for cloth simulation and N-body Collision scenarios. We observe up to a one-order of magnitude reduction in feature-pair tests and up to a 5X improvement in query time.

Stephane Redon - One of the best experts on this subject based on the ideXlab platform.

  • Continuous Collision Detection for Articulated Models using Taylor Models and Temporal Culling
    ACM Transactions on Graphics, 2007
    Co-Authors: Xinyu Zhang, Stephane Redon, Minkyoung Lee, Young Kim
    Abstract:

    We present a fast continuous Collision Detection (CCD) algorithm for articulated models using Taylor models and temporal culling. Our algorithm is a generalization of conservative advancement (CA) from convex models [Mirtich 1996] to articulated models with non-convex links. Given the initial and final configurations of a moving articulated model, our algorithm creates a continuous motion with constant translational and rotational velocities for each link, and checks for interferences between the articulated model under continuous motion and other models in the environment and for self-Collisions. If Collisions occur, our algorithm reports the first time of contact (TOC) as well as Collision witness features. We have implemented our CCD algorithm and applied it to several challenging scenarios including locomotion generation, articulated-body dynamics and character motion planning. Our algorithm can perform CCDs including self-Collision Detection for articulated models consisting of many links and tens of thousands of triangles in 1.22 ms on average running on a 3.6 GHz Pentium 4 PC. This is an improvement on the performance of prior algorithms of more than an order of magnitude.

  • cullide interactive Collision Detection between complex models in large environments using graphics hardware
    International Conference on Computer Graphics and Interactive Techniques, 2005
    Co-Authors: Naga K Govindaraju, Ming C. Lin, Stephane Redon, Dinesh Manocha
    Abstract:

    We present a novel approach for Collision Detection between multiple deformable and breakable objects in a large environment using graphics hardware. Our algorithm takes into account low bandwidth to and from the graphics cards and computes a potentially colliding set (PCS) using visibility queries. It involves no precomputation and proceeds in multiple stages: PCS computation at an object level and PCS computation at sub-object level, followed by exact Collision Detection. We use a linear time two-pass rendering algorithm to compute each PCS efficiently. The overall approach makes no assumption about the input primitives or the object's motion and is directly applicable to all triangulated models. It has been implemented on a PC with NVIDIA GeForce FX 5800 Ultra graphics card and applied to different environments composed of a high number of moving objects with tens of thousands of triangles. It is able to compute all the overlapping primitives up to image-space resolution in a few milliseconds.

  • fast continuous Collision Detection and handling for desktop virtual prototyping
    Virtual Reality, 2004
    Co-Authors: Stephane Redon
    Abstract:

    This paper presents an overview of our recent work on continuous Collision Detection methods and constraints handling for rigid polyhedral objects. We demonstrate that continuous Collision Detection algorithms are practical in interactive dynamics simulation of complex polyhedral rigid bodies and show how continuous Collision Detection and efficient constraint-based dynamics algorithms allow us to perform various virtual prototyping tasks intuitively, precisely and robustly on commodity desktop computers. Especially, we present two applications of our system to actual industrial cases. We note that both tasks are performed with a simple 2D mouse on a high-end computer.

  • CULLIDE: Interactive Collision Detection between complex models in large environments using graphics hardware
    2003
    Co-Authors: Naga K Govindaraju, Ming C. Lin, Stephane Redon, Dinesh Manocha
    Abstract:

    We present a novel approach for fast Collision Detection between multiple deformable and breakable objects in a large environment using graphics hardware. Our algorithm takes into account low bandwidth to and from the graphics cards and computes a potentially colliding set (PCS) using visibility queries. It involves no precomputation and proceeds in multiple stages: PCS computation at an object level and PCS computation at sub-object level, followed by exact Collision Detection. We use a linear time two-pass rendering algorithm to compute each PCS efficiently. The overall approach makes no assumption about the input primitives or the object's motion and is directly applicable to all triangulated models. It has been implemented on a PC with NVIDIA GeForce FX 5800 Ultra graphics card and applied to different environments composed of a high number of moving objects with tens of thousands of triangles. It is able to compute all the overlapping primitives between different objects up to image-space resolution in a few milliseconds.

  • Fast Continuous Collision Detection between Rigid Bodies
    Computer Graphics Forum, 2002
    Co-Authors: Stephane Redon, Abderrahmane Kheddar, Sabine Coquillart
    Abstract:

    This paper introduces a fast continuous Collision Detection technique for polyhedral rigid bodies. As opposed to most Collision Detection techniques, the computation of the first contact time between two objects is inherently part of the algorithm. The method can thus robustly prevent objects interpenetrations or Collisions misses, even when objects are thin or have large velocities. The method is valid for general objects (polygon soups), handles multiple moving objects and acyclic articulated bodies, and is efficient in low and high coherency situations. Moreover, the method can be used to speed up existent continuous Collision Detection methods for parametric or implicit rigid surfaces. The Collision Detection algorithms have been successfully coupled to a real-time dynamics simulator. Various experiments are conducted that show the method's ability to produce high-quality interaction (precise objects positioning for example) between models up to tens of thousands of triangles, which couldn't have been performed with previous continuous methods.

Michael C Yip - One of the best experts on this subject based on the ideXlab platform.

  • learning based proxy Collision Detection for robot motion planning applications
    IEEE Transactions on Robotics, 2020
    Co-Authors: Nikhil Das, Michael C Yip
    Abstract:

    This article demonstrates that Collision Detection-intensive applications such as robotic motion planning may be accelerated by performing Collision checks with a machine learning model. We propose Fastron, a learning-based algorithm, to model a robot's configuration space to be used as a proxy Collision detector in place of standard geometric Collision checkers. We demonstrate that leveraging the proxy Collision detector results in up to an order of magnitude faster performance in robot simulation and planning than state-of-the-art Collision Detection libraries. Our results show that Fastron learns a model more than 100 times faster than a competing C-space modeling approach, while also providing theoretical guarantees of learning convergence. Using the open motion planning libraries (OMPLs), we were able to generate initial motion plans across all experiments with varying robot and environment complexities and workspace obstacle locations. With Fastron, we can repeatedly generate new motion plans at a 56 Hz rate, showing its application toward autonomous surgical assistance task in shared environments with human-controlled manipulators. All performance gains were achieved despite using only CPU-based calculations, suggesting further computational gains with a GPU approach that can parallelize tensor algebra. Code is available online. 1

  • learning based proxy Collision Detection for robot motion planning applications
    arXiv: Robotics, 2019
    Co-Authors: Nikhil Das, Michael C Yip
    Abstract:

    This paper demonstrates that Collision Detection-intensive applications such as robotic motion planning may be accelerated by performing Collision checks with a machine learning model. We propose Fastron, a learning-based algorithm to model a robot's configuration space to be used as a proxy Collision detector in place of standard geometric Collision checkers. We demonstrate that leveraging the proxy Collision detector results in up to an order of magnitude faster performance in robot simulation and planning than state-of-the-art Collision Detection libraries. Our results show that Fastron learns a model more than 100 times faster than a competing C-space modeling approach, while also providing theoretical guarantees of learning convergence. Using the OMPL motion planning libraries, we were able to generate initial motion plans across all experiments with varying robot and environment complexities. With Fastron, we can repeatedly perform planning from scratch at a 56 Hz rate, showing its application toward autonomous surgical assistance task in shared environments with human-controlled manipulators. All performance gains were achieved despite using only CPU-based calculations, suggesting further computational gains with a GPU approach that can parallelize tensor algebra. Code is available online.

Gabriel Zachmann - One of the best experts on this subject based on the ideXlab platform.

  • simdop simd optimized bounding volume hierarchies for Collision Detection
    Intelligent Robots and Systems, 2019
    Co-Authors: Toni Tan, Rene Weller, Gabriel Zachmann
    Abstract:

    We present a novel data structure for SIMD optimized simultaneous bounding volume hierarchy (BVH) traversals like they appear for instance in Collision Detection tasks. In contrast to all previous approaches, we consider both the traversal algorithm and the construction of the BVH. The main idea is to increase the branching factor of the BVH according to the available SIMD registers and parallelize the simultaneous BVH traversal using SIMD operations. This requires a novel BVH construction method because traditional BVHs for Collision Detection usually are simple binary trees. To do that, we present a new BVH construction method based on a clustering algorithm, Batch Neural Gas, that is able to build efficient n-ary tree structures along with SIMD optimized simultaneous BVH traversal. Our results show that our new data structure outperforms binary trees significantly.

  • hardware accelerated Collision Detection using bounded error fixed point arithmetic
    International Conference in Central Europe on Computer Graphics and Visualization, 2006
    Co-Authors: Andreas Raabe, Stefan Hochgurtel, Joachim K Anlauf, Gabriel Zachmann
    Abstract:

    A novel approach for highly space-efficient hardware-accelerated Collision Detection is presented. This paper focuses on the architecture to traverse bounding volume hierarchies in hardware. It is based on a novel algorithm for testing discretely oriented polytopes (DOPs) for overlap, utilizing only fixed-point (i.e., integer) arithmetic. We derive a bound on the deviation from the mathematically correct result and give formal proof that no false negatives are produced. Simulation results show that real-time Collision Detection of complex objects at rates required by force-feedback and physicallybased simulations can be obtained. In addition, synthesis results prove the architecture to be highly space efficient. We compare our FPGA-optimized design with a fully parallelized ASIC-targeted architecture and a software implementation.

  • Collision Detection for Deformable Objects
    Computer Graphics Forum, 2005
    Co-Authors: Matthias Teschner, Gabriel Zachmann, Stefan Kimmerle, Bruno Heidelberger, Laks Raghupathi, Marie-paule Cani, François Faure, Nadia Magnenat-thalmann, Arnulph Fuhrmann, Wolfgang Strasser
    Abstract:

    Interactive environments for dynamically deforming objects play an important role in surgery simulation and entertainment technology. These environments require fast deformable models and very efficient Collision handling techniques. While Collision Detection for rigid bodies is well investigated, Collision Detection for deformable objects introduces additional challenging problems. This paper focuses on these aspects and summarizes recent research in the area of deformable Collision Detection. Various approaches based on bounding volume hierarchies, distance fields and spatial partitioning are discussed. In addition, image-space techniques and stochastic methods are considered. Applications in cloth modeling and surgical simulation are presented.

  • Collision Detection for Deformable Objects
    Computer Graphics Forum, 2005
    Co-Authors: Matthias Teschner, Gabriel Zachmann, Stefan Kimmerle, Bruno Heidelberger, Laks Raghupathi, Arnulph Fuhrman, Marie-paule Cani, François Faure, Nadia Magnenat-thalmann, Wolfgang Strasser
    Abstract:

    Interactive environments for dynamically deforming objects play an important role in surgery simulation and entertainment technology. These environments require fast deformable models and very efficient Collision han- dling techniques. While Collision Detection for rigid bodies is well-investigated, Collision Detection for deformable objects introduces additional challenging problems. This paper focuses on these aspects and summarizes recent research in the area of deformable Collision Detection. Various approaches based on bounding volume hierarchies, distance fields, and spatial partitioning are discussed. Further, image-space techniques and stochastic methods are considered. Applications in cloth modeling and surgical simulation are presented.

  • Point Cloud Collision Detection
    Computer Graphics Forum, 2004
    Co-Authors: Jan Klein, Gabriel Zachmann
    Abstract:

    In the past few years, many efficient rendering and surface reconstruction algorithms for point clouds have been developed. However, Collision Detection of point clouds has not been considered until now, although this is a prerequisite to use them for interactive or animated 3D graphics. We present a novel approach for time-critical Collision Detection of point clouds. Based solely on the point representation, it can detect intersections of the underlying implicit surfaces. The surfaces do not need to be closed. We construct a point hierarchy where each node stores a sufficient sample of the points plus a sphere covering of a part of the surface. These are used to derive criteria that guide our hierarchy traversal so as to increase convergence. One of them can be used to prune pairs of nodes, the other one is used to prioritize still to be visited pairs of nodes. At the leaves we efficiently determine an intersection by estimating the smallest distance. We have tested our implementation for several large point cloud models. The results show that a very fast and precise answer to Collision Detection queries can always be given.

H Inoue - One of the best experts on this subject based on the ideXlab platform.

  • real time and precise self Collision Detection system for humanoid robots
    International Conference on Robotics and Automation, 2005
    Co-Authors: Kei Okada, Masayuki Inaba, H Inoue
    Abstract:

    In this paper, we describe the real-time and precise self Collision Detection system that does not reduce the number of polygons and checks more than 100 Collision pairs in real-time by using AABB based Collision Detection libraries. Previous researches on Collision Detection of humanoid robots which reduce Collision pairs or simplify a shape of a robot has disadvantages such as increasing the dangerousness or decreasing range of movement. However our self Collision Detection system uses detailed geometric model and Collision pairs as many as possible. We have experimentally evaluated Collision Detection libraries on a real-time self Collision Detection application of a humanoid robot. This experiment suggests that AABBs based method is much faster than conventional OBBs based method. Finally, we demonstrated real-time Collision Detection and avoidance function that automatically stops entire motion if self Collision occurs using HRP2 humanoid robot.

  • self Collision Detection and prevention for humanoid robots
    International Conference on Robotics and Automation, 2002
    Co-Authors: James J Kuffner, Masayuki Inaba, Koichi Nishiwaki, Satoshi Kagami, Yasuo Kuniyoshi, H Inoue
    Abstract:

    We present an approach to self-Collision Detection suitable for complex articulated robots such as humanoids. Preventing self-Collisions is vital for the safe operation of robots that generate body trajectories online. Our approach uses a fast distance determination method for convex polyhedra in order to conservatively guarantee that a given trajectory is free of self-Collision. Experimental results using an online joystick control application for the humanoid robot "H7" demonstrate the feasibility and effectiveness of the method.