SEMINAR ON GRASPING AND MANIPULATION SYSTEMS
 
Danica Kragic
Place: Medieteknik meeting room, Lindstedsv. 5, 3rd floor

 
 

Overview:

This seminar course will survey basics and recent research results on algorithms for sensor based robotic manipulation and grasping.

Specific emphasis will be placed on:
  • sensing and planning
  • human prehension
  • hybrid force/position control
  • task level specification
  • dexterous grasping
  • learning by demonstration

  • I will give a short intro to the topic at the beginning of each lecture.
    Students are expected to participate in class by reading, presenting and discussing research papers.  Grading, which is up to 3pt, will be based on participation and activity. Earned points will be registered as a part of Topics in robotics course.
     

    Clientele:

    Graduate students in computer science, electrical engineering, mechanical engineering and related disciplines. If you are interested in participating, send an email to danik@nada.kth.se.

    If you are interested in presenting one of the proposed papers, include that in your email.

    Outline

    This is the current plan for the course.   Links point to notes or to relevant papers.

    Week 33, August 14, 10-11.30:

    A short overview of grasping and manipulation systems - state of the art:

  • visual servoing
  • integrated systems

    Week 34, Friday August 22, 10-11.30:

    Grasping - stability issues.

  • Some Discussion of Static Gripping and Its Stability
    (B. Mishra and N. Silver) - J.Tegin

  • The synthesis of 3D form-closure grasps
    (D. Ding, Y.-H. Liu and S. Wang) - L. Jennergren

  • Week 35, Thursday August 28, 10-11.30:

    Perception.

  • Visual determination of 3D grasping points on unknown objects with a binocular camera system
    (A. Hauck, J. Ruttinger, M. Sorg and G. Farber) - S. Ekvall

  • Vision-based computation of three-finger grasps on unknown planar objects
    ( A. Morales, P.J. Sanz and A.P. del Pobil) - J. Folkeson

  • Week 36, Thursday September 4, 11-12.30:

    Sensor fusion.

  • Combining eye-in-hand Visual Servoing and Force Control in Robotic Tasks Usingthe Task Frame
    (J. Baeten, H. Bruyninckx, J. de Schutter) - L. Jennergren

  • Shared Control in Hybrid Vision/Force Robotic Servoing Using the Task Frame
    (J. Baeten, H. Bruyninckx, J. de Schutter) - J. Folkeson

  • Developing Haptic and Visual Perceptual Categories for Reachning and Grasping with a Humanoid Robot
    (C. Coelho, J. Piater and R. Grupen) - S. Cedervall

  • Week 37, Thursday September 11, 10-11.30:

    Path planning - Cell Decomposition and Potential Field Methods.

  • Algorithmic motion planning in robotics
    (M. Sharir) - J. Tegin

  • Rapidly-exploring random trees: Progress and prospects
    (S. M. LaValle and J.J. Kuffner) - F. Lingelbach

  • Exact Robot Navigation Using Artificial Potential Functions
    (E. Rimon and D.E. Koditscheck) - S. Cedervall

  • Week 39, Thursday September 25, 10-11.30:

    Path planning - Probabilistic Roadmaps.

  • Probabilistic roadmaps for path planning in high-dimensional configuration spaces
    (L. Kavraki, P. Svetstka, J-C. Latombe and M.H. Overmars) - B. Iliev

  • Path Planning Using Lazy PRM
    (R. Bohlin and L. Kavraki) - F. Lingelbach

  • Week 40, Friday October 3, 9.15 - 10.45 :

    Human prehension and biologically motivated systems.

  • Human prehension and dexterous robot hands
    (T. Iberall) - L. Jennergren, B. Iliev

  • What can be learnd from human reach2grasp movements for the design of robotic hand-eye systems?
    (A. Hauck, M. Sorg and T. Schenk) - M. Bratt

  • Behaviour-based mobile manipulation inspired by the human example
    (B.J.W. Waarsing, M. Nuttin and H. Van Brussel) - L. Wenfeng

  • Week 41, Friday October 10, 9.15 - 10.45:

    Integrated systems:

  • An integrated approach to achieve dexterous grasping from task level specification
    (C. Bard, C. Laugier, C. Milesi-Bellier) - M. Bratt

  • A hierarchical behaviour-based approach to manipulation tasks
    (Z. Wasik and A. Saffiotti), L. Wenfeng

  • Estimating finger contact location and object pose from contact measurements in 3D grasping
    (S. Haidacher and G. Hirzinger) - J. Tegin

  • Week 42, Friday October 17, 9.15 - 10.45:

    Learning by demonstration

  • Hidden Markov Model for intelligent extraction of robot trajectory command from demonstrated trajectories
    (S.K.Tso and K.P. Liu) - S. Ekvall

  • Modeling Human Assembly Actions from Observation
    (G.V. Paul, Y. Jiar, M.D. Wheeler and K. Ikeuchi) - J. Folkeson

  • Interactive Natural Programming of Robots: Introductory Overview
    ( R. Dillmann, R. Zöllner, M. Ehrenmann, O. Rogalla) - M. Bratt

  • Week 43, Thursday October 23, 14.00 - 15.00:

    CAS seminar

    Week 45, Friday November 14, 9.15 - 10.45:

    Dynamics and programming environments.

  • Implementation of Multi-rigid-body Dynamics within a Robotic Grasping Simulator
    (A.T. Miller and H.I. Christensen) - S. Ekvall

  • Dynamic Motion Planning Whole Arm Grasp Systems Based of Switching Contact Modes
    (M. Yashima and H. Yamaguchi) - L. Wenfeng