Single Point of Contact Manipulation of Unknown Objects Stuart Anderson Advisor: Reid Simmons School of Computer Science Carnegie Mellon University.

Slides:



Advertisements
Similar presentations
TARGET DETECTION AND TRACKING IN A WIRELESS SENSOR NETWORK Clement Kam, William Hodgkiss, Dept. of Electrical and Computer Engineering, University of California,
Advertisements

Mobile Robot Localization and Mapping using the Kalman Filter
Chapters 17, 18 Review. Der Innere Schweinehund (The inner Pigdog)
Partially Observable Markov Decision Process (POMDP)
SA-1 Probabilistic Robotics Planning and Control: Partially Observable Markov Decision Processes.
Rotational Motion Chapter Opener. Caption: You too can experience rapid rotation—if your stomach can take the high angular velocity and centripetal acceleration.
Chapter 9 Rotational Dynamics.
Department of Computer Science, Iowa State University Robot Grasping of Deformable Objects Yan-Bin Jia (joint work with Ph.D. students Feng Guo and Huan.
Reducing Drift in Parametric Motion Tracking
(Includes references to Brian Clipp
Lab 2 Lab 3 Homework Labs 4-6 Final Project Late No Videos Write up
Visual Recognition Tutorial
Kalman’s Beautiful Filter (an introduction) George Kantor presented to Sensor Based Planning Lab Carnegie Mellon University December 8, 2000.
ME 4135 Fall 2011 R. R. Lindeke, Ph. D. Robot Dynamics – The Action of a Manipulator When Forced.
The L-E (Torque) Dynamical Model: Inertial Forces Coriolis & Centrifugal Forces Gravitational Forces Frictional Forces.
TOWARD DYNAMIC GRASP ACQUISITION: THE G-SLAM PROBLEM Li (Emma) Zhang and Jeff Trinkle Department of Computer Science, Rensselaer Polytechnic Institute.
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
SLAM: Simultaneous Localization and Mapping: Part I Chang Young Kim These slides are based on: Probabilistic Robotics, S. Thrun, W. Burgard, D. Fox, MIT.
Nonlinear and Non-Gaussian Estimation with A Focus on Particle Filters Prasanth Jeevan Mary Knox May 12, 2006.
Tracking using the Kalman Filter. Point Tracking Estimate the location of a given point along a sequence of images. (x 0,y 0 ) (x n,y n )
Manipulator Dynamics Amirkabir University of Technology Computer Engineering & Information Technology Department.
Introduction What is this ? What is this ? This project is a part of a scientific research in machine learning, whose objective is to develop a system,
Single Point of Contact Manipulation of Unknown Objects Stuart Anderson Advisor: Reid Simmons School of Computer Science Carnegie Mellon University.
Physics 121 Topics: Course announcements Newton’s Law of Motion: Review of Newton’s First, Second, and Third Law of Motion Problem Solving Strategies Friction:
Work Let us examine the work done by a torque applied to a system. This is a small amount of the total work done by a torque to move an object a small.
Physics. Session Rotational Mechanics - 6 Session Objectives.
Lecture VII Rigid Body Dynamics CS274: Computer Animation and Simulation.
T. K. Ng, HKUST Lecture IV. Mechanics of rigid bodies.
Tracking Pedestrians Using Local Spatio- Temporal Motion Patterns in Extremely Crowded Scenes Louis Kratz and Ko Nishino IEEE TRANSACTIONS ON PATTERN ANALYSIS.
Robot Dynamics – Slide Set 10 ME 4135 R. R. Lindeke, Ph. D.
Chapter 10 Rotation of a Rigid Object about a Fixed Axis.
Dynamics.  relationship between the joint actuator torques and the motion of the structure  Derivation of dynamic model of a manipulator  Simulation.
Chapter 5 Trajectory Planning 5.1 INTRODUCTION In this chapters …….  Path and trajectory planning means the way that a robot is moved from one location.
Chapter 5 Trajectory Planning 5.1 INTRODUCTION In this chapters …….  Path and trajectory planning means the way that a robot is moved from one location.
Mapping and Localization with RFID Technology Matthai Philipose, Kenneth P Fishkin, Dieter Fox, Dirk Hahnel, Wolfram Burgard Presenter: Aniket Shah.
ECE 8443 – Pattern Recognition ECE 8423 – Adaptive Signal Processing Objectives: Deterministic vs. Random Maximum A Posteriori Maximum Likelihood Minimum.
Questions From Reading Activity? Big Idea(s):  The interactions of an object with other objects can be described by forces.  Interactions between.
The L-E (Torque) Dynamical Model: Inertial Forces Coriolis & Centrifugal Forces Gravitational Forces Frictional Forces.
Young Ki Baik, Computer Vision Lab.
Karman filter and attitude estimation Lin Zhong ELEC424, Fall 2010.
ECE 8443 – Pattern Recognition LECTURE 07: MAXIMUM LIKELIHOOD AND BAYESIAN ESTIMATION Objectives: Class-Conditional Density The Multivariate Case General.
Natural Cost functions for contact selection Paul R. Schrater University of Minnesota Collaborators: Erik Schlicht, Erik Flister, Charles Sloane.
A Passive Approach to Sensor Network Localization Rahul Biswas and Sebastian Thrun International Conference on Intelligent Robots and Systems 2004 Presented.
Chapter 6 Motion In Two-Dimensional. Motion in Two Dimensions Using ________signs is not always sufficient to fully describe motion in more than one dimension.
Real-Time Simultaneous Localization and Mapping with a Single Camera (Mono SLAM) Young Ki Baik Computer Vision Lab. Seoul National University.
Spring Rigid Body Simulation. Spring Contents Unconstrained Collision Contact Resting Contact.
Chapter 7. Learning through Imitation and Exploration: Towards Humanoid Robots that Learn from Humans in Creating Brain-like Intelligence. Course: Robots.
Linear Momentum. Units of Momentum Momentum and Its Relation to Force Conservation of Momentum Collisions and Impulse Conservation of Energy and Momentum.
Apply the three equations of motion for a rigid body in planar motion. Analyze problems involving translational motion. PLANAR KINETIC EQUATIONS OF MOTION:
Robotics II Copyright Martin P. Aalund, Ph.D.
CS274 Spring 01 Lecture 7 Copyright © Mark Meyer Lecture VII Rigid Body Dynamics CS274: Computer Animation and Simulation.
Tracking with dynamics
SLAM Tutorial (Part I) Marios Xanthidis.
ES 07 These slides can be found at optimized for Windows)
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition Objectives: Statistical Significance Hypothesis Testing.
PHY205 Ch16: Rotational Dynamics 1.Combination Translational and Rotational motion and Atwood machine 2.Discuss Ball rolling down incline from 3 different.
Fundamentals of Computer Animation Rigid Body Simulation (1)
STATISTICS People sometimes use statistics to describe the results of an experiment or an investigation. This process is referred to as data analysis or.
11/25/03 3D Model Acquisition by Tracking 2D Wireframes Presenter: Jing Han Shiau M. Brown, T. Drummond and R. Cipolla Department of Engineering University.
Plane Dynamics of Rigid Bodies
Lecture Rigid Body Dynamics.
Kalman’s Beautiful Filter (an introduction)
Introduction to particle filter
CONCEPTS OF ESTIMATION
Manipulator Dynamics 2 Instructor: Jacob Rosen
Introduction to particle filter
Where did we stop? The Bayes decision rule guarantees an optimal classification… … But it requires the knowledge of P(ci|x) (or p(x|ci) and P(ci)) We.
Motion in Real and Virtual Worlds
Devil physics The baddest class on campus aP Physics
Presentation transcript:

Single Point of Contact Manipulation of Unknown Objects Stuart Anderson Advisor: Reid Simmons School of Computer Science Carnegie Mellon University

The Problem Given an object with unknown geometric and dynamic parameters, how can a robot discover these parameters? A six degree of freedom fiducial (pose sensor) is affixed to the object. We can manipulate the object by applying forces to its surface. Applied forces and fiducial observations have white gaussian noise

How can we learn about the world? Experimentation –Based on a belief about the state of the world make a prediction of what will happen when a particular action is taken. Then observe what really happens and incorporate this new information into the belief.

Learning Two approaches –Extensions to the Kalman filter –Particle Filter What do we learn about the system? –Geometry pre-selected set of normals learn their offsets, define a convex hull –Dynamics Parameters Mass, Inertial Tensor, Center of Mass, Coefficient of Friction

Physics The motion of a rigid body is described by the Newton-Euler equations. For simplicity, we use the term ‘wrench’ to describe vector composed of a force and a torque. We also introduce a generalize mass matrix. This allows us to write

Physics In order to predict the motion of an object, we need to know the forces applied to it. If we have some belief about the parameters of the object, then we can explicitly compute the wrench due to the manipulator and to gravity

Physics The contact wrench cannot be computed explicitly. The pressure at any given point is indeterminate and both the normal force and frictional force depend on it. This severely limits what can be known about the contact wrench

Physics So the total contact wrench falls within the convex hull of the wrenches produced by applying all pressure at a single point.

Physics We need to know more about these convex hulls. –The frictional load is modeled by Coulomb friction. The upper bound on the magnitude of the frictional load is linear in the contact pressure The direction of the frictional load at a given point is the direction that point is sliding. If the point is not sliding then the load direction is not known. Thus, when the object is sliding we have

Physics If the motion is a pure translation, then the direction of motion is constant for all points and So the set of w’(x) where x is the vertices of the convex hull of the contact region defines the convex hull of possible wrenches, and lies within a two dimensional slice of wrench space.

Physics If the motion is a generalized rotation then the direction of the frictional load is no longer linear in position. –The velocity of points on the surface is linear in X though.

Physics Since distance is linear in polar coordinates, we apply a change of coordinates to x. How do we visualize these equations?

Physics Developing an exact description of the convex wrench hull in this case is difficult. Instead, we take samples of w’(x) and show bounds on the error in the convex hull constructed from these samples. –Because w’(x) is linear in r we need only sample the minimal and maximal values of r for a given theta. –The number of samples needed for a given maximum error bound grows linearly in the radius of a circle centered at the rotation center which encloses the contact hull.

Physics Finally, when the object is not moving we take additional samples to model the indeterminacy in the direction of the frictional load.

Particle Filter Approximate the posterior distribution using a set of particles. –What’s a particle? A description of the system – a state vector –Lets us work with any system, don’t need to worry about linearization. –But we have to be careful or dimensionality becomes a problem. m(1), I(6), mu(1), cm(3), x(3), v(3),geom(~250)

Particle Filter Approach Given a particle b, when we make an observation o Then resample the distribution based on the relative likelihood of each particle.

Observations and Predictions We observe accelerations based on the fiducial movement. –Caveat: assume we take observations frequently enough that the forces applied to the object remain about constant. We can stop looking when bad stuff (impact) happens. –So we need to predict the acceleration based on state and force applied. –In general, we can’t get an explicit answer to this question since the contact pressure distribution is undetermined. –But we can compute bounds on the resulting contact force and torque based on the velocity, geometry, and applied force. We also observe the pose of the object, and use that to refine geometric estimates.

Particle Filter We can’t use a standard particle filter with our system, since it is not possible to compute p(o|b) exactly. –We let each particle have an upper and lower bound on its probability, instead of an explicit value. –But how to normalize the upper bound after an observation?

Particle Filter

How do we compute a new upper bound for a given particle?

Particle Filter We can solve a simpler case by quadratic programming. But we have no insight into finding the true normalized upper bound without resorting to general optimization strategies.

Planning and Behaviors Planning has a problem with dimensionality too. –The set of actions is a (potentially unconnected) path through the set of all forces at all points. –Behaviors are a way to deal with this Slide (maintaining current contact face) Switch contact face (a.k.a roll)

Uncertainty Given a set of particles, we can simulate a behavior many times, assuming a different particle to be the ‘truth’ each time. We can look at the statistics of these trials to see what effect a given behavior will have on the belief state. –Some behaviors tend to reduce the variance or entropy of the distribution. Pick these.

The Software Dynamics Simulation / Visualization –Human Interface –Planning Interface Geometric Reasoning –We can refine the convex hull and find the predicted contact hull. Wrench Reasoning –We can compute the probability of an observation within known and controllable error bounds for all motion cases. Particle Filter –Working implementation of the particle filter based on an incorrect assumption about the upper bound update. Behaviors –Slide, shift face. Reactive control is a little too good because the force can be shifted instantaneously.