Natural Cost functions for contact selection Paul R. Schrater University of Minnesota Collaborators: Erik Schlicht, Erik Flister, Charles Sloane.

Slides:



Advertisements
Similar presentations
Visual Servo Control Tutorial Part 1: Basic Approaches Chayatat Ratanasawanya December 2, 2009 Ref: Article by Francois Chaumette & Seth Hutchinson.
Advertisements

From Kinematics to Arm Control a)Calibrating the Kinematics Model b)Arm Motion Selection c)Motor Torque Calculations for a Planetary Robot Arm CS36510.
Analysis of Multifingered Hands Kerr and Roth 1986.
B659: Principles of Intelligent Robot Motion Spring 2013 David Tidd.
Manipulator Dynamics Amirkabir University of Technology Computer Engineering & Information Technology Department.
Dynamic Bayesian Networks (DBNs)
Kinematics & Grasping Need to know: Representing mechanism geometry Standard configurations Degrees of freedom Grippers and graspability conditions Goal.
Oklahoma State University Generative Graphical Models for Maneuvering Object Tracking and Dynamics Analysis Xin Fan and Guoliang Fan Visual Computing and.
Introduction to Control: How Its Done In Robotics R. Lindeke, Ph. D. ME 4135.
Dynamics of Articulated Robots Kris Hauser CS B659: Principles of Intelligent Robot Motion Spring 2013.
Visual Recognition Tutorial
Cursus Doelgericht Handelen (BPSN33) R.H. Cuijpers, J.B.J. Smeets and E. Brenner (2004). On the relation between object shape and grasping kinematics.
1Notes  Handing assignment 0 back (at the front of the room)  Read the newsgroup!  Planning to put 16mm films on the web soon (possibly tomorrow)
Model Predictive Control for Humanoid Balance and Locomotion Benjamin Stephens Robotics Institute.
ME 4135 Fall 2011 R. R. Lindeke, Ph. D. Robot Dynamics – The Action of a Manipulator When Forced.
Vision-Based Motion Control of Robots
PSY 5018H: Math Models Hum Behavior, Prof. Paul Schrater, Spring 2004 Vision as Optimal Inference The problem of visual processing can be thought of as.
Hybrid Manipulation: Force-Vision CMPUT 610 Martin Jagersand.
Ch. 7: Dynamics.
Motion Analysis (contd.) Slides are from RPI Registration Class.
PSY 5018H: Math Models Hum Behavior, Prof. Paul Schrater, Spring 2005 Making Decisions: Modeling perceptual decisions.
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 )
PSY 5018H: Math Models Hum Behavior, Prof. Paul Schrater, Spring 2004 Decision Theory: Action Problems.
Computational Vision Jitendra Malik University of California at Berkeley Jitendra Malik University of California at Berkeley.
Manipulator Dynamics Amirkabir University of Technology Computer Engineering & Information Technology Department.
Single Point of Contact Manipulation of Unknown Objects Stuart Anderson Advisor: Reid Simmons School of Computer Science Carnegie Mellon University.
Single Point of Contact Manipulation of Unknown Objects Stuart Anderson Advisor: Reid Simmons School of Computer Science Carnegie Mellon University.
Biological motor control Andrew Richardson McGovern Institute for Brain Research March 14, 2006.
Computational aspects of motor control and motor learning Michael I. Jordan* Mark J. Buller (mbuller) 21 February 2007 *In H. Heuer & S. Keele, (Eds.),
Introduction to ROBOTICS
Optimality in Motor Control By : Shahab Vahdat Seminar of Human Motor Control Spring 2007.
Definition of an Industrial Robot
Lecture VII Rigid Body Dynamics CS274: Computer Animation and Simulation.
1 CMPUT 412 Motion Control – Wheeled robots Csaba Szepesvári University of Alberta TexPoint fonts used in EMF. Read the TexPoint manual before you delete.
Mechanical Actuation System Lecture 6 (Chapter 8).
A kinematic cost Reza Shadmehr. Subject’s performanceMinimum jerk motion Flash and Hogan, J Neurosci 1985 Point to point movements generally exhibit similar.
Optimization-Based Full Body Control for the DARPA Robotics Challenge Siyuan Feng Mar
Game Physics – Part I Dan Fleck Coming up: Rigid Body Dynamics.
Advanced Programming for 3D Applications CE Bob Hobbs Staffordshire university Human Motion Lecture 3.
© Manfred Huber Autonomous Robots Robot Path Planning.
Robot Dynamics – Slide Set 10 ME 4135 R. R. Lindeke, Ph. D.
Robotics Chapter 5 – Path and Trajectory Planning
T. Bajd, M. Mihelj, J. Lenarčič, A. Stanovnik, M. Munih, Robotics, Springer, 2010 ROBOT CONTROL T. Bajd and M. Mihelj.
12 November 2009, UT Austin, CS Department Control of Humanoid Robots Luis Sentis, Ph.D. Personal robotics Guidance of gait.
University of Windsor School of Computer Science Topics in Artificial Intelligence Fall 2008 Sept 11, 2008.
Advanced Computer Graphics Rigid Body Simulation Spring 2002 Professor Brogan.
Motor Control. Beyond babbling Three problems with motor babbling: –Random exploration is slow –Error-based learning algorithms are faster but error signals.
ZMP-BASED LOCOMOTION Robotics Course Lesson 22.
Object Lesson: Discovering and Learning to Recognize Objects Object Lesson: Discovering and Learning to Recognize Objects – Paul Fitzpatrick – MIT CSAIL.
HCI / CprE / ComS 575: Computational Perception Instructor: Alexander Stoytchev
Evaluating Perceptual Cue Reliabilities Robert Jacobs Department of Brain and Cognitive Sciences University of Rochester.
Chapter 7. Learning through Imitation and Exploration: Towards Humanoid Robots that Learn from Humans in Creating Brain-like Intelligence. Course: Robots.
City College of New York 1 John (Jizhong) Xiao Department of Electrical Engineering City College of New York Mobile Robot Control G3300:
Optimal Path Planning Using the Minimum-Time Criterion by James Bobrow Guha Jayachandran April 29, 2002.
Robotics/Machine Vision Robert Love, Venkat Jayaraman July 17, 2008 SSTP Seminar – Lecture 7.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Department of Computer Science Columbia University rax Dynamically-Stable Motion Planning for Humanoid Robots Paper Presentation James J. Kuffner,
Shape2Pose: Human Centric Shape Analysis CMPT888 Vladimir G. Kim Siddhartha Chaudhuri Leonidas Guibas Thomas Funkhouser Stanford University Princeton University.
Gaits Cost of Transportation Wheeled Mobile Robots Most popular locomotion mechanism Highly efficient Simple mechanical implementation Balancing is.
Visual Recognition of Human Movement Style Frank E. Pollick Department of Psychology University of Glasgow.
Advanced Computer Graphics Rigid Body Simulation
CS b659: Intelligent Robotics
Modeling Robot with n total limbs n-1 limbs on the ground
Synthesis of Motion from Simple Animations
Learning Theory Reza Shadmehr
Mathematical Foundations of BME
Special English for Industrial Robot
Chapter 4 . Trajectory planning and Inverse kinematics
Presentation transcript:

Natural Cost functions for contact selection Paul R. Schrater University of Minnesota Collaborators: Erik Schlicht, Erik Flister, Charles Sloane

Task-dependent Perception Importance of visual information varies with task Potential state space of every natural scene is huge.

Example: Information for Distance How far the ball on the right from you? Which ball is closer to you? dede dbdb dtdt Which ball is closer to the table? Questions like these can involve different state spaces and optimal inference strategies (Schrater & Kersten, 2000)

Information for Inter-object distances Which ball is closer to the table?

Example: Information for Contact

By Construction Only reliable features are Shadows

Example: Information for surface smoothness Difference Image Which Ball is smoother? Dominant Information Specularities

Task-dependent Perception Importance of visual information varies with task, even within the same scene. Potential state space of every natural scene is huge. Computational resources limited in the brain. How does the brain determine how to allocate perceptual resources? Need a theory of goal-oriented perception Proposal : The brain turns perceptual and motor goals into loss functions to filter information relevant to the current task

Goal of a task can be encoded in a loss function Perceptual tasks- –Actions = judgments –Typical goal- minimize error in perceptual judgments –Loss functions Error rate (discrete) Estimation error (continuous) Motor control tasks- –Actions=Movement of body parts –Typical goal- achieve desired body position/motion with little effort. –Loss functions Sequential control decisions Cost-to-go to achieve goal position

Loss functions as Information Filters Risk = Expected Loss Taylor series in L around the expected state Plugging into the Risk Assume posterior distribution is approximately Gaussian After simplifying

Loss functions as Information Filters Each state variable contributes differentially to the risk: Thus, the impact of loss on the i th component of the state vector is to re-weight its reliability by the curvature of the loss in that direction.

Loss function for contact selection If relevant information is filtered by task goals, it should work for some non-trivial case: Where should you place your fingers when grasping an object? ? ? Depends on movement goal lift, rotate, flip, push, slide Seems like a visual task (Can’t wait till contact to decide) but has motor goal. Grasp quality depends on non- visual factors. (Mass, COM, Intertia, Friction, Geometry w.r.t. COM, etc) Why Non-Trivial

Perception for contact selection State variables needed: –Vision does well: Object boundary Object configuration w.r.t. the body Surface material properties of the object Collision time/velocity –Vision does poorly or not at all Mass Center of mass location Body inertia Friction open question - Is vision simply performing recognition of previously felt objects, or is it also making inferences based on assumptions- –mass uniformity+material inference? –Shininess => slippery

Goal of contact- Manipulation The goal of object contact is typically to manipulate the object. Therefore the information relevant to determining contact should be derived from that goal. Thus, we will try to connect manipulation with contact. Proposal: Brain has internal models for object manipulation. –Forward kinematic model to predict object motion given finger motions –Need inverse dynamic model for computing controls required to produce object motion and maintain contact. –Need observer model that can supply feedback Contact state Object state Finger state

Internal models for object motion Key ideas: –Once an object is grasped, it is effectively part of the hand. –The motor system has learned internal models for manipulation (maintaining contact and applying appropriate forces) Internal model idea well supported in motor control –(e.g. Neilson et al, 1985; Ghahramani & Wolpert, 1997, etc.) Evidence for internal models for contact- –Eye fixations directed to intended grasp locations (Johansson et. al, 2001) –Plan for object shape (Santello & Soechting, 2000; Jenmalm & Johansson, 1997) –Plan for grip force for familiar object weight (Johansson & Westling, Gordon et. al, Witney et. al, 2001, etc ) –Plan for center of mass –Plan for familiar friction (Burstedt et al, 2000)

Contact as a Kinematic Linkage Contact without slippage acts Like a 5-dof joint with transformations Given link parameters, object velocity determined by finger & contact velocities

Kinematic Grasp Constraint -> Dynamics For details, see Murray, Li, Sastry (1994) –Equations for the dynamics of the object can be written down using the Pfaffian kinematic constraints Standard robotics equation But defined on object variables and transformed by adding the object via the virtual linkage

Planning for Object Motion The goal of the task is to move the object. Proposal: Cost for desired object motion induces contact selection

Optimal Stochastic Control Model for Perception and Action Generative World ModelGenerative Perception Model Actions Beliefs Goals L( x t,u k ) P( x t |Data) ykyk Sensory Data

Stochastic Optimal Control (Abstract) Noise Model System Model LossOptimal Cost-to-go Control law Posterior distrib. on state Control lossGoal loss Typical Loss Function

Loss function for Object Motion Given: Goal states for object: Min control cost on motion, both without and with object Write Cost-to-go to penalize desired object via-states and control cost where Rewrite in terms of three control models: pre-,mid-,post-contact

Loss function for Object Motion After rewriting, the cost-to-go explicitly incorporates contact locations (and potentially velocities). Contact locations are determined by finger positions, and finger positions by controls Thus, in principle, minimizing cost-to-go with contact model would allow automatic online selection of contact conditions. Alternatively, contact points could be pre-picked (estimated )by partially optimizing the cost function.

Preliminary Tests More Torque Less Torque More Torque Less Torque Predictions: Optimal finger positions vary with cylinder orientation Contact velocities will produce impulses in desired direction of motion.

Qualitative Difference Between Touch and Lift 0 Degree: Touch Y X Z Gravity Touch

Y X Z Gravity 0 Degree: Lift Qualitative Difference Between Touch and Lift Lift

Preliminary testing of the idea

How optimal are observed contacts? Compute the cost function and compare to human behavior. –Full model too hard- Cheated by assuming object motion under min control would take a minimum Jerk path on average. Computed forces required to lift object 5cm in 500msec along min jerk path over a dense set of finger contact locations Simulated a contact dynamics model (frictional rolling without slip). Used kinematic constraints and required object forces to compute the finger controls needed to accomplish the task. Cost could then be computed on the set of finger controls.

Contact Cost for touch task

Object motion risk

Object Jerk Cost 180 mm 40 mm

Human vs. Loss function prediction Purple: Touch contact positions Black: Lift contact positions

Conclusions- Speculations Goals come first- perception should be driven by satisfying task demands Contact selection is a difficult problem (or maybe I made it into one). Perceptual principle of least commitment- don’t commit to an estimate when a distribution will do. New role for vision- Contact model estimation? What are the goals of natural conscious perception?