The Kinema*cs of End-Effectors in Collabora*ve Robots Soniya - - PowerPoint PPT Presentation

▶
the kinema cs of end effectors in collabora ve robots
SMART_READER_LITE
LIVE PREVIEW

The Kinema*cs of End-Effectors in Collabora*ve Robots Soniya - - PowerPoint PPT Presentation

May 14, 2023 153 likes •353 views

MIN Fakultt Fachbereich Informatik The Kinema*cs of End-Effectors in Collabora*ve Robots Soniya Vijayakumar Universitt Hamburg Fakultt fr Mathematik, Informatik, und Naturwissenschaften Fachbereich InformaKk Technische Aspeckte

slide-1
SLIDE 1

The Kinema*cs of End-Effectors in Collabora*ve Robots

Soniya Vijayakumar

MIN – Fakultät Fachbereich Informatik

Universität Hamburg

  • 17. December 2018

Technische Aspeckte Mul0modaler Systeme Fakultät für Mathematik, Informatik, und Naturwissenschaften Fachbereich InformaKk

1

slide-2
SLIDE 2
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Outline

Ø Introduction Ø Collaborative Robots Ø End Effector Systems Ø Kinematics in End Effectors Ø Hand Guiding Applications Ø Summary

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 2/18

slide-3
SLIDE 3
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

CO COllaborative RoBO BOTs

Cobot - robot with direct physical interaction

  • a human user
  • a shared workspace3
  • Invented professors J. Edward

Colgate and Michael Peshkin in 1996

  • At Northwestern University2

Sawyer and Baxter cobots from Rethink Robotics.1

1 https://www.roboticsbusinessreview.com/wp- content/uploads/2018/05/Sawyer_and_Baxter-300x229.jpg 2 http://peshkin.mech.northwestern.edu/cobot/

3 hIps://en.wikipedia.org/wiki/Cobot#cite_note-1 Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 3/18

slide-4
SLIDE 4
  • S. Vijayakumar – The Kinema3cs of End-Effectors in Collabora3ve Robots

End Effectors

2 https://en.wikipedia.org/wiki/Robot_end_effector

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 4/18

  • Device at end of the arm2
  • Designed to interact with environment

Human-Hand Force- Closure1

1 Richard Greenhill and Hugo Elias (myself) of the Shadow Robot Company 3 https://blog.robotiq.com/bid/65794/Magnetic-Robot-End-Effector-Top-5-Pros-and-Cons

Last Link of the Robot

MagneRc Robot End-Effector3

Types

  • Impactive
  • Ingressive
  • Astrictive
  • Contigutive
slide-5
SLIDE 5
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Importance of End Effectors

IntroducAon | CollaboraAve Robots | End-Effectors | KinemaAcs | Hand Guiding | Trajectory | Gripping | Summary 5/18

https://www.youtube.com/watch?v=1EpJv34gQ88

slide-6
SLIDE 6
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Kinema'cs

Forward Kinematics

  • Description of End-Effector Configuration (Position & Orientation)
  • Function of Joint Coordinates

Reverse Kinematics

  • Description of Joint Coordinates
  • Function of End-Effector Configuration

ÞWhat are we learning? ÞRelative pose between frame coordinates

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 6/18

slide-7
SLIDE 7
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Kinematics

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 7/18

Influencing Factors: [6] Ø End-Effector Weight Ø Degree of Freedom Ø Number of joints Ø Length of the links Ø External force/moment Ø Human force Ø Collisions in dynamic environments Ø Noise Ø Inertial Forces/moments dues to acceleration Ø Friction at joints

slide-8
SLIDE 8
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Hand Guiding

  • > Representative Functionality of Cobots
  • Teaching Pendant -> Unskilled users

interact and program robots

ÞLimits intuitiveness ÞWhat are we teaching them? [4] ÞPosition and Orientation

IntroducAon | CollaboraAve Robots | End-Effectors | KinemaAcs | Hand Guiding | Trajectory | Gripping | Summary 8/18

https://sites.google.com/site/hoomanleerobot/research

slide-9
SLIDE 9
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Hand Guiding

Assumption

  • A Force Feedback at the robot end-effector

Three motion groups

  • 1. Position in X,Y,Z

coordinates -> robot base

  • 2. Orientation in the

Cartesian space

  • 3. Rotation around its axis

Hand Guiding Force -> Linear positioning Hand Guiding Moment-> Angular positioning

IntroducAon | CollaboraAve Robots | End-Effectors | KinemaAcs | Hand Guiding | Trajectory | Gripping | Summary 9/18

slide-10
SLIDE 10
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Self-Learning: Trajectory

IntroducAon | CollaboraAve Robots | End-Effectors | KinemaAcs | Hand Guiding | Trajectory | Gripping | Summary 10/18

Controller Dynamics Action State State Initial State Final State

Trajectory Pattern [2]

  • Trajectory [2]
  • A length defined by repetition of pattern
  • State

– joint position vectors

  • Controller

– optimization function

  • Action

– joint target positions

  • Dynamics

– cost function and next state Smallest cost ac8on Aim: Learning of a Trajectory

slide-11
SLIDE 11
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Self-Learning: Trajectory

Aim: Learning of a Trajectory

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 11/18

  • Challenges [3]
  • Desired future trajectories
  • Solution
  • Impedence Control with

Interactive Trajectory Deformation

slide-12
SLIDE 12
  • S. Vijayakumar – The Kinematics of End-Effectors in Collaborative Robots

Self-Learning: Trajectory

Trajectory Deformation [3]

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 12/18

Desired Trajectory Human Force Smooth Trajectories

  • 1. Energy Function

Maps: trajectory deformations

  • > cost function
  • 2. Constrainted Optimization

Fixed end point

  • > Position
  • > Velocity
  • 3. Variation Field Estimation
  • > Trajectory deformation
slide-13
SLIDE 13
  • S. Vijayakumar – The Kinema3cs of End-Effectors in Collabora3ve Robots

Self-Learning: Trajectory

Achievements

Introduc3on | Collabora3ve Robots | End-Effectors | Kinema3cs | Hand Guiding | Trajectory | Gripping | Summary 13/18

Ø Compatible with traditional Impedence Control Ø Experiments ü Reduction in human intervention ü Reduction in torque application ü Improvement in movement quality

slide-14
SLIDE 14
  • S. Vijayakumar – The Kinema3cs of End-Effectors in Collabora3ve Robots

Self-Learning: Gripper

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 14/18

Aim: Learning of Gripper Orientation

  • Dextrous Gripper Mechanism2
  • Inputs: Position, force and vision Sensors
  • Robot joints – Position and Velocity
  • Fingers and Arms - Force
  • Controller: Torque Control
  • Robot joints
  • Robot hand fingers

Sarcos GRLA Arm1

2 http://users.cecs.anu.edu.au/~rsl/rsl_dextrous.html 1 h:p://www.cim.mcgill.ca/research/94-95AnnualReport/node99.html

slide-15
SLIDE 15
  • S. Vijayakumar – The Kinema3cs of End-Effectors in Collabora3ve Robots

Self-Learning: Gripper

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 15/18

  • Challenges[5]
  • Correspondence problem
  • Generalization
  • Robustness to Disturbances
  • Solution
  • Modified Dynamic Movement

Primitive Framework Aim: Learning of Gripper Orientation

slide-16
SLIDE 16
  • S. Vijayakumar – The Kinema3cs of End-Effectors in Collabora3ve Robots

Self-Learning: Gripper

16/18

  • 2. Obstacle Avoidance

Coupling Term

  • > Rotational Matrix
  • > Relative angle

DMP Control Diagram [5]

  • 1. Dynamic Movement Primitives

Transformation & Canonical System

  • > Converges to a Goal

Introduc3on | Collabora3ve Robots | End-Effectors | Kinema3cs | Hand Guiding | Trajectory | Gripping | Summary

slide-17
SLIDE 17
  • S. Vijayakumar – The Kinema3cs of End-Effectors in Collabora3ve Robots

Self-Learning: Gripper

17/18

Achievements

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary

Ø Improvement to dynamic movement primitives Ø Experiments ü Adapt movements with changing goals ü Adapt movements with moving obstacles ü Movement library that could be reused

slide-18
SLIDE 18
  • S. Vijayakumar – The Kinema3cs of End-Effectors in Collabora3ve Robots

Summary

ü Introduction ü Collaborative Robots ü End Effector Systems ü Kinematics in End Effectors ü Hand Guiding Applications ü Trajectory ü Gripper

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary 18/18

slide-19
SLIDE 19
  • S. Vijayakumar – The Kinema3cs of End-Effectors in Collabora3ve Robots

References

[1] Monkman, G. J.; Hesse, S.; Steinmann, R.; Schunk, H. (2007). Robot Grippers. Wiley-

  • VCH. p. 62.

[2] Joris Gue ́rin, Olivier Gibaru, Eric Nyiri and Ste ́phane Thiery, Learning local trajectories for high precision robo5c tasks : applica5on to KUKA LBR iiwa Cartesian posi5oning. [3] Dylan P. Losey, Student Member, IEEE, and Marcia K. O’Malley, Senior Member, IEEE, Trajectory Deforma5ons from Physical Human-Robot Interac5on. [4] Mohammad Safeea, Richard Bearee, and Pedro Neto, End-Effector Precise Hand-Guiding for Collabora5ve Robots. [5] Peter Pastor, Heiko Hoffmann, Tamim Asfour, and Stefan Schaal, Learning and Generaliza5on of Motor Skills by Learning from Demonstra5on. [6] Hatem A. Al-Dois, A. K. Jha and R. B. Mishra. Inves5ga5ons into the Parameters Influencing the Dynamic Performance of 3-RRR Planar & Ar5culated Robot Manipulators

Introduction | Collaborative Robots | End-Effectors | Kinematics | Hand Guiding | Trajectory | Gripping | Summary

Thank you.