Introduction: Anatomy of a

Manipulation System

MIT 6.881: Robotic Manipulation

Fall 2020, Lecture 1

Follow live at https://slides.com/russtedrake/fall20-lec01/live

(or later at https://slides.com/russtedrake/fall20-lec01)

Course Info

Instructor: Russ Tedrake

 

TAs:

 

 

 

 

Website: http://manipulation.mit.edu

 

Terry Suh

Meng Feng

Remote Teaching

I want lectures to be interactive.

(synchronous will be better!)

 

Piazza (sign up if you haven't)

Email: manipulation-staff@mit.edu

 

Open to everyone / anywhere:

Remote Teaching

I want lectures to be interactive.

(synchronous will be better!)

 

Please keep your video ON.

Please ask questions!

  • Voice is OK.
  • Chat is OK, too.
  • You will not show up on YouTube.

Remote Teaching

I hope to lecture better than I have before

(by injecting code into your browser!)

 

Simulation experiments during lecture.

 

I'm very open to suggestions / changes

 

Please forgive my experiments, and give me feedback!

https://itempool.com/MIT-Robotic-Manipulation/live

https://www.pinterest.com/pin/549579960772413472/

Today

  • What do I mean by "manipulation"?
  • Live experiment (breakout rooms)
  • What is drake?
  • Anatomy of a manipulation system
  • Goals for the course

Matt Mason says

  • Definition 1 (etymological). Manipulation refers to the activities performed by hands.
  • ...
  • Definition 5. Manipulation refers to an agent’s control of its environment through selective contact.

Matthew T. Mason.  Toward Robotic Manipulation.  Annual Review of Control, Robotics, and Autonomous Systems, 1:1-28, 2018.

Motivation

Consider the task of loading a dishwasher...

 

(One project I've been working on at TRI Robotics)

Why do I study manipulation?

To be clear: we're not just controlling the arm

state of the robot x state of the environment

How important is feedback?

Alternative: Open-loop stability

The complexities of grasping in the wild.  Nakamura et al, Humanoids, 2017

The complexities of grasping in the wild.  Nakamura et al, Humanoids, 2017

OpenAI - Learning Dexterity

kPAM: KeyPoint Affordances for Manipulation

Lucas Manuelli*, Wei Gao*, Peter R. Florence and Russ Tedrake. kPAM: KeyPoint Affordances for Category Level Manipulation. ISRR 2019

Dense Object Nets in Visuomotor Imitation Learning

Peter R. Florence, Lucas Manuelli, and Russ Tedrake. Self-Supervised Correspondence in Visuomotor Policy Learning. RA-L, April 2020

Time to experiment

(Zoom breakout rooms; lecture will continue in ~10 minutes)

also linked from Ch. 1 of http://manipulation.mit.edu

Your task: Run the simulator.  Teleop the robot.  Can you move the red brick from one bin to the other?

Try the 2D version, too. 

What is drake?

drake.mit.edu

iiwa_position→
iiwa_feedforward_torque→
wsg_position→
wsg_force_limit→
ManipulationStation
→ iiwa_position_commanded
→ iiwa_position_measured
→ iiwa_velocity_estimated
→ iiwa_state_estimated
→ iiwa_torque_commanded
→ iiwa_torque_measured
→ iiwa_torque_external
→ wsg_state_measured
→ wsg_force_measured
→ camera_[NAME]_rgb_image
→ camera_[NAME]_depth_image
→ camera_[NAME]_label_image
→ ...
→ camera_[NAME]_rgb_image
→ camera_[NAME]_depth_image
→ camera_[NAME]_label_image
→ pose_bundle
→ contact_results
→ plant_continuous_state
→ geometry_poses

Logistics

 

  • ~7 PSets throughout the class (approximately biweekly), due Monday (any time).
  • Final project.

https://forms.gle/bV3TRSEEunTpKnqBA