- 61 Views
- Uploaded on
- Presentation posted in: General

Learning From Demonstration Atkeson and Schaal

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Learning From DemonstrationAtkeson and Schaal

Dang, RLAB

Feb 28th, 2007

- Robot Learning from Demonstration
- Small number of human demonstrations
- Task level learning (learn intent, not just mimicry)

- Explore
- Parametric vs. nonparametric learning
- role of a priori knowledge

Dang, RLAB

- Pendulum swing-up task
- Like pole balancing, but more complex
- Difficult, but easy to evaluate success

- Simplified
- Restricted to horz. motion
- Impt. variables picked out
- Pendulum angle
- Pendulum angular velocity
- Hand location
- Hand velocity
- Hand acceleration

Dang, RLAB

- SARCOS 7DOF arm
- Stereo Vision, colored ball indicators
- 0.12s delay overcome with Kalman filter
- Idealized pendulum dynamics

- Redundant inverse kinematics and real-time inverse dynamics for control

Dang, RLAB

- Task composed of two subtasks
- Believe that subtask learning accelerates new task learning

- 1 Pole Swing up
- open-loop

- 2 Upright Balance
- Feedback

- Balancing already learned

Dang, RLAB

- Directly mimic human hand movement
- Fails
- Differences in human and robot capabilities
- Improper demonstration (not horizontal)
- Imprecise mimicry

- Fails

Dang, RLAB

- Learn reward
- Learn a model
- Use human demonstration as seed so a planner can find a good policy

Dang, RLAB

- Parametric:
- learn parameters via linear regression

- Nonparametric
- Use Locally Weighted Learning
- Given desired variable and a set of possibly relevant input variables
- Cross validation to tune meta-parameters

Dang, RLAB

- Transition to balance occurs at ± 0.5 radians with angular vel. < 3 rad/sec
- Reward function set to make robot want to be like demonstrator

Dang, RLAB

- Parameters learned from failure data
- Trajectory optimized using human trajectory as seed
- SUCCESS

Dang, RLAB

- Slower, but still successful

Dang, RLAB

- Double pump swing up
- Approach fails
- Believed to be due to improper modeling of the system
- Solved by

- Approach fails

Dang, RLAB

- Learn a correction term to add to the target angle
- Now target ± (0.5+∆)rad
- Use binary search

- Worked for parametric
- Didn’t for nonparametric
- Left region of validity of local models
- So, tweak velocity all over
- Binary search for coefficient

Dang, RLAB

Dang, RLAB

Succeeds for

Math

Watch demo, mimic hand

None

Learn model,

optimize demo trajectory

Parametric, single

Tune model, reoptimize

Nonparametric, single

Binary search for delta

Parametric, double

Binary search for c

Nonparametric, double

Dang, RLAB

- Reward function was given or learned?
- Does task-level direct learning make sense?
- Only useful in this task / implementation?
- I in PID?

- Nonparametrics don’t avoid all modeling errors
- Poor planner?
- Not enough data?

- A priori knowledge
- human selects inputs, outputs, control system, perception, model selection, reward function, task segmenting, task factors

- It Works!

Dang, RLAB