Bootstrapping Motor Skill Learning with Motion Planning

01/12/2021
by   Ben Abbatematteo, et al.
5

Learning a robot motor skill from scratch is impractically slow; so much so that in practice, learning must be bootstrapped using a good skill policy obtained from human demonstration. However, relying on human demonstration necessarily degrades the autonomy of robots that must learn a wide variety of skills over their operational lifetimes. We propose using kinematic motion planning as a completely autonomous, sample efficient way to bootstrap motor skill learning for object manipulation. We demonstrate the use of motion planners to bootstrap motor skills in two complex object manipulation scenarios with different policy representations: opening a drawer with a dynamic movement primitive representation, and closing a microwave door with a deep neural network policy. We also show how our method can bootstrap a motor skill for the challenging dynamic task of learning to hit a ball off a tee, where a kinematic plan based on treating the scene as static is insufficient to solve the task, but sufficient to bootstrap a more dynamic policy. In all three cases, our method is competitive with human-demonstrated initialization, and significantly outperforms starting with a random policy. This approach enables robots to to efficiently and autonomously learn motor policies for dynamic tasks without human demonstration.

READ FULL TEXT

page 1

page 6

research
09/28/2022

Bimanual rope manipulation skill synthesis through context dependent correction policy learning from human demonstration

Learning from demonstration (LfD) provides a convenient means to equip r...
research
03/21/2022

Learning robot motor skills with mixed reality

Mixed Reality (MR) has recently shown great success as an intuitive inte...
research
09/23/2017

Multi-task Learning with Gradient Guided Policy Specialization

We present a method for efficient learning of control policies for multi...
research
07/04/2022

Controlling the Cascade: Kinematic Planning for N-ball Toss Juggling

Dynamic movements are ubiquitous in human motor behavior as they tend to...
research
08/18/2020

Residual Learning from Demonstration

Contacts and friction are inherent to nearly all robotic manipulation ta...
research
03/05/2018

Kinematic Morphing Networks for Manipulation Skill Transfer

The transfer of a robot skill between different geometric environments i...
research
09/13/2022

Human-Guided Planning for Complex Manipulation Tasks Using the Screw Geometry of Motion

In this paper, we present a novel method for motion planning for perform...

Please sign up or login with your details

Forgot password? Click here to reset