Residual Robot Learning for Object-Centric Probabilistic Movement Primitives

03/08/2022
by   João Carvalho, et al.
0

It is desirable for future robots to quickly learn new tasks and adapt learned skills to constantly changing environments. To this end, Probabilistic Movement Primitives (ProMPs) have shown to be a promising framework to learn generalizable trajectory generators from distributions over demonstrated trajectories. However, in practical applications that require high precision in the manipulation of objects, the accuracy of ProMPs is often insufficient, in particular when they are learned in cartesian space from external observations and executed with limited controller gains. Therefore, we propose to combine ProMPs with recently introduced Residual Reinforcement Learning (RRL), to account for both, corrections in position and orientation during task execution. In particular, we learn a residual on top of a nominal ProMP trajectory with Soft-Actor Critic and incorporate the variability in the demonstrations as a decision variable to reduce the search space for RRL. As a proof of concept, we evaluate our proposed method on a 3D block insertion task with a 7-DoF Franka Emika Panda robot. Experimental results show that the robot successfully learns to complete the insertion which was not possible before with using basic ProMPs.

READ FULL TEXT

page 1

page 4

page 6

research
03/29/2023

Learning Excavation of Rigid Objects with Offline Reinforcement Learning

Autonomous excavation is a challenging task. The unknown contact dynamic...
research
08/11/2019

Experience Reuse with Probabilistic Movement Primitives

Acquiring new robot motor skills is cumbersome, as learning a skill from...
research
04/03/2021

A DMP-based Framework for Efficiently Generating Complete Stiffness Profiles of Human-like Variable Impedance Skill from Demonstrations

Human manipulation skills can be transferred to robots conveniently thro...
research
08/24/2020

Learning and Sequencing of Object-Centric Manipulation Skills for Industrial Tasks

Enabling robots to quickly learn manipulation skills is an important, ye...
research
03/25/2020

Adaptive Conditional Neural Movement Primitives via Representation Sharing Between Supervised and Reinforcement Learning

Learning by Demonstration provides a sample efficient way to equip robot...
research
10/30/2018

Learning to serve: an experimental study for a new learning from demonstrations framework

Learning from demonstrations is an easy and intuitive way to show exampl...
research
08/31/2018

Adaptation and Robust Learning of Probabilistic Movement Primitives

Probabilistic representations of movement primitives open important new ...

Please sign up or login with your details

Forgot password? Click here to reset