Self-supervised Learning for Precise Pick-and-place without Object Model

by   Lars Berscheid, et al.

Flexible pick-and-place is a fundamental yet challenging task within robotics, in particular due to the need of an object model for a simple target pose definition. In this work, the robot instead learns to pick-and-place objects using planar manipulation according to a single, demonstrated goal state. Our primary contribution lies within combining robot learning of primitives, commonly estimated by fully-convolutional neural networks, with one-shot imitation learning. Therefore, we define the place reward as a contrastive loss between real-world measurements and a task-specific noise distribution. Furthermore, we design our system to learn in a self-supervised manner, enabling real-world experiments with up to 25000 pick-and-place actions. Then, our robot is able to place trained objects with an average placement error of 2.7 (0.2) mm and 2.6 (0.8). As our approach does not require an object model, the robot is able to generalize to unknown objects while keeping a precision of 5.9 (1.1) mm and 4.1 (1.2). We further show a range of emerging behaviors: The robot naturally learns to select the correct object in the presence of multiple object types, precisely inserts objects within a peg game, picks screws out of dense clutter, and infers multiple pick-and-place actions from a single goal state.


page 1

page 3

page 5

page 6

page 7


Self-supervised 6D Object Pose Estimation for Robot Manipulation

To teach robots skills, it is crucial to obtain data with supervision. S...

simPLE: a visuotactile method learned in simulation to precisely pick, localize, regrasp, and place objects

Existing robotic systems have a clear tension between generality and pre...

Self-Supervised Goal-Conditioned Pick and Place

Robots have the capability to collect large amounts of data autonomously...

Robot Learning of 6 DoF Grasping using Model-based Adaptive Primitives

Robot learning is often simplified to planar manipulation due to its dat...

rduino Controlled Pick n Place RoboticArm

This document is an introduction to designing a multiple degree of freed...

Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience

Manipulating deformable objects, such as fabric, is a long standing prob...

Learning Relative Interactions through Imitation

In this project we trained a neural network to perform specific interact...

Please sign up or login with your details

Forgot password? Click here to reset