Sim2Real View Invariant Visual Servoing by Recurrent Control

12/20/2017
by   Fereshteh Sadeghi, et al.
0

Humans are remarkably proficient at controlling their limbs and tools from a wide range of viewpoints and angles, even in the presence of optical distortions. In robotics, this ability is referred to as visual servoing: moving a tool or end-point to a desired location using primarily visual feedback. In this paper, we study how viewpoint-invariant visual servoing skills can be learned automatically in a robotic manipulation scenario. To this end, we train a deep recurrent controller that can automatically determine which actions move the end-point of a robotic arm to a desired object. The problem that must be solved by this controller is fundamentally ambiguous: under severe variation in viewpoint, it may be impossible to determine the actions in a single feedforward operation. Instead, our visual servoing system must use its memory of past movements to understand how the actions affect the robot motion from the current viewpoint, correcting mistakes and gradually moving closer to the target. This ability is in stark contrast to most visual servoing methods, which either assume known dynamics or require a calibration phase. We show how we can learn this recurrent controller using simulated data and a reinforcement learning objective. We then describe how the resulting model can be transferred to a real-world robot by disentangling perception from control and only adapting the visual layers. The adapted model can servo to previously unseen objects from novel viewpoints on a real-world Kuka IIWA robotic arm. For supplementary videos, see: https://fsadeghi.github.io/Sim2RealViewInvariantServo

READ FULL TEXT

page 1

page 3

page 8

page 9

page 10

research
03/04/2020

Learning View and Target Invariant Visual Servoing for Navigation

The advances in deep reinforcement learning recently revived interest in...
research
09/13/2016

3D Simulation for Robot Arm Control with Deep Q-Learning

Recent trends in robot arm control have seen a shift towards end-to-end ...
research
01/05/2019

Control of a 2-DoF robotic arm using a P300-based brain-computer interface

In this study, a novel control algorithm for a P-300 based brain-compute...
research
05/18/2023

Robust Single-Point Pushing with Force Feedback

We present the first controller for quasistatic robotic planar pushing w...
research
05/25/2023

Hierarchical Whole-body Control of the cable-Suspended Aerial Manipulator endowed with Winch-based Actuation

During operation, aerial manipulation systems are affected by various di...
research
04/18/2023

A Hyper-network Based End-to-end Visual Servoing with Arbitrary Desired Poses

Recently, several works achieve end-to-end visual servoing (VS) for robo...
research
08/02/2021

Active Perception for Ambiguous Objects Classification

Recent visual pose estimation and tracking solutions provide notable res...

Please sign up or login with your details

Forgot password? Click here to reset