Visual Servoing from Deep Neural Networks

نویسندگان

  • Quentin Bateux
  • Éric Marchand
  • Jürgen Leitner
  • François Chaumette
چکیده

We present a deep neural network-based method to perform high-precision, robust and real-time 6 DOF visual servoing. The paper describes how to create a dataset simulating various perturbations (occlusions and lighting conditions) from a single real-world image of the scene. A convolutional neural network is fine-tuned using this dataset to estimate the relative pose between two images of the same scene. The output of the network is then employed in a visual servoing control scheme. The method converges robustly even in difficult real-world settings with strong lighting variations and occlusions. A positioning error of less than one millimeter is obtained in experiments with a 6 DOF robot.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Mimetic visual servoing with adaptive neural network (ANN)

In this paper we present a model free hybrid visual servoing system. The “model free” term refers to the system with the unknown kinematics model that has to be estimated on-line, while “hybrid” specifies the visual controller architecture. The proposed system has a conventional Jacobian estimation part necessary for control output generation and it is supplemented with an additional adaptive n...

متن کامل

Structure Adaptable Digital Neural Network Techniques in Visual Servoing of Robotic Manipulators

Robotics is one of the most challenging applications of soft computing techniques. It is characterized by direct interaction with a real world, sensory feedback and a complex control system. This paper reviews the application of soft computing approaches, particularly neural networks, in the domain of visual servoing of robotic manipulators. Various robotic tasks within the scope of visual serv...

متن کامل

A Short Review of Neural Network Techniques in Visual Servoing of Robotic Manipulators

Robotics is one of the most challenging applications of soft computing techniques. It is characterized by direct interaction with a real world, sensory feedback and a complex control system. This paper reviews the application of soft computing approaches, particularly neural networks, in the domain of visual servoing of robotic manipulators. Various robotic tasks within the scope of visual serv...

متن کامل

Implementing a Visual Servoing System for Robot Controlling

Nowadays, with the emerging of the new applications like robot control in image processing, artificial vision for visual servoing is a rapidly growing discipline and Human-machine interaction plays a significant role for controlling the robot. This paper presents a new algorithm based on spatio-temporal volumes for visual servoing aims to control robots. In this algorithm, after applying necess...

متن کامل

Evolutionary reinforcement learning of artificial neural networks

In this article we describe EANT2, Evolutionary Acquisition of Neural Topologies, Version 2, a method that creates neural networks by evolutionary reinforcement learning. The structure of the networks is developed using mutation operators, starting from a minimal structure. Their parameters are optimised using CMA-ES, Covariance Matrix Adaptation Evolution Strategy, a derandomised variant of ev...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1705.08940  شماره 

صفحات  -

تاریخ انتشار 2017