Exploring convolutional networks for end-to-end visual servoing
- Resource Type
- Conference
- Authors
- Saxena, Aseem; Pandya, Harit; Kumar, Gourav; Gaud, Ayush; Krishna, K. Madhava
- Source
- 2017 IEEE International Conference on Robotics and Automation (ICRA) Robotics and Automation (ICRA), 2017 IEEE International Conference on. :3817-3823 May, 2017
- Subject
- Robotics and Control Systems
Cameras
Visual servoing
Visualization
Feature extraction
Optical imaging
Jacobian matrices
- Language
Present image based visual servoing approaches rely on extracting hand crafted visual features from an image. Choosing the right set of features is important as it directly affects the performance of any approach. Motivated by recent breakthroughs in performance of data driven methods on recognition and localization tasks, we aim to learn visual feature representations suitable for servoing tasks in unstructured and unknown environments. In this paper, we present an end-to-end learning based approach for visual servoing in diverse scenes where the knowledge of camera parameters and scene geometry is not available a priori. This is achieved by training a convolutional neural network over color images with synchronised camera poses. Through experiments performed in simulation and on a quadrotor, we demonstrate the efficacy and robustness of our approach for a wide range of camera poses in both indoor as well as outdoor environments.