DeepMPCVS: Deep Model Predictive Control for Visual Servoing
Pushkal Katara1 YVS Harish1 Harit Pandya3 Abhinav Gupta1 AadilMehdi Sanchawala1 Gourav Kumar2 K. Madhava Krishna1 Brojeshwar Bhowmick2
The simplicity of the visual servoing approach makes it an attractive option for tasks dealing with vision-based control of robots in many real-world applications. However, attaining precise alignment for unseen environments pose a challenge to existing visual servoing approaches. While classical approaches assume a perfect world, the recent data-driven approaches face issues when generalizing to novel environments. In this paper, we aim to combine the best of both worlds. We present a deep model predictive visual servoing framework that can achieve precise alignment with optimal trajectories and can generalize to novel environments. Our framework consists of a deep network for optical flow predictions, which are used along with a predictive model to forecast future optical flow. For generating an optimal set of velocities we present a control network that can be trained on-the-fly without any supervision. Through extensive simulations on photo-realistic indoor settings of the popular Habitat framework, we show significant performance gain due to the proposed formulation vis-a-vis recent state of the art methods. Specifically, we show a faster convergence and an improved performance in trajectory length over recent approaches.
ContactFor any questions or clarifications, please get in touch with:
Pushkal Katara: email@example.com
YVS Harish: firstname.lastname@example.org
Abhinav Gupta: email@example.com
AadilMehdi Sanchawala: firstname.lastname@example.org