# DIViS: Domain Invariant Visual Servoing for Collision-Free Goal Reaching

## TL;DR

DIViS is a novel domain invariant visual servoing approach that enables collision-free goal reaching for mobile robots using semantic understanding learned entirely in simulation, with successful real-world deployment and generalization.

## Contribution

DIViS introduces a domain invariant policy learning method that incorporates semantics from static datasets, enabling collision-free visual servoing without real robot data and robust real-world performance.

## Key findings

- Successfully deployed on real robots in over 90 scenarios
- Achieved collision-free goal reaching with unseen object categories
- Generalized well in unstructured environments

## Abstract

Robots should understand both semantics and physics to be functional in the real world. While robot platforms provide means for interacting with the physical world they cannot autonomously acquire object-level semantics without needing human. In this paper, we investigate how to minimize human effort and intervention to teach robots perform real world tasks that incorporate semantics. We study this question in the context of visual servoing of mobile robots and propose DIViS, a Domain Invariant policy learning approach for collision free Visual Servoing. DIViS incorporates high level semantics from previously collected static human-labeled datasets and learns collision free servoing entirely in simulation and without any real robot data. However, DIViS can directly be deployed on a real robot and is capable of servoing to the user-specified object categories while avoiding collisions in the real world. DIViS is not constrained to be queried by the final view of goal but rather is robust to servo to image goals taken from initial robot view with high occlusions without this impairing its ability to maintain a collision free path. We show the generalization capability of DIViS on real mobile robots in more than 90 real world test scenarios with various unseen object goals in unstructured environments. DIViS is compared to prior approaches via real world experiments and rigorous tests in simulation. For supplementary videos, see: \href{https://fsadeghi.github.io/DIViS}{https://fsadeghi.github.io/DIViS}