# Towards Visual Ego-motion Learning in Robots

## TL;DR

This paper introduces a fully trainable, self-supervised visual ego-motion estimation method for robots, capable of handling varied camera optics and integrating sensor fusion for improved autonomous navigation.

## Contribution

It presents a novel architecture combining Mixture Density Networks and Conditional Variational Autoencoders for flexible, minimally supervised ego-motion learning in robots.

## Key findings

- Effective ego-motion estimation across different camera types.
- Enables self-supervised learning using standard navigation sensors.
- Improves autonomous robot navigation capabilities.

## Abstract

Many model-based Visual Odometry (VO) algorithms have been proposed in the past decade, often restricted to the type of camera optics, or the underlying motion manifold observed. We envision robots to be able to learn and perform these tasks, in a minimally supervised setting, as they gain more experience. To this end, we propose a fully trainable solution to visual ego-motion estimation for varied camera optics. We propose a visual ego-motion learning architecture that maps observed optical flow vectors to an ego-motion density estimate via a Mixture Density Network (MDN). By modeling the architecture as a Conditional Variational Autoencoder (C-VAE), our model is able to provide introspective reasoning and prediction for ego-motion induced scene-flow. Additionally, our proposed model is especially amenable to bootstrapped ego-motion learning in robots where the supervision in ego-motion estimation for a particular camera sensor can be obtained from standard navigation-based sensor fusion strategies (GPS/INS and wheel-odometry fusion). Through experiments, we show the utility of our proposed approach in enabling the concept of self-supervised learning for visual ego-motion estimation in autonomous robots.