Robot Shape and Location Retention in Video Generation Using Diffusion Models

TL;DR

This paper introduces diffusion models tailored for generating videos that accurately preserve the shape and location of moving robots, aiding in safer robot-human interaction research.

Contribution

The paper develops diffusion models with techniques like robot pose embedding and semantic mask regulation to improve shape and location retention in robot videos.

Findings

Significant improvement in shape and location retention over benchmark models

Enhanced overall video generation quality

Models facilitate safer robot-human interaction data creation

Abstract

Diffusion models have marked a significant milestone in the enhancement of image and video generation technologies. However, generating videos that precisely retain the shape and location of moving objects such as robots remains a challenge. This paper presents diffusion models specifically tailored to generate videos that accurately maintain the shape and location of mobile robots. This development offers substantial benefits to those working on detecting dangerous interactions between humans and robots by facilitating the creation of training data for collision detection models, circumventing the need for collecting data from the real world, which often involves legal and ethical issues. Our models incorporate techniques such as embedding accessible robot pose information and applying semantic mask regulation within the ConvNext backbone network. These techniques are designed to refine intermediate outputs, therefore improving the retention performance of shape and location. Through extensive experimentation, our models have demonstrated notable improvements in maintaining the shape and location of different robots, as well as enhancing overall video generation quality, compared to the benchmark diffusion model. Codes will be opensourced at \href{https://github.com/PengPaulWang/diffusion-robots}{Github}.