Recently Published by Autodesk Researchers

Autodesk Research teams regularly contribute to peer-reviewed scientific journals and present at conferences around the world. Check out some recent publications from Autodesk Researchers.

Flow-based Domain Randomization for Learning and Sequencing Robotic Skills

Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust to uncertainties along the randomized dimensions. While the environment distribution is typically specified by hand, in this work the team investigated automatically discovering a sampling distribution via entropy-regularized reward maximization of a normalizing-flow–based neural sampling distribution. Additionally, the team explored how these learned sampling distributions, along with a privileged value function, can be used for out-of-distribution detection in an uncertainty-aware multi-step manipulation planner.

Paratrouper – Exploratory Creation of Character Cast Visuals Using Generative AI

Great characters are critical to the success of many forms of media, such as comics, games, and films. Designing visually compelling casts of characters requires significant skill and consideration, and there is a lack of specialized tools to support this endeavor. In this paper, the team investigates how AI-driven image-generation techniques can empower creatives to explore a variety of visual design possibilities for individual and groups of characters. Informed by interviews with character designers, Paratrouper is a multi-modal system that enables creating and experimenting with multiple permutations for character casts and visualizing them in various contexts as part of a holistic approach to design. This work highlights the interplay between creative agency and serendipity, as well as the visual interrelationships among character aesthetics.

WhatIF – Branched Narrative Fiction Visualization for Authoring Emergent Narratives using Large Language Models

Branched Narrative Fiction (BNF) are non-linear, text based narrative games, where the player of the game is an active participant shaping the story. Unlike linear narratives, BNF allows players to influence the direction, outcomes, and progression of the plot. A narrative fiction developer designs these branching storylines, creating a dynamic interaction between the player and the narrative which requires significant time and skill. In this work the team builds and investigates the use of a visual analytics tool to help narrative fiction developers generate and plan these parallel worlds within a BNF. WhatIF is a visual analytics tool that aids BNF developers to create BNF graphs, edit the graphs, obtain recommendations, visualize differences between storylines and finally verify their BNF on custom metrics.