The Computational Fabrication Group at the MIT Computer Science and Artificial Intelligence Laboratory investigates problems in digital manufacturing and computer graphics. The group is led by Professor Wojciech Matusik.


Paper accepted to Advanced Intelligent Systems

Andrew Spielberg's paper A Simple, Inexpensive, Wearable Glove with Hybrid Resistive‐Pressure Sensors for Computational Sensing, Proprioception, and Task Identification has been published in Advanced Intelligent Systems. In this paper, Andy and his collaborators from Professor Daniela Rus' lab presented a fully soft, wearable glove which is capable of real‐time hand pose reconstruction, environment sensing, and task classification. The design is easy to fabricate using low cost, commercial off‐the‐shelf items in a manner that is amenable to automated manufacturing. The system can reconstruct user hand pose and identify sensory inputs such as holding force, object temperature, conductability, material stiffness, and user heart rate, all with high accuracy. Check out this article at Advanced Science News to see more exciting applications unlocked by this new technology!

Two papers accepted to ICML 2020

Two papers on the application of multi-objective optimization techniques in supervised learning and reinforcement learning have been accepted to ICML 2020: Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control from Jie Xu, Yunsheng Tian, and Pingchuan Ma proposed an efficient evolutionary learning algorithm to find the Pareto set approximation for continuous robot control problems, and Efficient Continuous Pareto Exploration in Multi-Task Learning from Pingchuan Ma and Tao Du presented a novel, efficient method that generates locally continuous Pareto sets and Pareto fronts for multi-task learning problems. Details about the two papers will be available soon.

Paper accepted to Physical Review Letters

The paper Physical Realization Of Elastic Cloaking With A Polar Material was recently accepted to Physical Review Letters (PRL). In this paper, Wan Shou and Beichen Li collaborated with researchers at University of Missouri and Dalian University of Technology to propose a novel elastic cloak by designing and fabricating a new class of polar materials with a distribution of body torque that exhibits asymmetric stresses. The work sets a precedent in the field of transformation elasticity and should find applications in mechanical stress shielding and stealth technologies. Check out their paper to learn more about this breakthrough in material science!

Papers accepted to ICCV and NeurIPS

Dr. Petr Kellnhofer's work "Gaze360: Physically Unconstrained Gaze Estimation in the Wild" was accepted to ICCV 2019. In this paper, we present Gaze360, a large-scale gaze-tracking dataset and method for robust 3D gaze estimation in unconstrained images. Our proposed 3D gaze model extends existing models to include temporal information and to directly output an estimate of gaze uncertainty. Finally, we demonstrate an application of our model for estimating customer attention in a supermarket setting. This paper was was in collaboration with Professor Antonio Torralba's group and Toyota Research Institute.

Andrew Spielberg's paper "Learning-In-The-Loop Optimization: End-To-End Control And Co-Design of Soft Robots Through Learned Deep Latent Representations" has been accepted to NeurIPS 2019 recently. This paper tackles the problem of controlling soft robots, which is very challenging due to their infinite degrees of freedom. Our solution marries hybrid particle-grid-based simulation with deep, variational convolutional autoencoder architectures that can capture salient features of robot dynamics with high efficacy, and we demonstrate our dynamics-aware feature learning algorithm on both 2D and 3D soft robots.

Dr. Changil Kim joins Facebook Research in September

Our very own Postdoctoral researcher Changil Kim is joining Facebook in Seattle as a research scientist in September, after spending two and a half wonderful years in our lab. During his time in our lab, Changil has actively contributed to many research projects, including motion magnificationreplicating oil paintingspeech to face, and video processing. Congratulations to Changil and wish him all the best in Seattle!