Designing perceptually-better video conferencing rruth@mit.eduProject PI: Ruth Rosenholtz With COVID-19, many of us spend a great deal of time interacting using video conferencing tools like Zoom or WebEx, and many of us find this fatiguing. This project asks: is some of that fatigue due to sub-optimal design of video conferencing
Full Stack Web Application Development with the Haystack Group karger@mit.eduProject PI: David Karger Research areas: Human Computer Interaction The Haystack group works on a broad variety of projects aimed at helping regular people manage the deluge of information that floods us every day. Some of our tools help manage complex structured
Machine Learning for Medical Image Segmentation Contact: Mazdak Abulnaga, abulnaga@mit.eduProject PIs: Polina Golland and Justin Solomon We are developing neural network models to automatically segment the placenta embedded in magnetic resonance images (MRI) of the uterus. The placenta is a critical organ that forms during pregnancy and provides nutrients to
Artificial Intelligence for Surgery Contact: Yutong Ban (yban@csail.mi.edu)Project PI: Daniela Rus The Distributed Robotics Lab (DRL) at MIT CSAIL and Surgical Artificial Intelligence Lab (SAIL) at MGH are collaborating to develop AI tools to assist surgery. The work applies to computer-assisted laparoscopic surgery which relies upon strong fundamental automated understanding
Designing Mobile Disinfection Robots Contact: Alyssa Pierson, apierson@mit.eduProject PI: Daniela Rus We aim to develop mobile robotic solutions for disinfection and hands-free sterilization of high-traffic locations to decrease the risk of Covid-19 transmission. Our goal is to prototype a low-cost, easy to deploy solution that can support and adapt to
AI-Based Approaches for Document Processing, Forecasting, Supply Chain, and Precision Indoor Agriculture Amar Gupta Contact: agupta@mit.edu Partly accelerated by the COVID-19 pandemic, AI-Based Approaches for Document Processing, Forecasting, Supply Chain, and Precision Indoor Agriculture are receiving increasing attention in terms of innovation and broad deployment. Research can be conducted during
COVID-19 and Enhancing Telehealth and Digital Healthcare Contact: Dhaman Kaur (dkaur@mit.edu)Project Supervisor: Amar Gupta COVID-19 has led to a sudden jump in the level of interest and use of telehealth concepts as highlighted at: https://www.csail.mit.edu/news/hot-topics-computing-telehealth-and-coronavirus Research can be conducted during summer, possibly beginning immediately, in the following areas: Interoperability: Please
Misinformation & Data Visualization in the Age of COVID-19 Arvind Satyanarayanarvindsatya@mit.edu Data visualizations have become key to a robust public health response to COVID-19. Experts are using them to track metrics, and graphics like “Flatten the Curve” have proven critical for engaging the broader public. However, as hundreds of charts
Synthesizing Software with AI and Formal Program Synthesis Methods Una-May O’ReillyAlfa-apply@csail.mit.edu As software proliferates and the need for it explodes, what methods contribute to improving our ability to write and repurpose code? To what extent can software be automatically engineered? Is it possible to describe a task to a software
Data Science and AI while Left of Boom: Sniffing Out Cyber Attacks Una-May O’Reilly In the increasingly adversarial setting of cyberspace, cyber defenders need to be active when protecting their cyber assets. Actively hunting for adversaries is one way of preventing attacks. Our question is whether it is possible to
Misinformation Security Una-May O’Reilly Have you noticed COVID-19 narratives floating around social media that seem to fly in the face of logic? They offer snake-oil like treatments, political rather than science-based motivations behind mitigations, or conspiratorial virus origins. Unfortunately, these are not always unintended. In fact, deliberate adversarial motives
Denial of Service (DoS) attacks on network storage Karen Sollins, sollins@csail.mit.edu Traditionally, storage in the nodes of the network have be used to store routing tables and for extremely temporary storage while forwarding network traffic. So, it is primarily used for buffering traffic queued up to be forwarded. In the
Building a Climate Machine (CliMa): High Performance Computing, Heterogeneous Computing, and Machine Learning Contact: edelman@mit.edu The Climate Machine (https://clima.caltech.edu/) is a new Earth system model that leverages recent advances in the computational and data sciences to learn directly from a wealth of Earth observations from space and the ground. The
Make the Imperial College Covid-19 Model more usable and extensible Contact: edelman@mit.edu The Imperial College model to simulate the COVID-19 pandemic has recently been published at https://github.com/mrc-ide/covid-sim The project consists of rewriting the code in Julia, taking advantage of Julia’s unique multiple dispatch structure to make the code clean and understandable.We
Simulation Environment for Soft Robotics Design Project PI: Daniela Rus and Wojciech Matusik Contact: Andrew Spielberg (aespielberg@csail.mit.edu) Research Area: Soft Robotics, Simulation, Computational Design. No description available. Interested? Apply Now!
Explore learning without exploration with application in autonomous driving Project Pi: Prof. Daniela Rus Contact: Xiao Li (xiaoli@mit.edu) Research Area: Behavior cloning, imitation learning, policy distillation, batch reinforcement learning. No description available. Interested? Apply Now!
Dataset-base simulator for reinforcement learning of autonomous driving agents Project PI: Prof. Daniela Rus Contact: Xiao Li (xiaoli@mit.edu) Research Area: Reinforcement learning, autonomous driving. No description available. Interested? Apply Now!
Peer to Peer Communication with Racecars Project PI: Sertac Karaman and Daniela Rus Contact: Noam Buckman (nbuckman@mit.edu) Research Area: Machine Learning, AI, Robotics No description for this UROP is available at this time. Interested? Apply Now!
Activity and Trajectory Reasoning based on Deep (Reinforcement) Learning Project PI: Sertac Karaman and Daniela Rus Contact: Igor Gilitschenski (igilitschenski@mit.edu) The Distributed Robotics Lab at MIT CSAIL is contributing to the development of self-driving cars within the Toyota-CSAIL joint research center. Our work addresses the full scope of challenges in
Studying driver behavior with novel datasets Project PI: Sertac Karaman and Daniela Rus Contact: Noam Buckman (nbuckman@mit.edu) There has been a recent emergence of self-driving car datasets from many of the major players: Waymo, Nutonomy, Argo, etc. While this data has been primarily used as a validation method for current
Studying cooperating at intersection with realistic traffic data Project PI: Sertac Karaman and Daniela Rus Contact: Noam Buckman (nbuckman@mit.edu) Smart intersection can allow for cooperation by allowing vehicles to negotiate for intersection access. In this work, we seek to explore the optimal distribution of cooperative personalities (a.k.a. Social Value
Creating an interactive driving platform to collect human driving experiments with CARLA Simulator Project PI: Sertac Karaman and Daniela Rus Contact: Noam Buckman (nbuckman@mit.edu) Many methods (including our own) claim to effectively capture the behaviors of other human drivers. While common datasets include data that can be used in this
Studying the effects of heterogeneity in multi-robot collision avoidance using the Robotarium platform Project PI: Sertac Karaman and Daniela Rus Contact: Noam Buckam (nbuckman@mit.edu) Deadlock is an issue with many decentralized collision avoidance techniques. Humans naturally have heterogeneity both in preferences and dynamis (how fast do we walk? Our reaction
COVID19 Project Contact: edelman@mit.edu If you want to stop playing with toy models of COVID-19 and work on the models which are influencing the policy decisions, this is the project for you. Aspects of the work range from the basic research to scaling and deploying the model at a country-wide
