We focus on finding novel approaches to improve the performance of modern computer systems without unduly increasing the complexity faced by application developers, compiler writers, or computer architects.
Self-driving cars are likely to be safer, on average, than human-driven cars. But they may fail in new and catastrophic ways that a human driver could prevent. This project is designing a new architecture for a highly dependable self-driving car.
BlueDBM is an architecture of computer clusters consisting of fast distributed flash storage and in-storage accelerators, which often outperforms larger and more expensive clusters in applications such as graph analytics.
Our goal is to develop collaborative agents (software or robots) that can efficiently communicate with their human teammates. Key threads involve designing algorithms for inferring human behavior and for decision-making under uncertainty.
Our goal is to develop unsupervised or minimally supervised marine learning frameworks that allow autonomous underwater vehicles (AUVs) to explore unknown marine environments and communicate their findings in a semantically meaningful manner.
Our goal is to create an online risk-aware planner for vehicle maneuvers that can make driving safer and less stressful through a “parallel” autonomous system that assists the driver by watching for risky situations, and by helping the driver take proactive, compensating actions before they become crises.
For all the progress made in self-driving technologies, there still aren’t many places where they can actually drive. Companies like Google only test their fleets in major cities where they’ve spent countless hours meticulously labeling the exact 3-D positions of lanes, curbs, off-ramps, and stop signs.
Last week CSAIL hosted the second “Hot Topics in Computing” speaker series, a monthly forum where computing experts hold discussions with community members on various topics in the computer science field.
We live in the age of big data, but most of that data is “sparse.” Imagine, for instance, a massive table that mapped all of Amazon’s customers against all of its products, with a “1” for each product a given customer bought and a “0” otherwise. The table would be mostly zeroes.
In a traditional computer, a microprocessor is mounted on a “package,” a small circuit board with a grid of electrical leads on its bottom. The package snaps into the computer’s motherboard, and data travels between the processor and the computer’s main memory bank through the leads.
Most modern websites store data in databases, and since database queries are relatively slow, most sites also maintain so-called cache servers, which list the results of common queries for faster access. A data center for a major web service such as Google or Facebook might have as many as 1,000 servers dedicated just to caching.
Despite what you might see in movies, today’s robots are still very limited in what they can do. They can be great for many repetitive tasks, but their inability to understand the nuances of human language makes them mostly useless for more complicated requests.
Eight years ago, Ted Adelson’s research group at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) unveiled a new sensor technology, called GelSight, that uses physical contact with an object to provide a remarkably detailed 3-D map of its surface. Now, by mounting GelSight sensors on the grippers of robotic arms, two MIT teams have given robots greater sensitivity and dexterity. The researchers presented their work in two papers at the International Conference on Robotics and Automation last week.
In recent years, a host of Hollywood blockbusters — including “The Fast and the Furious 7,” “Jurassic World,” and “The Wolf of Wall Street” — have included aerial tracking shots provided by drone helicopters outfitted with cameras. Those shots required separate operators for the drones and the cameras, and careful planning to avoid collisions. But a team of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and ETH Zurich hope to make drone cinematography more accessible, simple, and reliable.
Most robots are programmed using one of two methods: learning from demonstration, in which they watch a task being done and then replicate it, or via motion-planning techniques such as optimization or sampling, which require a programmer to explicitly specify a task’s goals and constraints.
Every other year, the International Conference on Automated Planning and Scheduling hosts a competition in which computer systems designed by conference participants try to find the best solution to a planning problem, such as scheduling flights or coordinating tasks for teams of autonomous satellites. On all but the most straightforward problems, however, even the best planning algorithms still aren’t as effective as human beings with a particular aptitude for problem-solving — such as MIT students.