Robotics | MIT News | Massachusetts Institute of Technology
2024年12月18日 · Combining next-token prediction and video diffusion in computer vision and robotics. A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments. October 16, 2024. Read full story →
A faster, better way to train general-purpose robots
2024年10月28日 · “In robotics, people often claim that we don’t have enough training data. But in my view, another big problem is that the data come from so many different domains, modalities, and robot hardware. Our work shows how you’d be able to train a robot with all of them put together,” says Lirui Wang, an electrical engineering and computer ...
Combining next-token prediction and video diffusion in computer …
2024年10月16日 · Diffusion Forcing, a method led by researchers at MIT CSAIL, can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.
Helping robots zero in on the objects that matter - MIT News
2024年9月30日 · The team details their results in a study appearing today in the journal Robotics and Automation Letters. Carlone’s co-authors include members of the SPARK Lab: Dominic Maggio, Yun Chang, Nathan Hughes, and Lukas Schmid; and members of MIT Lincoln Laboratory: Matthew Trang, Dan Griffith, Carlyn Dougherty, and Eric Cristofalo. Open fields
The new wave of robotic automation - MIT News
2021年6月16日 · In May 2017, Realtime Robotics set up shop at MassRobotics, a Boston-area robotics collective. Three months later they had completed their first seed round of funding and landed their first contract with Amazon Robotics. A year later, they had demonstrated their first killer demo for an audience that included two of the top six robot makers.
A technique for more effective multipurpose robots - MIT News
2024年6月3日 · But robots trained this way, with a relatively small amount of task-specific data, are often unable to perform new tasks in unfamiliar environments. In an effort to train better multipurpose robots, MIT researchers developed a technique to combine multiple sources of data across domains, modalities, and tasks using a type of generative AI known ...
Precision home robots learn with real-to-sim-to-real - MIT News
2024年7月31日 · MIT CSAIL's real-to-sim-to-real pipeline RialTo enables users to capture digital twins of their surroundings for on-the-fly robot learning. As a combination of reinforcement learning and imitation learning, the approach helps robot practice in …
Can robots learn from machine dreams? - MIT News
2024年11月19日 · Since the 1970s, the field has evolved from writing sophisticated programs to using deep learning, teaching robots to learn directly from human behavior. But a critical bottleneck remains: data quality. To improve, robots need to encounter scenarios that push the boundaries of their capabilities, operating at the edge of their mastery.
AI helps robots manipulate objects with their whole bodies
2023年8月24日 · Humans are generally good at whole-body manipulation, but robots struggle with such tasks. To the robot, each spot where the box could touch any point on the carrier’s fingers, arms, and torso represents a contact event that it must reason about. With billions of potential contact events, planning for this task quickly becomes intractable.
A better way to control shape-shifting soft robots - MIT News
2024年5月10日 · A new machine-learning technique can train and control a reconfigurable soft robot that can dynamically change its shape to complete a task. The researchers, from MIT and elsewhere, also built a simulator that can evaluate control algorithms for …