A faster, better way to train general-purpose robots
Oct 28, 2024 · At the same time, each robot is mechanically unique, with a different number and orientation of arms, grippers, and sensors. Plus, the environments where data are collected vary widely. The MIT researchers developed a new architecture called Heterogeneous Pretrained Transformers (HPT) that unifies data from these varied modalities and domains.
Robotics | MIT News | Massachusetts Institute of Technology
Oct 28, 2024 · 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.
What is a robot? - New Scientist
The word “robot” was coined by the Czech writer Karel Čapek in a 1920 play called Rossum’s Universal Robots, and is derived from the Czech robota, meaning “drudgery” or “servitude”.
A better way to control shape-shifting soft robots
May 10, 2024 · Here, a reconfigurable robot learns to elongate and curve its soft body to weave around obstacles and reach a target. Image: Courtesy of the researchers “Such a robot could have thousands of small pieces of muscle to control, so it is very hard to learn in a traditional way,” says Chen.
Helping robots zero in on the objects that matter - MIT News
Sep 30, 2024 · MIT engineers have developed a method that enables robots to make similarly intuitive, task-relevant decisions. The team’s new approach, named Clio, enables a robot to identify the parts of a scene that matter, given the tasks at hand. With Clio, a robot takes in a list of tasks described in natural language and, based on those tasks, it then ...
Computer-aided creativity in robot design - MIT News
Nov 30, 2020 · Choosing the best robot design requires controlling each robot’s movements and evaluating its function. “Up until now, these robots are just structures,” says Zhao. The controller is the set of instructions that brings those structures to life, governing the movement sequence of the robot’s various motors.
Finger-shaped sensor enables more dexterous robots
Oct 4, 2023 · MIT researchers developed a touch sensor for a robotic hand that is long and curved, like a human finger, and provides sensing along its entire length. This could enable a robot to grasp large or heavy objects more like a human would, with its entire fingers, while still being able to grasp small items with its fingertips.
The new wave of robotic automation - MIT News
Jun 16, 2021 · Peter Howard SM ’84 is the CEO of Realtime Robotics, a startup transforming autonomous robot motion planning to enable seamless, affordable human-robot collaboration. Realtime Robotics has developed a combination of proprietary software and hardware that reduces system deployment time by 70 percent or more, reduces deployment costs by 30 ...
How to help humans understand robots - MIT News
Mar 2, 2022 · Researchers from MIT and Harvard suggest that applying theories from cognitive science and educational psychology to the area of human-robot interaction can help humans build more accurate mental models of their robot collaborators, which could boost performance and improve safety in cooperative workspaces. Credits. Image: MIT News, iStockphoto.
3 Questions: How the MIT mini cheetah learns to run
Mar 17, 2022 · Q: Previous agile running controllers for the MIT Cheetah 3 and mini cheetah, as well as for Boston Dynamics’ robots, are “analytically designed,” relying on human engineers to analyze the physics of locomotion, formulate efficient abstractions, and implement a specialized hierarchy of controllers to make the robot balance and run.