Can robots learn from machine dreams? - MIT News
2024年11月19日 · LucidSim is an AI-powered simulator that trained a robot dog to perform parkour using generated images without any real-world data. This approach, from MIT CSAIL researchers, scales up training data, helping robots transfer skills to the real world without additional fine-tuning.
Robotics | MIT News | Massachusetts Institute of Technology
3 天之前 · MIT CSAIL researchers used AI-generated images to train a robot dog in parkour, without real-world data. Their LucidSim system demonstrates generative AI's potential for creating robotics training data. November 19, 2024. Read full story →
Helping robots practice skills independently to adapt to unfamiliar ...
2024年8月8日 · The robot, which has an arm attached to its back, completed manipulation tasks after practicing for a few hours. In one demonstration, the robot learned how to securely place a ball and ring on a slanted table in roughly three hours. In another, the algorithm guided the machine to improve at sweeping toys into a bin within about two hours.
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 faster, better way to train general-purpose robots
2024年10月28日 · 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.
Flying robot leaps upwards and then takes to the air like a bird
2024年12月4日 · A robot that can jump into flight like a bird could eliminate the need for runways for small fixed-winged drones.. Birds use the powerful explosive force generated by their legs to leap into the ...
A better way to control shape-shifting soft robots
2024年5月10日 · 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.
The way Cheerios stick together has inspired a new kind of robot
2024年11月28日 · A robot inspired by Cheerios releasing alcohol fuel with a fluorescent dye. Jackson K. Wilt et al. 2024. The same phenomena that let beetles float across ponds and cause Cheerios to cluster ...
Helping robots zero in on the objects that matter - MIT News
2024年9月30日 · A robot can then apply that neural network to spot a dog in a totally new scene. But a challenge still remains as to how to parse a scene in a useful way that is relevant for a particular task. “Typical methods will pick some arbitrary, fixed level of granularity for determining how to fuse segments of a scene into what you can consider as ...
Engineering household robots to have a little common sense
2024年3月25日 · Mapping a robot’s physical coordinates, or an image of the robot state, to a natural language label is known as “grounding.” The team’s new algorithm is designed to learn a grounding “classifier,” meaning that it learns to automatically identify what semantic subtask a robot is in — for example, “reach” versus “scoop ...