How Language Helps Robots Get a F3RM Grasp
Inspired by humans' ability to handle unfamiliar objects, a group from MIT designed Feature Fields for Robotic Manipulation (F3RM), a system that blends 2D images with foundation model features into 3D scenes to help robots identify and grasp nearby items. Watch this video to learn more.
More From SAE Media Group
Tech Briefs
ORNL’s INTERSECT: An Autonomous Chemistry Lab
Tech Briefs
Meet Picotaur: A First-of-its-Kind Micro Robot
Robotics & Automation INSIDER
Technology Focus: Turning Robot Operations Data into Actionable Insights
Motion Design
ChatGPT Enables Roboticist to Choreograph Flying Robots
Robotics & Automation INSIDER
Humanoid Robots: The Next-Generation Robotic Workforce
Tech Briefs
A SimPLE Way to Teach Robots to Pick and Place
Tech Briefs
A Soft Robot to Pack Your Groceries
Tech Briefs
A Picking Robot for a Greenhouse
Motion Design INSIDER
AI Helps Robots Manipulate Objects with Their Whole Bodies
Robotics & Automation INSIDER
Robots Learn from Videos
Tech Briefs
Robots One Step Closer to Learning Like Humans
Robotics & Automation INSIDER
A Faster, Better Way to Train General-Purpose Robots
Aerospace & Defense Tech Briefs
Will Generative AI Transform Robotics?
Tech Briefs
Recreating ‘Star Trek’ Virtual Environments
Tech Briefs
Giving Autonomous Vehicles the Ability to Reason
Tech Briefs
Next-Generation AMRs at Automate
Tech Briefs
Wheel-Legged Robots Navigating High Obstacles
Medical Manufacturing and Machining INSIDER
Industrial Robots Operate in Real Time
Tech Briefs
'Vestri' the Robot Imagines How to Perform Tasks
Tech Briefs
MIT’s Bio-Inspired Robots