Robotics

75 Posts

Robo-Football From Simulation to Reality: Reinforcement learning powers humanoid robots to play football
Robotics

Robo-Football From Simulation to Reality: Reinforcement learning powers humanoid robots to play football

Humanoid robots can play football (known as soccer in the United States) in the real world, thanks to reinforcement learning.
Conversational Robots: RFM-1, a model that enables robots to understand and act on human commands
Robotics

Conversational Robots: RFM-1, a model that enables robots to understand and act on human commands

Robots equipped with large language models are asking their human overseers for help.
Robot Chemist: RoboChem, a system that outshines human chemists in chemical synthesis efficiency
Robotics

Robot Chemist: RoboChem, a system that outshines human chemists in chemical synthesis efficiency

A robot outperformed human chemists at synthesizing chemicals. Researchers at University of Amsterdam built RoboChem, an integrated robotic system that learned to design light-activated chemical reactions while achieving optimal yields and throughput.
Figure showing how PaLM-E operates on multimodal sentences
Robotics

This Language Model Speaks Robot: PaLM-E, the model that improves robot control with large language model expertise

A pretrained large language model has helped a robot resolve high-level commands into sequences of subtasks. It can do this more precisely with additional training — both on language-vision tasks and robotics tasks. 
ChatGPT’s Best Friend: Unitree's robot dog Go2 is smarter than ever.
Robotics

ChatGPT’s Best Friend: Unitree's robot dog Go2 is smarter than ever.

The latest robot dog is smarter — and less expensive — than ever. Unitree Robotics of Hangzhou, China, unleashed Go2, a quadruped robot that trots alongside its owner, stands on two legs, jumps, talks, takes photos, and retails for less than a high-end MacBook.
Sample-Efficient Training for Robots: Reinforcement learning from human feedback to train robots
Robotics

Sample-Efficient Training for Robots: Reinforcement learning from human feedback to train robots

Training an agent that controls a robot arm to perform a task — say, opening a door — that involves a sequence of motions (reach, grasp, turn, pull, release) can take from tens of thousands to millions of examples...
AI-guided robotic arms crafting, forming and polishing metal
Robotics

AI Shows Its Metal: How Machina Labs uses AI to automate metal fabrication

Neural networks are predicting how metal will deform under pressure to pilot robots through the tricky process of fabricating aircraft. Machina Labs crafts metal using AI-guided robotic arms.
Results from a poll by Pew Research Center
Robotics

What Americans Want From AI: Pew survey asks 11,000 Americans about AI.

Adults in the United States tend to view AI’s medical applications favorably but are leery of text and image generation. Pew Research Center polled 11,004 U.S. adults for their opinions of AI in science, healthcare, and media.
Examples of learned gaits acquired on a variety of real-world terrains
Robotics

Real-World Training on the Double: A new method rapidly trains robots in the real world.

Roboticists often train their machines in simulation, where the controller model can learn from millions of hours of experience. A new method trained robots in the real world in 20 minutes.
Architecture for PointGoal Navigation on a legged robot
Robotics

Streamlined Robot Training: Robots trained in lo-fi simulation perform better in reality.

Autonomous robots trained to navigate in a simulation often struggle in the real world. New work helps bridge the gap in a counterintuitive way.
Illustration of three deers doing holiday household chores: washing a champagne flute, cooking pie and wrapping a gift
Robotics

One Model Does It All: Multi-task AI models got more sophisticated in 2022.

Individual deep learning models proved their mettle in hundreds of tasks. The scope of multi-task models expanded dramatically in the past year.
Ground truth video of a road on the left and predicted video with MaskViT on the right
Robotics

Seeing What Comes Next: Transformers predict future video frames.

If a robot can predict what it’s likely to see next, it may have a better basis for choosing an appropriate action — but it has to predict quickly. Transformers, for all their utility in computer vision, aren’t well suited to this because of their steep computational and memory requirements...
Robot with an arm, camera, and gripper handing over a plastic bottle to a person
Robotics

Parsing Commands Into Actions: NLP Helps Google Robot Understand Spoken Instructions

A new method enables robots to respond helpfully to verbal commands by pairing a natural language model with a repertoire of existing skills.
Fishermen insert their catch into a machine from Shinkei Systems, which automatically processes the fish.
Robotics

Neural Nets Catch Fresher Fish: Robot Deck Hand Automatically Processes Fish

Shinkei Systems developed a machine that uses computer vision to slaughter fish in a way that maximizes their shelf life and flavor.
TX SCAR robot restocks beverages at a FamilyMart in Japan.
Robotics

One Cool Robot: FamilyMart Uses TX SCAR Robots to Restock Beverages

FamilyMart, a chain of Japanese convenience stores, plans to employ robots to fill shelves with beverage bottles at 300 locations.
Load More

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox