Technology ❯ Robotics

Machine Learning

Vision-Language Models Vision-Language-Action Models Reinforcement Learning Vision-Language-Action Imitation Learning Data Processing Deep Learning Feedback Mechanisms Natural Language Processing Complex Task Performance

Three Papers Offer Data, Inference and Safety Fixes for Fragile VLA Robot Models

The proposals aim to cut shortcut learning, stop open-loop action failures, and predict collisions before they occur.

Stories older than 24h

DeepMind Unveils Gemini Robotics‑ER 1.5 and Gemini Robotics 1.5 to Let Robots Plan Tasks and Use the Web

Robots Master Sink Cleaning with Human-Like Learning

MIT Develops Clio to Enhance Robots' Task-Specific Object Recognition

Robots Learn to Navigate Rough Terrain with Animal-Inspired Gait Transitions

Robot Dog Trained to Open Doors Using Its Leg