Technology ❯ Robotics ❯ Machine Learning

Vision-Language Models

Robotic Manipulation Geometric Integration 3D Point Cloud Processing Tactile Feedback Action Generation Spatial Reasoning Benchmarking Action Prediction Evaluation Methods Zero-Shot Learning Vision-Language-Action Models Semantic Assembly Representation Corruption Restoration Gemini Robotics 1.5 DySL-VLA Framework Training and Scaling Primitive-Centric Framework Flow Matching Models

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.

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