Researchers have developed a new AI model called PEAfowl that can improve the performance of robots performing bimanual manipulation tasks in cluttered environments. The model uses multiple views and language to enhance its perception and action capabilities. It predicts depth distributions, lifts 3D features, and aggregates local cross-view neighbors to form geometrically grounded representations. The authors claim that PEAfowl outperforms existing models by a significant margin on both simulated and real-robot tasks. --- Why it matters: This matters because it could lead to more accurate and efficient robotic manipulation in industries such as manufacturing and logistics, where cluttered environments are common. Source: https://arxiv.org/abs/2601.17885