Visuomotor Policy

السياسة البصرية-الحركية

سياسة تحكّم تأخذ صور كاميرا خام كمدخل وتُخرج مباشرةً أوامر حركية (كعزوم المحركات)، فتجمع الإدراك البصري والتحكم الحركي في نموذج واحد مُدرَّب من الطرف إلى الطرف.

A control policy that takes raw camera images as input and directly outputs motor commands (such as torques), combining visual perception and motor control in a single end-to-end trained model.

Also translated asسياسة الرؤية والحركة، السياسة البصرية الحركية

First appears in this corpus in: End-to-End Training of Deep Visuomotor Policies (2016)

Appears in these papers

Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware2023 in the sky ✦
Diffusion Policy: Visuomotor Policy Learning via Action Diffusion2023 in the sky ✦
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation2018 in the sky ✦
RT-1: Robotics Transformer for Real-World Control at Scale2022 in the sky ✦
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances2022 in the sky ✦
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances2022 in the sky ✦
End-to-End Training of Deep Visuomotor Policies2016 in the sky ✦