Visuomotor Policy Learning

Visuomotor policies map what a robot sees to actions, helping it manipulate objects, navigate, and interact when the scene or task changes. Common approaches learn from demonstrations through action-chunking transformers, diffusion or flow-matching policies, and vision-language-action models; reinforcement learning and policy distillation are also used. Researchers improve these policies with geometric and object-centered visual features, memory, contact sensing, and predictions of how actions will change the scene, evaluating them on benchmarks such as LIBERO and RoboTwin as well as physical robots. A central tension is achieving reliable generalization and safe, precise control in real settings while keeping data needs, model size, and inference latency low.