CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision

Teaching robots desired skills in real-world environments remains challenging, especially for non-experts. The reliance on specialized expertise in robot control and teleoperation systems often limits accessibility to non-experts. We posit that natural language offers an intuitive and accessible interface for robot learning. To this end, we study two aspects: (1) enabling non-experts to collect robotic data through natural language supervision (e.g., "move the arm to the right") and (2) learning robotic policies directly from this supervision. Specifically, we introduce a data collection framework that collects robot demonstrations based on natural language supervision and further augments these demonstrations. We then present CLIP-RT, a vision-language-action (VLA) model that learns language-conditioned visuomotor policies from this supervision. CLIP-RT adapts the pretrained CLIP models and learns to predict language-based motion primitives via contrastive imitation learning. We train CLIP-RT on the Open X-Embodiment dataset and finetune it on in-domain data collected by our framework to learn diverse skills. CLIP-RT demonstrates strong capabilities in learning novel manipulation skills, outperforming the state-of-the-art model, OpenVLA (7B parameters), by 24% in average success rates, while using 7x fewer parameters (1B). We further observe that CLIP-RT shows significant improvements in few-shot generalization. Finally, through collaboration with humans or large pretrained models, we demonstrate that CLIP-RT can further improve its generalization on challenging tasks.