English

LocoVLM: Grounding Vision and Language for Adapting Versatile Legged Locomotion Policies

Robotics 2026-02-12 v1

Abstract

Recent advances in legged locomotion learning are still dominated by the utilization of geometric representations of the environment, limiting the robot's capability to respond to higher-level semantics such as human instructions. To address this limitation, we propose a novel approach that integrates high-level commonsense reasoning from foundation models into the process of legged locomotion adaptation. Specifically, our method utilizes a pre-trained large language model to synthesize an instruction-grounded skill database tailored for legged robots. A pre-trained vision-language model is employed to extract high-level environmental semantics and ground them within the skill database, enabling real-time skill advisories for the robot. To facilitate versatile skill control, we train a style-conditioned policy capable of generating diverse and robust locomotion skills with high fidelity to specified styles. To the best of our knowledge, this is the first work to demonstrate real-time adaptation of legged locomotion using high-level reasoning from environmental semantics and instructions with instruction-following accuracy of up to 87% without the need for online query to on-the-cloud foundation models.

Keywords

Cite

@article{arxiv.2602.10399,
  title  = {LocoVLM: Grounding Vision and Language for Adapting Versatile Legged Locomotion Policies},
  author = {I Made Aswin Nahrendra and Seunghyun Lee and Dongkyu Lee and Hyun Myung},
  journal= {arXiv preprint arXiv:2602.10399},
  year   = {2026}
}

Comments

Project page: https://locovlm.github.io