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

arXiv: https://arxiv.org/abs/2602.10399 · HTML: https://mlsanity.com/paper/2602.10399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2026.

## Built on by (most cited first, 1 of 1)

- [RDA: Reward Design Agent for Reinforcement Learning](https://mlsanity.com/paper/2606.01672/) (2026)

## Abstract (arXiv)

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.