Vision-language models (VLMs) show promise in automating reward design in humanoid locomotion, which could eliminate the need for tedious manual engineering. However, current VLM-based methods are essentially "blind", as they lack the environmental perception required to navigate complex terrain. We present E-SDS (Environment-aware See it, Do it, Sorted), a framework that closes this perception gap. E-SDS integrates VLMs with real-time terrain sensor analysis to automatically generate reward functions that facilitate training of robust perceptive locomotion policies, grounded by example videos. Evaluated on a Unitree G1 humanoid across four distinct terrains (simple, gaps, obstacles, stairs), E-SDS uniquely enabled successful stair descent, while policies trained with manually-designed rewards or a non-perceptive automated baseline were unable to complete the task. In all terrains, E-SDS also reduced velocity tracking error by 51.9-82.6%. Our framework reduces the human effort of reward design from days to less than two hours while simultaneously producing more robust and capable locomotion policies.
@article{arxiv.2512.16446,
title = {E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotion},
author = {Enis Yalcin and Joshua O'Hara and Maria Stamatopoulou and Chengxu Zhou and Dimitrios Kanoulas},
journal= {arXiv preprint arXiv:2512.16446},
year = {2025}
}