Loco-Loco-RL: Low-Cost Terrain Mapping for Humanoid Locomotion with Reinforcement Learning

arXiv:2609.19041v1 Announce Type: new Abstract: Informative terrain perception is important for robust reinforcement learning policies in humanoid locomotion. Still, common sensors such as depth cameras and LiDARs incur high cost, power, and processing overhead while often producing redundant, high-resolution data. This work uses a low-cost time-of-flight sensor to provide a compact 3D local terrain representation for humanoid locomotion. To efficiently use this sparse exteroceptive input, we introduce a token-compressed temporal transformer policy. Proprioceptive and terrain observations are tokenized and processed by a self-attention multi-head transformer to capture within-timestep relationships between observation terms. The attended tokens are then compressed through an MLP-based latent-space token compression module before being stored in a rolling 15-timestep history. A second cross-attention multi-head transformer extracts temporal locomotion features from this compact history for policy learning. By compressing tokens before temporal aggregation, the architecture preserves important terrain-observation structure while limiting the dimensional growth of attention over observation histories. We validate our method through sim-to-real transfer on physical hardware using a terrain-based locomotion benchmark, demonstrating robust humanoid terrain walking with low-cost local terrain sensing.

Abstract:Informative terrain perception is important for robust reinforcement learning policies in humanoid locomotion. Still, common sensors such as depth cameras and LiDARs incur high cost, power, and processing overhead while often producing redundant, high-resolution data. This work uses a low-cost time-of-flight sensor to provide a compact 3D local terrain representation for humanoid locomotion. To efficiently use this sparse exteroceptive input, we introduce a token-compressed temporal transformer policy. Proprioceptive and terrain observations are tokenized and processed by a self-attention multi-head transformer to capture within-timestep relationships between observation terms. The attended tokens are then compressed through an MLP-based latent-space token compression module before being stored in a rolling 15-timestep history. A second cross-attention multi-head transformer extracts temporal locomotion features from this compact history for policy learning. By compressing tokens before temporal aggregation, the architecture preserves important terrain-observation structure while limiting the dimensional growth of attention over observation histories. We validate our method through sim-to-real transfer on physical hardware using a terrain-based locomotion benchmark, demonstrating robust humanoid terrain walking with low-cost local terrain sensing.

6 pages, 3 figures. Accepted manuscript. Accepted for publication in the 2026 IEEE National Aerospace and Electronics Conference (NAECON)

Robotics (cs.RO)

arXiv:2609.19041 [cs.RO]

(or arXiv:2609.19041v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.19041 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Loco-Loco-RL: Low-Cost Terrain Mapping for Humanoid Locomotion with Reinforcement Learning

Related coverage