Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains

TL;DR

Gallant introduces a voxel-grid-based perception framework using LiDAR data and a specialized CNN to enhance humanoid robot navigation in complex 3D terrains, achieving high success rates in challenging scenarios.

Contribution

It presents a novel voxel-grid-based perception method with end-to-end training for humanoid locomotion in 3D environments, surpassing previous partial perception approaches.

Findings

Enables navigation beyond ground-level obstacles, including overhead and lateral clutter.

Achieves near 100% success in stair climbing and platform stepping tasks.

Supports scalable training with a realistic LiDAR simulation.

Abstract

Robust humanoid locomotion requires accurate and globally consistent perception of the surrounding 3D environment. However, existing perception modules, mainly based on depth images or elevation maps, offer only partial and locally flattened views of the environment, failing to capture the full 3D structure. This paper presents Gallant, a voxel-grid-based framework for humanoid locomotion and local navigation in 3D constrained terrains. It leverages voxelized LiDAR data as a lightweight and structured perceptual representation, and employs a z-grouped 2D CNN to map this representation to the control policy, enabling fully end-to-end optimization. A high-fidelity LiDAR simulation that dynamically generates realistic observations is developed to support scalable, LiDAR-based training and ensure sim-to-real consistency. Experimental results show that Gallant's broader perceptual coverage facilitates the use of a single policy that goes beyond the limitations of previous methods confined to ground-level obstacles, extending to lateral clutter, overhead constraints, multi-level structures, and narrow passages. Gallant also firstly achieves near 100% success rates in challenging scenarios such as stair climbing and stepping onto elevated platforms through improved end-to-end optimization.