ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal
This addresses the problem of balancing perceptual fidelity with computational efficiency for humanoid robots in complex environments, representing an incremental improvement over existing methods.
The paper tackles agile humanoid locomotion in complex 3D environments by proposing ADAPT, an adaptive dual-projection architecture that reduces observation dimensionality and computational overhead, achieving successful zero-shot transfer to a Unitree G1 Humanoid and outperforming fixed-range baselines.
Agile humanoid locomotion in complex 3D en- vironments requires balancing perceptual fidelity with com- putational efficiency, yet existing methods typically rely on rigid sensing configurations. We propose ADAPT (Adaptive dual-projection architecture for perceptive traversal), which represents the environment using a horizontal elevation map for terrain geometry and a vertical distance map for traversable- space constraints. ADAPT further treats its spatial sensing range as a learnable action, enabling the policy to expand its perceptual horizon during fast motion and contract it in cluttered scenes for finer local resolution. Compared with voxel-based baselines, ADAPT drastically reduces observation dimensionality and computational overhead while substantially accelerating training. Experimentally, it achieves successful zero-shot transfer to a Unitree G1 Humanoid and signifi- cantly outperforms fixed-range baselines, yielding highly robust traversal across diverse 3D environtmental challenges.