World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain

• URL: http://arxiv.org/abs/2609.02542v1
• Date: Wed, 02 Sep 2026 12:57:01 GMT
• Title: World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain
• Abstract summary: We ask whether a learned predictive summary of near-future observations and rewards can provide the anticipatory information required in such settings.<n>We present World-Model-Augmented Visual Locomotion (WM-LOCO), which jointly trains a recurrent world model and a PPO policy.<n>In simulation, WM-LOCO succeeds on gaps and stepping stones where a matched baseline fails completely, and matches the baseline's success rate on stairs.
• Score: 29.978527754674044
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foothold-constrained terrain is characterized by sparse, discontinuous, or geometrically restricted feasible foot contacts, as encountered on stepping stones, across gaps, and on narrow stair treads. On such terrain, a single misstep often leaves little room to recover, so policies that base foot-placement decisions primarily on the immediately visible terrain are prone to failure. We ask whether a learned predictive summary of near-future observations and rewards can provide the anticipatory information required in such settings. We present World-Model-Augmented Visual Locomotion (WM-LOCO), which jointly trains a recurrent world model and a PPO policy. Conditioned on proprioception and a single onboard depth image, the world model produces a predictive recurrent feature that guides the policy, without explicit foothold labels. In simulation, WM-LOCO succeeds on gaps and stepping stones where a matched baseline fails completely, and matches the baseline's success rate on stairs while improving stride efficiency and reducing pelvis acceleration. We deploy the same policy onboard a physical Unitree G1 humanoid using onboard proprioception and a single depth stream; it traverses all three terrain classes with an average success rate of 93.3%.

Related papers

• SOLO: Stable Omni-terrain Long-Horizon Perceptive Humanoid Locomotion [41.64988244398264]
  We present SOLO, a unified framework addressing two compounding causes of long-horizon fragility: dense terrain reconstruction smooths action-critical details, and pointwise imitation lacks temporal credit assignment.<n>Its Query Reconstructor (QR) uses Fourier-encoded cell queries to retrieve spatially specific evidence from depth-proprioception tokens, preserving sharp terrain boundaries.<n>Its Trajectory-Aware MSE (TA-MSE) Distillation adds next-state teacher-student disagreement to the PPO reward, enabling Generalized Advantage Estimation to propagate future disagreement penalties to preceding actions.
  arXiv  Detail & Related papers  (2026-08-27T03:49:55Z)
• PTDL:Multi-Terrain Fall Recovery via Phase-Terrain Decoupled Learning [13.93626645001]
  Humanoid robots can fall on slopes, gravel, and uneven ground in unstructured environments.<n>We propose Phase--Terrain Decoupled Learning (PTDL), which decouples training supervision along phase and terrain axes.<n>We validate PTDL on a 29-DoF Unitree G1 across flat ground, gravel, and slopes up to 20 degrees in simulation and on hardware.
  arXiv  Detail & Related papers  (2026-06-08T02:01:08Z)
• Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking [78.30338456206984]
  We introduce a novel framework for training general-purpose 3D foothold-tracking policies.<n>By dynamically providing footstep support through a goal sampler, this method enables the learned policy to be agnostic to specific terrains.<n>Our new target representation effectively mitigates challenges arising in the real world, such as noisy and inaccurate pose estimation and foot contact estimation.
  arXiv  Detail & Related papers  (2026-06-06T16:44:56Z)
• Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives [72.63181031215858]
  We propose a zero-shot floorplan localization method that generalizes to novel environments without any retraining.<n>Our key insight is that dominant geometric primitives are ubiquitous in human-made environments.<n> Experiments on both simulated and real-world datasets show that our approach outperforms state-of-the-art learning-based methods on unseen environments.
  arXiv  Detail & Related papers  (2026-06-03T12:14:24Z)
• Lifting Embodied World Models for Planning and Control [59.09016913513998]
  We train a lightweight policy that maps high-level actions to sequences of low-level joint actions.<n>We instantiate this framework for a human-like embodiment, defining the high-level action space as a small set of 2D waypoints.<n>We show that the lifted world model substantially outperforms searching directly in low-level joint space.
  arXiv  Detail & Related papers  (2026-04-28T23:59:19Z)
• Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training [54.896907620476675]
  We propose a post-training framework that uses a learned world model as a reusable corrective substrate for failure-targeted policy improvement.<n>Hi-WM caches intermediate states and supports rollback and branching, allowing a single failure state to be reused for multiple corrective continuations.<n>We evaluate Hi-WM on three real-world manipulation tasks spanning both rigid and deformable object interaction, and on two policy backbones.
  arXiv  Detail & Related papers  (2026-04-23T14:42:54Z)
• Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction [86.53248703859718]
  We introduce a perceptive locomotion framework that merges terrain sensing, gait regulation, and whole-body control into a single reinforcement learning policy.<n>Experiments conducted on a 31-DoF, 1.65 m humanoid robot demonstrate robust locomotion in both simulation and real-world settings.
  arXiv  Detail & Related papers  (2025-12-08T11:42:41Z)
• One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion [31.509149084648797]
  We propose a unified framework that enables a single policy to master diverse terrains.<n>By unifying offline data, diffusion-based trajectory, and policy optimization, DreamPolicy overcomes the "one task, one policy" bottleneck.
  arXiv  Detail & Related papers  (2025-05-24T16:33:44Z)
• Hidden Footprints: Learning Contextual Walkability from 3D Human Trails [70.01257397390361]
  Current datasets only tell you where people are, not where they could be. We first augment the set of valid, labeled walkable regions by propagating person observations between images, utilizing 3D information to create what we call hidden footprints. We devise a training strategy designed for such sparse labels, combining a class-balanced classification loss with a contextual adversarial loss.
  arXiv  Detail & Related papers  (2020-08-19T23:19:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.