Omnidirectional Humanoid Locomotion on Stairs via Unsafe Stepping Penalty and Sparse LiDAR Elevation Mapping

• URL: http://arxiv.org/abs/2603.07928v1
• Date: Mon, 09 Mar 2026 03:48:32 GMT
• Title: Omnidirectional Humanoid Locomotion on Stairs via Unsafe Stepping Penalty and Sparse LiDAR Elevation Mapping
• Abstract summary: This paper introduces a single-stage training framework incorporating a dense unsafe stepping penalty.<n>It achieves a near-100% safe stepping rate on stair terrains in simulation, while maintaining a remarkably high safe stepping rate in real-world deployments.<n>It completes a continuous long-distance walking test on complex outdoor terrains, demonstrating reliable sim-to-real transfer and long-term stability.
• Score: 6.267657984340167
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Humanoid robots, characterized by numerous degrees of freedom and a high center of gravity, are inherently unstable. Safe omnidirectional locomotion on stairs requires both omnidirectional terrain perception and reliable foothold selection. Existing methods often rely on forward-facing depth cameras, which create blind zones that restrict omnidirectional mobility. Furthermore, sparse post-contact unsafe stepping penalties lead to low learning efficiency and suboptimal strategies. To realize safe stair-traversal gaits, this paper introduces a single-stage training framework incorporating a dense unsafe stepping penalty that provides continuous feedback as the foot approaches a hazardous placement. To obtain stable and reliable elevation maps, we build a rolling point-cloud mapping system with spatiotemporal confidence decay and a self-protection zone mechanism, producing temporally consistent local maps. These maps are further refined by an Edge-Guided Asymmetric U-Net (EGAU), which mitigates reconstruction distortion caused by sparse LiDAR returns on stair risers. Simulation and real-robot experiments show that the proposed method achieves a near-100\% safe stepping rate on stair terrains in simulation, while maintaining a remarkably high safe stepping rate in real-world deployments. Furthermore, it completes a continuous long-distance walking test on complex outdoor terrains, demonstrating reliable sim-to-real transfer and long-term stability.

Related papers

• Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning [60.888463449435484]
  We present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift.<n>We show that imitation learning methods achieve high scores in ID benchmarks, but suffer from persistent drift when subjected to temporally correlated actuation noise.<n>Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.
  arXiv  Detail & Related papers  (2026-07-08T18:23:48Z)
• TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues [2.9521757117513823]
  Vision-language navigation (VLN) in long-range, open-world environments is frequently disrupted by semantic-cue interruptions.<n>We propose a unified outdoor VLN framework that survives semantic-cue interruptions by maintaining traversability-consistent executable guidance.
  arXiv  Detail & Related papers  (2026-05-29T10:30:36Z)
• Explicit Stair Geometry Conditioning for Robust Humanoid Locomotion [15.718523500563203]
  This paper proposes an explicit stair geometry conditioning framework for robust humanoid stair climbing.<n>Instead of encoding terrain as high-dimensional latent features, we extract a compact set of interpretable geometric parameters, including step height, step depth, and current yaw angle relative to the robot heading.<n>These explicit stair parameters directly condition a Proximal Policy Optimization (PPO)-based locomotion policy, enabling proactive modulation of swing-foot clearance and stride characteristics according to stair structure.
  arXiv  Detail & Related papers  (2026-05-11T03:47:24Z)
• RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework [49.531001563853984]
  RAD-2 is a unified generator-discriminator framework for closed-loop planning.<n>It produces diverse trajectory candidates, while an RL-optimized discriminator reranks these candidates according to their long-term driving quality.<n>It reduces the collision rate by 56% compared with strong diffusion-based planners.
  arXiv  Detail & Related papers  (2026-04-16T17:59:44Z)
• OnFly: Onboard Zero-Shot Aerial Vision-Language Navigation toward Safety and Efficiency [9.769964979769204]
  We propose OnFly, a fully onboard, real-time framework for zero-shot AVLN.<n>OnFly adopts a shared-perception dual-agent architecture that decouples high-frequency target generation from low-frequency progress monitoring.<n>In simulation, OnFly improves task success from 26.4% to 67.8%, compared with the strongest state-of-the-art baseline.
  arXiv  Detail & Related papers  (2026-03-11T11:48:22Z)
• Geometry of Drifting MDPs with Path-Integral Stability Certificates [14.721539799090904]
  Real-world reinforcement learning is often emphnonstationary: rewards and dynamics drift, accelerate, oscillate, and trigger abrupt switches in the optimal action.<n>We take a geometric view of nonstationary discounted Markov Decision Processes (MDPs) by modeling the environment as a differentiable homotopy path and tracking the induced motion of the optimal Bellman fixed point.<n>This yields a length--curvature--kink signature of intrinsic complexity: cumulative drift, acceleration/oscillation, and action-gap-induced nonsmoothness.
  arXiv  Detail & Related papers  (2026-01-29T17:03:23Z)
• FastStair: Learning to Run Up Stairs with Humanoid Robots [19.796528911795516]
  Running up stairs is effortless for humans but difficult for humanoid robots.<n>FastStair is a planner-guided, multi-stage learning framework to achieve fast and stable stair ascent.<n>We deploy the resulting controller on the Oli humanoid robot, achieving stable stair ascent at commanded speeds up to 1.65 m/s.
  arXiv  Detail & Related papers  (2026-01-15T13:14:59Z)
• Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids [30.976354277907664]
  textitHiking in the Wild is a scalable, end-to-end parkour perceptive framework designed for robust humanoid hiking.<n>Our approach utilizes a single-stage reinforcement learning scheme, mapping raw depth inputs and proprioception directly to joint actions, without relying on external state estimation.
  arXiv  Detail & Related papers  (2026-01-12T16:50:50Z)
• START: Traversing Sparse Footholds with Terrain Reconstruction [11.632418196552324]
  We propose START, a single-stage learning framework that enables agile, stable locomotion on highly sparse footholds.<n> START leverages only low-cost onboard vision and proprioception to accurately reconstruct local terrain heightmap.<n> Experimental results demonstrate that START achieves zero-shot transfer across diverse real-world scenarios.
  arXiv  Detail & Related papers  (2025-12-15T10:02:41Z)
• 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)
• Physical Adversarial Camouflage through Gradient Calibration and Regularization [48.064270454248316]
  adversarial camouflage poses a significant security risk by altering object textures to deceive detectors.<n>Existing techniques struggle with variable physical environments.<n>We propose a novel adversarial camouflage framework based on gradient optimization.
  arXiv  Detail & Related papers  (2025-08-07T14:07:49Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• Autonomous Control of a Novel Closed Chain Five Bar Active Suspension via Deep Reinforcement Learning [0.6456676618238324]
  This paper deals with an active suspension system focused on chassis stabilisation. SAC was applied along with Proportional Integral Derivative (PID) control to stabilise the chassis. The model uses the rover's distance from surrounding obstacles, the height of the obstacle, and the chassis' orientation to actuate the control links of the suspension accurately.
  arXiv  Detail & Related papers  (2024-06-27T05:27:39Z)
• VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation [78.92147339883137]
  We show that it is pivotal in increasing controller robustness by learning a latent space capturing the key stance phases constituting a particular gait. We demonstrate that specific properties of the drive signal map directly to gait parameters such as cadence, footstep height and full stance duration. The use of a generative model facilitates the detection and mitigation of disturbances to provide a versatile and robust planning framework.
  arXiv  Detail & Related papers  (2022-05-02T19:49:53Z)
• Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion [69.87112582900363]
  Current planners are unable to vary key gait parameters continuously while the robot is in motion. In this work we address this limitation by learning a latent space capturing the key stance phases constituting a particular gait. We demonstrate that specific properties of the drive signal map directly to gait parameters such as cadence, foot step height and full stance duration.
  arXiv  Detail & Related papers  (2021-12-09T10:02:02Z)
• STEP: Stochastic Traversability Evaluation and Planning for Safe Off-road Navigation [9.423950528323893]
  We propose an approach for assessing traversability and planning a safe, feasible, and fast trajectory in real-time. Our approach relies on: 1) rapid uncertainty-aware mapping and traversability evaluation, 2) tail risk assessment using the Conditional Value-at-Risk (CVaR), and 3) efficient risk and constraint-aware kinodynamic motion planning. We analyze our method in simulation and validate its efficacy on wheeled and legged robotic platforms exploring extreme terrains including an underground lava tube.
  arXiv  Detail & Related papers  (2021-03-04T04:24:19Z)

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.