CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains

• URL: http://arxiv.org/abs/2602.03511v1
• Date: Tue, 03 Feb 2026 13:30:18 GMT
• Title: CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains
• Abstract summary: We present Contractive Mapping for Robustness (CMR) framework that maps high-dimensional, disturbance-prone observations into a latent space.<n>CMR potently outperforms other locomotion algorithms under increased noise.
• Score: 30.85514738551041
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robust disturbance rejection remains a longstanding challenge in humanoid locomotion, particularly on unstructured terrains where sensing is unreliable and model mismatch is pronounced. While perception information, such as height map, enhances terrain awareness, sensor noise and sim-to-real gaps can destabilize policies in practice. In this work, we provide theoretical analysis that bounds the return gap under observation noise, when the induced latent dynamics are contractive. Furthermore, we present Contractive Mapping for Robustness (CMR) framework that maps high-dimensional, disturbance-prone observations into a latent space, where local perturbations are attenuated over time. Specifically, this approach couples contrastive representation learning with Lipschitz regularization to preserve task-relevant geometry while explicitly controlling sensitivity. Notably, the formulation can be incorporated into modern deep reinforcement learning pipelines as an auxiliary loss term with minimal additional technical effort required. Further, our extensive humanoid experiments show that CMR potently outperforms other locomotion algorithms under increased noise.

Related papers

• Overcoming "Physics Shock" in Earth Observation A Heteroscedastic Uncertainty Framework for PINN-based Flood Inference [0.29165586612027233]
  Rapid and accurate flood extent mapping from Remote Sensing data is critical for operational disaster response.<n>Standard Deep Learning models often produce physically impossible predictions due to a lack of hydrological constraints.<n>We propose a novel Uncertainty-Aware PINN framework tailored specifically for applied Earth Observation.
  arXiv  Detail & Related papers  (2026-05-22T18:14:17Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction [52.32112533846212]
  MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions.<n>We address this limitation by moving reconstruction to discrete multi-scale latent space and posing it as autoregressive next-acceleration-scale prediction.<n>We show that our approach delivers improved reconstruction performance across diverse sampling patterns under extreme undersampling.
  arXiv  Detail & Related papers  (2026-05-19T04:40:50Z)
• Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation [0.0]
  Unmanned Aerial Vehicles in dynamic environments face telemetry outages, structural vibrations, and regime-dependent noise.<n>We introduce the N-Deep Recurrent Sage-Husa Filter (NDR-SHKF), which replaces the scalar parameter with a vector-valued memory attenuation policy.<n>A bifurcated architecture routes shallow recurrent states to capture instantaneous sensor anomalies and deep states to encode sustained dynamic trends.
  arXiv  Detail & Related papers  (2026-05-18T17:38:13Z)
• Uncertainty Estimation for Deep Reconstruction in Actuatic Disaster Scenarios with Autonomous Vehicles [68.82821445619759]
  principled uncertainty quantification is critical for active sensing strategies.<n>Evidential Deep Learning achieves the best reconstruction accuracy and uncertainty calibration across all sensor configurations.<n>These findings support Evidential Deep Learning as the preferred method for uncertainty-aware field reconstruction in real-time autonomous vehicle deployments.
  arXiv  Detail & Related papers  (2026-04-07T19:17:44Z)
• Delayed Homomorphic Reinforcement Learning for Environments with Delayed Feedback [11.866061471514582]
  Delayed feedback breaks the Markov assumption and impedes learning and control.<n>We propose a framework grounded in MDP homomorphisms that collapses belief-equivalent augmented states.<n> Experiments on continuous control tasks in MuJoCo benchmark confirm that our algorithm outperforms strong augmentation-based baselines.
  arXiv  Detail & Related papers  (2026-04-04T08:38:52Z)
• Degeneracy-Resilient Teach and Repeat for Geometrically Challenging Environments Using FMCW Lidar [18.593167038234828]
  Teach and Repeat (T&R) topometric navigation enables robots to autonomously repeat previously traversed paths without relying on GPS.<n>We present a degeneracy-resilient Frequency-Modulated Continuous-Wave lidar T&R navigation system consisting of Doppler velocity-based odometry and degeneracy-aware scan-to-map localization.
  arXiv  Detail & Related papers  (2026-03-10T21:57:08Z)
• When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift [64.37959940809633]
  We study robustness of Proximal Policy Optimization (PPO) under temporally persistent sensor failures.<n>We show Transformer-based sequence policies substantially outperform, RNN, and SSMs in robustness, maintaining high returns even when large fractions of sensors are unavailable.
  arXiv  Detail & Related papers  (2026-03-04T22:21:54Z)
• RaUF: Learning the Spatial Uncertainty Field of Radar [2.6853734738584047]
  Millimeter-wave radar offers unique advantages in adverse weather but suffers from low spatial fidelity, severe azimuth ambiguity, and clutter-induced spurious returns.<n>We propose RaUF, a spatial uncertainty field learning framework that models radar measurements through their physically grounded anisotropic properties.<n>To resolve conflicting feature-to-label mapping, we design an anisotropic probabilistic model that learns fine-grained uncertainty.
  arXiv  Detail & Related papers  (2026-03-01T10:10:43Z)
• Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamics [8.820825533010543]
  We present a novel viewpoint on temporal-difference basedReinforcement learning.<n>We show that TD errors can be viewed as 1-cochain in the topological space of state transitions, while Markov dynamics are then interpreted as topological integrability.<n>This novel view enables us to obtain a Hodge-type decomposition of TD errors into an integrable component and a topological residual.
  arXiv  Detail & Related papers  (2026-02-06T18:35:41Z)
• From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstruction [3.2580743227673694]
  We present STRIDE, a framework that maps high-dimensional spatial fields to a latent state with a temporaltemporal decoder.<n>We show that STRIDE supports super-resolution, supports super-resolution, and remains robust to noise.
  arXiv  Detail & Related papers  (2026-02-04T04:39:23Z)
• Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation [67.69345363409835]
  Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism.<n>We design Non-Stateful (NS) models progressively removing membrane propagation to its stage-wise role. Experiments reveal a counterintuitive phenomenon: moderate removal in shallow layers improves performance, while excessive removal causes collapse.
  arXiv  Detail & Related papers  (2025-12-05T07:05:53Z)
• Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps [13.816031528661057]
  In this work, we introduce adversarially-refined VQ-GAN framework with dense motion tokenization for compressing-temporal heatmaps.<n>Our approach combines dense motion tokenization with adversarial refinement, which eliminates smearing and temporal misalignment observed in non-adversarial baselines.<n>Our experiments on the CMU Panoptic dataset provide conclusive evidence of our method's superiority, outperforming the dVAE baseline by 9.31% SSIM and reducing temporal instability by 37.1%.
  arXiv  Detail & Related papers  (2025-09-23T17:12:20Z)
• Diffusion-Based Limited-Angle CT Reconstruction under Noisy Conditions [10.287171164361608]
  Missing angular projections lead to incomplete sinograms and artifacts in reconstructed images.<n>We propose a diffusion-based framework that completes missing angular views using a Mean-Reverting Differential Equation (MR-SDE) formulation.<n>To improve robustness under realistic noise, we propose a novel noise-aware mechanism that explicitly models inference-time uncertainty.
  arXiv  Detail & Related papers  (2025-07-08T03:58:52Z)
• Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction [2.8237889121096034]
  We propose a novel way to train PD-DL networks via carefully-designed perturbations.<n>We show that the proposed training strategy effectively reduces aliasing artifacts and mitigates noise amplification at high acceleration rates.
  arXiv  Detail & Related papers  (2025-05-30T02:11:25Z)
• ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model [51.83639270669481]
  Unsupervised anomaly detection in hyperspectral images (HSI) aims to detect unknown targets from backgrounds.<n>HSI studies are hindered by steep computational costs due to the high-dimensional property of HSI and dense sampling-based training paradigm.<n>We propose an Asymmetrical Consensus State Space Model (ACMamba) to significantly reduce computational costs without compromising accuracy.
  arXiv  Detail & Related papers  (2025-04-16T05:33:42Z)
• A Differential Smoothness-based Compact-Dynamic Graph Convolutional Network for Spatiotemporal Signal Recovery [9.369246678101048]
  This paper proposes a Compact-fold Con Graphal Network (CDCN) fortemporal signal recovery. Experiments on real-world datasets show that CDCN significantly outperforms the state-of-the-art models fortemporal signal recovery.
  arXiv  Detail & Related papers  (2024-08-06T06:42:53Z)
• Fast Value Tracking for Deep Reinforcement Learning [7.648784748888187]
  Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interact with their environment. Existing algorithms often view these problem as static, focusing on point estimates for model parameters to maximize expected rewards. Our research leverages the Kalman paradigm to introduce a novel quantification and sampling algorithm called Langevinized Kalman TemporalTD.
  arXiv  Detail & Related papers  (2024-03-19T22:18:19Z)
• Towards Adversarially Robust Deep Image Denoising [199.2458715635285]
  This work systematically investigates the adversarial robustness of deep image denoisers (DIDs) We propose a novel adversarial attack, namely Observation-based Zero-mean Attack (sc ObsAtk) to craft adversarial zero-mean perturbations on given noisy images. To robustify DIDs, we propose hybrid adversarial training (sc HAT) that jointly trains DIDs with adversarial and non-adversarial noisy data.
  arXiv  Detail & Related papers  (2022-01-12T10:23:14Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)
• Attribute-Guided Adversarial Training for Robustness to Natural Perturbations [64.35805267250682]
  We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
  arXiv  Detail & Related papers  (2020-12-03T10:17:30Z)

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.