Physical Self-Supervised Learning: IMU Sensing without Manual Labels

• URL: http://arxiv.org/abs/2607.18361v1
• Date: Mon, 20 Jul 2026 14:01:10 GMT
• Title: Physical Self-Supervised Learning: IMU Sensing without Manual Labels
• Abstract summary: Deep neural networks have become a promising approach for IMU-based sensing, but their scalability is limited by labeled data and poor robustness to heterogeneous devices, placements, and users.<n>We propose physical self-supervised learning, an autoencoder-style paradigm for label-free IMU sensing.<n>We replace the conventional neural decoder with an auto-adaptive physics decoder, a learnable family of kinematic equations that enforces explicit physical structure while adapting across environments.
• Score: 10.122645401488084
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks have become a promising approach for IMU-based sensing, but their scalability is fundamentally limited by costly labeled data and poor robustness to heterogeneous devices, placements, and users. Existing unsupervised and self-supervised methods reduce but do not remove this dependence, still requiring labeled data for domain adaptation and largely ignoring known physical structure. We propose physical self-supervised learning, an autoencoder-style paradigm for label-free IMU sensing. We replace the conventional neural decoder with an auto-adaptive physics decoder, a learnable family of kinematic equations that enforces explicit physical structure while adapting across environments, and adopt a hybrid two-stage IMU encoder with reconstruction in a structured latent space to mitigate sensor noise. Our framework further introduces probabilistic frequency-spatial constraints to disentangle sensor and object motion, a multi-view kinematic tree to exploit sparse physical self-supervised signals, and an uncertainty-aware formulation to handle the inherent ambiguity of IMU inference. Evaluated on inertial tracking and full-body motion capture over public datasets and realistic deployments, physical self-supervised learning reduces errors by up to 5x for tracking and 4x for motion capture in challenging generalization scenarios, consistently outperforming state-of-the-art supervised and self-supervised baselines without any labels.

Related papers

• Physics-guided machine learning for sim-to-real calibration of NV diamond magnetometers [2.632334357996292]
  We introduce a physics-guided hybrid machine learning framework that embeds the Zeeman splitting directly into the learning pipeline.<n>Our framework delivers exceptional predictive accuracy for the scalar magnetic field.<n>This work paves the way toward self-calibrated sensors while establishing a machine learning training method applicable to other data-scarce physical systems.
  arXiv  Detail & Related papers  (2026-08-20T02:53:52Z)
• Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration [50.18488308004802]
  Sen-Cap is a 3D motion capture framework that integrates multi-modal data from LiDAR and camera.<n>Sen-Cap achieves state-of-the-art performance on major metrics on Human-M3 and FreeMotion.<n>This combination of flexibility and robustness opens new opportunities for motion capture in real-world scenarios.
  arXiv  Detail & Related papers  (2026-08-03T14:16:18Z)
• Online Learning of Robust Legged Odometry with Minimal Exteroceptive Supervision [7.541859903866144]
  Industrially packaged exteroceptive sensors can provide accurate motion tracking but remain vulnerable to perceptually degraded conditions.<n>We develop a plug-and-play, robust legged odometry system that eliminates the need for explicit exteroceptive-to-proprioceptive calibration or system kinematic modeling.<n>We demonstrate the platform-agnostic, easily deployable nature of our approach on different quadruped platforms.
  arXiv  Detail & Related papers  (2026-06-19T18:20:55Z)
• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference [4.238724345383632]
  Inertial measurement units (IMUs) serve as fundamental sensing modalities in robotic systems.<n>We propose KISS-IMU, a novel self-supervised inertial odometry framework.<n>Our approach embodies two key principles: keeping the IMU stable through motion-aware balanced training and keeping the IMU strong through uncertainty-driven adaptive weighting.
  arXiv  Detail & Related papers  (2026-03-06T12:22:14Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• UniForce: A Unified Latent Force Model for Robot Manipulation with Diverse Tactile Sensors [51.88112610411651]
  We propose a novel unified tactile representation learning framework that learns a shared latent force space across diverse tactile sensors.<n>UniForce reduces cross-sensor domain shift by jointly modeling inverse dynamics (image-to-force) and forward dynamics (force-to-image)<n>To avoid reliance on expensive external force/torque (F/T) sensors, we exploit static equilibrium and collect force-paired data via direct sensor--object--sensor interactions.
  arXiv  Detail & Related papers  (2026-02-01T11:03:01Z)
• Distribution-Free Uncertainty-Aware Virtual Sensing via Conformalized Neural Operators [1.7864593554171284]
  Conformalized Monte Carlo Operator (CMCO) transforms neural operator-based virtual sensing with calibrated, distribution-free prediction intervals.<n>CMCO achieves spatially resolved uncertainty estimates without retraining, ensembling, or custom loss design.<n>This breakthrough offers a general-purpose, plug-and-play UQ solution for neural operators, unlocking real-time, trustworthy inference in digital twins, sensor fusion, and safety-critical monitoring.
  arXiv  Detail & Related papers  (2025-07-15T04:26:40Z)
• Neuro-Informed Joint Learning Enhances Cognitive Workload Decoding in Portable BCIs [9.198002030833328]
  Muse headbands offer unprecedented mobility for daily brain-computer interface applications.<n>Non-stationarity in portable EEG signals constrains data fidelity and decoding accuracy.<n>We propose MuseCogNet, a unified joint learning framework integrating self-supervised and supervised training paradigms.
  arXiv  Detail & Related papers  (2025-06-30T01:42:31Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Neurosymbolic hybrid approach to driver collision warning [64.02492460600905]
  There are two main algorithmic approaches to autonomous driving systems. Deep learning alone has achieved state-of-the-art results in many areas. But sometimes it can be very difficult to debug if the deep learning model doesn't work.
  arXiv  Detail & Related papers  (2022-03-28T20:29:50Z)
• Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance [95.86944752753564]
  We propose an online path planning architecture that extends the model predictive control (MPC) formulation to consider future location uncertainties. Our algorithm combines an object detection pipeline with a recurrent neural network (RNN) which infers the covariance of state estimates. The robustness of our methods is validated on complex quadruped robot dynamics and can be generally applied to most robotic platforms.
  arXiv  Detail & Related papers  (2020-07-28T07:34:30Z)

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.