TRACE: Learned Proprioceptive Odometry for Legged Robots under Unreliable Contact Conditions

• URL: http://arxiv.org/abs/2608.05975v1
• Date: Thu, 06 Aug 2026 12:53:33 GMT
• Title: TRACE: Learned Proprioceptive Odometry for Legged Robots under Unreliable Contact Conditions
• Abstract summary: We present TRACE (Tokenized Robust Attention for Contact-Aware Estimation), an end-to-end learned proprioceptive odometry estimator for legged robots.<n>The proposed estimator directly predicts relative displacement, relative rotation, and body-frame velocity from a recent history of onboard inertial and joint measurements.<n>To improve robustness under unreliable contact conditions, we introduce a foot-aware cross-attention module that adaptively weights IMU and leg-wise kinematic tokens.
• Score: 4.317571381146645
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we present TRACE (Tokenized Robust Attention for Contact-Aware Estimation), an end-to-end learned proprioceptive odometry estimator for legged robots under unreliable contact conditions. The proposed estimator directly predicts relative displacement, relative rotation, and body-frame velocity from a recent history of onboard inertial and joint measurements. To improve robustness under unreliable contact conditions, we introduce a foot-aware cross-attention module that adaptively weights IMU and leg-wise kinematic tokens without relying on manually defined contact or slip thresholds. The estimator is trained with direct supervision and two physics-inspired auxiliary losses that promote kinematic consistency and reliable use of leg information. To reduce policy-specific overfitting and consequently improve sim-to-real transfer, simulation training incorporates policy randomization, followed by partial real-world fine-tuning of the temporal encoder and prediction head. Experiments across diverse indoor and outdoor terrains demonstrate consistent reductions in position drift compared with classical filtering-based, hybrid, and purely learning-based baselines. Ablation studies further validate the contributions of the proposed training objectives, policy randomization, and real-world fine-tuning, particularly under unreliable contacts and sim-to-real mismatch.

Related papers

• Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assembly [9.415285027294221]
  We present PACE (Proprioception-Anchored Cross-Modalception), which supervises temporal visual and F/T representations by predicting proprioceptive state transitions.<n>Across four contact-rich assembly tasks, PACE attains an average real-world success rate of 93.3% and only a 2.7-percentage-point sim-to-real drop.
  arXiv  Detail & Related papers  (2026-09-07T14:20:22Z)
• FOCUS: Foot Observation Confidence for Robust Humanoid Proprioceptive Odometry [4.918768564334209]
  Existing contact-aided estimators rely on binary contact decisions to determine whether FK measurements of an entire foot should be trusted.<n>We propose FOCUS, which predicts a continuous FK reliability weight for each foot instead of estimating binary foot contact.<n>Experiments demonstrate that FOCUS reduces absolute trajectory error (ATE) by 83.7% on simulated walking episodes.
  arXiv  Detail & Related papers  (2026-09-02T07:34:55Z)
• Contact-Aided Factor-Graph Localization for Underwater Sampling [3.884868746700691]
  We propose a Contact-Aided Factor-Graph localization framework that treats physical interaction as an informative geometric constraint.<n>We show that contact-induced constraints significantly reduce trajectory drift and improve object revisit accuracy.<n>Results highlight the role of embodied physical interaction as a localization primitive in perception-degraded underwater environments.
  arXiv  Detail & Related papers  (2026-08-27T10:34:22Z)
• CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion [6.612698611142421]
  CARO is a contact-agnostic residual observation framework for policy adaptation.<n>It embeds a fixed-base Euler--Lagrange model into a reinforcement learning control loop and constructs a torque-level residual observation.<n>A disturbance observer extracts a structured signal representing dynamics mismatch, while the policy learns to exploit this feedback for online adaptation.
  arXiv  Detail & Related papers  (2026-08-25T08:23:24Z)
• Learning to Throw: Agile and Accurate Cable-Suspended Payload Delivery with a Quadrotor [17.676294984292433]
  Quadrotors offer the agility needed to rapidly transport suspended payloads during time-critical applications.<n>State-of-the-art approaches typically rely on model-based trajectory optimization and tracking.<n>We propose a hybrid simulation framework that couples a high-fidelity analytical quadrotor model with a physics solver for complex rope and payload interactions.
  arXiv  Detail & Related papers  (2026-06-25T23:30:52Z)
• 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)
• Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representation [51.463992799813816]
  A primary bottleneck in contact-rich manipulation is the difficulty of collecting real-world data.<n>We introduce Center-of-Pressure, an effective tactile representation grounded in physical principles.<n>We evaluate CoP on two blind, challenging contact-rich manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-27T17:59:02Z)
• PRIME: Physically-consistent Robotic Inertial and Motion Estimation for Legged and Humanoid Robots [6.944742823560998]
  We propose PRIME to enable accurate motion estimation from onboard kinematics in real-world deployment.<n>Our approach incorporates differentiable contact dynamics with smoothed complementarity constraints and an Anitescu-style friction model.<n> PRIME can be calibrated to provide high-quality data for downstream learning applications, including large-scale behavior modeling and robot foundation models.
  arXiv  Detail & Related papers  (2026-05-17T22:43:10Z)
• CoCo-InEKF: State Estimation with Learned Contact Covariances in Dynamic, Contact-Rich Scenarios [10.290787487255301]
  CoCo-InEKF is a differentiable invariant extended Kalman filter that utilizes continuous contact velocity covariances instead of binary contact states.<n>We employ a lightweight neural network trained end-to-end using a state-error loss to predict contact candidate points.<n> Experiments on a bipedal robot demonstrate a superior accuracy-efficiency tradeoff for linear velocity estimation.
  arXiv  Detail & Related papers  (2026-05-14T17:35:06Z)
• System Identification under Constraints and Disturbance: A Bayesian Estimation Approach [5.58001571731715]
  We introduce a Bayesian system identification (SysID) framework for jointly estimating robot's state trajectories and physical parameters with high accuracy.<n>It embeds physically consistent inverse dynamics, contact and loop-closure constraints, and fully featured joint friction models as hard, stage-wise equality constraints.
  arXiv  Detail & Related papers  (2026-02-18T10:45:30Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM [52.64097278841485]
  Review examines how incorporating learning and observational biases through physics-informed modeling and data strategies can guide models toward physically consistent and reliable predictions.<n>Fast adaptation methods including meta-learning and few-shot learning are reviewed alongside domain generalization techniques.
  arXiv  Detail & Related papers  (2025-09-25T14:15:43Z)
• DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation [81.11585774044848]
  We present DeepSimHO, a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network. Our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization.
  arXiv  Detail & Related papers  (2023-10-11T05:34:36Z)
• Online Body Schema Adaptation through Cost-Sensitive Active Learning [63.84207660737483]
  The work was implemented in a simulation environment, using the 7DoF arm of the iCub robot simulator. A cost-sensitive active learning approach is used to select optimal joint configurations. The results show cost-sensitive active learning has similar accuracy to the standard active learning approach, while reducing in about half the executed movement.
  arXiv  Detail & Related papers  (2021-01-26T16:01:02Z)

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.