CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion

• URL: http://arxiv.org/abs/2608.24217v1
• Date: Tue, 25 Aug 2026 08:23:24 GMT
• Title: CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion
• Abstract summary: 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.
• Score: 6.612698611142421
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose CARO, a contact-agnostic residual observation framework for policy adaptation. CARO embeds a fixed-base Euler--Lagrange model into the reinforcement learning control loop and constructs a torque-level residual observation without requiring torque sensors, explicit contact estimation, or vision-based measurements of the floating-base position and linear velocity. A disturbance observer extracts a structured signal representing dynamics mismatch, while the policy learns to exploit this feedback for online adaptation. CARO is trained under the same terrain, command, and domain-randomization conditions as the nominal policy, without specialized disturbance curricula or additional adaptation supervision. Nevertheless, it achieves substantially improved zero-shot robustness in simulation and sim-to-real transfer tasks involving out-of-distribution payloads, center-of-mass shifts, terrain geometries, abrupt dynamics changes, and elevated-platform landings.

Related papers

• 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)
• A Neural Network Based Teleoperation for Remote Controlled Vehicles [98.38733381483934]
  Direct teleoperation of vehicles faces critical technical bottlenecks.<n> communication latency and the operator's inability to physically perceive unmodeled environmental disturbances.<n>We propose a tailored unilateral teleoperation framework.
  arXiv  Detail & Related papers  (2026-08-11T01:51:08Z)
• TRACE: Learned Proprioceptive Odometry for Legged Robots under Unreliable Contact Conditions [4.317571381146645]
  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.
  arXiv  Detail & Related papers  (2026-08-06T12:53:33Z)
• Fixed-Time Dynamic Landing of Quadrotors using Adaptive Unscented Kalman Filtering and Nonlinear Model Predictive Control [0.0]
  This paper introduces an estimation and control framework for dynamic landing of multi-rotor uncrewed aerial vehicles on moving platforms.<n>The proposed method integrates nonlinear model predictive control with a real-time minimum-jerk trajectory planner.<n>It is shown to achieve repeatable landings and improved platform velocity prediction accuracy relative to EKF/UKF-based methods.
  arXiv  Detail & Related papers  (2026-06-01T06:05:34Z)
• MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation [65.068801413044]
  Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams.<n>We introduce MoASE, a mixture-of-experts that disentangles domain-agnostic structure from domain-specific texture.
  arXiv  Detail & Related papers  (2026-05-18T01:52:12Z)
• Online Inertia Tensor Identification for Non-Cooperative Spacecraft via Augmented UKF [0.0]
  This paper presents an augmented Unscented Kalman Filter (UKF) framework designed to jointly estimate the relative 6-DOF pose and the full inertia tensor of a non-cooperative target spacecraft.<n>The proposed architecture fuses visual measurements from monocular vision-based Convolutional Neural Networks (CNN) with depth information from LiDAR to constrain the coupled rigid-body dynamics.<n>By augmenting the state vector to include the six independent elements of the inertia tensor, the filter dynamically recovers the target's normalized mass distribution in real-time without requiring ground-based pre-calibration.
  arXiv  Detail & Related papers  (2026-03-28T18:13:03Z)
• Toward Operationalizing Rasmussen: Drift Observability on the Simplex for Evolving Systems [0.0]
  Monitoring drift into failure is hindered by Euclidean anomaly detection.<n>Rasmussen's dynamic safety model motivates drift under competing pressures.<n>We propose a vision for drift observability on the simplex.
  arXiv  Detail & Related papers  (2026-02-05T09:41:49Z)
• Efficiently Learning Robust Torque-based Locomotion Through Reinforcement with Model-Based Supervision [14.246416873754905]
  We propose a control framework that integrates model-based bipedal locomotion with residual reinforcement learning.<n>Our method demonstrates improved robustness and generalization across a range of randomized conditions.
  arXiv  Detail & Related papers  (2026-01-22T16:56:52Z)
• Dual-quaternion learning control for autonomous vehicle trajectory tracking with safety guarantees [39.146761527401424]
  We propose a learning-based trajectory tracking controller for autonomous robotic platforms whose motion can be described kinematically.<n>The controller is formulated in the dual quaternion framework and operates at the velocity level, assuming direct command of angular and linear velocities.
  arXiv  Detail & Related papers  (2026-01-06T15:30:02Z)
• 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)
• Guided Conditional Diffusion for Controllable Traffic Simulation [42.198185904248994]
  Controllable and realistic traffic simulation is critical for developing and verifying autonomous vehicles. Data-driven approaches generate realistic and human-like behaviors, improving transfer from simulated to real-world traffic. We develop a conditional diffusion model for controllable traffic generation (CTG) that allows users to control desired properties of trajectories at test time.
  arXiv  Detail & Related papers  (2022-10-31T14:44:59Z)
• Learning Variable Impedance Control for Aerial Sliding on Uneven Heterogeneous Surfaces by Proprioceptive and Tactile Sensing [42.27572349747162]
  We present a learning-based adaptive control strategy for aerial sliding tasks. The proposed controller structure combines data-driven and model-based control methods. Compared to fine-tuned state of the art interaction control methods we achieve reduced tracking error and improved disturbance rejection.
  arXiv  Detail & Related papers  (2022-06-28T16:28:59Z)

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.