GAUGE: Planner-Conditioned Active Calibration of Opaque Quadruped Velocity Interfaces

2026-09-26

AI Summary

This study addresses the systematic discrepancy between commanded and actual motion in black-box velocity interfaces of quadruped robots by proposing a planner-aware active calibration framework. The method constructs a command-motion model via Bayesian optimization, leveraging expected information gain to guide efficient exploration. Precise error correction is achieved through a validation-based stopping criterion combined with bounded inverse compensation. Experimental results demonstrate that the proposed framework satisfies joint accuracy and uncertainty criteria within controlled response families using significantly fewer trials. Furthermore, it meets non-inferiority requirements across diverse navigation scenarios, enabling efficient parameter calibration and motion compensation.

Abstract

In this paper, we present a Goal-Aware Uncertainty-Guided Exploration (GAUGE) framework for planner-conditioned active calibration of opaque quadruped velocity interfaces. Commercial quadrupeds commonly expose planar-velocity commands, but the underlying locomotion controller remains inaccessible and can produce systematic discrepancies between commanded and realized motion. A navigation planner typically uses a structured subset of the command envelope. GAUGE maintains a Bayesian command-to-motion model and selects authorized trials according to their expected reduction of posterior epistemic uncertainty under the planner-induced command distribution. The resulting posterior supports validation-based stopping, bounded inverse compensation, and task-relevant recalibration after detected interface shifts. In three controlled response families, GAUGE reaches the joint criterion for task-facing accuracy and uncertainty with fewer trials than passive, D-optimal, and task-agnostic alternatives. Across six held-out Isaac Sim navigation maps, it meets the declared noninferiority margins against dense calibration. Code is available at https://github.com/EurekaZang/CalibAgent.

Problem

• quadruped robots
• velocity interface calibration
• opaque locomotion controller
• command-to-motion discrepancy
• navigation planning

Innovation

• Active Calibration
• Bayesian Uncertainty
• Quadruped Locomotion
• Goal-Aware Exploration
• Velocity Interface