GaRLILEO: Gravity-aligned Radar-Leg-Inertial Enhanced Odometry

2025-11-17

AI Summary

Legged robots suffer from vertical pose drift on challenging terrains—such as stairs and slopes—due to contact impacts, foot slippage, and vibration. To address this, we propose a vision- and LiDAR-free continuous-time gravity-aligned odometry method. Our approach innovatively fuses millimeter-wave radar Doppler velocity, leg kinematics, and IMU measurements to construct a vehicle-speed spline leveraging SoC radar and leg-control information, thereby decoupling IMU velocity integration. We further introduce a soft S²-manifold constrained gravity factor to enable high-precision gravity vector estimation. Evaluated on a custom multi-scenario dataset, our method achieves significantly improved vertical odometry accuracy over state-of-the-art approaches—particularly on stairs and sloped terrain—setting a new benchmark. The source code and dataset are publicly released.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Low Level & Physics-based Vision
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Deployment of legged robots for navigating challenging terrains (e.g., stairs, slopes, and unstructured environments) has gained increasing preference over wheel-based platforms. In such scenarios, accurate odometry estimation is a preliminary requirement for stable locomotion, localization, and mapping. Traditional proprioceptive approaches, which rely on leg kinematics sensor modalities and inertial sensing, suffer from irrepressible vertical drift caused by frequent contact impacts, foot slippage, and vibrations, particularly affected by inaccurate roll and pitch estimation. Existing methods incorporate exteroceptive sensors such as LiDAR or cameras. Further enhancement has been introduced by leveraging gravity vector estimation to add additional observations on roll and pitch, thereby increasing the accuracy of vertical pose estimation. However, these approaches tend to degrade in feature-sparse or repetitive scenes and are prone to errors from double-integrated IMU acceleration. To address these challenges, we propose GaRLILEO, a novel gravity-aligned continuous-time radar-leg-inertial odometry framework. GaRLILEO decouples velocity from the IMU by building a continuous-time ego-velocity spline from SoC radar Doppler and leg kinematics information, enabling seamless sensor fusion which mitigates odometry distortion. In addition, GaRLILEO can reliably capture accurate gravity vectors leveraging a novel soft S2-constrained gravity factor, improving vertical pose accuracy without relying on LiDAR or cameras. Evaluated on a self-collected real-world dataset with diverse indoor-outdoor trajectories, GaRLILEO demonstrates state-of-the-art accuracy, particularly in vertical odometry estimation on stairs and slopes. We open-source both our dataset and algorithm to foster further research in legged robot odometry and SLAM. https://garlileo.github.io/GaRLILEO

Problem

• Addresses vertical drift in legged robot odometry from impacts and slippage
• Improves roll and pitch estimation without LiDAR or cameras
• Enhances vertical pose accuracy on stairs and slopes

Innovation

• Uses radar-leg-inertial fusion for odometry
• Decouples velocity via continuous-time ego-velocity spline
• Employs soft S2-constrained gravity factor for accuracy