aiqbench analysis
This research introduces TRACE, a novel machine learning framework for legged robot odometry that leverages tokenized attention mechanisms to maintain accurate positioning under unreliable contact conditions. By integrating physics-inspired losses with policy randomization, the method effectively bridges sim-to-real gaps without relying on manual thresholds or classical filtering baselines. The work represents a significant advancement in applying deep learning directly to core robotic perception tasks where traditional sensor fusion often fails.
TRACE: Learned Proprioceptive Odometry for Legged Robots under Unreliable Contact Conditions
arXiv:2608.05975v1 Announce Type: new 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.
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.
8 pages, 7 figures. Submitted to IEEE Robotics and Automation Letters (RA-L)
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2608.05975 [cs.RO]
(or arXiv:2608.05975v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.05975 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 278 words
Related coverage
Interacting Multiple Model Proprioceptive Odometry for Legged Robots
arXiv · Jul 22, 2026
DogLegs: Robust Proprioceptive State Estimation for Legged Robots Using Multiple Leg-Mounted IMUs
arXiv · Sep 4, 2026
LAG-IO: Multi-IMU State Estimation for Legged Robots Using Factor Graphs
arXiv · Oct 14, 2026
KING: Embodiment-Aware Kinematic Graph Neural Network for Unified Motion Representation of Legged and Wheeled Robots
arXiv · Aug 5, 2026