DAWN (Denoising and Alignment in World models for Noise-robustness) is a perception framework that builds noise robustness directly into a world model for vision-based legged locomotion. It achieves this by feeding noisy depth to the encoder while reconstructing clean depth, and by using contrastive learning to align latent states of noisy and clean depth. The method requires no manual filter tuning, incurs no extra inference cost, and enables zero‑shot quadruped parkour on a Unitree Go1, successfully traversing stairs, gaps, and steps from raw depth observations.
arXiv:2601. 15995v2 Announce Type: replace-cross Abstract: Parkour tasks for quadrupeds have emerged as a promising benchmark for agile locomotion.
arXiv:2607. 13579v1 Announce Type: cross Abstract: Enabling quadrupedal robots to traverse complex terrains-from rugged outdoor environments to urban landscapes-requires seamless integration of multiple motor skills, smooth transitions between gaits, and high-speed perceptive locomotion using only onboard sensors.
arXiv:2510. 18348v2 Announce Type: replace-cross Abstract: State-of-the-art perceptive Reinforcement Learning controllers for legged robots typically either (i) impose oscillator-or IK-based gait priors that constrain the action space, bias policy optimization, and limit adaptability across robot morphologies, or (ii) operate "blind," making them unable to anticipate hind-leg terrain and brittle to observation noise.
arXiv:2606. 15896v1 Announce Type: cross Abstract: Learning-based quadrupedal locomotion typically relies on complex reward formulations that entangle task specification, operational limits, gait preference, and terrain adaptation within a single optimization objective.
Autonomous navigation of quadrupedal robots in diverse environments fundamentally relies on resilient Simultaneous Localization and Mapping (SLAM). While visual-inertial SLAM has matured across wheeled, handheld, and aerial platforms, a critical evaluation gap remains regarding how hardware-level sensor configurations affect performance under the aggressive dynamics of legged locomotion.
FootQuery is a perceptive locomotion framework that retrieves depth information from a robot’s own history by querying each foot’s predicted next touchdown. The policy uses proprioceptive predictions of touchdown locations and uncertainties to sample relevant historical depth frames, fuses these per‑foot features with global visual memory, and generates control actions. In simulation and on a real Unitree G1 robot, FootQuery enables continuous traversal of complex outdoor stairs, indoor routes, platforms, and gaps, outperforming component ablations.
arXiv:2504.15776v2 Announce Type: replace Abstract: Public autonomous driving datasets underpin the training and benchmarking of perception, mapping, and localization algorithms, yet residual inaccur...
arXiv:2607. 20785v1 Announce Type: cross Abstract: Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently.
arXiv:2608. 05975v1 Announce Type: cross 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.
arXiv:2607. 16314v1 Announce Type: cross Abstract: World models, especially based on JEPA architectures, have been shown to learn robust dynamics of various environments.
arXiv:2603. 25937v2 Announce Type: replace-cross Abstract: Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations.
arXiv:2609.38653v1 Announce Type: cross Abstract: Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated agents to reproduce increasingly complex human mo...