arXiv AI
Jun 19
CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion
arXiv:2606. 19633v1 Announce Type: cross Abstract: Perceptive legged locomotion over discontinuous terrain (e.
Mind the Phase: Effective Rank and Representation Health in Legged Locomotion
The paper investigates how reinforcement‑learning policies for legged robots encode gait information by examining the effective rank of the policy Jacobian conditioned on gait phase. It finds that common architectural features such as layer normalization and residual connections allocate more representational capacity to swing than stance, a pattern absent in vanilla MLPs. Leveraging these insights, the authors propose a simple recipe that improves sim‑to‑real transfer, reducing joint jitter on a physical Spot robot by roughly three‑fold.
Related stories
arXiv AI
Jul 23
PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotion
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 Machine Learning
Aug 4
Open-DiffLoco: Open-Source Differentiable Learning for Deployable Blind Quadruped Locomotion
arXiv:2608. 02069v1 Announce Type: cross Abstract: Developing deployable locomotion policies through conventional reinforcement learning often requires complex reward engineering and expensive training times.
arXiv Machine Learning
Aug 10
Learning Fault-Tolerant Locomotion with Adaptive Gait Timing
arXiv:2608. 07328v1 Announce Type: cross Abstract: Hardware failures require legged robots to rapidly reorganize coordination and gait timing to maintain stability and mobility.
arXiv AI
Jul 15
GaitSpan: Growing Humanoid Locomotion from Walking to Running
arXiv:2607. 12114v1 Announce Type: cross Abstract: A humanoid that can walk should not relearn locomotion from scratch to jog or run.
arXiv Machine Learning
Jun 16
LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors
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.
arXiv Machine Learning
Jun 11
Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation
arXiv:2606. 11891v1 Announce Type: cross Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy.
arXiv Machine Learning
Jul 31
REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning
arXiv:2603. 13707v3 Announce Type: replace-cross Abstract: Humanoid loco-manipulation requires coordinated task-space motion planning with stable loco-manipulation command tracking under complex robot-environment dynamics and long-horizon tasks.
arXiv AI
Jul 2
Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications
arXiv:2607. 00442v1 Announce Type: cross Abstract: Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that limit both interpretability of learned policies and lack explicit control over gait behaviors.
arXiv Machine Learning
Jun 5
OLIVE: Online Low-Rank Incremental Learning for Efficient Adaptive Exoskeletons
arXiv:2606. 05234v1 Announce Type: cross Abstract: Wearable exoskeleton systems hold promise for restoring mobility in individuals with physical impairments, yet most existing controllers rely on static gait policies that lack the ability to adapt to dynamic real-world environments or individual user characteristics.
arXiv AI
Jun 4
Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics
arXiv:2602. 12643v2 Announce Type: replace-cross Abstract: We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead.
arXiv AI
Jul 14
PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour
arXiv:2601. 15995v2 Announce Type: replace-cross Abstract: Parkour tasks for quadrupeds have emerged as a promising benchmark for agile locomotion.