#Locomotion (26)

Waterfall Pagination

0:20

Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids

Traversing sparse 3D structures requires humanoid robots to perceive thin, overhanging geometry while executing agile, accurate whole-body motions. We study this problem through monkey-bar traversal, where the robot must jump to the structure, traverse it through sparse bar interactions, and land safely. For this task, we present a reinforcement-learning-based perceptive control system that operates directly on observations from a head-mounted solid-state lidar. To extract task-relevant geometry from the sparse returns, the policy consumes the raw lidar scan through an attention-based encoder with recurrent memory. This policy is obtained by a phase-scheduled teacher- student pipeline that combines privileged experts for jumping up, brachiating, and jumping down. For transfer to hardware, we model lidar noise, battery-voltage sag, and actuator thermal limits, and equip the humanoid with passive hook end-effectors for robust bar interaction. On hardware, the resulting policy completes the full jump-up->brachiation->jump-down sequence in 14 of 15 trials across three bar configurations and reaches brachiation speeds up to 0.5 m/s. Beyond brachiation, the same perception backbone supports a separately trained policy that ducks beneath thin overhead obstacles with 2 cm cross-sections.

Ongan, Efe, Zhang, Chong, Sun, BoyangAug 30, 2026

HumanoidBrachiationReinforcement LearningAug 30, 2026

0:16

Unitree G1 Drives an Office Chair With Its Feet

@takato1414 · 307 views · 2026-09-03

Unitree G1Sim-to-RealHumanoid

CReF: Cross-modal and Recurrent Fusion for Depth-conditioned Humanoid Locomotion

CReF is a single-stage depth-conditioned humanoid locomotion framework that maps onboard proprioception and forward-facing depth directly to joint position targets, without explicit geometric intermediates. It couples proprioception and depth tokens via proprioception-queried cross-modal attention, fuses them with a gated residual block, and integrates temporal context with a GRU regulated by a highway-style output gate. A terrain-aware foothold placement reward extracts supportable candidates from foot-end point-cloud windows and rewards touchdowns near them. Full CReF leads all terrain categories and difficulty levels in simulation and transfers zero-shot to a physical AGIBOT X2 Ultra across handrail stairs, hollow pallets, reflective interference, and cluttered outdoor scenes.

Yuan Hao, Ruiqi Yu, Shixin LuoMar 31, 2026

HumanoidLocomotiondepth-conditionedMar 31, 2026

1:04

Stairs Test: Agibot, Figure and Unitree Humanoids Compared

@techniahqrobot · 270 views · 2026-08-31

HumanoidLocomotionstairs

1:05

Figure 03 Walking: The Helix 02 Three-Layer Control Architecture

@techniahqrobot · 256 views · 2026-08-27

Figure AIHelixFigure 03

1:25

SOLO Humanoid: 1.5 km Continuous All-Terrain Walk with a Single Depth Camera

@techniahqrobot · 288 views · 2026-08-28

SOLOTechniaHumanoid

0:52

Neura 4NE1 Walks More Fluidly

@humanoidsdaily · 102 views · 2026-08-27

NEURA Robotics4NE1Humanoid

DELTA: Deformable Elevation-Based Local Terrain Attention Encoder for Sparse-Terrain Quadrupedal Locomotion

Stable quadrupedal locomotion on sparse terrain requires selecting state-relevant terrain evidence for precise foot placement. Model-based foothold planners provide precise foothold selection but rely heavily on explicit model assumptions. Recent attention-based map encoding (AME) studies show that end-to-end reinforcement learning (RL) can learn implicit foothold guidance. However, the computational cost of dense AME encoding grows with map resolution, limiting its scalability to fine-grained sparse terrain. We propose DELTA, a Deformable Elevation-Based Local Terrain Attention encoder. DELTA predicts state-conditioned sampling locations, forms terrain evidence tokens from adaptive local elevation patches, and attends only to a fixed-size token set. With fixed sampling and patch settings, DELTA's encoder cost is independent of map resolution. Experiments show that DELTA achieves final traversal performance comparable to AME at the standard resolution while improving learning efficiency. This fixed encoder cost enables the use of higher-resolution terrain maps, improving traversal on fine-grained sparse terrain. DELTA also demonstrates strong generalization to unseen mixed evaluation courses composed of continuous and discrete terrain elements. Beyond simulation, DELTA demonstrates successful sim-to-real transfer on RAIBO2. Analysis of the learned sampling offsets and attention weights shows that DELTA samples steppable regions and attends to terrain evidence relevant to future touchdowns without foothold labels or attention supervision.

Sanghyun Park, Moonkyu Jung, Jemin HwangboAug 22, 2026

Sim-to-RealQuadruped robotsLocomotionAug 22, 2026

T-GMP: Terrain-conditioned Generative Motion Priors for Versatile and Natural Humanoid Locomotion

Achieving both anthropomorphic naturalness and robust terrain traversal remains a fundamental challenge in humanoid locomotion. Existing Reinforcement Learning (RL) approaches typically rely on fixed motion priors, limiting their adaptability to varying environments. We propose Terrain-conditioned Generative Motion Priors (T-GMP), a module that captures a terrain-conditioned latent motion manifold from a few expert state-terrain demonstrations using a Conditional Variational Autoencoder (CVAE). The learned priors enable smooth style transitions, facilitating a unified policy that adapts to terrain variations. We integrate T-GMP into an adversarial learning pipeline with our proposed Foothold Penalty, where a discriminator dynamically modulates naturalness constraints conditioned on local terrain features, guiding the generation of versatile and human-like motions. Experimental results demonstrate that our method outperforms existing baselines in traversal success rate and motion smoothness, while preserving biomimetically natural and physically coordinated motions.

Junhong Guo, Hao Hu, Chen ChenJun 5, 2026

CVAERLLocomotionJun 5, 2026

0:15

Biggest jump at the World Humanoid Robot Games

@WHRGFUN · 143 views · 2026-08-23

World Humanoid Robot GamesWHRGHumanoid

Tac4Loco: Learning Spatiotemporal Plantar Pressure Representations for Humanoid Locomotion

Humanoid robots are expected to traverse complex terrains, where the plantar support may vary dramatically due to foot placement errors, ground properties, and transient dynamics. To achieve robust locomotion, the robots are required to adapt to uneven terrain and uncertain foot–ground interactions. Existing locomotion policies rely primarily on proprioception or exteroceptive terrain perception, where the former provides only indirect evidence of plantar support, while the latter predicts contact conditions before touchdown but cannot observe the actual support in real-time. Although some studies incorporate plantar contacts as an auxiliary perception, they rely mainly on summary statistics, overlooking the spatial topology of plantar pressure, which provides a more direct characterization of the realized contact state. To bridge this gap, we present Tac4Loco, a tactile-perceptive framework that incorporates multi-array plantar pressure as direct feedback for humanoid locomotion. We formulate a topology-preserving ordinal representation to map simulated and physical sensor signals into a shared observation space, with a dual-branch encoder for extracting their spatial and temporal representations. Subsequently, the learned spatiotemporal features are integrated with augmented proprioception including terrain estimation cues, and provided to an asymmetric actor-critic architecture for policy learning. Extensive simulation and real-world experiments demonstrate improved tracking performance and support adaptation on terrains with inclined, partial, asymmetric, and changing support. We further demonstrate its zero-shot deployment on unseen compliant and unstructured terrains, including a foam platform and a gravel road. All code and experimental configurations will be released as open-source to facilitate reproducibility.

Ziyun Liu, Sikai Guo, Zheng LiAug 16, 2026

Tac4LocoLocomotionTactileAug 16, 2026

0:51

PHYBOT: robot soccer as a full-contact locomotion test

@ErenChenAI · 138 views · 2026-08-15

PHYBOTrobot soccerHumanoid

0:30

Unitree's New Humanoid Superman Jumps 2m, Faster Than Bolt

@AYi_AInotes · 146 views · 2026-08-17

HumanoidUnitreeLocomotion

1:08

PHYBOT humanoids play football in dynamic environments

@HumanoidRTech · 121 views · 2026-08-14

PHYBOTHumanoidLocomotion

0:05

Robot's Rising-to-Stand Motion Demo

@XueJia24682 · 106 views · 2026-08-13

HumanoidLocomotionStand-Up Standing

Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning

Humans exhibit remarkable motor agility, which highlights the great potential of humanoid robots for athletic locomotion. Long rope skipping requires two rope turners to cooperatively swing the rope while adapting to a player under different jumping rhythms. We propose Marope, a multi-agent reinforcement learning (MARL) framework for cooperative long rope skipping with multiple humanoid robots. It adopts a hierarchical RL framework: the lower level learns decentralized rope manipulation policies through MARL, while the upper level trains a centralized scheduling policy to coordinate execution. Diverse jumping policies are incorporated to improve generalization across player behavioral styles. Experiments on Unitree G1 robots in simulation and the real world show that Marope outperforms baselines.

Zihao Wang, Shijie Peng, Kerui WuJun 6, 2026

MARLhierarchical RLUnitree G1Jun 6, 2026