Reinforcement learning produces a policy for passive inline skating on a humanoid robot that achieves up to 50% lower cost of transport than walking and transfers zero-shot to physical hardware.
hub
Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
abstract
While recent advances in humanoid locomotion have achieved stable walking on varied terrains, capturing the agility and adaptivity of highly dynamic human motions remains an open challenge. In particular, agile parkour in complex environments demands not only low-level robustness, but also human-like motion expressiveness, long-horizon skill composition, and perception-driven decision-making. In this paper, we present Perceptive Humanoid Parkour (PHP), a modular framework that enables humanoid robots to autonomously perform long-horizon, vision-based parkour across challenging obstacle courses. Our approach first leverages motion matching, formulated as nearest-neighbor search in a feature space, to compose retargeted atomic human skills into long-horizon kinematic trajectories. This framework enables the flexible composition and smooth transition of complex skill chains while preserving the elegance and fluidity of dynamic human motions. Next, we train motion-tracking reinforcement learning (RL) expert policies for these composed motions, and distill them into a single depth-based, multi-skill student policy, using a combination of DAgger and RL. Crucially, the combination of perception and skill composition enables autonomous, context-aware decision-making: using only onboard depth sensing and a discrete 2D velocity command, the robot selects and executes whether to step over, climb onto, vault or roll off obstacles of varying geometries and heights. We validate our framework with extensive real-world experiments on a Unitree G1 humanoid robot, demonstrating highly dynamic parkour skills such as climbing tall obstacles up to 1.25m (96% robot height), as well as long-horizon multi-obstacle traversal with closed-loop adaptation to real-time obstacle perturbations.
hub tools
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 15years
2026 15roles
background 1polarities
background 1representative citing papers
HumanoidArena is a new benchmark of 7 leg-critical HOI/HSI tasks that evaluates egocentric hierarchical whole-body policies in humanoids and finds performance is strongly conditioned on the low-level GMT used.
SceneBot conditions a humanoid tracking policy on motion references and contact labels, using reconstructed scene-interaction data to unify free-space locomotion with contact-rich manipulation and terrain tasks.
TaskNPoint lets humanoid robots learn dynamic skills such as tennis backhands from single short human video demonstrations plus under one hour of single-GPU simulation training, achieving zero-shot generalization to new goal locations without per-task reward tuning.
Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.
LUCID learns embodiment-agnostic intent models from unstructured human videos to train dexterous robot policies in simulation, enabling zero-shot transfer on real-world tasks like stirring and wiping.
GuideWalk unifies traversability-aware navigation and terrain-adaptive locomotion into a single policy for humanoid robots via teacher distillation and RL refinement.
VAIC distills a teacher policy into a vision-and-proprioception student policy using recurrent adaptation and decoupled commands, enabling diverse real-robot tasks like box carrying and skateboarding that outperform baselines.
HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports VLM-driven agentic planning with no task-specific data.
A hybrid motion-tracking and imitation-reinforcement pipeline produces a depth-based visuomotor policy that lets humanoids climb varied ladders zero-shot on hardware and perform teleoperated manipulation while climbing.
SSR is an end-to-end vision-based framework for humanoid traversal that learns imagined foothold guidance, equivariant latent-space symmetry augmentation, and terrain-specific multi-discriminator motion priors to enable safe locomotion on diverse real-world terrains.
ParkourFormer achieves 93.85% average success on multi-terrain humanoid parkour by fusing Transformer sequence modeling with supervised future-state prediction.
Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.
HTD, a multimodal transformer policy trained with behavioral cloning and touch dreaming to predict future tactile latents, achieves a 90.9% relative success rate improvement over baselines on five real-world contact-rich humanoid loco-manipulation tasks.
A multi-channel terrain affordance reward combined with lower-body compliance training via virtual wrenches enables end-to-end PPO-trained humanoid policies to walk at 1 m/s on 0.2 m risers with improved payload robustness.
citing papers explorer
-
Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot
Reinforcement learning produces a policy for passive inline skating on a humanoid robot that achieves up to 50% lower cost of transport than walking and transfers zero-shot to physical hardware.
-
HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
HumanoidArena is a new benchmark of 7 leg-critical HOI/HSI tasks that evaluates egocentric hierarchical whole-body policies in humanoids and finds performance is strongly conditioned on the low-level GMT used.
-
SceneBot: Contact-Prompted General Humanoid Whole Body Tracking with Scene-Interaction
SceneBot conditions a humanoid tracking policy on motion references and contact labels, using reconstructed scene-interaction data to unify free-space locomotion with contact-rich manipulation and terrain tasks.
-
TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes
TaskNPoint lets humanoid robots learn dynamic skills such as tennis backhands from single short human video demonstrations plus under one hour of single-GPU simulation training, achieving zero-shot generalization to new goal locations without per-task reward tuning.
-
Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain
Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.
-
LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition
LUCID learns embodiment-agnostic intent models from unstructured human videos to train dexterous robot policies in simulation, enabling zero-shot transfer on real-world tasks like stirring and wiping.
-
GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains
GuideWalk unifies traversability-aware navigation and terrain-adaptive locomotion into a single policy for humanoid robots via teacher distillation and RL refinement.
-
VAIC: Vision-Guided Humanoid Agile Object Interaction Control via Decoupled Commands
VAIC distills a teacher policy into a vision-and-proprioception student policy using recurrent adaptation and decoupled commands, enabling diverse real-robot tasks like box carrying and skateboarding that outperform baselines.
-
HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports VLM-driven agentic planning with no task-specific data.
-
LadderMan: Learning Humanoid Perceptive Ladder Climbing
A hybrid motion-tracking and imitation-reinforcement pipeline produces a depth-based visuomotor policy that lets humanoids climb varied ladders zero-shot on hardware and perform teleoperated manipulation while climbing.
-
SSR: Scaling Surefooted and Symmetric Humanoid Traversal to the Open World
SSR is an end-to-end vision-based framework for humanoid traversal that learns imagined foothold guidance, equivariant latent-space symmetry augmentation, and terrain-specific multi-discriminator motion priors to enable safe locomotion on diverse real-world terrains.
-
ParkourFormer: Integrating Predictive Supervision and Sequence Modeling into Parkour Locomotion
ParkourFormer achieves 93.85% average success on multi-terrain humanoid parkour by fusing Transformer sequence modeling with supervised future-state prediction.
-
Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy
Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.
-
Learning Versatile Humanoid Manipulation with Touch Dreaming
HTD, a multimodal transformer policy trained with behavioral cloning and touch dreaming to predict future tactile latents, achieves a 90.9% relative success rate improvement over baselines on five real-world contact-rich humanoid loco-manipulation tasks.
-
TACT-ful: Multi-Channel Terrain Affordance and Compliance Training for Payload-Robust Perceptive Humanoid Locomotion
A multi-channel terrain affordance reward combined with lower-body compliance training via virtual wrenches enables end-to-end PPO-trained humanoid policies to walk at 1 m/s on 0.2 m risers with improved payload robustness.