REVIEW 9 cited by
Learning Humanoid Locomotion with Perceptive Internal Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In contrast to quadruped robots that can navigate diverse terrains using a "blind" policy, humanoid robots require accurate perception for stable locomotion due to their high degrees of freedom and inherently unstable morphology. However, incorporating perceptual signals often introduces additional disturbances to the system, potentially reducing its robustness, generalizability, and efficiency. This paper presents the Perceptive Internal Model (PIM), which relies on onboard, continuously updated elevation maps centered around the robot to perceive its surroundings. We train the policy using ground-truth obstacle heights surrounding the robot in simulation, optimizing it based on the Hybrid Internal Model (HIM), and perform inference with heights sampled from the constructed elevation map. Unlike previous methods that directly encode depth maps or raw point clouds, our approach allows the robot to perceive the terrain beneath its feet clearly and is less affected by camera movement or noise. Furthermore, since depth map rendering is not required in simulation, our method introduces minimal additional computational costs and can train the policy in 3 hours on an RTX 4090 GPU. We verify the effectiveness of our method across various humanoid robots, various indoor and outdoor terrains, stairs, and various sensor configurations. Our method can enable a humanoid robot to continuously climb stairs and has the potential to serve as a foundational algorithm for the development of future humanoid control methods.
Forward citations
Cited by 9 Pith papers
-
MuJoCo Playground
An open-source, MJX-based robot learning framework with integrated batch rendering that provides fast training and demonstrates sim-to-real transfer on six robot platforms.
-
KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
A robot control method that adaptively tightens motion-tracking reward tolerances achieves lower tracking errors on dynamic skills and transfers zero-shot to a real humanoid.
-
MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains
A two-stage reinforcement learning pipeline with a mixture of latent residual experts gives a Unitree G1 humanoid multiple commanded human-like gaits over complex terrains.
-
Hold My Beer: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control
A slow-fast two-agent reinforcement learning architecture with separate upper- and lower-body policies reduces end-effector shaking during humanoid locomotion.
-
Learning Humanoid Standing-up Control across Diverse Postures
HoST uses multi-critic reinforcement learning, a force curriculum, and smoothness constraints in simulation so a Unitree G1 humanoid can stand up from diverse postures in the real world without predefined motion trajectories.
-
KiVi: Kinesthetic-Visuospatial Integration for Dynamic and Safe Egocentric Legged Locomotion
A quadruped locomotion controller that explicitly separates proprioceptive and visual pathways stays stable under camera occlusion and visual corruption that destabilizes fused-vision policies.
-
Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
A humanoid-specific multimodal occupancy perception system with a new dataset, sensor layout, and a fusion network that claims state-of-the-art results on its own benchmark.
-
Robust RL Control for Bipedal Locomotion with Closed Kinematic Chains
A reinforcement-learning gait controller that explicitly models closed kinematic chains outperforms one trained on a simplified serial model, both in simulation and on the physical TopA robot.
-
A Survey: Learning Embodied Intelligence from Physical Simulators and World Models
Embodied intelligence learning is reviewed through the complementary lenses of physical simulators and world models, with a proposed IR-L0 to IR-L4 robot capability taxonomy.
Discussion (0). Continue with ORCID to comment.