mlsanityData to 7 Oct 2026

Hierarchical visuomotor control of humanoids

arXiv 1811.09656 ↗First posted 23 Nov 2018cs.AI cs.ROcited by 29

Not on the map. Why?

Abstract (arXiv)

We aim to build complex humanoid agents that integrate perception, motor control, and memory. In this work, we partly factor this problem into low-level motor control from proprioception and high-level coordination of the low-level skills informed by vision. We develop an architecture capable of surprisingly flexible, task-directed motor control of a relatively high-DoF humanoid body by combining pre-training of low-level motor controllers with a high-level, task-focused controller that switches among low-level sub-policies. The resulting system is able to control a physically-simulated humanoid body to solve tasks that require coupling visual perception from an unstabilized egocentric RGB camera during locomotion in the environment. For a supplementary video link, see https://youtu.be/7GISvfbykLE .

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 8; 2022: 11; 2023: 5; 2024: 2; 2025: 1; 2026: 1.

29 papers.

Sort:

By area:

  1. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
  2. 2022Deep Hierarchical Planning from Pixelscited by 96
  3. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  4. 2021Learning and Planning in Complex Action Spacescited by 76
  5. 2020RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learningcited by 57
  6. 2021Hierarchical Reinforcement Learning By Discovering Intrinsic Optionscited by 57
  7. 2021Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularizationcited by 44
  8. 2023Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulationcited by 43
  9. 2021Hierarchical Skills for Efficient Explorationcited by 37
  10. 2022MoCapAct: A Multi-Task Dataset for Simulated Humanoid Controlcited by 24
  11. 2024Hierarchical World Models as Visual Whole-Body Humanoid Controllerscited by 24
  12. 2023DiffMimic: Efficient Motion Mimicking with Differentiable Physicscited by 17
17 more
  1. 2022Learning to Get Upcited by 11
  2. 2023Hierarchical generative modelling for autonomous robotscited by 9
  3. 2022Transfering Hierarchical Structure with Dual Meta Imitation Learningcited by 7
  4. 2022ASPiRe:Adaptive Skill Priors for Reinforcement Learningcited by 7
  5. 2022Leveraging Sequentiality in Reinforcement Learning from a Single Demonstrationcited by 6
  6. 2025Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learningcited by 5
  7. 2021Learning Setup Policies: Reliable Transition Between Locomotion Behaviourscited by 2
  8. 2021Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchiescited by 2
  9. 2022Leveraging Demonstrations with Latent Space Priorscited by 2
  10. 2024Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practicecited by 1
  11. 2022Unified Simulation, Perception, and Generation of Human Behaviorcited by 0
  12. 2022Learning fast and agile quadrupedal locomotion over complex terraincited by 0
  13. 2022What deep reinforcement learning tells us about human motor learning and vice-versacited by 0
  14. 2022Hippocampus-Inspired Cognitive Architecture (HICA) for Operant Conditioningcited by 0
  15. 2023RObotic MAnipulation Network (ROMAN) -- Hybrid Hierarchical Learning for Solving Complex Sequential Taskscited by 0
  16. 2023A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Controlcited by 0
  17. 2026EATR-Stereo: Embodiment-Aware Token Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action Controlcited by 0