mlsanityData to 14 Oct 2026

Hierarchical generative modelling for autonomous robots

arXiv 2308.07775 ↗First posted 15 Aug 2023cs.RO cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Humans can produce complex whole-body motions when interacting with their surroundings, by planning, executing and combining individual limb movements. We investigated this fundamental aspect of motor control in the setting of autonomous robotic operations. We approach this problem by hierarchical generative modelling equipped with multi-level planning-for autonomous task completion-that mimics the deep temporal architecture of human motor control. Here, temporal depth refers to the nested time scales at which successive levels of a forward or generative model unfold, for example, delivering an object requires a global plan to contextualise the fast coordination of multiple local movements of limbs. This separation of temporal scales also motivates robotics and control. Specifically, to achieve versatile sensorimotor control, it is advantageous to hierarchically structure the planning and low-level motor control of individual limbs. We use numerical and physical simulation to conduct experiments and to establish the efficacy of this formulation. Using a hierarchical generative model, we show how a humanoid robot can autonomously complete a complex task that necessitates a holistic use of locomotion, manipulation, and grasping. Specifically, we demonstrate the ability of a humanoid robot that can retrieve and transport a box, open and walk through a door to reach the destination, approach and kick a football, while showing robust performance in presence of body damage and ground irregularities. Our findings demonstrated the effectiveness of using human-inspired motor control algorithms, and our method provides a viable hierarchical architecture for the autonomous completion of challenging goal-directed tasks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 17 of its 98 references that are in the map. First posted on arXiv 15 Aug 2023.

Builds on

17 of 98 references.

References · 17

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 455
  4. 2018PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planningcited by 150
  5. 2018Neural probabilistic motor primitives for humanoid controlcited by 97
  6. 2020Active inference on discrete state-spaces: a synthesiscited by 92
  7. 2020Multi-expert learning of adaptive legged locomotioncited by 67
  8. 2019HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulatorscited by 55
  9. 2019Deep Active Inference as Variational Policy Gradientscited by 53
  10. 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
  11. 2019ASNets: Deep Learning for Generalised Planningcited by 42
  12. 2018Task Planning in Robotics: an Empirical Comparison of PDDL-based and ASP-based Systemscited by 40
5 more
  1. 2018Hierarchical visuomotor control of humanoidscited by 30
  2. 2019Hierarchical Reinforcement Learning for Quadruped Locomotioncited by 24
  3. 2019Generative models as parsimonious descriptions of sensorimotor loopscited by 11
  4. 2020Learning natural locomotion behaviors for humanoid robots using human knowledgecited by 11
  5. 2020Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Networkcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 5; 2025: 3.

9 papers.

  1. 2024Towards Generalist Robot Learning from Internet Video: A Surveycited by 40
  2. 2024Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regressioncited by 5
  3. 2025HEIR: Learning Graph-Based Motion Hierarchiescited by 1
  4. 2023A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Controlcited by 0
  5. 2024Deep hybrid models: infer and plan in a dynamic worldcited by 0
  6. 2024Dynamic planning in hierarchical active inferencecited by 0
  7. 2024Hierarchical learning control for autonomous robots inspired by central nervous systemcited by 0
  8. 2025Robust Robotic Exploration and Mapping Using Generative Occupancy Map Synthesiscited by 0
  9. 2025Dissociating model architectures from inference computationscited by 0