mlsanityData to 14 Oct 2026

Cognitive Manipulation: Semi-supervised Visual Representation and Classroom-to-real Reinforcement Learning for Assembly in Semi-structured Environments

arXiv 2406.00364 ↗First posted 1 Jun 2024cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Assembling a slave object into a fixture-free master object represents a critical challenge in flexible manufacturing. Existing deep reinforcement learning-based methods, while benefiting from visual or operational priors, often struggle with small-batch precise assembly tasks due to their reliance on insufficient priors and high-costed model development. To address these limitations, this paper introduces a cognitive manipulation and learning approach that utilizes skill graphs to integrate learning-based object detection with fine manipulation models into a cohesive modular policy. This approach enables the detection of the master object from both global and local perspectives to accommodate positional uncertainties and variable backgrounds, and parametric residual policy to handle pose error and intricate contact dynamics effectively. Leveraging the skill graph, our method supports knowledge-informed learning of semi-supervised learning for object detection and classroom-to-real reinforcement learning for fine manipulation. Simulation experiments on a gear-assembly task have demonstrated that the skill-graph-enabled coarse-operation planning and visual attention are essential for efficient learning and robust manipulation, showing substantial improvements of 13% in success rate and 15.4% in number of completion steps over competing methods. Real-world experiments further validate that our system is highly effective for robotic assembly in semi-structured environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 51 references that are in the map. First posted on arXiv 1 Jun 2024.

Builds on

14 of 51 references.

References · 14

  1. 2019Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewardscited by 64
  2. 2021Learning to See before Learning to Act: Visual Pre-training for Manipulationcited by 51
  3. 2021Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Studycited by 30
  4. 2022Affordance Learning from Play for Sample-Efficient Policy Learningcited by 30
  5. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 29
  6. 2020Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learningcited by 25
  7. 2018A Framework for Robot Manipulation: Skill Formalism, Meta Learning and Adaptive Controlcited by 17
  8. 2021Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertaintycited by 10
  9. 2020Fast robust peg-in-hole insertion with continuous visual servoingcited by 9
  10. 2024ManiPose: A Comprehensive Benchmark for Pose-aware Object Manipulation in Roboticscited by 7
  11. 2022Learning Skills from Demonstrations: A Trend from Motion Primitives to Experience Abstractioncited by 5
  12. 2023Visual Spatial Attention and Proprioceptive Data-Driven Reinforcement Learning for Robust Peg-in-Hole Task Under Variable Conditionscited by 5
2 more
  1. 2020Proactive Action Visual Residual Reinforcement Learning for Contact-Rich Tasks Using a Torque-Controlled Robotcited by 4
  2. 2023Automatically Prepare Training Data for YOLO Using Robotic In-Hand Observation and Synthesiscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Zero-Shot Visual Generalization in Robot Manipulation
  2. 2026SparTa: Sparse Graphical Task Models from a Handful of Demonstrations
  3. 2024Subassembly to Full Assembly: Effective Assembly Sequence Planning through Graph-based Reinforcement Learning
  4. 2025Video-to-BT: Generating Reactive Behavior Trees from Human Demonstration Videos for Robotic Assembly
  5. 2025MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignment
  6. 2025SViP: Sequencing Bimanual Visuomotor Policies with Object-Centric Motion Primitives
  7. 2026VE2VF: Vision-Enabled to Vision-Free Distillation via Real-world Reinforcement Learning for Robust Contact-Rich Manipulation
  8. 2026ATG-MoE: Autoregressive trajectory generation with mixture-of-experts for assembly skill learning ↗