mlsanityData to 14 Oct 2026

InsertionNet -- A Scalable Solution for Insertion

arXiv 2104.14223 ↗First posted 29 Apr 2021cs.RO cs.AI cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Complicated assembly processes can be described as a sequence of two main activities: grasping and insertion. While general grasping solutions are common in industry, insertion is still only applicable to small subsets of problems, mainly ones involving simple shapes in fixed locations and in which the variations are not taken into consideration. Recently, RL approaches with prior knowledge (e.g., LfD or residual policy) have been adopted. However, these approaches might be problematic in contact-rich tasks since interaction might endanger the robot and its equipment. In this paper, we tackled this challenge by formulating the problem as a regression problem. By combining visual and force inputs, we demonstrate that our method can scale to 16 different insertion tasks in less than 10 minutes. The resulting policies are robust to changes in the socket position, orientation or peg color, as well as to small differences in peg shape. Finally, we demonstrate an end-to-end solution for 2 complex assembly tasks with multi-insertion objectives when the assembly board is randomly placed on a table.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 29 Apr 2021.

Builds on

16 of 32 references.

References · 16

  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  2. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  3. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  4. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 174
  5. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  6. 2018Residual Policy Learningcited by 164
  7. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 154
  8. 2019Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learningcited by 104
  9. 2019Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Taskscited by 67
  10. 2019Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewardscited by 64
  11. 2017Deep Reinforcement Learning for High Precision Assembly Taskscited by 39
  12. 2018A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learningcited by 36
4 more
  1. 2020Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learningcited by 25
  2. 2019Compare Contact Model-based Control and Contact Model-free Learning: A Survey of Robotic Peg-in-hole Assembly Strategiescited by 14
  3. 2020Deep Reinforcement Learning for Contact-Rich Skills Using Compliant Movement Primitivescited by 6
  4. 2019Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradientcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 3; 2024: 7; 2025: 2; 2026: 1.

16 papers.

Sort:

By area:

  1. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learningcited by 136
  2. 2024From Imitation to Refinement -- Residual RL for Precise Assemblycited by 90
  3. 2021Offline Meta-Reinforcement Learning for Industrial Insertioncited by 39
  4. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 38
  5. 2024TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulationcited by 23
  6. 2022Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Visioncited by 13
  7. 2022InsertionNet 2.0: Minimal Contact Multi-Step Insertion Using Multimodal Multiview Sensory Inputcited by 9
  8. 2024MResT: Multi-Resolution Sensing for Real-Time Control with Vision-Language Modelscited by 5
  9. 2023Efficient Skill Acquisition for Complex Manipulation Tasks in Obstructed Environmentscited by 2
  10. 2024AugInsert: Learning Robust Visual-Force Policies via Data Augmentation for Object Assembly Taskscited by 2
  11. 2025Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policiescited by 2
  12. 2023PolyFit: A Peg-in-hole Assembly Framework for Unseen Polygon Shapes via Sim-to-real Adaptationcited by 1
4 more
  1. 2024Automating Deformable Gasket Assemblycited by 1
  2. 2023Working Backwards: Learning to Place by Pickingcited by 0
  3. 2025A comparison of visual representations for real-world reinforcement learning in the context of vacuum grippingcited by 0
  4. 2026Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assemblycited by 0