mlsanityData to 7 Oct 2026

InsertionNet 2.0: Minimal Contact Multi-Step Insertion Using Multimodal Multiview Sensory Input

arXiv 2203.01153 ↗First posted 2 Mar 2022cs.RO cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

We address the problem of devising the means for a robot to rapidly and safely learn insertion skills with just a few human interventions and without hand-crafted rewards or demonstrations. Our InsertionNet version 2.0 provides an improved technique to robustly cope with a wide range of use-cases featuring different shapes, colors, initial poses, etc. In particular, we present a regression-based method based on multimodal input from stereo perception and force, augmented with contrastive learning for the efficient learning of valuable features. In addition, we introduce a one-shot learning technique for insertion, which relies on a relation network scheme to better exploit the collected data and to support multi-step insertion tasks. Our method improves on the results obtained with the original InsertionNet, achieving an almost perfect score (above 97.5% on 200 trials) in 16 real-life insertion tasks while minimizing the execution time and contact during insertion. We further demonstrate our method's ability to tackle a real-life 3-step insertion task and perfectly solve an unseen insertion task without learning.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

17 of 29 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  6. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  7. 2014Deep metric learning using Triplet networkcited by 421
  8. 2018Residual Reinforcement Learning for Robot Controlcited by 242
  9. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 171
  10. 2018Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Taskscited by 150
  11. 2019Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewardscited by 58
  12. 2017Deep Reinforcement Learning for High Precision Assembly Taskscited by 37
5 more
  1. 2018A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learningcited by 35
  2. 2020Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learningcited by 22
  3. 2021InsertionNet -- A Scalable Solution for Insertioncited by 15
  4. 2019Compare Contact Model-based Control and Contact Model-free Learning: A Survey of Robotic Peg-in-hole Assembly Strategiescited by 13
  5. 2020Deep Reinforcement Learning for Contact-Rich Skills Using Compliant Movement Primitivescited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 4; 2025: 2.

9 papers.

  1. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 36
  2. 2024TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulationcited by 23
  3. 2022Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Visioncited by 11
  4. 2025Manual2Skill++: Connector-Aware General Robotic Assembly from Instruction Manuals via Vision-Language Modelscited by 5
  5. 2024AugInsert: Learning Robust Visual-Force Policies via Data Augmentation for Object Assembly Taskscited by 2
  6. 2024Towards Natural Language-Driven Assembly Using Foundation Modelscited by 1
  7. 2023Working Backwards: Learning to Place by Pickingcited by 0
  8. 2023PolyFit: A Peg-in-hole Assembly Framework for Unseen Polygon Shapes via Sim-to-real Adaptationcited by 0
  9. 2025EasyInsert: A Data-Efficient and Generalizable Insertion Policycited by 0