# Zero-Shot Transfer of Haptics-Based Object Insertion Policies

arXiv: https://arxiv.org/abs/2301.12587 · HTML: https://mlsanity.com/paper/2301.12587/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 29 Jan 2023.

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks](https://mlsanity.com/paper/1810.10191/) (2018)
- [ContactOpt: Optimizing Contact to Improve Grasps](https://mlsanity.com/paper/2104.07267/) (2021)
- [Reducing the Barrier to Entry of Complex Robotic Software: a MoveIt! Case Study](https://mlsanity.com/paper/1404.3785/) (2014)
- [Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks](https://mlsanity.com/paper/1907.13098/) (2019)
- [Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards](https://mlsanity.com/paper/1906.05841/) (2019)
- [Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry](https://mlsanity.com/paper/2104.01167/) (2021)
- [Deep Reinforcement Learning for High Precision Assembly Tasks](https://mlsanity.com/paper/1708.04033/) (2017)
- [kPAM 2.0: Feedback Control for Category-Level Robotic Manipulation](https://mlsanity.com/paper/2102.06279/) (2021)
- [A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning](https://mlsanity.com/paper/1810.01531/) (2018)
- [Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks](https://mlsanity.com/paper/2004.14404/) (2020)
- [Variable Compliance Control for Robotic Peg-in-Hole Assembly: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2008.10224/) (2020)
- [Reverb: A Framework For Experience Replay](https://mlsanity.com/paper/2102.04736/) (2021)
- [A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies](https://mlsanity.com/paper/2208.00596/) (2022)
- [A Framework for Robot Manipulation: Skill Formalism, Meta Learning and Adaptive Control](https://mlsanity.com/paper/1805.08576/) (2018)
- [Occlusion-Aware Object Localization, Segmentation and Pose Estimation](https://mlsanity.com/paper/1507.07882/) (2015)
- [Prim-LAfD: A Framework to Learn and Adapt Primitive-Based Skills from Demonstrations for Insertion Tasks](https://mlsanity.com/paper/2212.00955/) (2022)
- [Imitation Learning for High Precision Peg-in-Hole Tasks](https://mlsanity.com/paper/2101.01052/) (2020)

## Built on by (most cited first, 2 of 2)

- [Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist](https://mlsanity.com/paper/2402.18002/) (2024)
- [GenCHiP: Generating Robot Policy Code for High-Precision and Contact-Rich Manipulation Tasks](https://mlsanity.com/paper/2404.06645/) (2024)

## Abstract (arXiv)

Humans naturally exploit haptic feedback during contact-rich tasks like loading a dishwasher or stocking a bookshelf. Current robotic systems focus on avoiding unexpected contact, often relying on strategically placed environment sensors. Recently, contact-exploiting manipulation policies have been trained in simulation and deployed on real robots. However, they require some form of real-world adaptation to bridge the sim-to-real gap, which might not be feasible in all scenarios. In this paper we train a contact-exploiting manipulation policy in simulation for the contact-rich household task of loading plates into a slotted holder, which transfers without any fine-tuning to the real robot. We investigate various factors necessary for this zero-shot transfer, like time delay modeling, memory representation, and domain randomization. Our policy transfers with minimal sim-to-real gap and significantly outperforms heuristic and learnt baselines. It also generalizes to plates of different sizes and weights. Demonstration videos and code are available at https://sites.google.com/view/compliant-object-insertion.