# Interpreting Contact Interactions to Overcome Failure in Robot Assembly Tasks

arXiv: https://arxiv.org/abs/2101.02725 · HTML: https://mlsanity.com/paper/2101.02725/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2021.

## Built on by (most cited first, 9 of 9)

- [Factory: Fast Contact for Robotic Assembly](https://mlsanity.com/paper/2205.03532/) (2022)
- [3D Part Assembly Generation with Instance Encoded Transformer](https://mlsanity.com/paper/2207.01779/) (2022)
- [Efficient Recovery Learning using Model Predictive Meta-Reasoning](https://mlsanity.com/paper/2209.13605/) (2022)
- [Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities](https://mlsanity.com/paper/2107.05789/) (2021)
- [Tactile-Filter: Interactive Tactile Perception for Part Mating](https://mlsanity.com/paper/2303.06034/) (2023)
- [Streaming Motion Forecasting for Autonomous Driving](https://mlsanity.com/paper/2310.01351/) (2023)
- [Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations](https://mlsanity.com/paper/2410.00436/) (2024)
- [DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion Models](https://mlsanity.com/paper/2503.01274/) (2025)
- [Harnessing human expertise for high-precision robotic assembly in industrialized construction: A sample-efficient installer-in-the-loop interactive reinforcement learning framework](https://mlsanity.com/paper/2609.13234/) (2026)

## Abstract (arXiv)

A key challenge towards the goal of multi-part assembly tasks is finding robust sensorimotor control methods in the presence of uncertainty. In contrast to previous works that rely on a priori knowledge on whether two parts match, we aim to learn this through physical interaction. We propose a hierarchical approach that enables a robot to autonomously assemble parts while being uncertain about part types and positions. In particular, our probabilistic approach learns a set of differentiable filters that leverage the tactile sensorimotor trace from failed assembly attempts to update its belief about part position and type. This enables a robot to overcome assembly failure. We demonstrate the effectiveness of our approach on a set of object fitting tasks. The experimental results indicate that our proposed approach achieves higher precision in object position and type estimation, and accomplishes object fitting tasks faster than baselines.