# Perceiving Extrinsic Contacts from Touch Improves Learning Insertion Policies

arXiv: https://arxiv.org/abs/2309.16652 · HTML: https://mlsanity.com/paper/2309.16652/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2023.

## Built on by (most cited first, 4 of 4)

- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [ViTaSCOPE: Visuo-tactile Implicit Representation for In-hand Pose and Extrinsic Contact Estimation](https://mlsanity.com/paper/2506.12239/) (2025)
- [FlowTouch: View-Invariant Visuo-Tactile Prediction](https://mlsanity.com/paper/2603.08255/) (2026)
- [UNIC: Learning Unified Multimodal Extrinsic Contact Estimation](https://mlsanity.com/paper/2601.04356/) (2026)

## Abstract (arXiv)

Robotic manipulation tasks such as object insertion typically involve interactions between object and environment, namely extrinsic contacts. Prior work on Neural Contact Fields (NCF) use intrinsic tactile sensing between gripper and object to estimate extrinsic contacts in simulation. However, its effectiveness and utility in real-world tasks remains unknown. In this work, we improve NCF to enable sim-to-real transfer and use it to train policies for mug-in-cupholder and bowl-in-dishrack insertion tasks. We find our model NCF-v2, is capable of estimating extrinsic contacts in the real-world. Furthermore, our insertion policy with NCF-v2 outperforms policies without it, achieving 33% higher success and 1.36x faster execution on mug-in-cupholder, and 13% higher success and 1.27x faster execution on bowl-in-dishrack.