# Learning Distributional Demonstration Spaces for Task-Specific Cross-Pose Estimation

arXiv: https://arxiv.org/abs/2405.04609 · HTML: https://mlsanity.com/paper/2405.04609/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2024.

## Built on by (most cited first, 1 of 1)

- [Non-rigid Relative Placement through 3D Dense Diffusion](https://mlsanity.com/paper/2410.19247/) (2024)

## Abstract (arXiv)

Relative placement tasks are an important category of tasks in which one object needs to be placed in a desired pose relative to another object. Previous work has shown success in learning relative placement tasks from just a small number of demonstrations when using relational reasoning networks with geometric inductive biases. However, such methods cannot flexibly represent multimodal tasks, like a mug hanging on any of n racks. We propose a method that incorporates additional properties that enable learning multimodal relative placement solutions, while retaining the provably translation-invariant and relational properties of prior work. We show that our method is able to learn precise relative placement tasks with only 10-20 multimodal demonstrations with no human annotations across a diverse set of objects within a category.