# Viewpoint Push Planning for Mapping of Unknown Confined Spaces

arXiv: https://arxiv.org/abs/2303.03126 · HTML: https://mlsanity.com/paper/2303.03126/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2023.

## Built on by (most cited first, 5 of 5)

- [Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation](https://mlsanity.com/paper/2409.14891/) (2024)
- [Exploiting Priors from 3D Diffusion Models for RGB-Based One-Shot View Planning](https://mlsanity.com/paper/2403.16803/) (2024)
- [DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction](https://mlsanity.com/paper/2504.11674/) (2025)
- [Map Space Belief Prediction for Manipulation-Enhanced Mapping](https://mlsanity.com/paper/2502.20606/) (2025)
- [Next-Best-Trajectory Planning of Robot Manipulators for Effective Observation and Exploration](https://mlsanity.com/paper/2503.22588/) (2025)

## Abstract (arXiv)

Viewpoint planning is an important task in any application where objects or scenes need to be viewed from different angles to achieve sufficient coverage. The mapping of confined spaces such as shelves is an especially challenging task since objects occlude each other and the scene can only be observed from the front, posing limitations on the possible viewpoints. In this paper, we propose a deep reinforcement learning framework that generates promising views aiming at reducing the map entropy. Additionally, the pipeline extends standard viewpoint planning by predicting adequate minimally invasive push actions to uncover occluded objects and increase the visible space. Using a 2.5D occupancy height map as state representation that can be efficiently updated, our system decides whether to plan a new viewpoint or perform a push. To learn feasible pushes, we use a neural network to sample push candidates on the map based on training data provided by human experts. As simulated and real-world experimental results with a robotic arm show, our system is able to significantly increase the mapped space compared to different baselines, while the executed push actions highly benefit the viewpoint planner with only minor changes to the object configuration.