# Online Next-Best-View Planner for 3D-Exploration and Inspection With a Mobile Manipulator Robot

**Authors:** Menaka Naazare, Francisco Garcia Rosas, Dirk Schulz  
**arXiv:** [2203.10113](https://arxiv.org/abs/2203.10113)  
**Date:** 2022-03-18  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2203.10113v1/

## Key points


## Summary

The paper titled "Online Next-Best-View Planner for 3D-Exploration and Inspection With a Mobile Manipulator Robot" presents a novel approach for autonomous exploration and inspection using a mobile manipulator robot. The authors highlight the need for robotic systems that can not only map an environment but also perform simultaneous inspection of regions of interest for end-users. To address this challenge, the authors propose a Next-Best-View (NBV) planner that can effectively perform both full exploration and user-oriented exploration with inspection. They frame the exploration-inspection problem as a Multi-Objective Optimization (MOO) task and introduce a weighted-sum based information gain function to compute NBVs for the RGB-D camera mounted on the robot's arm. In order to evaluate their approach, the authors compare it with an existing state-of-the art exploration method as a baseline. They demonstrate improvements in terms of total volume mapped and lower computational requirements achieved by their proposed NBV planner. To validate the practicality and effectiveness of their approach, real experiments are conducted with a mobile manipulator robot in outdoor environments. The results showcase the feasibility of their method in performing autonomous exploration and inspection tasks. Overall, this paper contributes to the field of robotics by presenting an innovative solution for end user oriented autonomous exploration and inspection. The proposed NBV planner offers improved performance compared to existing methods, making it a promising tool for various scenarios requiring mapping and region specific inspection.