TY - CHAP
T1 - Real-Time Volumetric-Semantic Exploration and Mapping
T2 - 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
AU - De Figueiredo, Rui Pimentel
AU - Le Fevre Sejersen, Jonas
AU - Hansen, Jakob Grimm
AU - Brandao, Martim
AU - Kayacan, Erdal
N1 - Funding Information:
The authors would like to acknowledge the financial contribution from Smart Industry Program (European Regional Development Fund and Region Midtjylland, grant no.: RFM-17-0020). The authors would further like to thank Upteko Aps for bringing use-case challenges.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In this work we propose a holistic framework for autonomous aerial inspection tasks, using semantically-aware, yet, computationally efficient planning and mapping algorithms. The system leverages state-of-the-art receding horizon exploration techniques for next-best-view (NBV) planning with geometric and semantic segmentation information provided by state-of-the-art deep convolutional neural networks (DCNNs), with the goal of enriching environment representations. The contributions of this article are threefold, first we propose an efficient sensor observation model, and a reward function that encodes the expected information gains from the observations taken from specific view points. Second, we extend the reward function to incorporate not only geometric but also semantic probabilistic information, provided by a DCNN for semantic segmentation that operates in real-time. The incorporation of semantic information in the environment representation allows biasing exploration towards specific objects, while ignoring task-irrelevant ones during planning. Finally, we employ our approaches in an autonomous drone shipyard inspection task. A set of simulations in realistic scenarios demonstrate the efficacy and efficiency of the proposed framework when compared with the state-of-the-art.
AB - In this work we propose a holistic framework for autonomous aerial inspection tasks, using semantically-aware, yet, computationally efficient planning and mapping algorithms. The system leverages state-of-the-art receding horizon exploration techniques for next-best-view (NBV) planning with geometric and semantic segmentation information provided by state-of-the-art deep convolutional neural networks (DCNNs), with the goal of enriching environment representations. The contributions of this article are threefold, first we propose an efficient sensor observation model, and a reward function that encodes the expected information gains from the observations taken from specific view points. Second, we extend the reward function to incorporate not only geometric but also semantic probabilistic information, provided by a DCNN for semantic segmentation that operates in real-time. The incorporation of semantic information in the environment representation allows biasing exploration towards specific objects, while ignoring task-irrelevant ones during planning. Finally, we employ our approaches in an autonomous drone shipyard inspection task. A set of simulations in realistic scenarios demonstrate the efficacy and efficiency of the proposed framework when compared with the state-of-the-art.
UR - http://www.scopus.com/inward/record.url?scp=85124368274&partnerID=8YFLogxK
U2 - 10.1109/IROS51168.2021.9635986
DO - 10.1109/IROS51168.2021.9635986
M3 - Conference paper
AN - SCOPUS:85124368274
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 9064
EP - 9070
BT - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 27 September 2021 through 1 October 2021
ER -