Monitoring and mapping of crop fields with UAV swarms based on information gain

Autor: Carbone, Albani, Magistri, Ognibene, Stachniss, Kootstra, Nardi, Trianni
Přispěvatelé: Carbone, C, Albani, D, Magistri, F, Ognibene, D, Stachniss, C, Kootstra, G, Nardi, D, Trianni, V
Rok vydání: 2022
Předmět:
Zdroj: Distributed Autonomous Robotic Systems-15th International Symposium, 2022. Cham: Springer
Distributed Autonomous Robotic Systems-15th International Symposium, 2022
15th International Symposium on Distributed Autonomous Robotic Systems, DARS 2021, pp. 306–319, 1-4 June 2021
info:cnr-pdr/source/autori:Carbone, C. and Albani, D. and Magistri, F. and Ognibene, D. and Stachniss, C. and Kootstra, G. and Nardi, D. and Trianni, V./congresso_nome:15th International Symposium on Distributed Autonomous Robotic Systems, DARS 2021/congresso_luogo:/congresso_data:1-4 June 2021/anno:2022/pagina_da:306/pagina_a:319/intervallo_pagine:306–319
Distributed Autonomous Robotic Systems ISBN: 9783030927899
DOI: 10.48550/arxiv.2203.11766
Popis: Monitoring crop fields to map features like weeds can be efficiently performed with unmanned aerial vehicles (UAVs) that can cover large areas in a short time due to their privileged perspective and motion speed. However, the need for high-resolution images for precise classification of features (e.g., detecting even the smallest weeds in the field) contrasts with the limited payload and flight time of current UAVs. Thus, it requires several flights to cover a large field uniformly. However, the assumption that the whole field must be observed with the same precision is unnecessary when features are heterogeneously distributed, like weeds appearing in patches over the field. In this case, an adaptive approach that focuses only on relevant areas can perform better, especially when multiple UAVs are employed simultaneously. Leveraging on a swarm-robotics approach, we propose a monitoring and mapping strategy that adaptively chooses the target areas based on the expected information gain, which measures the potential for uncertainty reduction due to further observations. The proposed strategy scales well with group size and leads to smaller mapping errors than optimal pre-planned monitoring approaches. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Databáze: OpenAIRE
Externí odkaz: