Energy Saving Quadrotor Control for Field Inspections

Wang, Yafeng; Wang, Yeqin; Ren, Beibei

doi:10.1109/tsmc.2020.3037071

Cited by 30 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) The distribution is more uniform. (2) The rank values have a fixed lower bound (i.e., zero), and upper bound (i.e., the number of the elements). It is easier to choose appropriate hyper-parameters due to their fixed range.…”

Section: Previous Oursmentioning

confidence: 99%

See 1 more Smart Citation

Soft Ranking Threshold Losses For Image Retrieval

Yang

Wang

Lin

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

This paper proposes a novel loss, soft ranking threshold loss, for driving deep networks to learn better representations for image retrieval. Instead of working in the metric space, our loss works in the rank space which has a more uniform distribution and explicit scale and bounds. Our loss reduces the ranks of the distances between anchor-positive pairs below the threshold while increasing the ones between anchornegative pairs above the threshold. In addition to the basic form, two extensions are proposed for improving the effectiveness: hard thresholds and ranking margin. Experiments show that the proposed loss outperforms the state-of-the-art losses on image retrieval applications.

show abstract

Section: Previous Oursmentioning

confidence: 99%

“…Content-based image retrieval (CBIR) has been a popular topic with the potential of enabling a myriad of real-life applications [1,2]. Given a query image, the goal is to find corresponding images in a gallery set that have the same class label as the query image or are visually similar to it.…”

Section: Introductionmentioning

confidence: 99%

Soft Ranking Threshold Losses For Image Retrieval

Yang

Wang

Lin

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Over the past few decades, there has been remarkable progress in the development of aerial robots, particularly small unmanned aerial vehicles (UAVs) and drones [1], [2]. These advancements have encompassed various aspects, including their design, operational techniques, flight capabilities, and navigation control.…”

Section: Introductionmentioning

confidence: 99%

Observer-Based Fuzzy Tracking Control for an Unmanned Aerial Vehicle With Communication Constraints

Kong,

Liu,

Zhao

et al. 2024

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

show abstract

“…However, such models also require a set of parameters [10,11] that must be estimated carefully to make the simulation reliable and realistic. Very often, only the energy consumed by the main rotors is considered [12,13]. Neglecting energy consumption by onboard subsystems, this approach might lead to overestimating the real flight duration.…”

Section: Introductionmentioning

confidence: 99%

Validation of the energy consumption model for a quadrotor using Monte-Carlo simulation

Głębocki,

Żugaj,

Jacewicz

2022

Archive of Mechanical Engineering

View full text Add to dashboard Cite

Unmanned, battery-powered quadrotors have a limited onboard energy resources. However, flight duration might be increased by reasonable energy expenditure. A reliable mathematical model of the drone is required to plan the optimum energy management during the mission. In this paper, the theoretical energy consumption model was proposed. A small, low-cost DJI MAVIC 2 Pro quadrotor was used as a test platform. Model parameters were obtained experimentally in laboratory conditions. Next, the model was implemented in MATLAB/Simulink and then validated using the data collected during real flight trials in outdoor conditions. Finally, the Monte-Carlo simulation was used to evaluate the model reliability in the presence of modeling uncertainties. It was obtained that the parameter uncertainties could affect the amount of total consumed energy by less than 8% of the nominal value. The presented model of energy consumption might be practically used to predict energy expenditure, battery state of charge, and voltage in a typical mission of a drone.

show abstract

Energy Saving Quadrotor Control for Field Inspections

Cited by 30 publications

References 35 publications

Soft Ranking Threshold Losses For Image Retrieval

Soft Ranking Threshold Losses For Image Retrieval

Observer-Based Fuzzy Tracking Control for an Unmanned Aerial Vehicle With Communication Constraints

Validation of the energy consumption model for a quadrotor using Monte-Carlo simulation

Contact Info

Product

Resources

About