Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data
This paper presents three different machine-learning techniques to predict the payloads of DJI Matrice 100 quadcopter drones. The tracking data is based on real-life experimentation that is provided as open source. The payloads are 0.0, 250, 500, and 750 grams. The Machine Learning techniques are LS...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , |
| منشور في: |
2024
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://depot.sorbonne.ae/handle/20.500.12458/1593 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1857415065151471616 |
|---|---|
| author | Kashkash, Mariam |
| author2 | Seghrouchni, Amal El Fallah Barbaresco, Frederic Abu Zitar, Raed |
| author2_role | author author author |
| author_facet | Kashkash, Mariam Seghrouchni, Amal El Fallah Barbaresco, Frederic Abu Zitar, Raed |
| author_role | author |
| dc.creator.none.fl_str_mv | Kashkash, Mariam Seghrouchni, Amal El Fallah Barbaresco, Frederic Abu Zitar, Raed |
| dc.date.none.fl_str_mv | 2024-05-15T07:16:14Z 2024-05-15T07:16:14Z 2024 |
| dc.identifier.none.fl_str_mv | https://depot.sorbonne.ae/handle/20.500.12458/1593 10.1109/AERO58975.2024.10521302 |
| dc.language.none.fl_str_mv | en |
| dc.relation.none.fl_str_mv | 2024 IEEE Aerospace Conference |
| dc.subject.none.fl_str_mv | Training Machine learning Kinematics Predictive models Data models Long short term memory Payloads |
| dc.title.none.fl_str_mv | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data |
| dc.type.none.fl_str_mv | Controlled Vocabulary for Resource Type Genres::text::conference object::conference proceedings |
| description | This paper presents three different machine-learning techniques to predict the payloads of DJI Matrice 100 quadcopter drones. The tracking data is based on real-life experimentation that is provided as open source. The payloads are 0.0, 250, 500, and 750 grams. The Machine Learning techniques are LSTM, TCN, and GRU. The values of the tracks’ kinematics come from several different flights for the different loads. The tracks’ kinematics in addition to some flight parameters are used in training the three models. The temporal nature of the data values triggers the need for machine learning methods that use history/memory as part of inputs. The input variables went through the data reduction stage as some variables turned out to be less relevant than others for the prediction operation. The original data has more than 1400 records for every flight with more than 22 variable values. More than 270 flights were conducted with the 4 payloads. The flight/track data is accessed in parallel at every time stamp by the learning models and the model converges after a few epochs to the payload label. The training/validation/testing values show that the three models captured the predicted load efficiently. Comparisons between the three models as predictors for the carried payloads are presented and discussed in the paper. The TCN showed slight superiority over the other models |
| id | sorbonner_8e7fdedab290587d657ad375f2a19a5d |
| identifier_str_mv | 10.1109/AERO58975.2024.10521302 |
| language_invalid_str_mv | en |
| network_acronym_str | sorbonner |
| network_name_str | Sorbonne University Abu Dhabi repository |
| oai_identifier_str | oai:depot.sorbonne.ae:20.500.12458/1593 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking DataKashkash, MariamSeghrouchni, Amal El FallahBarbaresco, FredericAbu Zitar, RaedTrainingMachine learningKinematicsPredictive modelsData modelsLong short term memoryPayloadsThis paper presents three different machine-learning techniques to predict the payloads of DJI Matrice 100 quadcopter drones. The tracking data is based on real-life experimentation that is provided as open source. The payloads are 0.0, 250, 500, and 750 grams. The Machine Learning techniques are LSTM, TCN, and GRU. The values of the tracks’ kinematics come from several different flights for the different loads. The tracks’ kinematics in addition to some flight parameters are used in training the three models. The temporal nature of the data values triggers the need for machine learning methods that use history/memory as part of inputs. The input variables went through the data reduction stage as some variables turned out to be less relevant than others for the prediction operation. The original data has more than 1400 records for every flight with more than 22 variable values. More than 270 flights were conducted with the 4 payloads. The flight/track data is accessed in parallel at every time stamp by the learning models and the model converges after a few epochs to the payload label. The training/validation/testing values show that the three models captured the predicted load efficiently. Comparisons between the three models as predictors for the carried payloads are presented and discussed in the paper. The TCN showed slight superiority over the other models2024-05-15T07:16:14Z2024-05-15T07:16:14Z2024Controlled Vocabulary for Resource Type Genres::text::conference object::conference proceedingshttps://depot.sorbonne.ae/handle/20.500.12458/159310.1109/AERO58975.2024.10521302en2024 IEEE Aerospace Conferenceoai:depot.sorbonne.ae:20.500.12458/15932024-05-15T07:21:45Z |
| spellingShingle | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data Kashkash, Mariam Training Machine learning Kinematics Predictive models Data models Long short term memory Payloads |
| title | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data |
| title_full | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data |
| title_fullStr | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data |
| title_full_unstemmed | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data |
| title_short | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data |
| title_sort | Temporal Machine Learning Payload Prediction for DJI Matrice 100 Quadcopter Drone Based on Tracking Data |
| topic | Training Machine learning Kinematics Predictive models Data models Long short term memory Payloads |
| url | https://depot.sorbonne.ae/handle/20.500.12458/1593 |