Explainable Early Activity Recognition via Wearable Inertial Sensors for Human–Robot Collaboration in Agriculture
Open accessThe DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Abstract
In open-field agriculture, timely human activity recognition (HAR) is critical for anticipating worker actions and enabling proactive human–robot collaboration. This study developed an offline early HAR framework based on pre-segmented activity sequences. Long Short-Term Memory (LSTM) networks were used in conjunction with wearable inertial sensors mounted on the chest, cervical region, lumbar region, and right and left wrists. Accelerometer, gyroscope, and magnetometer signals were collected from 20 participants during an outdoor agricultural material-handling task, with a mobile ground robot serving as the receiving platform for the crate. Each activity was represented by cumulative prefixes from 30% to 100% of its duration. At the 30% observation ratio, the model achieved a macro-F1 score of 0.9314, compared with 0.9481 for the full sequence, corresponding to an absolute difference of 0.0167. Shapley Additive Explanations (SHAP) were also used to identify the body locations, sensor modalities, and signal channels that contributed most. The early decisions were mainly supported by sensors placed on the trunk, with wrist sensors providing complementary information, particularly for standing classification. Multimodal inertial information was also important. The most influential inputs were mainly gyroscope and magnetometer channels from the chest, cervical region, and lumbar region. In conclusion, the high performance at early observation ratios highlights the potential to support more adaptive and better-coordinated robot-assistance strategies.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Vision-based navigation and guidance for agricultural autonomous vehicles and robots: A review
Bai, Y., Zhang, B., Xu, N., Zhou, J., Shi, J., & Diao, Z. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107584 · Cited by 353
An Overview of Cooperative Robotics in Agriculture
Lytridis, C., Kaburlasos, V. G., Pachidis, T., Manios, M., Vrochidou, E., Kalampokas, T., & Chatzistamatis, S. (2021) · Agronomy · doi:10.3390/agronomy11091818 · Cited by 169
Approaches and Applications of Early Classification of Time Series: A Review
Gupta, A., Gupta, H. P., Biswas, B., & Dutta, T. (2020) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2020.3027279 · Cited by 167
Safety and ergonomics in human-robot interactive agricultural operations
Benos, L. T., Bechar, A., & Bochtis, D. (2020) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2020.09.009 · Cited by 138
Self-citationBuerkle, A., Eaton, W. C., Lohse, N., Bamber, T., & Ferreira, P. (2021) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2021.102137 · Cited by 127
Inferring Human Intent and Predicting Human Action in Human–Robot Collaboration
Hoffman, G., Bhattacharjee, T., & Nikolaidis, S. (2023) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-071223-105834 · Cited by 121
End-to-end learned early classification of time series for in-season crop type mapping
Rußwurm, M., Courty, N., Emonet, R., Lefèvre, S., Tuia, D., & Tavenard, R. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.12.016 · Cited by 107
Human–robot collaboration systems in agricultural tasks: A review and roadmap
Adamides, G., & Edan, Y. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107541 · Cited by 100
Ding, L., Luo, J., Smith, D. M., Mackey, M. J., Fu, H., Davis, M. M., & Hu, Y. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph19106336 · Cited by 91
Human–Robot Interaction in Agriculture: A Systematic Review
Benos, L. T., Moysiadis, V., Katerıs, D., Tagarakis, A. C., Busato, P., Pearson, S., & Bochtis, D. (2023) · Sensors · doi:10.3390/s23156776 · Cited by 79
Self-citation
Research works printed but not linked: 2
- Sundararajan, M., Taly, A., and Yan, Q. (2017, January 6–11). Axiomatic Attribution for Deep Networks. Proceedings of the 34th International Conference on Machine Learning (ICML), PMLR 70, Sydney, Australia.
- Awad, 2022, Learning Architecture for the Recognition of Walking and Prediction of Gait Period Using Wearable Sensors, Neurocomputing, 470, 1
Metadata
- Authors
- Benos, L., Skordilis, E., Berruto, R., & Bochtis, D.
- Affiliations
- Centre for Research and Technology Hellas (GR)
- University of Miami (US)
- University of Turin (IT)
- Corresponding author
- Benos, Lefteris
- Venue
- Information
- Publisher
- MDPI AG
- Published
- 2026-09-07
- Volume
- 17
- Issue
- 9
- Pages
- 865
- ISSN
- 2078-2489 (ISSN-L)
- OpenAlex
- W7211917291
- Cited by
- 0
- References
- 52
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Information (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Keywords
- human activity recognition, wearable inertial sensors, human-robot collaboration, agricultural robotics, explainable AI, SHAP, LSTM, multimodal sensor fusion, robotic assistance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Explainable Early Activity Recognition via Wearable Inertial Sensors for Human–Robot Collaboration in Agriculture. https://app.cochat.ai/papers/10.3390/info17090865
- The paper
- Benos, L., Skordilis, E., Berruto, R., & Bochtis, D. (2026). Explainable Early Activity Recognition via Wearable Inertial Sensors for Human–Robot Collaboration in Agriculture. Information. https://doi.org/10.3390/info17090865
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.