CARPOS

Coachable Robot for Fruit Picking Operations

The project is carried out within the framework of the National Recovery and Resilience Plan Greece 2.0, funded by the European Union - NextGenerationEU (Implementation Body: HFRI)

HFRI Project Number:16523

Results

Public Deliverables:

(All our Public deliverables are availabel at the Project’s Zenodo page here: https://zenodo.org/communities/carpos-hfri)

CARPOS Deliverable 1- Requirements, use-cases and KPIs of CARPOS

CARPOS Deliverable 3 – Fruit Picking Action Identification and Skill Extraction from Visual Observation

CARPOS Deliverable 4 – Control schemes for occlusion-free active perception

CARPOS Deliverable 5-Controller for unintentional and intentional pHRI during the coaching and autonomous operation

CARPOS Deliverable 6 – (Video) Graphical human-machine interface and skill extraction through proprioceptive data

CARPOS Deliverable 7 – Multimodal skill encoding and generalization in fruit geometry variations

CARPOS Deliverable 8 – System Integration and experimental evaluation (Not public yet, as a publication is under preparation)

Publications:

[6]  “ On the Capabilities of LLMs for Classifying and Segmenting Time Series of Fruit Picking Motions into Primitive Actions“, Eleni Konstantinidou, Nikolaos Kounalakis, Nikolaos Efstathopoulos, Dimitrios Papageorgiou, Late Breaking Results Poster at the 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2025), Eindhoven, the Netherlands, Aug 2025. https://arxiv.org/abs/2507.07745

[5] “LAIF: Learning by demonstration through Active Incremental data Fusion of task observations“, Dimitrios Papageorgiou, Nikolaos Efstathopoulos, Yann Angus, Nikolaos Kounalakis, 2025 IEEE International Conference on Imaging Systems and Techniques (IEEE IST 2025), Strasbourg, France, Oct 2025. (https://zenodo.org/records/17814950)

Github repository: https://github.com/CSRL-HMU/AIF-LbD

[4]  “Towards Multi-Modal Learning by Demonstration: Combining Depthless Visual Data with Kinesthetic Teaching“, Dimitrios Papageorgiou, Charalampos Athanasiadis, John Fasoulas, Michael Sfakiotakis, 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2025), Eindhoven, the Netherlands, Aug 2025.

Github repository: CSRL-HMU/viskin

[3]  “ GRAsPAD: Generalized Framework for Optimal Grasp Key-Points Active Detection“, Efstathopoulos, Nikolaos, Kounalakis, Nikolaos, Balaska, Vasiliki, Fasoulas, John, Papageorgiou, Dimitrios, 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2025), Eindhoven, the Netherlands, Aug 2025.

Github repository: CSRL-HMU/GRAsPAD

[2]  “Optimized UKF-Based Perception of a Repetitive Dynamic Event“, Nikolaos Efstathopoulos, Dimitrios Papageorgiou, 23rd European Control Conference (ECC), Thessaloniki, Greece, June 2025.

Github repository: CSRL-HMU/ECC_OPTIMIZED_NBV

[1] “ActIVO: An Active perception framework for skill transfer through Iterative Visual Observations”, Dimitrios Papageorgiou, Nikolaos Kounalakis, Nikolaos Efstathopoulos, John Fasoulas, Michael Sfakiotakis, at the 32nd Mediterranean Conference on Control and Automation (MED 2024), Chania, Greece.

Github reposiory: CSRL-HMU/ActIVO