This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Imitation Learning from a Single Demonstration Leveraging Vector Quantization for Robotic Harvesting
by
Antonios Porichis
Antonios Porichis 1,2,*,
Myrto Inglezou
Myrto Inglezou 1
,
Nikolaos Kegkeroglou
Nikolaos Kegkeroglou 3
,
Vishwanathan Mohan
Vishwanathan Mohan 1 and
Panagiotis Chatzakos
Panagiotis Chatzakos 1
1
AI Innovation Centre, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK
2
National Structural Integrity Research Centre, Granta Park, Great Abington, Cambridge CB21 6AL, UK
3
TWI-Hellas, 280 Kifisias Ave., 152 32 Halandri, Greece
*
Author to whom correspondence should be addressed.
Robotics 2024, 13(7), 98; https://doi.org/10.3390/robotics13070098 (registering DOI)
Submission received: 9 May 2024
/
Revised: 21 June 2024
/
Accepted: 23 June 2024
/
Published: 30 June 2024
Abstract
The ability of robots to tackle complex non-repetitive tasks will be key in bringing a new level of automation in agricultural applications still involving labor-intensive, menial, and physically demanding activities due to high cognitive requirements. Harvesting is one such example as it requires a combination of motions which can generally be broken down into a visual servoing and a manipulation phase, with the latter often being straightforward to pre-program. In this work, we focus on the task of fresh mushroom harvesting which is still conducted manually by human pickers due to its high complexity. A key challenge is to enable harvesting with low-cost hardware and mechanical systems, such as soft grippers which present additional challenges compared to their rigid counterparts. We devise an Imitation Learning model pipeline utilizing Vector Quantization to learn quantized embeddings directly from visual inputs. We test this approach in a realistic environment designed based on recordings of human experts harvesting real mushrooms. Our models can control a cartesian robot with a soft, pneumatically actuated gripper to successfully replicate the mushroom outrooting sequence. We achieve 100% success in picking mushrooms among distractors with less than 20 min of data collection comprising a single expert demonstration and auxiliary, non-expert, trajectories. The entire model pipeline requires less than 40 min of training on a single A4000 GPU and approx. 20 ms for inference on a standard laptop GPU.
Share and Cite
MDPI and ACS Style
Porichis, A.; Inglezou, M.; Kegkeroglou, N.; Mohan, V.; Chatzakos, P.
Imitation Learning from a Single Demonstration Leveraging Vector Quantization for Robotic Harvesting. Robotics 2024, 13, 98.
https://doi.org/10.3390/robotics13070098
AMA Style
Porichis A, Inglezou M, Kegkeroglou N, Mohan V, Chatzakos P.
Imitation Learning from a Single Demonstration Leveraging Vector Quantization for Robotic Harvesting. Robotics. 2024; 13(7):98.
https://doi.org/10.3390/robotics13070098
Chicago/Turabian Style
Porichis, Antonios, Myrto Inglezou, Nikolaos Kegkeroglou, Vishwanathan Mohan, and Panagiotis Chatzakos.
2024. "Imitation Learning from a Single Demonstration Leveraging Vector Quantization for Robotic Harvesting" Robotics 13, no. 7: 98.
https://doi.org/10.3390/robotics13070098
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.