Mechanical Interaction Sensing for Robotic Kiwifruit Handling with an Optoelectronic Soft Suction Cup
Overview
This research presents an optoelectronic soft suction cup designed for handling delicate kiwifruit, capable of accurately estimating mechanical interaction forces during contact. The system achieves a grouped out-of-fold pooled R-squared of 0.968 with a mean absolute error of 0.138 N using a shallow network, and maintains strong performance (R-squared = 0.955) when validated across different collection days. While binary soft/firm classification shows moderate accuracy, finer grading tasks remain challenging.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · R-squared: 0.968 other · Basis not reported · Differing source assertions
“ely estimate interaction force on fruits excluded from model training: the best shallow network achieves grouped out-of-fold pooled R-squared = 0.968 +/- 0.005 (MAE = 0.138 N), with a median per-fruit held-out R-squared = 0.973 (MAE = 0.134 N). A simple monotonic mapping from the mean optical response alone achieves R-squared = 0.925 +/- 0.005, showing that substantial force-related information is already present in”
Exact source · revision 1Source owner not reported
Reported quantity · Mean Absolute Error: 0.138 other · Basis not reported · Differing source assertions
“ely estimate interaction force on fruits excluded from model training: the best shallow network achieves grouped out-of-fold pooled R-squared = 0.968 +/- 0.005 (MAE = 0.138 N), with a median per-fruit held-out R-squared = 0.973 (MAE = 0.134 N). A simple monotonic mapping from the mean optical response alone achieves R-squared = 0.925 +/- 0.005, showing that substantial force-related information is already present in”
Exact source · revision 1Source owner not reported
Reported quantity · R-squared: 0.973 other · Basis not reported · Differing source assertions
“ely estimate interaction force on fruits excluded from model training: the best shallow network achieves grouped out-of-fold pooled R-squared = 0.968 +/- 0.005 (MAE = 0.138 N), with a median per-fruit held-out R-squared = 0.973 (MAE = 0.134 N). A simple monotonic mapping from the mean optical response alone achieves R-squared = 0.925 +/- 0.005, showing that substantial force-related information is already present in”
Exact source · revision 1Source owner not reported
Reported quantity · Mean Absolute Error: 0.134 other · Basis not reported · Differing source assertions
“ely estimate interaction force on fruits excluded from model training: the best shallow network achieves grouped out-of-fold pooled R-squared = 0.968 +/- 0.005 (MAE = 0.138 N), with a median per-fruit held-out R-squared = 0.973 (MAE = 0.134 N). A simple monotonic mapping from the mean optical response alone achieves R-squared = 0.925 +/- 0.005, showing that substantial force-related information is already present in”
Exact source · revision 1Source owner not reported
Reported quantity · R-squared: 0.925 other · Basis not reported · Differing source assertions
“ely estimate interaction force on fruits excluded from model training: the best shallow network achieves grouped out-of-fold pooled R-squared = 0.968 +/- 0.005 (MAE = 0.138 N), with a median per-fruit held-out R-squared = 0.973 (MAE = 0.134 N). A simple monotonic mapping from the mean optical response alone achieves R-squared = 0.925 +/- 0.005, showing that substantial force-related information is already present in”
Exact source · revision 1Source owner not reported
Reported quantity · R-squared: 0.955 other · Basis not reported · Differing source assertions
“the optical response. Leave-one-collection-day-out validation remains strong (R-squared = 0.955 +/- 0.031), supporting robustness across acquisition sessions. As an exploratory secondary analysis, binary Soft/Firm classification from compression-test reference labels achieves moderate balanced accuracy (approximately 0.705) under grouped held-out-fruit validation, while finer three-class grading shows limited perform”
Exact source · revision 1Source owner not reported
Reported quantity · Balanced Accuracy: 0.705 other · Basis not reported
“the optical response. Leave-one-collection-day-out validation remains strong (R-squared = 0.955 +/- 0.031), supporting robustness across acquisition sessions. As an exploratory secondary analysis, binary Soft/Firm classification from compression-test reference labels achieves moderate balanced accuracy (approximately 0.705) under grouped held-out-fruit validation, while finer three-class grading shows limited perform”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalMechanical Interaction Sensing for Robotic Kiwifruit Handling with an Optoelectronic Soft Suction Cup
This research presents an optoelectronic soft suction cup designed for handling delicate kiwifruit, capable of accurately estimating mechanical interaction forces during contact. The system achieves a grouped out-of-fold pooled R-squared of 0.968 with a mean absolute error of 0.138 N using a shallow network, and maintains strong performance (R-squared = 0.955) when validated across different collection days. While binary soft/firm classification shows moderate accuracy, finer grading tasks remain challenging.
Event coverage history
Current attention 3·Peak within the comparable range 4（2026-11-10 11:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).