Non-Destructive Robotic Assessment of Mango Ripeness via Multi-Point Soft Haptics

Abstract

To match the ever increasing standards of fresh products, and the need to reduce waste, we devise an alternative to the destructive and highly variable fruit ripeness estimation by a penetrometer. We propose a fully automatic method to assess the ripeness of mango which is non-destructive, allows the user to test multiple surface areas with a single touch and is capable of dissociating between ripe and non-ripe fruits. A custom-made gripper equipped with a capacitive tactile sensor array is used to palpate the fruit. The ripeness is estimated as mango stiffness extracted through a simplified spring model. We test the framework on a set of 25 mangoes of the Keitt variety, and compare the results to penetrometer measurements. We show it is possible to correctly classify 88% of the mango without removing the skin of the fruit. The method can be a valuable substitute for non-destructive fruit ripeness testing. To the authors knowledge, this is the first robotics ripeness estimation system based on capacitive tactile sensing technology.

Cloaking by coating: how effectively does a thin, stiff coating hide a soft substrate?

“…How does one tell when a piece of fruit is ripe? While for fruits such as tomatoes and bananas colour alone is a reliable indicator of ripeness [19,25], everyday experience suggests that for fruits including plums [23] and mangoes [24,25], one must instead 'poke' the fruit: if the fruit is soft then it is ripe, while if relatively stiff the flesh is not yet ripe. Of course, how soft is soft enough depends on the type of fruit and is knowledge gained by experience.…”

“…A common strategy producers use for measurements of ripeness is a mechanized version of the poking test used by consumers: the force required to impose a given indentation depth via a cylindrical punch is measured and the resulting stiffness is then correlated to the ripeness. Particular protocols have been proposed for fruits including apples [6,9], plums [23], pumpkins [7], mangoes [24,25], oranges and tomatoes [19].…”

Electronic skins and machine learning for intelligent soft robots

“…(A) A range of e-skins and soft sensors that increase in complexity, from bottom to top, by metrics including density, resolution, and fabrication (2)(3)(4)(5)(6)(7)(8). (B) Soft robots and e-skins that merge actuation and sensing (9)(10)(11)(12)(13)(14)(15)(16)(17)(18)(19)(20)(21), from left to right and top to bottom. (C) A range of soft robots, from left to right, focused primarily on actuation and mechanisms (22)(23)(24)(25)(26).…”

Smart fingertip sensor for food quality control: Fruit maturity assessment with a magnetic device

“…Various tactile sensors have been reported for fruit quality assessment [7]: a tactile sensor with piezoelectric films and strain gauges was used to evaluate and classify the surface roughness of cucumbers, cantaloupes and apples, achieving a 94% accuracy [8]. A sensor consisting of a gripper with a capacitive tactile sensor array correctly classified 88% of the mangoes according to their ripeness stage [9]. Tactile sensors inspired by the extremely sensitive mechanosensorial hair-like cilia receptors found in nature consist of an artificial cilia array inserted over a magnetic sensing element.…”