Robotics for de‐heading fish – a case study

Abstract

Robotic solutions for the handling of food products have been notably absent from suppliers’ catalogues and indeed from research laboratories. This is primarily due to the peculiarities that handling food adds to the general pick‐and‐place task. These are the complexity of handling non‐rigid products that are infinitely variable in shape, the hygiene requirement which stipulates IP65 or better for the hose‐down environment, and the reality that the food industry produces low margin products that only make substantial profits at large volumes, whilst also requiring perfect product presentation to the consumer. In this environment, tasks which have both a short payback and other commercial advantages, such as increased operator safety or improved quality, whilst also being technically feasible, are not immediately obvious.

Robotic manipulation of food products – a review

“…The complete manipulator has a reach of 1 m and stands 2 m tall ( Figure 6). Buckingham et al (2001) described the completed system now called Robofish II. Hall et al (1996) reports on the Silsoe Automatic Milking System (MK I and MK II).…”

Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey

“…Endowing robots with the ability to manipulate deformable objects spawns diverse applications with tremendous economical benefit. For instance, using robots to handle fragile products in the food industry could reduce labor cost (Buckingham et al, 2001; Tokumoto et al, 1999), manufacturing plants could use robots to manipulate flexible objects to lessen physical burden on workers (Acker and Henrich, 2003; Rambow et al, 2012), or robots could become more involved in caregiving activities (e.g. dressing, feeding) for the elderly and disabled (Chen et al, 2013; Yamazaki et al, 2014).…”

An automated salmonid slaughter line using machine vision

“…Previous work on integration of intelligent sensing, robots and end‐effector technology for fish inspection and processing tasks has resulted in several solutions based on machine vision and robots (Arnarson and Khodabandehloo, 1993; White et al , 2006; Buckingham and Davey, 1995; Buckingham et al , 2001). Robofish 1 was developed as a prototype high‐speed, vision‐guided robot (two rotating arms) with an end‐effector (two‐fingered gripper) that is able to grasp slippery fish and accurately place them within a de‐heading machine (Buckingham and Davey, 1995).…”

“…Robofish 1 was developed as a prototype high‐speed, vision‐guided robot (two rotating arms) with an end‐effector (two‐fingered gripper) that is able to grasp slippery fish and accurately place them within a de‐heading machine (Buckingham and Davey, 1995). Further research resulted in Robofish 2, which integrated the cutting and handling tasks identified in Robofish 1 to produce a self‐feeding robotic de‐header (Buckingham et al , 2001). Image processing and statistical pattern recognition methods were used to locate the cutter positioning of gill in pink salmon (Gama et al , 1993), resulting later in an automated machine for fish cutting (de Silva and Wickramarachchi, 1997; Jain et al , 2001; de Silva, 2005).…”