Efficient Fine-Grained Object Detection
for Robot-Assisted WEEE Disassembly
Ioannis Athanasiadis
(B) , Athanasios Psaltis, Apostolos Axenopoulos,
and Petros Daras
Centre for Research and Technology Hellas, Thessaloniki, Greece
johnyath@gmail.com
Abstract. In the current study, a region-based approach for object
detection is presented that is suitable for handling very small objects and
objects in low-resolution images. To address this challenge, an anchoring
mechanism for the region proposal stage of the object detection algorithm is proposed, which boosts the performance in the detection of
small objects with an insignificant computational overhead. Our method
is applicable to the task of robot-assisted disassembly of Waste Electrical
and Electronic devices (WEEE) in an industrial environment. Extensive
experiments have been conducted in a newly formed device disassembly
segmentation dataset with promising results.
Keywords: Human-robot collaboration · WEEE disassembly · Small
object detection
1 Introduction
Human-robot collaboration has been recently introduced in industrial environments, where the fast and precise, but at the same time dangerous, traditional
industrial robots have started being replaced with industrial collaborative robots
for disassembling of WEEE in WEEE recycling plants [1]
1 . The rationale behind
the selection of the latter is to combine the endurance and precision of the
robot with the dexterity and problem-solving ability of humans. An advantage of
industrial collaborative robots (or cobots) is that they can coexist with humans
without the need to be kept behind fences. Cobots can be utilised in numerous industrial tasks for automated parts assembling. In the context of the EUfunded project HR-Recycler, industrial collaborative robots are introduced for
disassembling of WEEE in WEEE recycling plants. Due to the complexity and
high variability of devices, the fully-robotised disassembly is not feasible, thus, a
human-robot collaboration scenario is much appreciated. The robot will be able
to unscrew, cut or grasp the constituting parts of an electronic device and put
them to separate baskets, depending on their type (e.g. capacitors, batteries,
PCBs, etc). In this direction, Computer Vision is necessary to assist the robot’s
1 https://www.hr-recycler.eu/.
c
Springer Nature Switzerland AG 2020
V. Vouloutsi et al. (Eds.): Living Machines 2020, LNAI 12413, pp. 17–22, 2020.
https://doi.org/10.1007/978-3-030-64313-3_3
for Robot-Assisted WEEE Disassembly
Ioannis Athanasiadis
(B) , Athanasios Psaltis, Apostolos Axenopoulos,
and Petros Daras
Centre for Research and Technology Hellas, Thessaloniki, Greece
johnyath@gmail.com
Abstract. In the current study, a region-based approach for object
detection is presented that is suitable for handling very small objects and
objects in low-resolution images. To address this challenge, an anchoring
mechanism for the region proposal stage of the object detection algorithm is proposed, which boosts the performance in the detection of
small objects with an insignificant computational overhead. Our method
is applicable to the task of robot-assisted disassembly of Waste Electrical
and Electronic devices (WEEE) in an industrial environment. Extensive
experiments have been conducted in a newly formed device disassembly
segmentation dataset with promising results.
Keywords: Human-robot collaboration · WEEE disassembly · Small
object detection
1 Introduction
Human-robot collaboration has been recently introduced in industrial environments, where the fast and precise, but at the same time dangerous, traditional
industrial robots have started being replaced with industrial collaborative robots
for disassembling of WEEE in WEEE recycling plants [1]
1 . The rationale behind
the selection of the latter is to combine the endurance and precision of the
robot with the dexterity and problem-solving ability of humans. An advantage of
industrial collaborative robots (or cobots) is that they can coexist with humans
without the need to be kept behind fences. Cobots can be utilised in numerous industrial tasks for automated parts assembling. In the context of the EUfunded project HR-Recycler, industrial collaborative robots are introduced for
disassembling of WEEE in WEEE recycling plants. Due to the complexity and
high variability of devices, the fully-robotised disassembly is not feasible, thus, a
human-robot collaboration scenario is much appreciated. The robot will be able
to unscrew, cut or grasp the constituting parts of an electronic device and put
them to separate baskets, depending on their type (e.g. capacitors, batteries,
PCBs, etc). In this direction, Computer Vision is necessary to assist the robot’s
1 https://www.hr-recycler.eu/.
c
Springer Nature Switzerland AG 2020
V. Vouloutsi et al. (Eds.): Living Machines 2020, LNAI 12413, pp. 17–22, 2020.
https://doi.org/10.1007/978-3-030-64313-3_3