Skip to main content

Self-reconfiguration of a robotic workcell for the recycling of electronic waste

Periodic Reporting for period 1 - ReconCycle (Self-reconfiguration of a robotic workcell for the recycling of electronic waste)

Reporting period: 2020-01-01 to 2021-03-31

Currently electro-recycling is still mostly performed following the crude “crush-and-separate” method, where devices are crushed and split into tiny particles, which are then physio-chemically separated into reusable components. Many times, this requires manual work to remove dangerous components or to disassemble sub-parts that cannot go into the crusher. Recycling companies are here faced with tons of material that arrive in different states of damage. The manual pre-processing of this kind constitutes a major (cost-)effort. An inappropriate “alternative” for this is currently still to ship waste to developing countries and abuse their cheap labour to address these problems (or let the waste just be dumped there). Clearly, there is a very strong incentive to improve on this and this way increase profitability, efficiency, and positive environmental impact of recycling and, thus, even partial automation of some of these steps can make a big difference.

One specificity of electronic recycling is that usually many different models of the same type but in vastly different conditions need to be disassembled. Thus, in this domain we have to deal with large batches of the same type of device, which limits variability at least to some degree, but we are at the same time confronted with many different models within any given device-type and the fact that they are in vastly different conditions, which requires a flexible robotic system that adapts to these circumstances. As a consequence, electronic waste recycling offers an ideal test-bed for self-reconfiguration of robotic cells as the complexity of the required changes within a given device-type is not too high.

The aim of the project is to introduce self-reconfigurable hardware and software for disassembly of electronic devices. A two-step procedure is foreseen:
a) When changing from one device-type to another, the reconfiguration shall be performed in an interactive mode, where the application-engineer will be able to provide his/her input.
b) When changing from one device-model to another within a given device-type, the cell shall perform re-configuration (predominantly) on its own through a combination of sensorimotor learning approaches and other AI techniques.
The challenge of this is to provide methodologies for re-design of the recycling cell and approaches for fast re-programming, re-use and adaptation of manipulation actions for disassembly with soft robots and grippers.
We started our work with the development of hardware and software setup to implement the first solutions for the disassembly of electronic devices. Towards this goal, we developed The reconCycle archetypical module. This module provides the basis to implement a variety of specific modules from which different variants of disassembly cell can be quickly constructed. Several specific modules were developed: "Robot module" (equipped with Franka Emika Panda manipulator and qb SoftHand Research gripper), "Vise module", and "Cutter module". To easily connect different modules, we developed a new Plug-and-Produce (PnP) connector. The centre piece of the PnP connector is its power and data pass-through unit that enables all modules in the cell to use power and share data. In parallel with the hardware developments, we also worked on the development of modular ROS-based software architecture to control the cell. The developed architecture supports quick exchange and reconfiguration of modules in the cell, communication between modules and their control. It also supports the programming of skills by manual guidance as well as task-level programming based on a FlexBE behaviour engine with a graphical user interface.

An important line of research was the development of computer vision procedures for pose detection and geometric scene description of electronic devices to be recycled. The developed software currently supports the detection of heat cost allocators and their components. It is based on the Yolact neural network to implement instance segmentation. The implemented software is ready for integration with the rest of the ReconCycle control software.

In the area of tactile manipulation skill definition, we worked on unifying motion trajectories and force profiles in order to achieve more adaptable and flexible manipulation capabilities. We also developed a unified force-impedance control for tactile skills, where precise force tracking is important. The availability of such operations should improve the effectiveness of robots in the ReconCycle cell and increase safety.

In ReconCycle, the manipulation of possibly damaged objects is supported by utilizing soft grippers and tools, more specifically qb SoftHand. Although the current qb SoftHand is suitable to fulfil many of the disassembly procedures relevant for recycling, some changes could bring important improvements that can be beneficial in terms of grasp adaptability, precise interaction with small parts and in hand-manipulation capabilities. For this purpose, we integrated an articulated and adaptive palm into the SoftHand design. To provide also inexpensive soft robotics solutions for disassembly tasks, we furthermore developed new qb Soft Gripper that can handle both heavy and fragile objects.

The developed hardware and methods were integrated to provide the first implementation of a reconfigurable, modular recycling cell. We analyzed in detail the manual disassembly of a typical heat cost allocator and identified the necessary robotic operations that need to be available to automate the dismantling process in the proposed cell. An important achievement of the project in the first reporting period was the practical implementation of this automated procedure in the real recycling cell.
While ReconCycle is still in relatively early stage of development, progress beyond the state of the art can already been observed in several areas of development. A new hardware and software architecture for recycling cells has been developed, with support for modularity and reconfigurability both in hardware and software. This should enable the disassembly of a variety of devices and models for recycling purposes for the first time. Progress beyond the state of the art has already been shown also in the design of soft hands, tools, and grippers suitable for disassembly of electronic devices, which are important for the area of soft robotics in general.

In the first reporting period, ReconCycle laid the groundwork to address the main scientific issues of ReconCycle: the development of partially automated methodologies for re-design of the recycling cell to enable switching of the disassembly procedure from one electronic device to another and the development of approaches for fast re-programming and adaptation of disassembly with soft robots and grippers. These main research issues will be addressed in the next stage of the project.

From the application point of view, ReconCycle aims to substantially reduce human effort and increase accuracy and efficiency of recycling. As ReconCycle uses highly compliant robots, humans will be able to operate together with the machines to complete the missing steps. This reduces the automation complexity further and brings this project into a feasible regime. The first disassembly procedures for recycling have already been demonstrated in the proposed cell.
ReconCycle modular, reconfigurable robotic cell