Smart Tooling focusses on automation in the process industry: making maintenance safer, cheaper, cleaner, and more efficient by developing new robot prototypes and tools. For example, robots that clean and inspect areas that are hard or impossible to reach for humans. The R&D topics are inspection robots, cleaning robots, shared workspace robots (cobots), and unmanned aerial systems (UAS).
Robot technology is an important development in the maintenance industry, but because it is relatively new there are many uncertainties and many unresearched possibilities. Smart Tooling provides funding to small companies to stimulate robot technology innovation and development in the Flanders-The Netherlands region.
Smart Tooling is an Interreg Flanders-Netherlands project sponsored by the European Union.
Smart Tooling is coordinated by Knowledge and Innovation Center for Maintenance in the Processindustry (Ki<|MPi), and is a collaboration of partners from industry (engineering companies, inspection companies, asset owners) and academia.
- Avans University of Applied Sciences (Avans Hogeschool)
- BEMAS - Belgian Maintenance Association vzw
- BASF Antwerpen
- BOM Business Development & Foreign Investments B.V.
- Dow Benelux B.V.
- N.V. Economische Impuls Zeeland (Impuls)
- REWIN Projects BV
- University of Gent
- University of Twente (that’s us!)
Role of RaM in the project
The focus of RaM’s work in Smart Tooling is on autonomous inspection of industrial pipelines. Typical inspection tasks are locating defects and deformations, and verifying the wall thickness. Pipelines with turns, splits, or with sections with varying diameter cannot be inspected by a PIG (Pipeline Inspection Gauge). Currently, the whole inspection process of such pipes is performed manually by technicians, but the technician doesn’t fit inside these pipes and thus the pipe is inspected from the outside. However, the pipe may be covered with isolation layers which need to be removed first, only to discover that there are no damages (e.g. rust) beneath the isolation layers.
The solution RaM is working on is a robot that can be placed inside the pipe to carry out the inspection. This way, the technicians only have to check and repair the points of interest that the robot detected.
Simultaneous Localization and Mapping
The first step is to be able to localize the robot in the pipeline network with good accuracy in order to locate the defects found during the inspection. The localization problem is usually tightly connected with the map of the environment in which the robot has to localize itself in. Thus, Simultaneous Localization and Mapping algorithms (SLAM) are employed to reconstruct 2D/3D maps of the pipeline networks and simultaneously estimate the robot location.
Navigation in the pipeline network
To perform the inspection, the robot has to be able to autonomously navigate in the pipeline network. One of the biggest challenges is the navigation through sharp corners because of the complex sequence of actions that the robot has to carry out. To tackle this problem two approaches are used:
- Finite state machine and motion primitives: high level control actions, called motion primitives ( i.e. clamp, unclamp, drive, bend, rotate, turn, etc), are selected based on the sensor readings (i.e. measurements from LiDAR sensor and encoders). A motion primitive corresponds to the sequence of motors commands required to achieve a specific behavior. Currently we are working on travelling 90 degrees sharp turns, using only the on-board sensors (i.e. wheels and joints encoders and LiDAR).
- Machine learning techniques: to increase the robustness of the motion through different sharp corners, machine learning algorithms are used. Currently, the PIRATE can navigate through corners with angle from 60 to 120 degrees and diameter from 90 to 120 mm. The results obtain so far are achieved on a simulation platform and further tests will be done on the real robot.
In order to perform autonomous inspection a lot of steps need to be done on the robot “brain” and we will work mainly in that direction, but not only.
We are currently working on:
- Improving the simulation model of the robot in the pipeline network.
- On-board sensing for perceiving the environment and gather inspection measurements (e.g. wall thickness measurements).
- AI and learning approaches for making the robot more autonomous and smarter.
We are always looking for very motivated students (BSc or MSc) that want to dive in the awesome world of robotics. Interested students can contact Nicolò Botteghi (firstname.lastname@example.org) for available assignments.