Heriot-Watt University Develops Autonomous Environments for Offshore Energy Sector

0
1920

The rising want for vital infrastructure and expertise as a service has fuelled a worldwide demand for good methods throughout all sectors of trade. Organizations want to increase their workforce with instruments to extend productiveness, effectivity, and create safer workplaces by way of evaluation and eradicating individuals from hazardous conditions. 

The Smart Systems Group from the Heriot-Watt University in Edinburgh is working to advertise sustainability and to create resilience in methods, organizations, networks, and societies. Their tasks embody collaboration with a worldwide community of educational and industrial companions to ship the flexibleness, resilience, and sustainability that our world infrastructure requires. The work was accomplished in collaboration with the Offshore Robotics for the Certification of Assets (ORCA) Hub, MicroSense Technologies Ltd, and Offshore Renewable Energy Catapult. The cluster of this work was pushed by the business wants of the offshore vitality sector.

FMCW Radar inspection paired with two UR5 manipulators finishing raster scan for detection of corrosion (left), FMCW deployed on autonomous confined area inspection mission on the pan-tilt unit on the entrance on the OREC facility (proper).

Developing a Connected, Collaborative Environment

The workforce’s challenge, titled “Symbiotic System Design for Safe and Resilient Autonomous Robotics” is using Husky UGV to create resilient and protected autonomous companies for the offshore vitality sector. To do that, the Smart Systems Group designed a “Symbiotic Digital Architecture” (SDA) that linked individuals, infrastructure, the surroundings, and robotics right into a hyper-enabled collaborative surroundings. Their challenge addressed three key features:

  • Using robotic assistants to take away individuals from hazardous environments
  • Unlocking the worth of autonomous companies for more practical asset integrity administration operations by way of advances in mission resilience utilizing improved situational consciousness and run-time reliability evaluation
  • Creating an SDA that might be transferred to different missions and robotic platforms to speed up the adoption of reliable autonomous service

 

But as is pure on this planet of analysis and improvement, such an formidable challenge had a number of concerns concerning previous innovation and the objectives that the workforce was trying to meet. To start, they needed to set up the best way to couple human information and expertise right into a collaborative partnership with autonomous methods, whereas additionally monitoring a dynamic vary of variables throughout elements resembling environmental circumstances, human interplay, robotic platform reliability, and dynamic security circumstances. 

Next, to enhance “foresight” to modifications within the mission surroundings, the workforce created a patented radar expertise for the detection of obstacles outdoors of the mission area (e.g. individuals behind partitions approaching some extent of room entry throughout run-time autonomous inspections). To assist such features, additionally they created a sensor that might detect individuals and objects in opaque environments. Finally, for asset integrity inspection inside a confined area, the workforce used radar expertise and AI evaluation.

 

Husky UGV Enables SDA Design

The use of an out-of-the-box robotic platform like Husky UGV allowed the workforce to check and develop many core options of their challenge. The Symbiotic Digital Architecture (SDA) helps the mixing of distributed methods and human-in-the-loop observers, to exhibit augmented run-time operational reliability and security compliance. 

The design of their SDA incorporates the advanced mission variables throughout environmental circumstances, security circumstances, mission aims, robotic platform state of well being, infrastructure necessities, and distant human observer queries. It allows close to to real-time and bidirectional communication and knowledge alternate throughout all mission property. Through these design options, the system has the potential to include 1000 totally different property e.g. sensors, actuators, robots, and many others!

Husky UGV additionally enabled the SDA and its functions:

  • A digital twin of the robotic asset converts diagnostic info from the run-time reliability ontology into human-readable actionable details about the well being and fault standing of the robotic platform. A 3D mannequin of Husky UGV with a pair of manipulators was accessible to make use of which was extremely adaptable for their system. The workforce may color code the mannequin to make sure that faults might be simply considered by the operator.
  • A ghosting perform for the manipulators to simulate the trajectories of the arms earlier than committing the motion to the real-world asset to reduce danger and enhance belief for a distant operator. Due to the accuracy of the 3D mannequin created, the workforce may implement their ghosting perform on the mannequin within the artificial surroundings and for the robotic within the real-world. This allowed for the arms to be managed from the dual and mirror the real-world asset.
  • The description and integration of a novel inspection answer – Frequency Modulated Continuous Wave (FMCW) that helps multipurpose necessities, particularly, floor and subsurface asset integrity inspection, security compliance, and collision avoidance in poor visibility. The extremely customizable structure of Husky UGV enabled the workforce to simply combine their novel sensing unit with the robotic. They may place the sensor on the pan-tilt unit or on the manipulators. Husky UGV’s structure additionally meant that the researchers may retailer their information onboard Husky UGV and/or ship the information collected straight to the digital twin.
  • Validation of the resilient autonomous mission utilizing an integration of applied sciences throughout the SDA in a confined area asset integrity mission. The ontology might be built-in and linked with the workforce’s digital twin the place the datasheets for Husky UGV had been broadly accessible and had loads of info for the workforce to arrange the fault and warning thresholds. The AI-assisted ontology then had extra info to make the most of when autonomously detecting faults and relaying the warnings again to the human-in-the-loop within the digital twin.

 

Demonstration of the robotic’s “ghost twin”, exhibiting the deliberate place of the manipulator as a light manipulator and present place of manipulator (left) and augmented actuality interface (proper)

Husky UGV supplied a suitable interoperable platform that supported the workforce’s technology-agnostic method to the design, implementation, and analysis of our SDA. Its extremely customizable structure supported the mixing of their novel security and asset integrity sensing expertise – FMCW radar. Ultimately then, Husky UGV allowed the workforce to create a case examine to indicate that their symbiotic system and self-certification framework are platform agnostic.

Creating a Dynamic Simulation Environment

The major features of this workforce’s challenge included the collective aim of asset integrity inspection within the difficult offshore surroundings analogue utilized for their demonstration. In addition to core mission waypoints and aims, the workforce launched three main system points to simulate modifications within the working surroundings, ensuing within the want for the robotic platform to repeatedly reassess the mission and system standing; to judge the core goal of returning safely to the bottom station. 

In doing so, the workforce demonstrated an ‘adapt and survive’ situation, the place the dynamic circumstances imposed on the cellular robotic platform created the necessity for the onboard AI-assisted decision-making core to generate a constantly updating system. This reliability management system could be able to making certain that the robotic asset can accomplish processes resembling figuring out limitations to the success of the mission utilizing built-in sensing or providing options to the computational decision-making parts, represented by each the AI and/or the human-in-the-loop operator.

The profitable integration of the symbiotic system parts ensures that the robotic platform is at all times able to finishing its mission below optimum circumstances or stays able to assessing when the platform ought to replan and return to base when circumstances grow to be much less favorable. At the core of this work is the necessity for the robotic platform to exhibit resilience whereas working autonomously and completely throughout the envelope of security compliance. Husky UGV can function in a variety of environmental circumstances, rising the uptime of the system.

“The platform provides a scalable and modular architecture to readily customize the robotic platform to a range of mission requirements. Using such a robust off-the-shelf system allowed us to demonstrate to decision-makers the significant advancements our research had made on the challenges of run-time safety compliance and reliability of robotic platforms.”

Professor David Flynn

The SDA Loadout

To get this challenge up and operating, the Husky UGV was geared up with a pair of UR-5 manipulators, a 16 beam Velodyne 3D LIDAR and a low-mounted SICK 2D LIDAR sensor. For asset integrity inspection and to assist navigation in opaque circumstances, they geared up a FMCW radar. Furthermore, they put in run-time reliability ontology onboard the platform and utilized a Microsoft HoloLens for augmented actuality prognosis of faults with entry to the digital twin.

Design of the resilient symbiotic methods framework

Without the Clearpath robotic improvement platform, nonetheless, the Smart Systems Group would have been compelled to create a robotic platform from scratch or buy one other sort of robotic platform which can not have the mechanical and software program elements they required. The former method, although, could be pricey and time-consuming. 

Instead, by utilizing a tried and examined platform, the workforce may get straight into creating and growing additional options, in the end making certain that their analysis efforts are strategically utilized to key areas for development. The latter method might have created potential issue in mounting their sensors and deploying their system in a variety of situations.

The workforce selected Husky UGV because it simplified the mixing of sensors, permitting the workforce to deal with growing their symbiotic system software program. As properly, Professor David Flynn spoke about its easy-to-use utility:  “The platform provides a scalable and modular architecture to readily customize the robotic platform to a range of mission requirements. Using such a robust off-the-shelf system allowed us to demonstrate to decision-makers the significant advancements our research had made on the challenges of run-time safety compliance and reliability of robotic platforms.”

As properly, the workforce discovered Husky UGV to be significantly suited for educating and for superior college students resembling mechanical engineering or Masters college students and as a proof of ideas platform because the platform is ROS based mostly and might traverse a variety of terrains.

Asset Integrity Dashboard highlighting a tiered degree of accelerating description of the delamination fault on the decommissioned wind turbine blade

Creating Designs for the Future

A symbiotic system displays the lifecycle studying and co-evolution with information sharing for the mutual achieve of robotic platforms and distant human operators. This allows run-time verification of security, reliability, and resilience throughout autonomous missions.

The Smart Systems Group at Heriot-Watt University demonstrated their system at tier 1- ‘Adapt and Survive’; the place an autonomous mission or service has predefined mission aims. The “adapt and survive” management system can forecast and routinely mitigate towards recognized and unknown dangers within the mission surroundings. This functionality is transformative by way of run-time security compliance and mission resilience. For instance, if there have been an emergent fault inside Husky UGV, the system would routinely re-optimize the mission to make sure optimum outcomes that by no means violated security guidelines. Alternatively, if somebody entered the mission area or was truly positioned within the mission area, the SDA would reprioritize the mission to make sure the security of or restoration of the person.

To summarize then, the system can obtain the next:

  • Evaluate the implications of a situation of variables from the surroundings, infrastructure, human interplay, and robotic reliability
  • Share information with and collaborate with a distant human observer
  • Mitigate recognized and unknown threats to the resilience and security case of the autonomous mission

 

In a future demonstration showcase the workforce’s plans to make the most of a second robotic platform for a collaborative autonomous mission the place the robotic platforms autonomously assist one another. The worth created from the symbiotic system framework will apply to host bidirectional information alternate and advance the aim of servitization, additional advancing the roadmap to trusted autonomy and security compliance within the offshore surroundings. 

Ultimately, the workforce is sort of pleased with the success of their challenge. They have confirmed the seamless integration of an improved dashboard for past visible line of sight operation of autonomous methods as a result of hyperlinks between the human-in-the-loop, digital twin, run-time reliability ontology, and robotic platform.

 

Digital twin that includes a battery fault

The workforce can be hoping to garner some recognition for the challenge as they’ve submitted their symbiotic system demonstration abstract video for the IEEE Access Best Video Award. As properly, that they had hoped to submit their Self-Repairing Cities- Robots for Resilient Infrastructure, ORCA Hub information article, and accompanying video footage to the Leeds Robotic Competition, however sadly it was canceled as a result of COVID-19.

The Smart Systems Group at Heriot-Watt University consists of Daniel Mitchell, Dr. Osama Zaki, Dr. Jamie Blanche, Joshua Roe, Leo Kong, Samuel Harper, Dri. Valentin Robu, Dr. Theodore Lim, and Professor David Flynn.

If you have an interest in studying extra concerning the challenge, you possibly can check-out the Smart Systems Group’s following publications:

To be taught extra about Husky UGV, go to our web site.