Much has been made of the growing use of autonomous mining haulers at several sites around the world. Entrepreneurs at Israeli start-up Intsite hope to do the same for the construction industry, by developing the controls and software to permit autonomous cranes. The company recently announced it was awarded $1.35 million in funding by Terra Venture Partners, to keep the project moving ahead.
Although interest in autonomous systems and robots in the construction industry is on the rise, many experts say progress has lagged behind that in other industries. Intsite’s goal is to introduce what it says will be the first autonomous crane suitable for construction sites around the world.
The system uses off-the-shelf and customized hardware running state-of-the-art algorithms for computer vision, trajectory control, navigation and machine learning. The proposed crane will use multiple camera feeds and computer vision software to learn the intricacies of the work space. For instance, the system can make the crane aware of nearby workers and obstacles that present a hazard, to prevent collisions. Thus, the products are designed to increase safety on construction jobs.
The technology also uses real-time data to automate the crane’s controls. The robot crane could significantly improve precision, speed up operations, minimize errors and delays, and work around the clock without lunch breaks or shift changes. Company officials say Intsite technology could help cut construction time up to 30%.
The construction industry is faced with a growing shortage of skilled workers, and productivity has been lackluster in recent years. In fact, consulting company McKinsey says most large projects exceed budget and fail to meet deadlines up to 40% of the time. The development of next-generation autonomous machinery can address these types of problems.
For now, the autonomous crane will not completely eliminate the job of the crane operator. Trained personnel will still be needed to ensure safe and efficient movements, and operators will be able to override the machine controls when necessary.
Intsite completed a prototype in mid-2017, and the platform has been tested on construction projects in Israel. Plans are to launch similar trials in Europe and Asia in 2019.The company is now seeking a partnership with a leading crane manufacturer to assist with additional development and market validation, help steer future regulations for autonomous cranes, and provide further funding.
Of course, Intsite isn’t alone in pushing the digital footprint in the construction industry. Equipment manufacturer Komatsu began in 2015 rolling out its SMARTCONSTRUCTION initiative, connecting data related to onsite workers and objects to make worksites safer and more productive. The initiative has been introduced in more than 4,000 job locations.
Last year Komatsu partnered with Nvidia, the maker of real-time artificial intelligence (AI) systems for processing of complex data on board-level devices. Extending the SMARTCONSTRUCTION initiative, Komatsu will use Nvidia technology to create 3D visualizations of construction sites, showing the real-time interaction of people, machinery and objects. Costly onsite equipment can be closely monitored to ensure it is used with optimal efficiency. Nvidia GPUs will communicate with drones and cameras, acting as an AI platform for analysis and visualization.
At the center of the collaboration is Nvidia Jetson, a credit-card sized platform that delivers AI computing. Working in tandem with Nvidia cloud technology, Jetson will power cameras mounted on Komatsu’s construction equipment and enable 360° views to readily identify people and machines nearby to prevent collisions and other accidents. According to one Komatsu executive, “By leveraging Nvidia’s experience in image processing, virtualization and AI, we can further transform construction areas into jobsites of the future.”
Intsite
www.intsite-ai.com
William K. says
While a computer controlling in the absence of n operator is new, I worked on a computer assisted excavator project back in 1981, at the Pegasus division of Kohering Excavator company. At that time the target was improved accuracy when digging and improved efficiency while loading trucks. Because there was no thought of cameras and machine vision, safe operation was still the responsibility of the operator.. Trusting a computer to provide adequate safety is a fools task and it can’t be done very well.