At first, it’s not quite clear what you’re looking at. The yellow robots, sitting in silence, are lined up so closely that they almost resemble deck chairs stacked on top of one another. Then, in time with the music, their arms shoot out into a fluid series of patterns, giving the appearance of a single, many-armed robot peacocking for the camera. Finally, the seven Spots separate, synchronizing their steps and appearing to play off of one another’s dance moves.
The construction industry hasn’t always been quick to embrace new technologies, but more recently (accelerated in part by the pandemic) there has been a surge in new construction tech. New automation, robotics, and digital transformation technologies are affording opportunities to disrupt processes that are traditionally very labor-intensive. Chief among these are data capture tools and methodologies that offer construction companies greater visibility into their projects by effectively monitoring progress across their jobsites.
It’s been a little over a year since Spot graduated from our early adopter program and was released for sale. Our early adopters helped us answer the question, “Can robots handle the real world?” Our customers’ experience with Spot over the past year has answered a follow up question, “Where is Spot adding value?”
Many applications for Spot are centered around the robot's ability to collect frequent, consistent, reliable data. We've been working on tools to help customers use the Spot API to integrate machine learning (ML) into those applications, so they can make the most use of the data collected by the robot. Machine learning algorithms help Spot find and apply patterns in that data. These integrations allow Spot to do things like identify specific objects in its environment and respond based on what it detects.
Agile mobile robots have been helping industry leaders operate more intelligently, efficiently and safely. More capable than ever before, these robots can go anywhere that people can on your sites, carrying sensors and computers to collect and process data at the edge.
On the surface, automated depalletizing looks relatively straightforward. A computer vision system identifies a box and then a robotic arm with a gripper lifts the box off a pallet and onto a conveyor belt. However, solving carton location and path planning to successfully unpack a pallet requires highly advanced perception and intelligent vision processing algorithms.
Over the past year, COVID-19 has put a huge strain on warehouse operations—making hiring and staffing a challenge, while simultaneously accelerating the demand for fast, effective e-commerce services. Even as social distancing restrictions lift, e-commerce adoption rates continue to rise dramatically, highlighting the need for ongoing solutions to fulfillment, shipping, and delivery challenges. The warehousing industry is primed for an automation boom to support this new landscape.
According to a recent survey from McKinsey, automation transformation is a priority for 88 percent of respondents in heavy industry, but under 5 percent have actually seen significant bottom-line improvements from these projects. Automation is nothing new for industrial and manufacturing companies hoping to improve efficiency, safety and reliability. So why aren’t they seeing better ROI on these new initiatives?
In an industrial setting, equipment failure or faulty infrastructure often requires costly unplanned downtime to repair. Process industries are looking to asset performance management (APM) and industrial predictive analytics technologies to identify impending failures, before they cause larger problems. But research from ARC Advisory Group found that 59 percent of APM system users receive less than a week notice of impending failure. This is, in part, because data capture for condition monitoring and predictive maintenance is often resource-intensive and unreliable.