Komatsu, one of the world’s largest manufacturers of heavy equipment for construction and mining, has teamed up with RBR50 company NVIDIA to add artificial intelligence (AI) to its construction sites across Japan for increased safety and efficiency.
The partnership, announced by NVIDIA founder and CEO Jensen Huang at GTC Japan, will use NVIDIA’s GPUs to communicate with drones and cameras throughout construction sites. NVIDIA’s Jetson AI platform will power cameras mounted on Komatsu’s heavy machinery to create real-time, 360-degree views to identify people and machines nearby to prevent accidents. Stereo cameras inside the cabs of construction equipment will also have Jetson to alert human drivers to changing conditions in real time.
Komatsu told Robotics Business Review safety and skilled labor shortage are the two main reasons it’s turning to AI for help. According to the Japan Construction Occupational Safety and Health Association, construction sites in Japan saw 300 deaths and 15,000-plus injuries in the last year.
The labor shortage is a result of Japan’s aging population, according to the Japan Federation of Construction Contractors. Of the 3.4 million skilled workers in the domestic industry (as of 2014), roughly 1.1 million, or one-third, are likely to leave in the next decade.
“Artificial intelligence is sweeping across industries, and its next frontier is autonomous intelligent machines,” Huang said during his GTC Japan keynote. “Future machines will perceive their surroundings and be continuously alert, helping operators work more efficiently and safely. The construction and mining industries will benefit greatly from these advances.”
Komatsu equipment, jobsites will become more efficient
In addition to safety, increased efficiency is the next major benefit of this partnership. Komatsu will use SkyCatch drones to gather and map 3D images for visualizing the construction site. For example, the drones can scan a site to monitor how much excavation has been done. Komatsu will use NVIDIA GPUs to process this video data from the drones for analysis and visualization mapping.
The drones can also monitor equipment usage and infer how much time an excavator, for example, is idle. It can determine that an excavator is spending 30 percent of its time moving dirt, 20 percent of its time moving from place to place, and 50 percent of its time sitting idle. Fifty percent idle time isn’t ideal on such expensive equipment, of course, so this could help drastically reduce costs.
Future applications include high-resolution rendering and virtual simulations of construction and mining sites along with automated control of machinery.
“By leveraging NVIDIA’s experience in image processing, virtualization and AI, we can further transform construction areas into job sites of the future,” Yuichi Iwamoto, senior executive officer and chief technology officer at Komatsu, said in a statement.
Construction sites are a ways off from being fully automated, but this is definitely a step in the right direction. It’s also another industry NVIDIA is looking to turn upside down with its AI. NVIDIA recently partnered with GE Healthcare and Nuance on medical imaging.Read More