There are so many autonomous devices nowadays that can run Skynet Inside(TM) that it’s hard to keep track. But one was still missing: the versatile Bobcat. When we say “Bobcat”, we mean track loader — it’s just one of those things that the name and the brand stoke together so strongly that it’s hard to actually recall the technical name. A company by the name of Built Robotics is betting on autonomous track loaders as being a big part of the future of construction.
The tractor can navigate, excavate, and carry a 1,000 pound load with 1 cm precision using its LIDAR, specially designed to work with high-vibration, high-impact environment of construction excavation. Additionally, the lasers also allow the robot to measure the amount of material it has scooped up. But the precision does not come from the LIDAR alone. To position the robot, Built Robotics uses augmented GPS, which combines an on-site base station and GPS satellites to produce accurate location data.
It is supposed to be completely autonomous: given a location and holes to dig, it can plan and execute the work. It resembles a self-driving car, but the challenges are actually quite different. Cars are mean to drive around and reach a destination without touching anything. Like the CEO of Built Robotics says:
“If a car is changing the environment around it, then something’s gone really wrong.”







What really caught our eye is the Goliath’s unique positioning system. While most CNC machines have the luxury of end-stops or servomotors capable of precise positional control, the Goliath has two “base sensors” that are tethered to the top of the machine and mounted to the edge of the workpiece. Each sensor connects to the host computer via USB and uses vaguely termed “Radio Frequency technology” that provides a 100Hz update for the machine’s coordinate system. This setup is sure to beat out dead-reckoning for positional awareness, but details are scant on how it precisely operates. We’d love to know more if you’ve used a similar setup for local positioning as this is still a daunting task for indoor robots.