Domo Arigato, Mister Roboto!

RSS

Thank you very much/Mister Roboto/For doing the jobs/that nobody wants to ...” –From the song Mister Roboto by Styx

At first glance, forklifts might seem mundane pieces of equipment next to Class 8 rigs in the trucking world; small, easy to operate, and above all offering a far safer work environment compared to the crowded high-speed asphalt truckers ply every day.

Yet in many ways, that’s far from the truth.

robotlifttruck.jpg

Consider these statistics for a moment: 100 workers are killed in forklift related accidents every year in the U.S., with 25% of those fatalities due to rollover accidents. On top of that, roughly 20,000 workers are seriously injured in forklift related accidents annually, with some 34,000 injuries treated in emergency rooms across the country every year due to forklift accidents.

Suddenly, the forklift doesn’t seem so innocuous after all, does it?

However, all of that could possibly change based on a robot forklift prototype developed the Massachusetts Institute of Technology (MIT), BAE Systems, and Lincoln Laboratory based off a Toyota Material Handling U.S.A. (TMHU) chassis.

This project – sponsored by U.S. Army Logistics Innovation Agency (LIA), the Combined Arms Support Command (CASCOM) Sustainment Battle Lab, the Office of the Secretary of Defense (OSD) and the Director of Defense Research and Engineering (DDR&E) – modified a 3,000-pound capacity internal combustion engine-powered Toyota 8-Series lift truck to be operated without a human driver in the seat, directly operating the controls. Instead, the operator is at a distance, using voice and gesture commands to control the vehicle.

[Below, you’ll see how this robot forklift picks up pallets from the ground, filmed during recent demonstration testing hosted by LIA at Fort Lee, VA.]

This unmanned robotic forklift is capable of locating, lifting, moving and placing palletized supplies within an existing outdoor supply depot for right now, but I suspect that moving to indoor operations (the ‘modus operandi’ at most trucking terminals and warehouses) isn’t far behind.

Over the last two years, researchers at MIT’s Computer Science and Artificial Intelligence Laboratory developed a number of technologies to help this robot forklift function: using embodied speech and gesture understanding; shape estimation (from laser range scanner data); machine vision (from camera data); motion estimation (from GPS, inertial data and wheel odometry encoders); and autonomous mobility and pallet manipulation.

[Here’s how the robot forklift loads material onto a truck – in this case a flatbed medium-duty vehicle.]

Proprietary Controller Area Network (CAN-bus) protocols, provided by Toyota’s 8-Series product engineering team, enabled the MIT team to connect its algorithms directly to the lift truck’s manual and electrical controls, the participants noted.

“We chose the internal combustion-style lift truck because it can be operated outdoors on packed earth or gravel and – with mini-lever control – some of its functionality can be controlled electronically rather than solely mechanically,” said MIT Professor Seth Teller, who leads this project.

[Here’s how it off loads cargo from a truck.]

The reason the military is so involved in this project is pretty simple, too, explained Brett Wood, president of TMHU: it takes valuable personnel out of harm’s way.

“Robotic forklifts have the potential to protect both military and civilian personnel working in high-risk environments, such as hazardous material storage facilities,” he explained. “That’s why we are excited to work with the innovative researchers at MIT on this promising application of lift trucks.”

Neat stuff, indeed. Now the challenge is to make the technology cost efficient and robust enough to survive in real-world operations – all while being very simple to operate.

What's Trucks at Work?

Trucks at Work: Sean Kilcarr comments on trends affecting the many different strata of the trucking industry.

Blog Archive

Sponsored Introduction Continue on to (or wait seconds) ×