CORVALLIS, OR — In autonomous robotics, the right inputs reveal the right path. Each day the University of Waterloo’s WAVELab Research Group navigates these waters as they work out the best ways to help robot commanders get their mecha-assistants from point A to point B without the use of manual controls. And for them, the most precise way to achieve this is with the help of an OptiTrack (www.optitrack.com) motion capture system.
Professor Steven Waslander began WAVELab’s autonomous vehicle program with the traditional measurement tools of the field: IMU sensors, gyroscopes, onboard GPS. These devices gave real time estimates that stabilized his squadron of aerial and ground rovers, but failed to deliver the control needed to prevent those same vehicles from veering off into hazardous areas like walls. To address this problem, Waslander increased his state estimation system’s scope by enlisting the input of an 18 camera OptiTrack tracking system.
“We selected OptiTrack for its combination of function and affordability,” said Professor Steven Waslander, head of WAVELab Research Group. “Not every school can afford a $100,000 motion capture system, and honestly, they don’t need it. An OptiTrack setup gives you more than enough tracking power to realize your ambitions.”
The addition of the cameras enabled the team to estimate in real time if the onboard sensors were working and the robots had stayed locked to their predetermined route. Quick adjustments to the onboard control algorithms could be made from this data, which significantly reduced its development time.
Now, each time the WAVELab’s robots go for a spin on the ground, or in the air, they can sense unknown surroundings, develop accurate 3D maps and navigate through their environment with the assistance of OptiTrack’s sub-millimeter data. And as OptiTrack’s system helps the algorithm increase in potency, new opportunities for robot crossover should start to materialize in our lives as well. In time, you may see WAVELab’s robots out in the world as sample collectors for scientists exploring hard-to-reach crevasses in Antarctica; or as scouts that keep soldiers safe; or even (someday) as the pilot that flies you home from a well deserved vacation.
“If you want to increase the level of autonomy of your vehicles quickly, you need a ground truth system that can return highly accurate motion data,” adds Waslander. “You have to know where the weak spots in your algorithm are, so you can readjust and get better results the next time around. These cameras are like an all seeing eye.”