Motion Planning Improvements Made For ROS

 Robots

While working as research engineer at Willow Garage, Ken Anderson improved upon motion planning by developing a more fluid and more efficient way for robots to move using the ROS operating system. The developments represent an improvement for arm navigation applications for robot arms and other robotic components.

D uring his visit as a research engineer at Willow Garage, Ken Anderson improved upon motion planning by developing a more fluid and computationally lighter trajectory smoother along with incremental distance field updates.

The new trajectory smoother modifies the timing intervals to respect velocity and acceleration bounds. This differs from the existing shortcutting techniques, which move the actual point locations. Incremental distance field updates save computation time by only updating the portions of the distance map that have changed.

The iterative trajectory filter and incremental distance field updates are significantly faster than previous methods making motion-planning and safe teleoperation more responsive.

Anderson’s road to a career in robotics research has taken some interesting twists and turns. He began with his ECE degree at Queen's University where he attributes joining the programming team in second year to a lot of his success.

Anderson with a PR2 Robot

“Sometimes you have to pick and choose where you apply yourself,” he says. “Joining the programming team led me to summer internships in the ECE Department. I worked on Deep Green, a robotic pool-playing table, and the Canadarm 2, a robotic arm for the International Space Station. These jobs gave me new skills and an understanding of the practical applications of robots and robotic research – applications such as object localization and recognition, collision detection, and motion planning.”






SOURCE  Willow Garage Blog

By 33rd Square

Subscribe to 33rd Square