New algorithm helps robots avoid collisions with moving objects

Developed at the University of California San Diego, the Fastron algorithm is said to run up to eight times faster than existing collision detection algorithms.

The engineers, led by Prof Michael Yip envision Fastron being useful for robots that operate in human environments where they work with moving objects and people fluidly. They are also exploring robot-assisted surgeries using the da Vinci Surgical System. In this scenario, a robotic arm would autonomously perform assistive tasks – such as suction, irrigation or pulling tissue back - without obstructing the surgeon-controlled arms or the patient's organs.

The team also envisions that Fastron can be used for robots that work at home for assisted living applications.

Existing collision detection algorithms spend time specifying all the points in a given space -the specific 3D geometries of the robot and obstacles - and performing collision checks on every single point to determine whether two bodies are intersecting at any given time.