Better vision for robots

A new 3D sensor is promising to give robots the ability to observe their environment in a more natural and human-like manner.

The technology being developed by an EU-funded consortium will make it possible to apply robots in more sophisticated markets so they will play a major role in the fields of cleaning, construction, maintenance, security, health care, entertainment and personal assistance in the future.

The sensor employs 3D foveation–a digital imaging process–to significantly improve on current 3D sensor systems.

Jens T Thielemann, the technical lead of what is known as the TACO (Three-dimensional Adaptive Camera with Object Detection and Foveation) project said his group’s technology will enable significantly better, faster and cheaper 3D sensing compared to current laser scanners.

‘Through the foveation process, the sensor will provide 10 times better resolution than existing sensors with hardware enabling a 10 times size resolution,’ he said.

These 3D foveation properties are achieved by using the power of micro-mirror MEMS technology combined with time-of-flight methods in a system that is small, light-weight and easily mounted on an ordinary-sized service robot or even a robot arm.

Engineers on the three year project will explore control strategies for 3D foveation allowing 3D robot vision that is adaptable with space- and time-variant sampling, processing and understanding.

Norwegian research organisation SINTEF, one of the members of the consortium, will be developing the system’s 3D foveation software.

The project will verify and test the 3D sensing system in a robotic environment, exploring its ability to allow the robot to navigate autonomously and interact with a diverse number of everyday objects.

In addition to SINTEF, the TACO project is relying on expertise from a range of European academic and industrial partners. These include UK companies Shadow Robotics and Oxford Technology, which will be providing applications for robot grippers and robots for harsh environments.

Other members of the consortium include the Fraunhofer Institute, CTR and TU Wien in Austria.