Robots are on the march. Still today they are most closely associated in most people’s minds with heavy industrial environments such as car assembly plants, but advancing technology enables manufacturers to extend the uses of robots into homes, shops, city streets, hotels and many other settings.
The exciting new uses for robots will increasingly involve interaction with people, and require detailed awareness of the environment. Now a portfolio of sophisticated optical technologies from ams OSRAM is being deployed in the next generation of robots, enabling them to see and navigate the world around them, detect objects in proximity, and provide indicator signals to help people interact safely with them.
Mapping the environment around a robot
Object detection and mapping are crucial functions for a fully autonomous robot to perform. The more precisely and accurately the robot senses its environment, the faster and more efficiently it can move around a shared space.
Sophisticated robot designs build on 3D sensing, to build a ‘depth map’, which accurately represents the size and shape of objects within the field of view, and their distance from the sensor. Effective 3D sensing typically uses a combination of infrared emitters (IR LEDs or lasers) and high-resolution IR sensors for stereo or structured light based vision solutions. The Mira family of image sensors is especially useful in robotics applications because it is sensitive to both visible and IR wavelengths. For instance, the Mira220 is a near infrared global shutter image sensor that offers high quantum efficiency in the visible spectrum as well as in the near-infrared light spectrum, where quantum efficiency is up to 38% at 940nm based on our internal tests. There is more about the Mira family in this video.
A Mira image sensor can be used both for 3D sensing (in combination with 940nm IR emitters), as well as providing video image outputs to enable object recognition and other artificial intelligence (AI) functions. New use cases for imaging solutions on robots are emerging all the time, such as service robots collecting garbage from city streets. The combination of image sensing and AI allows the robot to identify and collect waste items correctly.
Integration of emitters and image sensors into a 3D sensing system can be eased by use of a reference design kit – the Oclea 3D Vision SDK from Teknique is particularly helpful. It provides a plug-and-play development platform for direct integration into the robot system of choice.
If 3D scanning accuracy is less crucial for the robot’s application use case and algorithmically simpler obstacle detection is already sufficient, multi-zone direct time-of-flight sensors could be the sensing solution of choice. These TMF882X sensors can be easily paired to scanning arrays with wider field of view or even combined with image based 3D scanning solutions for system wake-up if ultimate low-power design is required.
Advanced sensors to identify materials
A robot’s environment awareness will not be limited just navigation and collision avoidance. In a robotic floor cleaner, for instance, a spectral sensing IC such as the AS7343 can detect flooring materials, distinguishing wool from polyester from wood from ceramics. Besides material categorization, ams OSRAM's spectral sensors can also perform accurate measurements, to enable cleaning operations to be automatically optimized for the type of floor.
Spectral measurements made by a spectral sensor more accurately identify flooring materials than a visual camera backed by complex algorithms, and are simpler to implement: the sensor system relies only on machine learning-based algorithms to match an acquired spectral pattern with a reference sample stored in memory.
Light signals for communication with people
Optical technology can be used to signal to the outside world, as well as to sense the world around the robot.
New light projection technology provides an ideal method for a robot to signal intention. In the automotive sector, ams OSRAM has pioneered the implementation of projection lighting through micro-lens arrays to display, for instance, turn signals on to the road surface below the wing mirror.
In a robot, a micro-lens array could project symbols such as left-turn or right-turn arrows, or a set of pulsing rings surrounding the robot to indicate the extent of its safety zone, as the picture below shows. By communicating information and intention with light, the robot can guide humans to step out of its way more intuitively or navigate smoothly around it, without annoying alarm sounds or slowing the movement either of the robot or the person.
Advanced optical technology brings new value to robotics
Innovation in robotics is bringing exciting new use cases to the market. In many of them, robots will need to interact spontaneously and autonomously with people and objects in their environment. Advanced optical technologies from ams OSRAM for sensing and illumination provide the foundation for the development of this next generation of robots.
