Human-like robot has skin with sensory abilities

Human-like robot has skin with sensory abilities
A team at the Technical University of Munich (TUM) has developed a system combining artificial skin with control algorithms to help create the first autonomous humanoid robot with full-body artificial skin. (Technical University of Munich)

Inspired by human skin, researchers at the Technical University of Munich (TUM) have developed a system combining artificial skin with control algorithms to help create the first autonomous humanoid robot with full body artificial skin.

The artificial skin developed by Prof. Gordon Cheng and his team comprises hexagonal cells about the size of a two-euro coin (i.e. about one inch in diameter). Each is equipped with a microprocessor and sensors to detect contact, acceleration, proximity and temperature. Such artificial skin enables robots to perceive their surroundings in much greater detail and with more sensitivity. This helps them to move safely and gives them the ability to anticipate and actively avoid accidents.

The biggest obstacle in developing robot skin has always been computing capacity. Human skin has around 5 million receptors. Efforts to implement continuous processing of data from sensors in artificial skin quickly became overloaded with data from just a few hundred sensors.

Sponsored by Infosys

In Conversation with Antonio Neri, President & CEO – Hewlett Packard Enterprise & Salil Parekh, CEO – Infosys

Hear the CEOs of Infosys & HPE discuss the current crisis and how it has accelerated the need for digital transformation for their clients. Connectivity at the Edge, right mix of hybrid cloud, ability to extract data faster than ever before… these are just some of the contributions that HPE and Infosys make to our clients’ digital transformation journey.

To overcome this problem, using a NeuroEngineering approach, Cheng and his team do not monitor the skin cells continuously, but rather with an event-based system. This reduces the processing effort by up to 90 percent. The event-based approach involves individual cells transmitting information from their sensors only when values are changed. This is similar to the way the human nervous system works.

The event-based approach enabled the researchers to apply artificial skin to a human-size autonomous robot not dependent on any external computation. The H-1 robot  is equipped with 1260 cells (with more than 13000 sensors) on its upper body, arms, legs and even the soles of its feet. Designed with sensitive feet, H-1 is able to respond to uneven floor surfaces and even balance on one leg.

The robot skin system is also highly robust and versatile. Because the skin consists of cells, and not a single piece of material, it remains functional even if some cells stop working.

"Our system is designed to work trouble-free and quickly with all kinds of robots," said Cheng. "Now we're working to create smaller skin cells with the potential to be produced in larger numbers."

Suggested Articles

Revenues overall hit $3.82 billion, up 1% from third quarter of 2019, as auto plants reopened and personal electronics revenues grew

MIT Sloan and Boston Consulting Group call for expanding organizational learning to gain better financial rewards of AI deployments

Originally a 1960s memory manufacturer, Intel wants out of NAND following the market decline in 2018