A game of cat and mouse shows how chips in the brain can be used to make decisions.
The person is Jeremy Hsu.
Future possibilities of robots carrying out search and rescue missions or wildlife surveys without much human guidance are provided by a game of cat and mouse in a lab.
Researchers at Tsinghua University in China have created a robot that uses a brain-inspired chip. Multiple artificial intelligence techniques can be run at the same time in an energy efficient manner. It is an example of an experiment that could use limited computing resources and power to make decisions.
The researchers challenged the robot to chase another robot in a room filled with obstacles. The mouse robot had to be tracked by using both visual recognition and sound detection, as well as figuring out the best path to chase it down without hitting anything. The team says that the TianjicX chip reduced the amount of power required for the robot cat to make decisions during the chase by about half.
It would be difficult for a commercialised robot to perform a cat and mouse chase. Many robots that interact with more complex and unpredictable environments rely on remote control by human operators, or else must maintain wireless connections with distant data centers that have the computing power necessary for more intensive decision making.
It's not easy to tell how well the chip stacks up against other systems. The approach of designing computer chips to more closely mimic a biological brain has been used by many scientists.
It hasn't yet been commercialised in a large way. Practical advantages could be provided by their low size, weight and power requirements.
Jeffrey Krichmar is a professor at the University of California, Irvine.
ScienceRobotics.abk2948 is a journal reference.
There are more on this topic.
All Rights Reserved © 2024
