A computer algorithm that copies the navigation functionality of humans and animals helps robots navigate unfamiliar spaces.
This robot uses neural schemes similar to humans to navigate an office environment. © 2015 A*STAR Institute for Infocomm Research
A robot with a navigation system that mirrors the neural scheme used by humans and animals to find their way around has been developed by Agency for Science, Technology and Research (A*STAR) researchers in Singapore .
The human navigation function is operated by two types of brain cells — place cells and grid cells. Place cells become active in the brain when we recognize familiar places, while grid cells provide us with an absolute reference system, so we can determine exactly where we are on a map.
The way sailors used to navigate through tracking of relative movement, however, is essential for finding a way through unfamiliar areas, explains Miaolong Yuan from the A*STAR Institute for Infocomm Research team. “A sailor will use cues such as the stars or landmarks to determine where their ship is on a map, and then, as the ship moves, will update its location on the map by observing only speed and direction.”
The human brain uses grid cells, which provide a virtual reference frame for spatial awareness to handle this type of relative navigation. Each time we move through and pass one of the virtual grid points that the brain has set up, the respective grid cell becomes active, and we know our relative movement in relation to those coordinates. By using both place and grid cells for navigation, humans and animals are able to accurately move through the environment.
Yuan and the team have implemented the same neural scheme for robots, using computer programs that simulate the activity of place and grid cells in the brain. Crucial to the computational algorithm is the strength of the feedback mechanism between the grid cells and place cells, and the calibration of the visual signals is integral to the map building process of the computer algorithm.
The algorithm was tested in a robot (see image) that explored a 35 meter x 35 meter indoor office environment. The robot was able to detect loops in the path through the office space and, by using visual cues to recognize areas visited repeatedly, built its own neurological map of the office.
The computer navigation system assists the robot in situations where it is lost in a new environment, says Yuan. “Cognitive maps can help the robot when it is lost, because they can provide global topological information of the navigating environment to help the robot localize itself.”
The A*STAR-affiliated researchers contributing to this research are from the Institute for Infocomm Research
 Yuan, M., Tian, B., Shim, V. A., Tang, H. & Li, H. An entorhinal-hippocampal model for simultaneous cognitive map building. Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 586–592 (2015).
Original article from A*STAR Research
A*STAR Research | Research SEA
UT professor develops algorithm to improve online mapping of disaster areas
29.11.2016 | University of Tennessee at Knoxville
New standard helps optical trackers follow moving objects precisely
23.11.2016 | National Institute of Standards and Technology (NIST)
A multi-institutional research collaboration has created a novel approach for fabricating three-dimensional micro-optics through the shape-defined formation of porous silicon (PSi), with broad impacts in integrated optoelectronics, imaging, and photovoltaics.
Working with colleagues at Stanford and The Dow Chemical Company, researchers at the University of Illinois at Urbana-Champaign fabricated 3-D birefringent...
In experiments with magnetic atoms conducted at extremely low temperatures, scientists have demonstrated a unique phase of matter: The atoms form a new type of quantum liquid or quantum droplet state. These so called quantum droplets may preserve their form in absence of external confinement because of quantum effects. The joint team of experimental physicists from Innsbruck and theoretical physicists from Hannover report on their findings in the journal Physical Review X.
“Our Quantum droplets are in the gas phase but they still drop like a rock,” explains experimental physicist Francesca Ferlaino when talking about the...
The Max Planck Institute for Physics (MPP) is opening up a new research field. A workshop from November 21 - 22, 2016 will mark the start of activities for an innovative axion experiment. Axions are still only purely hypothetical particles. Their detection could solve two fundamental problems in particle physics: What dark matter consists of and why it has not yet been possible to directly observe a CP violation for the strong interaction.
The “MADMAX” project is the MPP’s commitment to axion research. Axions are so far only a theoretical prediction and are difficult to detect: on the one hand,...
Broadband rotational spectroscopy unravels structural reshaping of isolated molecules in the gas phase to accommodate water
In two recent publications in the Journal of Chemical Physics and in the Journal of Physical Chemistry Letters, researchers around Melanie Schnell from the Max...
The efficiency of power electronic systems is not solely dependent on electrical efficiency but also on weight, for example, in mobile systems. When the weight of relevant components and devices in airplanes, for instance, is reduced, fuel savings can be achieved and correspondingly greenhouse gas emissions decreased. New materials and components based on gallium nitride (GaN) can help to reduce weight and increase the efficiency. With these new materials, power electronic switches can be operated at higher switching frequency, resulting in higher power density and lower material costs.
Researchers at the Fraunhofer Institute for Solar Energy Systems ISE together with partners have investigated how these materials can be used to make power...
16.11.2016 | Event News
01.11.2016 | Event News
14.10.2016 | Event News
02.12.2016 | Medical Engineering
02.12.2016 | Agricultural and Forestry Science
02.12.2016 | Physics and Astronomy