Tag: Brain-inspired Navigation

Insect-Inspired Robots Don’t Need GPS For Orientation

The ‘Brains on Board’ project is a collaboration between several British universities in partnership with the Human Brain Project and seeks to ‘translate’ the brains of ants and bees into algorithms that a machine will understand. Its aim is …

Be the First to comment. Read More

How a simple robotics model of mammal navigation is useful to interpret neurobiological recordings

Place recognition is a complex process involving idiothetic and allothetic information. In mammals, evidence suggests that visual information stemming from the temporal and parietal cortical areas (‘what’ and ‘where’ information) is merged at the level of the entorhinal cortex (EC) …

Be the First to comment. Read More

Brain-inspired dynamic path replanning in autonomous navigation for robotic swarms

What do animal brains have in common with a swarm of robots? 

In an effort to improve robotic swarming algorithms, an interdisciplinary team of scientists will study how the brain allows an animal to navigate and change its route while …

Be the First to comment. Read More

How to build spatial representation model (x, y, z, yaw) for 3D SLAM inspired by the brain?

The excerpt note is some relevant references about 2.5D SLAM inspired by the brain, which is expanded from the RatSLAM system.

Guth F. A. et. al. present an Hippo 3D (DolphinSLAM), expanded from the RatSLAM system, which was initially designed …

Be the First to comment. Read More

3D Spatial Representation: Coding of 3D space by 3D Grid Cells, 3D Border Cells, 3D Head Direction Cells

Latest reports about 3D Spatial Representation by Gily Ginosar at Weizmann Institute of Science and Misun Kim at UCL in the Grid Cell Meeting on May 21-22, 2018. (http://www.cognitive-map.com/img/GCMposters.pdf )

Gily Ginosar, Weizmann Institute of Science

Grid cells recorded

Be the First to comment. Read More

How to implement the visual processing module for pose calibration in RatSLAM?

In this report, I summarized some key methods for visual processing module in RatSLAM or RatSLAM-based System. There are more than six approaches as following. By comparing and doing some practical experiments, I think that the intensity scanline profile and

Be the First to comment. Read More

为什么类脑(Rat-Brained)机器人能够在不熟悉的地形中进行很好地导航

为什么类脑(Rat-Brained)机器人能够在不熟悉的地形中进行很好地导航

Why Rat-Brained Robots Are So Good at Navigating Unfamiliar Terrain

运行模拟大鼠导航神经元的算法,能够使重型机器在澳大利亚的地下矿山中进行作业。

Jean Kumagai   1 June, 2017   翻译:Fangwen Yu     原文链接:IEEE Spectrum

 1

Photo: Dan Saelinger

 如果你把一只普通的棕色老鼠放在一个实验室的迷宫或地铁隧道里,它将立即开始探索周围的环境,嗅闻边缘,对着角落和障碍物,将其胡须刷在表面上。 过了一会儿,它会回到起步的地方,从此,它将把探索过的地形视为熟悉的环境。

机器人科学家长期以来一直梦想着给机器人创造类似的导航技能。 为了让机器人能够在我们的环境中变得更有用,机器人就必须具备在周围环境中靠自己寻路的能力。 有些机器人已经在家庭、办公室、仓库、医院、酒店以及自驾车,甚至整个城市范围内的环境中正在学习找路。尽管如此,这些机器人平台仍然难以在轻微挑战的条件下可靠地运行。 例如,自主驾驶车辆可能配备了复杂的传感器和前方道路的精细地图,但是司机仍然需要在大雨或下雪或夜间进行控制。

相比之下,棕色的老鼠是一个灵活的导航仪,在最恶劣的环境中也能找到路,比如在地下、地面等复杂情况下都没问题。 当一只老鼠探索一个不熟悉的区域时,在2克大脑中专门的神经元会放电或产生尖峰,对地标或边界产生响应。其他神经元以规则的距离形成尖峰, 每20厘米一次,每米一次等等,这样就形成一种空间的心理表征。还有其他的神经元就像一个内部的罗盘,记录着动物头部转动的方向。总而言之,这种神经活动允许大鼠记住它去过哪儿以及怎样到达那。 无论何时当沿着相同的道路行走,尖峰会加强,使大鼠的导航更加健壮。

Be the First to comment. Read More