Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems

By Ingmar Kanitscheider, Ila Rani Fiete. 2016

60 citations recorded by the source corpus.

Self-localization during navigation with noisy sensors in an ambiguous world is computationally challenging, yet animals and humans excel at it. In robotics, Simultaneous Location and Mapping (SLAM) algorithms solve this problem though joint sequential probabilistic inference of their own coordinates and those of external spatial landmarks. We generate the first neural solution to the SLAM problem by training recurrent LSTM networks to perform a set of hard 2D navigation tasks that include generalization to completely novel trajectories and environments. The hidden unit representations exhibit several key properties of hippocampal place cells, including stable tuning curves that remap between environments. Our result is also a proof of concept for end-to-end-learning of a SLAM algorithm using recurrent networks, and a demonstration of why this approach may have some advantages for robotic SLAM.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, neutral): “…and Mapping (SLAM) (Thrun et al., 2005) procedures, either partially or fully and embedded internally or externally, into DRL network architectures, with the intention to cultivate more sophisticated navigation capabilities in DRL agents (Stachenfeld et al., 2017; Kanitscheider and Fiete, 2017).”
Attractor and integrator networks in the brain (2021, background): “A few continuous attractor development models show how they could emerge simply through unsupervised associative plasticity [180, 239, 206]; others are based on combining feedback of known or plausible error signals with neural activity in relatively simple learning rules [270, 180, 271]; the rest t”
A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists (2017, methodology): “In real neuroscience, researchers trained LSTM networks to perform two-dimensional navigation tasks, and visualized hidden unit representations [Kanitscheider and Fiete, 2016].”
MapNet: An Allocentric Spatial Memory for Mapping Environments (2018, background): “Another recent line of research has focused on replacing the whole SLAM pipeline, with encouraging preliminary results [12, 28, 8].”