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

نویسندگان

  • Ingmar Kanitscheider
  • Ila Fiete
چکیده

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.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Temporal-Kernel Recurrent Neural Networks

A Recurrent Neural Network (RNN) is a powerful connectionist model that can be applied to many challenging sequential problems, including problems that naturally arise in language and speech. However, RNNs are extremely hard to train on problems that have long-term dependencies, where it is necessary to remember events for many timesteps before using them to make a prediction. In this paper we ...

متن کامل

How hard is it to cross the room? - Training (Recurrent) Neural Networks to steer a UAV

This work explores the feasibility of steering a drone with a (recurrent) neural network, based on input from a forwardlooking camera, in the context of a high-level navigation task. We set up a generic framework for training a networkto perform navigation tasks based on imitation learning. It can be applied to both aerial and land vehicles. As a proofof concept we apply it to a UAV...

متن کامل

Navigation of a Mobile Robot Using Virtual Potential Field and Artificial Neural Network

Mobile robot navigation is one of the basic problems in robotics. In this paper, a new approach is proposed for autonomous mobile robot navigation in an unknown environment. The proposed approach is based on learning virtual parallel paths that propel the mobile robot toward the track using a multi-layer, feed-forward neural network. For training, a human operator navigates the mobile robot in ...

متن کامل

Memetic cooperative coevolution of Elman recurrent neural networks

Cooperative coevolution decomposes an optimisation problem into subcomponents and collectively solves them using evolutionary algorithms. Memetic algorithms provides enhancement to evolutionary algorithms with local search. Recently, the incorporation of local search into a memetic cooperative coevolution method has shown to be efficient for training feedforward networks on pattern classificati...

متن کامل

O2: Neuroscience and Talent: How Neuroscience Can Enhance Successful Plan of Talent Strategy

Performance and development are based on hard work, experience and learning. Learning how to change different behaviors is crucial to successful talent management plans. Within the brain there are complex connected circuits that can identify threats. The brain reacts to change as a threat. There is also a collection of brain structures tied to a natural reward system that are involved in the re...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017