3
$\begingroup$

Is there a common way to build a neural network that seeks to extract spatial and temporal information simultaneously? Is there an agreed up protocol on how to extract this information?

What combination of layers works: convolution + LSTM? What would be the alternatives?

$\endgroup$
3
$\begingroup$

Yes, there are different ways. What I think you are looking for is under the research field of Localization and Mapping. Which divides in the following subfields: enter image description here

  • For getting current (the robot) position and trajectory go to models for Odometry Estimation
  • For getting a representation of the world around the robot go to models for Mapping
  • If you want both of them (I am guessing you want). Go for SLAM (Simultaneous Localization and Mapping) models

Here it is the amazing survey that links you to tons of papers with different models for each category. If you want to know what are the most common architectural blocks (LSTM, ConvLSTM, RNN...) used for your problem, read the most promising papers under your target category.

References:

Survey: https://arxiv.org/abs/2006.12567

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.