Vision-based route following by an embodied insect-inspired sparse neural network
This work addresses route-following for robotics or autonomous systems, but it appears incremental as it builds on prior models.
The paper tackled the problem of embodied navigation by comparing the FlyHash model, an insect-inspired sparse neural network, to non-sparse models in a vision-based route-following task, concluding that FlyHash is more efficient, particularly in data encoding.
We compared the efficiency of the FlyHash model, an insect-inspired sparse neural network (Dasgupta et al., 2017), to similar but non-sparse models in an embodied navigation task. This requires a model to control steering by comparing current visual inputs to memories stored along a training route. We concluded the FlyHash model is more efficient than others, especially in terms of data encoding.