Training and test routes for simulated agents navigating using insect inspired strategies
<p dir="ltr">These folders contain train routes, test routes and terrain information (labelled as per filenames) for a set of insect-inspired route navigation experiments conducted in Unity.</p><p dir="ltr">For code analysing this data see: <a href="http...
Saved in:
| Main Author: | |
|---|---|
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | <p dir="ltr">These folders contain train routes, test routes and terrain information (labelled as per filenames) for a set of insect-inspired route navigation experiments conducted in Unity.</p><p dir="ltr">For code analysing this data see: <a href="https://github.com/amanyazevedoamin/RecapitulatedTrackConvergence" rel="noreferrer" target="_blank">https://github.com/amanyazevedoamin/RecapitulatedTrackConvergence</a></p><p dir="ltr">All trajectories are 2D and stored as csv files with headings of 'x','y' and 'heading' (degrees)</p><p dir="ltr">The folder names encode the following:</p><p dir="ltr">The first 3 characters corresponds to the training route length: "EXT" is 20m, "LON" is a longer 100m training route</p><p dir="ltr">The second 3 characters refer to the route recapitulation strategy in use.</p><p dir="ltr">- VBO = view based orientation</p><p dir="ltr">- FCS = cast and surge</p><p dir="ltr">- FBM = familiarity based modulation</p><p dir="ltr">The remaining batches of 3-character sets refer to the route heuristics implemented during the initial training route.</p><p dir="ltr">- _OS = oscillatory (gated)</p><p dir="ltr">- NES = goal loop</p><p dir="ltr">- _BA = beacon aiming</p><p dir="ltr">- RES = restricted field of view</p><p dir="ltr">- __NA = baseline (i.e. path integration and obstacle avoidance alone)</p><p dir="ltr">All experiments are repeated across 75 environment seeds, hence 75 entries for train, test and terrain for each folder representing the route learning heuristic and navigation algorithm being used.</p><h4><b>Paper Abstract</b><br><br>Individually foraging ants use egocentric views as a dominant navigation strategy for learning and retracing routes. Evidence suggests that route retracing can be achieved by algorithms which use views as `visual compasses’, where individuals choose the heading that leads to the most familiar visual scene when compared to route memories. However, such a mechanism does not naturally lead to route approach, and alternative strategies are required to enable convergence when off-route and for correcting on-route divergence. In this work we investigate how behaviour incorporated into visual compass like route learning and recapitulation strategies might enable convergence to a learned route and its destination. Without alterations to the basic form of the initial learning route, the most successful recapitulation method comes from a `cast and surge’ approach, a mechanism seen across arthropods for olfactory navigation. In this strategy casts form a ‘zig-zagged’ or oscillatory search in space for familiar views, and surges exploit visual familiarity gradients. We also find that performance improves if the learned route consists of an oscillatory motor mechanism with learning gated to occur when the agent approaches the central axis of the oscillation. Furthermore, such oscillations combined with the cast and surge method additively enhance performance, showing that it benefits to incorporate oscillatory behavior in both learning and recapitulation. As destination reaching is the primary goal of navigation, we show that a suitably sized goal-orientated learning walk might suffice, but that the scale of this is dependent on the degree of divergence, and thus depends on route length and the route learning and recapitulation strategies used. Finally we show that view familiarity can modulate on-the-spot scans performed by an agent, providing a better reflection of ant behavior. Overall, our results show that the visual compass can provide a basis for robust visual navigation, so long as it is considered holistically with the details of basic motor and sensory-motor patterns of ants undertaking route learning and recapitulation.</h4><h4><br></h4><p dir="ltr"><br></p> |
|---|