FBW-P04
Visual Motion and Target Tracking
Connect visual motion processing to neural control for direction detection and continuous target following.
Training preparationApplications open
Statistics temporarily unavailable
Project background
Establish motion-direction recognition before connecting the readout to steering and continuous tracking. Evaluation will vary target speed, contrast, background interference and occlusion. Input mapping and circuit structure must be justified rather than replaced with hidden access to target coordinates.
This project connects a defined neural-computation question to a reproducible evaluation protocol and a community participation pathway. Results will be interpreted only within their recorded model, task and evidence scope.
Training goals
- Improve stable direction recognition.
- Reduce tracking angle error and target loss.
- Reduce reacquisition time after an occlusion.
Current foundation and milestones
The connectome and general simulation form a foundation. Visual encoding and tracking-specific readouts still need development and evidence.
Next milestone: Establish a motion-direction recognition benchmark
- PlannedEstablish a motion-direction recognition benchmark
- PlannedImplement the versioned task and measurement interface
- PlannedEvaluate frozen conditions and independent reproduction
Content updated:
Technical approach
Build simplified visual stimuli and spatiotemporal encoding, verify the relation between visual cell types and input positions, and read downstream responses. Evaluate the visual readout and behavioral controller separately before assessing them together. Ground-truth screen coordinates are evaluator inputs, not a substitute for neural visual recognition.
Method schematic
Task and evaluation design
Evaluation design
| Indicator | Definition | Direction | Units | Observation |
|---|---|---|---|---|
| Direction accuracy | Fraction of held-out stimuli with the correct direction readout. | Higher is better | % | Awaiting evaluation |
| Tracking angle error | Angular difference between desired and realized tracking direction. | Lower is better | degrees | Awaiting evaluation |
| Target loss | Fraction of the evaluation interval outside the tracking criterion. | Lower is better | % | Awaiting evaluation |
| Reacquisition time | Model time needed to recover tracking after occlusion. | Lower is better | model time | Awaiting evaluation |
No measured values have been published. Acceptance thresholds will be frozen in each task protocol before evaluation.
Expected deliverables
- Motion-direction readout configurations.
- Versioned tracking-control configurations.
- Speed and occlusion evaluation sets with reproduction reports.
Ways to participate
- Visual stimulus construction
- Parameter optimization
- Batch evaluation
- Control-interface development
Device requirements and task schedules will be matched by the community after runnable profiles have been evaluated. Unknown specifications are welcome in the application.
Apply to join training
Applications are received for community review and matching. Selection does not mean training has started.
References and related work
External sources provide technical background. They do not establish equivalent FBW capabilities.
View published research records ↗