FBW-P08
Hexapod Coordination and Recovery
Link neural control to a virtual body to study coordinated walking, steering, and recovery from perturbations.
Training preparationApplications open
Statistics temporarily unavailable
Project background
This is a long-term embodied-control project. MaleCNS includes brain and ventral nerve cord data, while complete body control also needs dynamics, action interfaces, sensory feedback and validation. Establish stable planar walking before extending to steering and disturbances.
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
- Establish stable walking in a virtual body.
- Evaluate speed changes and steering.
- Measure recovery from small perturbations and simple terrain changes.
Current foundation and milestones
The CNS connectome is a reusable foundation. There is no accepted complete six-legged controller for this new project without its body and interface evidence.
Next milestone: Select a body model and establish the neural-to-motor interface
- PlannedSelect a body model and establish the neural-to-motor interface
- PlannedImplement the versioned task and measurement interface
- PlannedEvaluate frozen conditions and independent reproduction
Content updated:
Technical approach
Use layered control: brain-level output selects speed and turning, a declared lower-level rhythm or motor controller drives a six-legged body, and body feedback returns to the system. Public simulation components may be reused with explicit attribution of each control layer. An external preprogrammed gait must not be attributed entirely to the FBW neural model.
Method schematic
Task and evaluation design
Evaluation design
| Indicator | Definition | Direction | Units | Observation |
|---|---|---|---|---|
| Stable walking duration | Model time satisfying the declared balance and motion criteria. | Higher is better | model time | Awaiting evaluation |
| Fall fraction | Fraction of trials failing the declared body-stability criterion. | Lower is better | % | Awaiting evaluation |
| Speed tracking error | Difference between requested and realized body speed. | Lower is better | environment speed | Awaiting evaluation |
| Recovery time | Model time from a defined disturbance to recovered stability. | Lower is better | model time | Awaiting evaluation |
| Control smoothness | Change in commanded joint or motor action between consecutive model steps, with stability assessed separately. | Lower is better | action units / model step | Awaiting evaluation |
No measured values have been published. Acceptance thresholds will be frozen in each task protocol before evaluation.
Expected deliverables
- Versioned body-control configurations.
- Stability and perturbation-recovery evaluation.
- Reproduction documentation for the body and control interface.
Ways to participate
- Simulation development
- Control parameter optimization
- Batch body-task evaluation
- Independent reproduction
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 ↗