# Research Goal

> Generated from repository source files. Do not edit this page directly; edit the source file listed below and rerun `vp run docs:generate`.

> Source: `research/01-research-goal.md`

## Research Goal

Status: `planning source`

## Target

SAH-BRI studies how a non-invasive EEG interface can act as a high-level intention channel inside a scene-aware robot system.

The current system instance, SAH-BRI-Grasp, narrows that goal to robotic grasping:

```text
human intention -> scene understanding -> shared autonomy -> robot grasp execution
```

## Core Question

Can a scene-aware hybrid BCI reduce the control burden of non-invasive EEG by moving low-level robot motion into shared autonomy, while keeping the user in the loop through high-level target selection, confirmation, intervention, and stopping commands?

## Working Hypothesis

The central hypothesis is `inferred` from the current evidence base:

* SSVEP is suitable for reliable discrete target selection and confirmation.
* MI is suitable for active intervention, mode control, and stop/confirmation signals.
* YOLO-style visual detection can convert the physical scene into a dynamic command space.
* Robot planning and grasp execution should handle low-level continuous control.
* Shared autonomy is the integration layer that combines user intent and robot capability.

Integrated SAH-BRI-Grasp performance remains `needs confirmation` until Exp1-Exp4 data exist.

## What The Project Is Not

This project is not trying to prove that non-invasive EEG can directly control every robot joint or every 6-DoF motion primitive.

The research direction is:

```text
from brain-controlled robot arm
to brain-intent-guided robotic grasping
```

## Evidence Boundary

The 73-paper corpus supports component-level rationale and system-design comparisons. It does not yet support claims about project-specific grasp success rate, workload reduction, low-channel online performance, or clinical efficacy.

## Next Step

Continue to the [SAH-BRI framework](/framework/sah-bri) to see how the framework and current system instance relate.