feat(scene): hardware-aware perception tiers with contract-sourced camera intrinsics#89
Open
HeartLinked wants to merge 1 commit into
Open
feat(scene): hardware-aware perception tiers with contract-sourced camera intrinsics#89HeartLinked wants to merge 1 commit into
HeartLinked wants to merge 1 commit into
Conversation
…efault Change-Id: I1b7975a34eb2f27136fc230cc740a702245f2fd7
enkerewpo
requested review from
Copilot and
enkerewpo
and removed request for
Copilot
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Depth back-projection scales every 3D point by fx/fy and offsets it by cx/cy. Feeding ConceptGraphs incorrect intrinsics silently places objects at the wrong map position.
Scene previously defaulted every camera to the Webots Tiago K intrinsics: That default is correct for simulation only. Any other camera produced misplaced objects without crashing or warning unless an operator manually set SCENE_CAMERA_INTRINSICS.
Detector selection was previously implemented as an inline if/elif on hub.has(...), which silently fell through to detector disabled when no camera was wired.This change extracts detector selection into a pure, testable probe that names the tier Scene runs and logs the plan once at startup.
Adds plan_perception(hub), returning a frozen PerceptionPlan that selects one of three tiers based on camera availability:
metric: RGB-D camera → ConceptGraphs
visual: RGB camera → VLM
geometric: no camera → detector disabled; occupancy_grid and goal_near remain available