Frame coordinates robot arms and laser sensing for flexible inspection
Task-Specified Active Metrological Inspection with Measurement-Steered VLA Manipulation and Deterministic Evidence Gating
RoboticsArtificial IntelligenceComputer Vision and Pattern Recognition
Summary
Manufacturing of many different parts in small amounts is hard to inspect flexibly because usual inspection systems follow fixed steps and can’t easily adapt. The authors propose a system called FRAME that helps robots understand inspection tasks and carefully measure parts using laser scanners and robot arms. FRAME keeps track of what parts have been measured and makes sure measurements meet requirements before giving a final pass. Tests showed FRAME inspection was more reliable, faster, and made fewer mistakes than older methods.
What this means in practice
- •For manufacturing engineers: Implement adaptable inspection workflows that automatically ensure measurement validity for diverse custom parts without manual reprogramming.
- •For robotics integrators: Build inspection robots that can actively position sensors and verify measurement correctness to reduce errors and speed up quality control tasks.
- •For automotive quality teams: Improve part acceptance processes by using active inspection that guarantees coverage and traceable evidence, reducing false approvals.$Commercial implications: This enables building quality inspection products that meet strict automotive industry standards with automated evidence verification.
Authors
Zhiling Chen, Jingzhan Ge, Ruimin Chen, Matthew P. Castanier, David Gorsich, Farhad Imani
Abstract
High-mix low-volume (HMLV) manufacturing requires inspection systems to adapt to changing parts, specifications, and work orders without repeated task-specific programming. Existing inspection automation typically assumes predefined sensing sequences, while general purpose robot agents optimize task completion rather than the completeness and validity of metrological evidence. We formulate task-specified active metrological inspection and propose From Requirements to Admissible Metrological Evidence (FRAME), a hierarchical dual-arm framework that converts an inspection instruction and structured specification into traceable conformance evidence. FRAME coordinates learned manipulation with calibrated laser profilometry: a task manager grounds and schedules requirements, active surface correspondence verifies physical-to-specification localization, and evidence memory tracks measurement provenance, admissibility, and coverage. Learned components may propose inspection targets and physical access actions, but deterministic datum-grounded measurement, admissibility checks, coverage auditing, and conformance evaluation prevent incomplete or unverified evidence from authorizing PASS. A series of physical experiments shows that FRAME achieves higher end-to-end inspection reliability, fewer false accepts, and shorter task completion time.