PIER: An Evidence-Gated Execution Interface for Robotic Manipulation
This study addresses the vulnerability of robotic systems to erroneous actions under severe occlusion, where high-confidence visual outputs often lack evidential support. To mitigate this, we propose the PIER interface, which decouples evidence verification, decision traceability, and hardware control by jointly evaluating visuo-tactile inputs through deterministic gating logic. Furthermore, a novel phase-level re-observation budget mechanism is introduced to enable auditable execution authorization. Evaluated across 1,600 synthetic trajectory test cases, the proposed approach achieves zero safety violations. The re-observation mechanism substantially reduces the false rejection rate for valid states from 57% to 18%. These findings highlight the inherent limitations of purely threshold-based methods when operating under complex perceptual noise, demonstrating that structured evidential reasoning yields significantly more robust and verifiable robotic control.