🤖 AI Summary
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.
📝 Abstract
Generating a plausible robot action does not establish that current observations justify its execution. Motivated by exploratory observations of high-confidence visual outputs under severe occlusion, we present PIER, an execution-authorization interface that separates evidence checks, decision provenance, and stage-scoped re-observation from hardware control. The deterministic gate evaluates declared visual and tactile inputs, while its caller maintains a budget of at most one re-observation per stage. We evaluate the implementation using 1,600 threshold-grid cases and 1,200 paired synthetic traces spanning score noise, missing tactile inputs, stale observations, and falsely reassuring scores. The finite grid yields zero declared invariant violations, and a matched Boolean baseline reproduces all non-recovery decisions. Under synthetic score noise, re-observation reduces valid-state denials from 57/120 to 18/120 while increasing invalid-state proceeds from 5/120 to 7/120. Stale and falsely reassuring inputs expose limitations that threshold checks alone cannot resolve. Exploratory visual, tactile, and robot setup records provide context but do not establish physical task performance. These results characterize an inspectable authorization interface and its input-contract limitations, without claiming superiority over equivalent rule logic, calibrated tactile accuracy, or certified physical safety.