We studied how a mobile Jackal robot equipped with AI-based visual crack detection can support inspectors working in nuclear facilities. By teaming humans with perception-enabled robots, the workflow reduces exposure to hazardous areas and lowers the cognitive load that comes with manual inspections.
Overview
- Crack detection was automated with deep learning models tuned for nuclear-grade concrete surfaces.
- The robot handled navigation, data capture, and candidate crack annotation, while operators validated results through an intuitive interface.
- The experiment benchmarked human-only inspections against the collaborative mode to quantify efficiency gains.
Findings
- Human-robot collaboration improved detection accuracy and consistency over manual-only inspection.
- Operators reported reduced workload thanks to automated pre-filtering of likely defects and richer situational awareness delivered through shared displays.
- The study highlights deployment considerations for high-radiation environments, including communication robustness and safety protocols.
Why It Matters
Structural integrity checks are essential for nuclear operations yet traditionally hazardous. Combining mobile robotics with trustworthy AI narrows the gap between safety and thoroughness, paving the way for continuous monitoring without overburdening human experts.