Enhancing transportation agility through neuroadaptive AI and behavioural decision intelligence

Transportation systems increasingly face real-time disruptions—from urban congestion to infrastructure failures—that demand agile, human-informed responses. While traditional AI tools offer operational support, they often overlook the cognitive and emotional conditions under which critical decisions are made by drivers, dispatchers, and mobility coordinators. This gap limits their effectiveness in high-stress, rapidly changing environments where human decision-makers play a critical role.

To address this, the present study introduces a neuroadaptive framework for transportation agility that integrates real-time behavioral insights into intelligent decision-support systems. This framework, inspired by the foundational principles of supply chain agility (SCA), consists of three interconnected stages: sensing operator stress and cognitive load, predicting decision tendencies, and reconfiguring mobility strategies in real time. Crucially, the framework incorporates a reinforcement learning element, forming a continuous feedback loop that refines AI responses based on user behaviour and system performance. This adaptive mechanism ensures that transport platforms evolve toward more human-aligned, context-aware decision-making, enhancing both agility and resilience over time.

By advancing this novel, human-centric model, the study extends the agility discourse into the transportation domain, emphasizing the critical link between cognitive awareness, real-time adaptation, and long-term system learning. This approach offers a scalable foundation for adaptive, context-aware, and resilient mobility networks, aligning closely with the demands of future smart cities and intelligent transport systems.