Hybrid Quantum-Classical Optimization Algorithms for Autonomous Vehicle Navigation and Intelligent Smart Transportation Systems

AVs and intelligent transportation systems (ITS) are increasingly relying on large-scale, real-time optimization problems to solve, including path planning, traffic light coordination, and fleet management problems, which are hard to effectively solve in dynamic and multi-agent environments with classical algorithms. Although quantum computing has hypothetical benefits in the form of superposition and entanglement, by current Noisy Intermediate-Scale Quantum (NISQ) hardware constraints, standalone quantum solutions are, in practice, not possible. To ensure this is bridged, hybrid quantum-classical algorithms have sprung up, which use quantum subroutines, but with classical control to enable scalability and resilience to noise. The review summarises the recent advancements in the hybrid optimization of AV navigation and the ITS including ground rules which govern quantum concepts, hybrid meta heuristics, and noise reduction methods. It presents a new 4D systematic of extant algorithms as specified by quantum-classical ratio split, type of problem encoding, NISQ-compatibility and application granularity, as well as a comparative performance synthesis benchmarking quantum-inspired algorithms against classical references of their own. Results on convergence speed and exploration of solution-space Hybrid methods always yield faster convergence and exploration of solution-space, especially on combinatorial problems, such as vehicle routing, and signal timing. Such insights have been useful in applications throughout trajectory optimization, multi-agent coordination, traffic signal control, and fleet management, providing researchers with a systematic basis to create scalable, real-time hybrid optimization platforms that can be used to build autonomous mobility infrastructures of the next generation.