Cross-medium acoustic–radio collaborative networks enable integrated communication among underwater, surface, and aerial nodes for marine observation and detection. However, heterogeneous propagation characteristics of acoustic and radio channels significantly degrade the performance of conventional single-medium routing protocols, resulting in excessive control overhead, a low packet delivery ratio (PDR), and high latency. To address these challenges, this paper proposes an optimized AODV protocol for Cross-medium Acoustic–Radio Collaborative Networks (CACN-OAODV). The proposed protocol incorporates a medium-aware routing initiation mechanism to reduce unnecessary broadcasts, a link stability factor that jointly considers hop count and channel quality for reliable path selection, and a lightweight control optimization scheme to limit routing overhead in acoustic environments. Extensive simulations conducted in NS-3 with realistic multi-channel propagation models demonstrate that CACN-OAODV significantly outperforms the standard AODV protocol, achieving improved PDR, higher throughput, and reduced end-to-end delay. These results indicate that CACN-OAODV provides an effective routing solution for heterogeneous cross-medium marine communication networks.

Marine cross-medium acoustic–radio collaborative networks must route traffic across heterogeneous underwater acoustic and radio links while coping with energy imbalance, congestion, and mobility-induced link instability. This paper proposes Q-Learning AODV, an AODV extension that integrates distributed Q-value updating and multipath route maintenance into existing RREQ, RREP, and HELLO procedures. The routing reward combines normalized residual energy, queue availability, inter-node distance/link stability, relative velocity, and, for air–sea links, elevation-angle information. The protocol maintains multiple node-disjoint candidate paths and forwards data through the currently highest-valued path. NS-3 simulations are reported for underwater-to-underwater, underwater-to-air, and air-to-underwater communication scenarios. Relative to conventional AODV, Q-Learning AODV increases packet delivery ratio from 55.8% to 88.3%, from 68.3% to 76.1%, and from 86.9% to 91.9%, corresponding to relative improvements of 58.2%, 11.4%, and 5.8%, respectively. The results indicate improved delivery reliability and communication-subsystem energy balancing at the cost of additional state exchange, Q-table storage, and route-selection computation.