To provide high quality of service (QoS) for delay sensitive real-time traffic in wireless local area network-based (WLAN) mesh networks is a challenging task. In particular for real-time flows subject to multiple hops, mobility and time-varying channel, the performance of real-time flows will be degraded greatly. Efficient allocation and management of resources, such as transmission rate and throughput, is a crucial element and an attractive and efficient way for interconnecting access points (APs) to form an efficient multihop WLAN mesh network supporting QoS. Considering that IEEE 802.11 WLAN physical layers (PHYs) provide multiple transmission rates by employing different modulations and channel coding schemes, it is an important issue how to select the transmission rate so that the performance is improved, since each link generally has different characteristics with other links. In order to support real-time traffic, an efficient intelligent rate control algorithm is proposed in this paper, which aims to improve the system performance by adaptively adjusting the transmission rate to the current channel status. Based on the learning the local information of each node, the proposed algorithm can achieve accurate channel estimation without any extra implementation effort and modifications to the current 802.11 standard. And each node is able to select the optimized transmission rate, so that the system performance can be improved obviously. The proposed scheme also offers an appealing combination of the allocation of transmission rate and the current link condition. Based on the basic relationship between them, the intelligent rate control algorithm maximizes the throughput with periodic learning of channel variation and system status. Theoretical analysis proves that the proposed algorithm is quickly convergent. Detailed simulation and numerical results show the proposed rate control algorithm closely approximates the ideal case with the perfect knowledge about the channel. Compared with the existed schemes, the proposed algorithm can also significantly improve the system performance in terms of packet loss rate, end-to-end delay and throughput.