No abstract

Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving (AD) system. However, most proposed methods aim at addressing one of the two challenges mentioned above with a single model. To tackle this dilemma, this paper proposes spatio‐temporal semantics and interaction graph aggregation for multi‐agent perception and trajectory forecasting (ST‐SIGMA), an efficient end‐to‐end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework. ST‐SIGMA adopts a trident encoder–decoder architecture to learn scene semantics and agent interaction information on bird’s‐eye view (BEV) maps simultaneously. Specifically, an iterative aggregation network is first employed as the scene semantic encoder (SSE) to learn diverse scene information. To preserve dynamic interactions of traffic agents, ST‐SIGMA further exploits a spatio‐temporal graph network as the graph interaction encoder. Meanwhile, a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed. Extensive experiments on the nuScenes data set have demonstrated that the proposed ST‐SIGMA achieves significant improvements compared to the state‐of‐the‐art (SOTA) methods in terms of scene perception and trajectory forecasting, respectively. Therefore, the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in real‐world AD scenarios.

No abstract

This paper focuses on energy efficiency that is a key performance metric in heterogeneous cellular networks to two key areas. First, based on the Poisson point process distributions of small-cell base stations (SBSs) and macrocell base stations (MBSs), the energy-efficiency model is formulated, and the effect of base stations' distribution on energy efficiency is analyzed. For maximizing energy efficiency, the joint optimal densities of SBSs and MBSs are deduced under the constraint of quality of service. Second, according to this, we propose a joint sleep strategy of MBSs and that of SBSs. We deduce the optimal threshold of traffic load according to the joint optimal densities. If the traffic load of SBSs (or MBSs) is less than the optimal threshold of traffic load, these SBSs (or MBSs) go to sleep; otherwise, it is activated. This makes the SBSs and MBSs adaptively and distributively sleep according to their own traffic loads. The simulation results verify that the deduced joint optimal densities of the SBS and the MBS are accurate, and energy efficiency is improved when SBSs and MBSs adaptively sleep.

No abstract