25 July 2023 in IEEE Transactions on Mobile Computing
In connected autonomous vehicles (CAVs), the driving safety can be greatly deteriorated, in the presence of occlusions which are adverse to CAVs’ perception of region-of-interest (RoI). Collaborative perception on the basis the information sharing of occlusions among CAVs, in a real-time and accurate manner, provides a means of the occlusion-free RoI perception for safe driving. In this paper, we propose a novel framework of C ollaborative O cclusion- f ree P erception ( COFP ) in CAVs, to regain the real-time and accurate occlusion awareness. The innovative COFP targets two goals: well-balanced computation resource allocation, as well as fast and high-quality RoI information fusion. Specifically, the resource allocation problem, with the objective of minimizing CAVs’ completion delay, is formulated as a multi-player continuous potential game and solved by a better response dynamics (BRD) algorithm. The RoI information fusion, with the objective of maximizing the overall object depiction quality, is formulated as a combinatorial optimization problem, and solved by a modified discrete salp swarm (MDSSA) algorithm. Experimental results show that the proposed COFP with 5 GHz computing power can achieve full occlusion awareness for CAVs with 69.61% completion time reduction and 19.03% fusion quality improvement, compared to the existing methods.
2 March 2026 in IEEE Transactions on Mobile Computing
Integrating Generative AI (Gen-AI) into vehicular computing can significantly enhance road safety and driving experience. The performance of Gen-AI inference in vehicular computing is highly sensitive to the number of inference steps, where even minor adjustments can disrupt the balance between delay and inference quality. This raises a critical question: how can inference steps be optimally determined for diverse tasks, given the inherent delay-quality trade-offs? Existing approaches fail to offer an optimal solution due to the lack of flexible inference services and efficient memory bandwidth allocation strategies. To address these challenges, we develop a Criticality-aware Resource-efficient Inference (CARIN) framework, where inference steps are dynamically adjusted to balance delay and quality for multi-criticality tasks. Leveraging an accurate inference model, CARIN fully exploits in-vehicle resources to accelerate both parameter loading and task computing during inference. The joint optimization problem of step control, memory bandwidth allocation, and compute resource scheduling is formulated as a mixed-integer nonlinear programming (MINLP) problem, and solved by a novel learning-to-optimize (L2O) algorithm efficiently. Experimental results demonstrate that, for high-criticality tasks, the proposed approach achieves $28.4\%$ latency reduction and $36\%$ quality improvement over baseline methods.