Muhammad Mahbub Alam | Searcharxiv

arXiv2026

Task-Oriented Semantic Communication for Hazard Warning and Remote Operation in Connected Vehicle Platoons

Connected and automated vehicle platoons require reliable dissemination of task-relevant hazard information to enable appropriate downstream responses, with unresolved situations additionally requiring remote human intervention. However, the limited channel bandwidth of V2X communication makes high-volume sensor data transmission challenging, motivating the exchange of only task-relevant information rather than raw sensor data. This paper proposes an integrated semantic and task-oriented communication framework for cooperative hazard response and remote operation in automated vehicle platoons. The framework combines onboard instance segmentation and monocular depth estimation for task-oriented hazard decision-making with Stable Diffusion Variational Autoencoder (SD-VAE)-based semantic scene compression. Task-relevant hazard information and the compact semantic representation are jointly disseminated through a broadcast-based Emergency Semantic Message (ESM) over the existing V2X protocol stack. Evaluation demonstrates that SD-VAE consistently outperforms JPEG and JPEG 2000 on task-relevant reconstruction metrics, exhibiting graceful degradation rather than a sharp cliff effect under low-SINR conditions, demonstrating its feasibility for remote scene reconstruction when human intervention is required. Moreover, an extensive campaign of 7,290 simulation runs shows a low overall inter-vehicle collision rate of 0.99%, with collisions occurring mainly under extreme high-speed and short-gap conditions.

cs.NI↗

arXiv2014

A Probabilistic Delay Model for Bidirectional VANETs in City Environments

Routing in VANETs (Vehicular Ad hoc NETworks) is a challenging task due to large network sizes, rapidly changing topology and frequent network disconnections. State-of-the-art routing protocols tried to address these specific problems especially in city environments (vehicles constrained by road geometry, signal transmissions blocked by obstacles, degree of congestion in roads etc). It was noticed that in city scenarios codirectional roads consist of a collection of disconnected clusters because of traffic control strategies (e.g., RSU (Road Side Units), stop signs and traffic lights). In this paper, we propose an intervehicle ad-hoc routing metric called EFD (Expected Forwarding Delay) based on the vehicular traffic statistics (e.g., densities and velocities) collected on-the-fly. We derive an analytical expression for the expected size of a cluster in co-directional traffic. In case of disconnection between two co-directional clusters the opposite directional clusters are used as a bridge to propagate a message in the actual forwarding direction to reduce the delay due to carry and forward. Through theoretical analysis and extensive simulation, it is shown that our link delay model provides the accurate link delay estimation in bidirectional city environments.

cs.NI↗