Task-Oriented Semantic Communication for Hazard Warning and Remote Operation in Connected Vehicle Platoons
Authors: S M Sabit Bananee, Shahriar Hasan, Muhammad Mahbub Alam, Nafiul Rashid
Organizations: Department of Computer Science and Engineering, Islamic University of Technology, Gazipur 1704, Bangladesh · Department of Computer Science and Engineering, Mälardalen University, 721 23 Väster˚as, Sweden · Samsung Research America, Mountain View, CA 94043, USA
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.
Figures & tables
Fig. 1: System architecture for semantic and task-oriented hazard warning and remote operation.
Fig. 2: End-to-end encoder-decoder architecture of the proposed semantic and task-oriented framework. The platoon LV extracts hazard features and sparse latent semantics, and the receiver reconstructs the scene and performs zone-based response.
Parameter
Values
Count
Platoon size
4, 6, 8 vehicles
3
non-platooning vehicles
50, 100, 200
3
Leader speed
80, 100, 120 km/h
3
CACC algorithm
Rajamani et al. [ 21 ] , Ploeg et al. [ 22 ]
2
Inter-platoon gap
50, 100, 150 m
3
Deceleration rate
−5 , −6 , −8 m/s 2
3
TABLE I: Simulation parameter space ( 7,290 runs).
Fig. 3: SD-VAE BPP as a function of input resolution, illustrating continuous rate control via resolution-adaptive encoding.
Fig. 4: Rate-distortion performance of SD-VAE compared against JPEG and JPEG 2000 across pixel-level ( SSIM, top left ), perceptual ( LPIPS, top right ), and task-relevant ( mIoU, bottom left ; [email protected], bottom right ) reconstruction quality as a function of BPP.
Fig. 5: Decoded scene quality of SD-VAE, evaluated across all tested input resolutions (thin lines, 64–320 px, with 160 px highlighted in bold), compared to JPEG and JPEG 2000 for varying SINR (dB).
Class
Box Precision
Box Recall
Box F1 Score
Box mAP50
Mask mAP50
Pedestrian
0.756
0.419
0.539
0.500
0.464
Car
0.784
0.623
0.694
0.673
0.611
Truck
0.603
0.343
0.437
0.409
0.384
Bus
0.702
0.311
0.431
0.363
0.360
Motorcycle
0.638
0.255
0.364
0.325
0.324
Bicycle
0.397
0.062
0.107
0.094
0.079
TABLE II: YOLOv8n-seg validation results on BDD100K-10K.
Fig. 6: Decision path for collision occurrence across all 7,290 simulation runs, identified by a decision tree classifier. Every leaf reaches exactly 0% or 100% collision rate.
Intelligent Transportation Systems (ITS) demand real-time collision prediction to ensure road safety and reduce accident severity. Conventional approaches rely on transmitting raw video or high-dimensional sensory data from roadside units (RSUs) to vehicles, which is impractical under vehicular communication bandwidth and latency constraints. In this work, we propose a semantic V2X framework in which RSU-mounted cameras generate spatiotemporal semantic embeddings of future frames using the Video Joint Embedding Predictive Architecture (V-JEPA). To evaluate the system, we construct a digital twin of an urban traffic environment enabling the generation of d verse traffic scenarios with both safe and collision events. These embeddings of the future frame, extracted from V-JEPA, capture task-relevant traffic dynamics and are transmitted via V2X links to vehicles, where a lightweight attentive probe and classifier decode them to predict imminent collisions. By transmitting only semantic embeddings instead of raw frames, the proposed system significantly reduces communication overhead while maintaining predictive accuracy. Experimental results demonstrate that the framework with an appropriate processing method achieves a 10% F1-score improvement for collision prediction while reducing transmission requirements by four orders of magnitude compared to raw video. This validates the potential of semantic V2X communication to enable cooperative, real-time collision prediction in ITS.
Murat Arda Onsu, Poonam Lohan, Burak Kantarci +3
School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada. · Nokia Bell Labs, 600 March Road, Kanata, ON K2K 2E6, Canada.
Remote Operation is touted as being key to the rapid deployment of automated vehicles. Streaming imagery to control connected vehicles remotely currently requires a reliable, high throughput network connection, which can be limited in real-world remote operation deployments relying on public network infrastructure. This paper investigates how the application of computer vision assisted semantic communication can be used to circumvent data loss and corruption associated with traditional image compression techniques. By encoding the segmentations of detected road users into colour coded highlights within low resolution greyscale imagery, the required data rate can be reduced by 50% compared with conventional techniques, while maintaining visual clarity. This enables a median glass-to-glass latency of below 200 ms even when the network data rate is below 500 kbit/s, while clearly outlining salient road users to enhance situational awareness of the remote operator. The approach is demonstrated in an area of variable 4G mobile connectivity using an automated last-mile delivery vehicle. Results indicate that large-scale deployment of remotely operated automated vehicles could be possible even on the often constrained public 4G/5G mobile network, providing the potential to expedite the nationwide roll-out of automated vehicles.
Sebastian Donnelly, Ruth Anderson, George Economides +4
Autonomous Driving and Intelligent Transport Group, Oxford Brookes University, Oxford, UK · Oxfordshire County Council, Oxford, UK · Department for Transport, London, UK +2
Vehicle-to-Everything (V2X) cooperative perception improves 3-D detection by sharing intermediate features, but dense remote features may repeat context that the ego agent can infer locally. Most communication-efficient designs optimize masks or codes empirically, leaving a more basic question open: which remote evidence is indispensable given the receiver's own observation? We introduce a closure-fidelity perspective on ego conditioned remote perception. Under a finite deductive abstraction and explicit conditions, its rate--distortion function decomposes over an irredundant core, and the exact zero-distortion rate becomes PAH(πA). This analysis suggests a concrete design principle: transmit compact evidence and recover derivable context with bounded receiver-side inference. Guided by this principle, SemRD-V2X is an operational neural proxy that combines exact-budget BEV support selection, pointwise channel compression, and masked shared-weight reconstruction before standard fusion. Experiments on simulated V2XSet and real-world DAIR-V2X validate the resulting design. In a controlled five-run V2XSet comparison against a locally reproduced V2X-ViT-v1 baseline on one Tesla V100, SemRD-V2X reduces the analytical feature payload by 26.6× while improving [email protected]/[email protected] by 4.13/8.57 points, with 3.81% additional mean compute latency. These results position closure fidelity as both an analytical lens and an actionable design principle for communication-efficient cooperative perception.