Networked mobility sensing couples local trajectory inference with remote geospatial context, making communication decisions part of the prediction system. We present GeoSplit, an edge--server framework for travel-mode recognition that separates the utility of map evidence, its training-time transfer, and its selective acquisition at runtime. On GeoLife with 10% labels, we evaluate these components under user-day and user-disjoint grouping. For unseen users, aligned full-map context raises macro-F1 from 0.7154 to 0.7864, while map-informed distillation yields a motion-only student at 0.7225. Through a compact query interface, entropy gating achieves 0.7729 macro-F1 versus 0.7738 for all queries, querying 39.5% of trajectories and reducing application payload by 60.5%. Under user-day grouping, selective and all-query scores are similarly close at a 21.6% query rate. Learned value estimation and probability fusion offer no consistent improvement. These results illustrate communication-efficient edge--server inference for an intelligent transportation sensing task.
Figures & tables
Figure 1: GeoSplit: local motion prediction with gated map-server assistance. Selected trajectories transmit compact motion and geometry; the server returns a class label. Offline calibration and distillation support evaluation of map utility, training-time transfer, and runtime acquisition.
Figure 2: Recognition–payload tradeoffs with 10% labels. Policies share predictors within each independently fitted protocol. Thresholds target 10/25/50/75% queries on inner calibration data; costs are realized outer-fold payloads. All-query scores use the fine interface.
Input or model
User-day
Unseen user
Motion only
0.8377
0.7154
Map only
0.6726
0.5602
Motion + coarse location
0.8404
0.7059
Motion + full map
0.8592
0.7864
Motion + shifted map
0.8388
0.7122
Motion + shuffled map
0.8336
0.7142
Table 1: Spatial evidence and training-time transfer with 10% labels. Entries are pooled outer-fold macro-F1. Both students use only motion at inference.
Grouping
Policy
q (%)
Bytes
F1
User-day
Local only
0.0
0.00
0.8377
All fine
100.0
104.39
0.8535
Entropy 25%
21.6
22.46
0.8539
Entropy 50%
46.4
48.46
0.8535
Unseen user
Local only
0.0
0.00
0.7154
All fine
100.0
104.39
0.7738
Table 2: Observed operating points with 10% labels. Entropy percentages are calibration targets; q and mean bytes per trajectory are measured on outer folds. Query policies use the fine-query interface.
We propose a momentum-guided federated split distillation framework for personalized, efficient, and autonomous temporal edge intelligence. We introduce TeRR-SAtt, our novel temporal reservoir student attention design that combines fixed reservoir representations, a lightweight temporal student, and personalized output modules. We also present AMGF, our anticipatory momentum-guided fusion mechanism that clusters clients through learning momentum and derives specialized teacher updates. On real-world smart-building data, TeRR-SAtt reduces edge training latency by 65.50%, inference latency by 44.70%, training memory usage by 18.40%, and inference CPU usage by 33.10% over the considered baselines. At the same time, AMGF improves local learning by up to 35.31% in RMSE compared to global updates.
Autonomous robots increasingly rely on edge computing to offload computationally intensive perception tasks while maintaining real-time operation over 5G networks. However, conventional fiducial marker detection pipelines provide limited opportunities for efficient task partitioning, making them poorly suited for communication-aware edge deployment. This paper proposes a semantic split inference framework for fiducial marker processing in 5G-enabled Edge SLAM. A DeepTag-inspired convolutional neural network is partitioned between the robot and the edge server, where intermediate feature representations serve as task-oriented semantic information transmitted over the wireless link. The framework is integrated into a ROS2-based robotic architecture and characterized over a real 5G communication testbed. Experimental results demonstrate accurate keypoint estimation, illustrate the impact on downstream pose estimation, and quantify the communication--computation trade-offs associated with different split points, providing practical insights for communication-aware deployment of deep visual perception in connected robotic systems.
Boris Radovanovic, Vukan Ninkovic, Katarina Vidojevic +2
Faculty of Technical Sciences, University of Novi Sad, Serbia · The Institute for Artificial Intelligence Research and Development of Serbia, Serbia
Vehicle trajectory prediction is central to highway perception, but deployment on roadside edge devices necessitates bounded, deterministic end-to-end latency. We present EdgeVTP, an embedded-first trajectory predictor that combines interaction-aware graph modeling with a lightweight transformer backbone and a one-shot curve decoder. By predicting future motion as compact curve parameters (anchored at the last observed position) rather than horizon-scaled autoregressive waypoints, EdgeVTP reduces decoding overhead while producing smooth trajectories. To keep runtime predictable in crowded scenes, we explicitly bound interaction complexity via a locality graph with a hard neighbor cap. Across three highway benchmarks and two Jetson-class platforms, EdgeVTP achieves the lowest measured end-to-end latency under a protocol that includes graph construction and post-processing, while attaining state-of-the-art (SotA) prediction accuracy on two of the three datasets and competitive error on other benchmarks. Our code is available at https://github.com/SeungjinStevenKim/EdgeVTP.
Seungjin Kim, Reza Jafarpourmarzouni, Christopher Neff +2
University of Wyoming · University of North Carolina at Charlotte · North Carolina A&T State University