Soto Anno

Takuma Tsubaki, Soto Anno, Seiya Komatsu et al.

Multipath transport has long been studied to improve robustness over heterogeneous networks, and Multipath QUIC (MPQUIC) is particularly attractive for low-latency applications because QUIC Datagram enables transmission without retransmissions. However, this advantage comes with a key drawback: QUIC Datagram is vulnerable to packet loss, especially in vehicular cellular environments with handovers and rapidly varying radio conditions. While prior studies have explored adaptive-FEC and coded multipath designs, practical deployment remains challenging when such mechanisms require substantial modifications to the transport stack or scheduler. In this paper, we present an adaptive Forward Error Correction (FEC) scheme for MPQUIC Datagram that reuses QUIC loss detection signals and an off-the-shelf Reed-Solomon (RS) coding library. The sender estimates smoothed per-path loss rates from QUIC loss signals and adaptively determines the number of parity packets for each FEC block according to the expected packet loss. We implement the proposed scheme on an existing MPQUIC stack and evaluate it through vehicular field experiments over three commercial LTE/5G paths. Under the main 4.0 Mbps setting, the proposed scheme improves both reliability and latency compared with No-FEC: the average one-way delay is reduced from 103.0 ms to 70.8 ms, the 95th-percentile delay from 281.2 ms to 142.3 ms, and the packet loss rate from 1.7 % to 0.8 %, with an average coding rate of 0.94. These results indicate that scheduler-agnostic adaptive-FEC can provide practical latency and reliability gains for MPQUIC Datagram under the measured vehicular mobile conditions.

Takashi Torii, Soto Anno, Masaki Okada et al.

We present CloudEmu, a trace-driven, cloud-native cellular-emulation testbed for vehicle video uplink communication. Reliable, low-latency video uplink over cellular networks is essential for remote monitoring of autonomous vehicles. However, existing testbeds fall into two extremes. Physical-vehicle platforms provide realism but are costly and make validation under identical network conditions difficult, whereas simulations are inexpensive and reproducible but generally cannot replay field-measured end-to-end performance dynamics without substantial calibration or readily run production video-uplink stacks. A software-defined, cloud-native emulation approach can combine the fidelity of trace-driven replay with the agility and scalability that network softwarization principles offer. To this end, we propose CloudEmu that replays time-synchronized cellular and position traces, collected once from vehicles, on commodity Linux-based virtual vehicle and video-receiver nodes. A Linux-based emulation framework couples traffic replay with position replay, tying network dynamics to each point along the route and enabling repeatable, route-aware experiments without repeated on-road trials. Our demo deploys a production-grade video-uplink stack on CloudEmu, allowing attendees to experience low-cost, repeatable trials and controlled comparisons under identical replayed network conditions.

Soto Anno, Kota Tsubouchi, Masamichi Shimosaka

Forecasting rail congestion is crucial for efficient mobility in transport systems. We present rail congestion forecasting using reports from passengers collected through a transit application. Although reports from passengers have received attention from researchers, ensuring a sufficient volume of reports is challenging due to passenger's reluctance. The limited number of reports results in the sparsity of the congestion label, which can be an issue in building a stable prediction model. To address this issue, we propose a semi-supervised method for congestion forecasting for trains, or SURCONFORT. Our key idea is twofold: firstly, we adopt semi-supervised learning to leverage sparsely labeled data and many unlabeled data. Secondly, in order to complement the unlabeled data from nearby stations, we design a railway network-oriented graph and apply the graph to semi-supervised graph regularization. Empirical experiments with actual reporting data show that SURCONFORT improved the forecasting performance by 14.9% over state-of-the-art methods under the label sparsity.