ITS Monday: Edition 25, 2025
ITS Monday is a small, weekly collection of curated content from the worlds of intelligent transport systems, smart mobility, and associated areas.
Included this week, a surge in home battery installations, WA electric superhighway news, a, Aussie autonomous vehicle update, and more.
The article headlines below are:
- Australia’s surge in household battery installations is ‘off the charts’ as government subsidy program powers up
- WA’s RAC electric-highway charging project ends despite rise in EVs
- World’s top court targets fossil fuels + Driverless cars are here
- An Ensemble Deep Learning Framework for Real-Time Queue Length Estimation at Signalized Intersections
- Australia will need a lot of big charging hubs: ARENA says electrifying road freight no longer optional
- Dynamic electric vehicle fleets management problem for multi-service platforms with integrated ride-hailing, on-time delivery, and vehicle-to-grid services
This week’s articles
Now, scroll down, and see what’s in this week’s edition. Oh, and before you do, be sure check out the quickest way to receive our new content via the subscription box just below …
“A federal government program that gives a 30% subsidy on home batteries has sparked an “off the charts” surge in installations, with more than 11,500 applications to the scheme in its first three weeks.”
Related iMOVE article:
READ THE ARTICLEWA’s RAC electric-highway charging project ends despite rise in EVs
“Western Australian car insurer RAC is withdrawing from its “electric-highway” project after 10 years. The highway was the first network of electric-vehicle chargers of its kind in Australia.”
Related iMOVE articles:
- FACTS: A Framework for an Australian Clean Transport Strategy
- Sustainable Transportation: Info, Projects & Resources
World’s top court targets fossil fuels + Driverless cars are here
An episode of The Briefing podcast, part of which is a chat with Professor Michael Milford. The topic? Michael “explains why Australia is still behind despite being a world leader in the development of autonomous vehicle technology.”
Related iMOVE articles:
- Autonomous Driving Info, Projects & Resources
- Autonomous Driving Technology: Info, Projects & Resources
Related iMOVE projects:
- CAVs and Australians: Attitudes, perceptions, preferences
- Environmental impacts of Connected and Automated Vehicles
- Safely deploying automated vehicles on Australian roads
A new academic paper, co-authored by Wanuji Abewickrema, Mehmet Yildirimoglu, and Jiwon Kim. The abstract:
Optimal traffic control and signal planning can considerably reduce intersection congestion and delays. To accomplish this, it is essential to have accurate knowledge of the current and prospective vehicle queue lengths. This paper proposes a novel ensemble deep learning approach to estimate and predict the cycle-based maximum queue length in real time.
The proposed data-driven framework is built on high resolution traffic data obtained from a single loop detector. In contrast to traditional traffic flow theory-based approaches which depend on deterministic models, this methodology relies on learning the traffic patterns and queue length variations from data, allowing it to capture discrepancies within traffic patterns and as a result, produce improved results. The ensemble deep learning method employs two distinct neural networks: a multi-layer feedforward neural network (FNN) that maps the relationship between high resolution data and the cycle-based maximal queue length, and a stacked long–short-term memory (LSTM) model that captures the temporal variation of the queue lengths. The notion of ensemble produced by combining the outputs of both of these neural networks outperform the performance of the base models separately. This algorithm is trained and tested with simulated data and validated with real-world data obtained from an isolated intersection.
In addition, the proposed framework is compared to model-based techniques such as the Kalman filter.
READ THE ARTICLE“The Australian Renewable Energy Agency (ARENA) has published the country’s first national blueprint for the electrification of its road freight industry, which highlights the need for 165 heavy vehicle charging hubs and upgrades to energy transmission and distribution infrastructure.”
Related iMOVE article:
Related iMOVE projects:
- Zero emissions heavy vehicles: Analysis, planning and policy
- Investigating the viability of hydrogen fuel for heavy vehicle use
Last up this week, another new academic paper, this one co-authored by Qingying He, Wei Liu, and Haoning Xi. The abstract:
The rapid adoption of electric vehicles (EVs) and the surge in mobility service demand necessitate efficient management of EV fleets. In practice, these vehicles often remain idle for extended periods due to fluctuating demand, leading to underutilized resources and lost revenue. In response, this paper investigates a dynamic multi-service platform that concurrently coordinates ride-hailing, on-time delivery, and vehicle-to-grid (V2G) energy services.
By leveraging synergies across these services, the proposed coordination strategy improves resource utilization, reduces operational costs, and increases profitability. Upon accessing the platform, users submit various service requests that specify the origin, destination, time windows, and either the number of riders or the weight of goods. To meet these heterogeneous, real-time demands, we propose a dynamic multi-service electric vehicle fleet management (MEFM) problem to optimize the allocation, routing, and scheduling of EV fleets to maximize platform profits over each time period. We formulate the proposed MEFM problem as an arc-based mixed-integer linear programming (MILP) model and develop a customized branch-and-price-and-cut (B&P&C) algorithm for its efficient solution.
Our algorithm integrates Dantzig–Wolfe decomposition, improved with subset row cuts, and a novel labeling sub-algorithm that effectively captures multi-service coordination, fleet capacity, and battery-level constraints under partial recharging flexibility. Extensive numerical experiments based on a case study in the context of Shenzhen, China, demonstrate that the customized B&P&C algorithm achieves computation speeds on average 150.99 times faster than the state-of-the-art commercial solver (Gurobi), with speed-ups ranging from 3.33 to 477.42 times, while consistently obtaining optimal solutions for large-scale instances where Gurobi fails.
Moreover, our results highlight the benefits of integrating on-time delivery and V2G energy services, e.g., despite a modest increase in operational costs, the substantial rise in profits validates the economic potential of the multi-service platforms. We also identify that partial recharging flexibility for EVs further reduces delay costs by up to 70.27% and boosts overall profits by up to 40.90%.
READ THE ARTICLEDiscover more from iMOVE Australia Cooperative Research Centre | Transport R&D
Subscribe to get the latest posts sent to your email.