Marco Rinaldi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Marco Rinaldi has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Francesco Viti
University of Luxembourg
14 shared publications - Chris M. J. Tampere
KU Leuven
7 shared publications - Chaopeng Tan
Technische Universität Dresden
6 shared publications - Claudio Roncoli
KU Leuven
3 shared publications - Dingshan Sun
Tongji University
3 shared publications - Georgios Laskaris
Laboratory of Transportation Engineering, School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, Athens, Zographos, Greece
3 shared publications
Latest Publications
- Open Access
- 10 November 2026
- Published by Elsevier in Transportation Research Today
Unpacking seamlessness in transportation: A systematic literature review approach
- 10 November 2026
- Published by Elsevier in Transportation Research Today
Open AccessUnpacking seamlessness in transportation: A systematic literature review approach
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (11) , 15036-15048
Weather-Robust Ramp Metering Using Pre-Trained Deep Q-Networks
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (11) , 15036-15048
Weather-Robust Ramp Metering Using Pre-Trained Deep Q-Networks
- 16 October 2026
- Published by Elsevier in Transportation Research Part B: Methodological
- Vol. 215
Transit-MP: Transit-prioritized max-pressure control in sparse connected vehicle environments
- 16 October 2026
- Published by Elsevier in Transportation Research Part B: Methodological
- Vol. 215
Transit-MP: Transit-prioritized max-pressure control in sparse connected vehicle environments
- 18 August 2026
- Published by Springer Nature
- p. 74-92
A Unified Privacy-Preserving Federated Learning Framework for Horizontal and Vertical Data Partitioning
- 18 August 2026
- Published by Springer Nature
- p. 74-92
A Unified Privacy-Preserving Federated Learning Framework for Horizontal and Vertical Data Partitioning
- Open Access
- 24 July 2026
- Published by Elsevier in SSRN Electronic Journal
Preference-Adaptive Eco-Driving for Electric Buses under Transit-Priority Adaptive Signals
Eco-driving for electric buses under transit-priority adaptive signals requires balancing two primary operational objectives: travel (schedule) efficiency and energy consumption. Existing studies mainly rely on fixed-objective optimization, which limits their adaptability to varying operational contexts and dynamic service requirements. To address this limitation, this paper proposes a preference-adaptive eco-driving framework for electric buses operating under transit-priority adaptive signals. The proposed approach builds on a preference-conditioned deep reinforcement learning policy that learns a unified control strategy over diverse context-dependent trade-offs between schedule-oriented operation and energy conservation, while retaining comfort-preserving smoothness regularization for executable longitudinal control. On top of this, an online preference adaptation mechanism is introduced to dynamically adjust objective weights according to real-time bus operating conditions, such as service delay, energy status, and local driving context, while a smoothing scheme is designed to ensure stable and executable preference transitions. The framework is evaluated on a simulated real-world corridor in Amsterdam with multiple bus lines and adaptive signal interactions, considering both seen and unseen operational scenarios. Results show that the proposed method captures diverse schedule--energy trade-offs, improves context matching across heterogeneous lines, and maintains better energy feasibility under dynamic energy-budget stress. These results demonstrate the effectiveness of online preference adaptation for context-matched and feasibility-aware electric bus eco-driving.
- 24 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessPreference-Adaptive Eco-Driving for Electric Buses under Transit-Priority Adaptive Signals
Eco-driving for electric buses under transit-priority adaptive signals requires balancing two primary operational objectives: travel (schedule) efficiency and energy consumption. Existing studies mainly rely on fixed-objective optimization, which limits their adaptability to varying operational contexts and dynamic service requirements. To address this limitation, this paper proposes a preference-adaptive eco-driving framework for electric buses operating under transit-priority adaptive signals. The proposed approach builds on a preference-conditioned deep reinforcement learning policy that learns a unified control strategy over diverse context-dependent trade-offs between schedule-oriented operation and energy conservation, while retaining comfort-preserving smoothness regularization for executable longitudinal control. On top of this, an online preference adaptation mechanism is introduced to dynamically adjust objective weights according to real-time bus operating conditions, such as service delay, energy status, and local driving context, while a smoothing scheme is designed to ensure stable and executable preference transitions. The framework is evaluated on a simulated real-world corridor in Amsterdam with multiple bus lines and adaptive signal interactions, considering both seen and unseen operational scenarios. Results show that the proposed method captures diverse schedule--energy trade-offs, improves context matching across heterogeneous lines, and maintains better energy feasibility under dynamic energy-budget stress. These results demonstrate the effectiveness of online preference adaptation for context-matched and feasibility-aware electric bus eco-driving.
- Open Access
- 6 July 2026
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 191
Private-MP: Privacy-Preserving Max-Pressure control based on heterogeneous data fusion
- 6 July 2026
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 191
Open AccessPrivate-MP: Privacy-Preserving Max-Pressure control based on heterogeneous data fusion
- Open Access
- 30 June 2026
- Published by Elsevier in Transportation Research Part B: Methodological
- Vol. 211
Mitigating network traffic congestion via link- and path-based incentives
- 30 June 2026
- Published by Elsevier in Transportation Research Part B: Methodological
- Vol. 211
Open AccessMitigating network traffic congestion via link- and path-based incentives
- Open Access
- 9 April 2026
- Published by Elsevier in SSRN Electronic Journal
TUD-SUMO: A Research-oriented SUMO Wrapper for Traffic Simulation in Python
TUD-SUMO is a Python wrapper for SUMO, a traffic simulation software, designed to support the development of traffic control systems, particularly adaptive systems where data is frequently transferred between a controller and the traffic environment. It provides automated data collection and a set of modular, extensible tools allowing for a wide range of scenarios and control strategies to be simulated and compared. These capabilities are accessed through a simplified interface that enables rapid prototyping of control strategies with complex interactions using minimal code, promoting ease of use and portability. TUD-SUMO has already been employed in multiple projects at Delft University of Technology, including two Horizon Europe projects and 2 transportation engineering courses.
- 9 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTUD-SUMO: A Research-oriented SUMO Wrapper for Traffic Simulation in Python
TUD-SUMO is a Python wrapper for SUMO, a traffic simulation software, designed to support the development of traffic control systems, particularly adaptive systems where data is frequently transferred between a controller and the traffic environment. It provides automated data collection and a set of modular, extensible tools allowing for a wide range of scenarios and control strategies to be simulated and compared. These capabilities are accessed through a simplified interface that enables rapid prototyping of control strategies with complex interactions using minimal code, promoting ease of use and portability. TUD-SUMO has already been employed in multiple projects at Delft University of Technology, including two Horizon Europe projects and 2 transportation engineering courses.
- Open Access
- 3 January 2026
- Published by Elsevier in Transportation Research Part B: Methodological
- Vol. 204
CV-MP: Max-pressure control in heterogeneously distributed and partially connected vehicle environments
- 3 January 2026
- Published by Elsevier in Transportation Research Part B: Methodological
- Vol. 204
Open AccessCV-MP: Max-pressure control in heterogeneously distributed and partially connected vehicle environments
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (9) , 1-14
Dwelling and Speed Advisory Enhanced Max-Pressure Control With Transit Signal Priority
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (9) , 1-14
Dwelling and Speed Advisory Enhanced Max-Pressure Control With Transit Signal Priority