| 1. |
- Andersson, Viktor, 1995, et al.
(författare)
-
Controlled Decent Training
- 2023
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- In this work, a novel and model-based artificial neural network (ANN) training method is developed supported by optimal control theory. The method augments training labels in order to robustly guarantee training loss convergence and improve training convergence rate. Dynamic label augmentation is proposed within the framework of gradient descent training where the convergence of training loss is controlled. First, we capture the training behavior with the help of empirical Neural Tangent Kernels (NTK) and borrow tools from systems and control theory to analyze both the local and global training dynamics (e.g. stability, reachability). Second, we propose to dynamically alter the gradient descent training mechanism via fictitious labels as control inputs and an optimal state feedback policy. In this way, we enforce locally H2 optimal and convergent training behavior. The novel algorithm, Controlled Descent Training (CDT), guarantees local convergence. CDT unleashes new potentials in the analysis, interpretation, and design of ANN architectures. The applicability of the method is demonstrated on standard regression and classification problems.
|
|
| 2. |
- Andersson, Viktor, 1995, et al.
(författare)
-
Controlled Descent Training
- 2024
-
Ingår i: International Journal of Robust and Nonlinear Control. - 1099-1239 .- 1049-8923.
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, a novel and model-based artificial neural network (ANN) training method is developed supported by optimal control theory. The method augments training labels in order to robustly guarantee training loss convergence and improve training convergence rate. Dynamic label augmentation is proposed within the framework of gradient descent training where the convergence of training loss is controlled. First, we capture the training behavior with the help of empirical Neural Tangent Kernels (NTK) and borrow tools from systems and control theory to analyze both the local and global training dynamics (e.g. stability, reachability). Second, we propose to dynamically alter the gradient descent training mechanism via fictitious labels as control inputs and an optimal state feedback policy. In this way, we enforce locally H2 optimal and convergent training behavior. The novel algorithm, Controlled Descent Training (CDT), guarantees local convergence. CDT unleashes new potentials in the analysis, interpretation, and design of ANN architectures. The applicability of the method is demonstrated on standard regression and classification problems.
|
|
| 3. |
- Varga, Balázs, 1990, et al.
(författare)
-
Constrained Policy Gradient Method for Safe and Fast Reinforcement Learning: a Neural Tangent Kernel Based Approach
- 2021
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a constrained policy gradient algorithm. We introduce constraints for safe learning with the following steps. First, learning is slowed down (lazy learning) so that the episodic policy change can be computed with the help of the policy gradient theorem and the neural tangent kernel. Then, this enables us the evaluation of the policy at arbitrary states too. In the same spirit, learning can be guided, ensuring safety via augmenting episode batches with states where the desired action probabilities are prescribed. Finally, exogenous discounted sum of future rewards (returns) can be computed at these specific state-action pairs such that the policy network satisfies constraints. Computing the returns is based on solving a system of linear equations (equality constraints) or a constrained quadratic program (inequality constraints). Simulation results suggest that adding constraints (external information) to the learning can improve learning in terms of speed and safety reasonably if constraints are appropriately selected. The efficiency of the constrained learning was demonstrated with a shallow and wide ReLU network in the Cartpole and Lunar Lander OpenAI gym environments. The main novelty of the paper is giving a practical use of the neural tangent kernel in reinforcement learning.
|
|
| 4. |
- Varga, Balázs, 1990, et al.
(författare)
-
Data-driven distance metrics for kriging - Short-term urban traffic state prediction
- 2023
-
Ingår i: IEEE Transactions on Intelligent Transportation Systems. - 1524-9050 .- 1558-0016. ; 24:6, s. 6268-6279
-
Tidskriftsartikel (refereegranskat)abstract
- Estimating traffic flow states at unmeasured urban locations provides a cost-efficient solution for many ITS applications. In this work, a geostatistical framework, kriging is extended in such a way that it can both estimate and predict traffic volume and speed at various unobserved locations, in real-time. In the paper, different distance metrics for kriging are evaluated. Then, a new, data-driven one is formulated, capturing the similarity of measurement sites. Then, with multidimensional scaling the distances are transformed into a hyperspace, where the kriging algorithm can be used. As a next step, temporal dependency is injected into the estimator via extending the hyperspace with an extra dimension, enabling for short horizon traffic flow prediction. Additionally, a temporal correction is proposed to compensate for minor changes in traffic flow patterns. Numerical results suggest that the spatio-temporal prediction can make more accurate predictions compared to other distance metric-based kriging algorithms. Additionally, compared to deep learning, the results are on par while the algorithm is more resilient against traffic pattern changes.
|
|
| 5. |
- Varga, Balázs, 1990, et al.
(författare)
-
Deep Q-learning: a robust control approach
- 2023
-
Ingår i: International Journal of Robust and Nonlinear Control. - : Wiley. - 1099-1239 .- 1049-8923. ; 33:1, s. 526-544
-
Tidskriftsartikel (refereegranskat)abstract
- This work aims at constructing a bridge between robust control theory and reinforcement learning. Although, reinforcement learning has shown admirable results in complex control tasks, the agent’s learning behaviour is opaque. Meanwhile, system theory has several tools for analyzing and controlling dynamical systems. This paper places deep Q-learning is into a control-oriented perspective to study its learning dynamics with well-established techniques from robust control. An uncertain linear time-invariant model is formulated by means of the neural tangent kernel to describe learning. This novel approach allows giving conditions for stability (convergence) of the learning and enables the analysis of the agent’s behaviour in frequency-domain. The control-oriented approach makes it possible to formulate robust controllers that inject dynamical rewards as control input in the loss function to achieve better convergence properties. Three output-feedback controllers are synthesized: gain scheduling H2, dynamical Hinf, and fixed-structure Hinf controllers. Compared to traditional deep Q-learning techniques, which involve several heuristics, setting up the learning agent with a control-oriented tuning methodology is more transparent and has well-established literature. The proposed approach does not use a target network and randomized replay memory. The role of the target network is overtaken by the control input, which also exploits the temporal dependency of samples (opposed to a randomized memory buffer). Numerical simulations in different OpenAI Gym environments suggest that the Hinf controlled learning can converge faster and receive higher scores (depending on the environment) compared to the benchmark Double deep Q-learning.
|
|
| 6. |
- Varga, Balazs, et al.
(författare)
-
Network-Level Optimal Control for Public Bus Operation
- 2020
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 53:2, s. 15003-15010
-
Konferensbidrag (refereegranskat)abstract
- The paper presents modeling, control and analysis of an urban public transport network. First, a centralized system description is given, built up from the dynamics of individual buses and bus stops. Aiming to minimize three conflicting goals (equidistant headways, timetable adherence, and minimizing passenger waiting times), a reference tracking model predictive controller formulated based on the piecewise-affine system model. The closed-loop system is analyzed with three methods. Numerical simulations on a simple experimental network showed that the temporal evolution of headways and passenger numbers could maintain their periodicity with the help of velocity control. With the help of randomized simulation scenarios, sensitivity of the system is analyzed. Finally, infeasible regions for the bus network control was sought using by formulating an explicit model predictive controller.
|
|
| 7. |
- Varga, Balázs, et al.
(författare)
-
Public transport trajectory planning with probabilistic guarantees
- 2020
-
Ingår i: Transportation Research Part B: Methodological. - : Elsevier BV. - 0191-2615. ; 139, s. 81-101
-
Tidskriftsartikel (refereegranskat)abstract
- The paper proposes an eco-cruise control strategy for urban public transport buses. The aim of the velocity control is ensuring timetable adherence, while considering upstream queue lengths at traffic lights in a probabilistic way. The contribution of the paper is twofold. First, the shockwave profile model (SPM) is extended to capture the stochastic nature of traffic queue lengths. The model is adequate to describe frequent traffic state interruptions at signalized intersections. Based on the distribution function of stochastic traffic volume demand, the randomness in queue length, wave fronts, and vehicle numbers are derived. Then, an outlook is provided on its applicability as a full-scale urban traffic network model. Second, a shrinking horizon model predictive controller (MPC) is proposed for ensuring timetable reliability. The intention is to calculate optimal velocity commands based on the current position and desired arrival time of the bus while considering upcoming delays due to red signals and eventual queues. The above proposed stochastic traffic model is incorporated in a rolling horizon optimization via chance-constraining. In the optimization, probabilistic guarantees are formulated to minimize delay due to standstill in queues at signalized intersections. Optimization results are analyzed from two particular aspects, (i) feasibility and (ii) closed-loop performance point of views. The novel stochastic profile model is tested in a high fidelity traffic simulator context. Comparative simulation results show the viability and importance of stochastic bounds in urban trajectory design. The proposed algorithm yields smoother bus trajectories at an urban corridor, suggesting energy savings compared to benchmark control strategies.
|
|
| 8. |
- Auriol, Jean, et al.
(författare)
-
Mean-square exponential stabilization of coupled hyperbolic systems with random parameters
- 2023
-
Ingår i: IFAC-PapersOnLine. - 2405-8963. ; 56:2, s. 8153-8158
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we consider a system of two coupled scalar-valued hyperbolic partial differential equations (PDEs) with random parameters. We formulate a stability condition under which the classical backstepping controller (designed for a nominal system whose parameters are constant) stabilizes the system. More precisely, we guarantee closed-loop mean-square exponential stability under random system parameter perturbations, provided the nominal parameters are sufficiently close to the stochastic ones on average. The proof is based on a Lyapunov analysis, the Lyapunov functional candidate describing the contraction of L2-norm of the system states. An illustrative traffic flow regulation example shows the viability and importance of the proposed result
|
|
| 9. |
- Bae, Sangjun, 1986, et al.
(författare)
-
A Game Approach for Charging Station Placement Based on User Preferences and Crowdedness
- 2022
-
Ingår i: IEEE Transactions on Intelligent Transportation Systems. - 1524-9050 .- 1558-0016. ; 23:4, s. 3654-3669
-
Tidskriftsartikel (refereegranskat)abstract
- The placement of electric vehicle charging stations (EVCSs), which encourages the rapid development of electric vehicles (EVs), should be considered from not only operational perspective such as minimizing installation costs, but also user perspective so that their strategic and competitive charging behaviors can be reflected. This paper proposes a methodological framework to consider crowdedness and individual preferences of electric vehicle users (EVUs) in the selection of locations for fast-charging stations. The electric vehicle charging station placement problem (EVCSPP) is solved via a decentralized game theoretical decision-making algorithm and k-means clustering algorithm. The proposed algorithm, referred to as k-GRAPE, determines the locations of charging stations to maximize the sum of utilities of EVUs. In particular, we analytically present that 50% of suboptimality of the solution can be at least guaranteed, which is about 17% better than the existing game theoretical based framework. We show a few variants to describe the utility functions that may capture the difference in preferences of EVUs. Finally, we demonstrate the viability of the decision framework via three real-world data-based experiments. The results of the experiments, including a comparison with a baseline method are then discussed.
|
|
| 10. |
|
|
| 11. |
- Bae, Sangjun, et al.
(författare)
-
Personalized Dynamic Pricing Policy for Electric Vehicles: Reinforcement learning approach
- 2024
-
Ingår i: Transportation Research, Part C: Emerging Technologies. - 0968-090X. ; 161
-
Tidskriftsartikel (refereegranskat)abstract
- With the increasing number of fast-electric vehicle charging stations (fast-EVCSs) and the popularization of information technology, electricity price competition between fast-EVCSs is highly expected, in which the utilization of public and/or privacy-preserved information will play a crucial role. Self-interest electric vehicle (EV) users, on the other hand, try to select a fast-EVCS for charging in a way to maximize their utilities based on electricity price, estimated waiting time, and their state of charge. While existing studies have largely focused on finding equilibrium prices, this study proposes a personalized dynamic pricing policy (PeDP) for a fast-EVCS to maximize revenue using a reinforcement learning (RL) approach. We first propose a multiple fast-EVCSs competing simulation environment to model the selfish behavior of EV users using a game-based charging station selection model with a monetary utility function. In the environment, we propose a Q-learning-based PeDP to maximize fast-EVCS' revenue. Through numerical simulations based on the environment: (1) we identify the importance of waiting time in the EV charging market by comparing the classic Bertrand competition model with the proposed PeDP for fast-EVCSs (from the system perspective); (2) we evaluate the performance of the proposed PeDP and analyze the effects of the information on the policy (from the service provider perspective) and the robustness of the proposed approach; and (3) it can be seen that privacy-preserved information sharing can be misused by artificial intelligence-based PeDP in a certain situation in the EV charging market (from the customer perspective).
|
|
| 12. |
- Basso, Rafael, 1979, et al.
(författare)
-
Dynamic Stochastic Electric Vehicle Routing with Safe Reinforcement Learning
- 2022
-
Ingår i: Transportation Research Part E: Logistics and Transportation Review. - : Elsevier BV. - 1366-5545. ; 157:157
-
Tidskriftsartikel (refereegranskat)abstract
- Dynamic routing of electric commercial vehicles can be a challenging problem since besides the uncertainty of energy consumption there are also random customer requests. This paper introduces the Dynamic Stochastic Electric Vehicle Routing Problem (DS-EVRP). A Safe Reinforcement Learning method is proposed for solving the problem. The objective is to minimize expected energy consumption in a safe way, which means also minimizing the risk of battery depletion while en route by planning charging whenever necessary. The key idea is to learn offline about the stochastic customer requests and energy consumption using Monte Carlo simulations, to be able to plan the route predictively and safely online. The method is evaluated using simulations based on energy consumption data from a realistic traffic model for the city of Luxembourg and a high-fidelity vehicle model. The results indicate that it is possible to save energy at the same time maintaining reliability by planning the routes and charging in an anticipative way. The proposed method has the potential to improve transport operations with electric commercial vehicles capitalizing on their environmental benefits
|
|
| 13. |
- Basso, Rafael, 1979, et al.
(författare)
-
Electric Vehicle Routing Problem with Machine Learning for Energy Prediction
- 2021
-
Ingår i: Transportation Research Part B: Methodological. - : Elsevier BV. - 0191-2615. ; 145, s. 24-55
-
Tidskriftsartikel (refereegranskat)abstract
- Routing electric commercial vehicles requires taking into account their limited driving range, which is affected by several uncertain factors such as traffic conditions. This paper presents the time-dependent Electric Vehicle Routing Problem with Chance- Constraints (EVRP-CC) and partial recharging. The routing method is divided into two stages, where the first finds the best paths and the second optimizes the routes. A probabilistic Bayesian machine learning approach is proposed for predicting the expected energy consumption and variance for the road links, paths and routes. Hence it is possible to consider the uncertainty in energy demand by planning charging within a confidence interval. The energy estimation is validated with data from electric buses driving a public transport route in Gothenburg-Sweden as well as with realistic simulations for 24 hours traffic in the city of Luxembourg connected to a high fidelity vehicle model. Routing solutions are compared with a deterministic formulation of the problem similar to the ones found in the literature. The results indicate high accuracy for the energy prediction as well as energy savings and more reliability for the routes.
|
|
| 14. |
- Cao, Danni, et al.
(författare)
-
A Platoon Regulation Algorithm to Improve the Traffic Performance of Highway Work Zones
- 2021
-
Ingår i: Computer-Aided Civil and Infrastructure Engineering. - : Wiley. - 1093-9687 .- 1467-8667. ; 36:7, s. 941-956
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a cooperative traffic control strategy to increase the capacity of non-recurrent bottlenecks such as work zones by making full use of the spatial resources upstream of work zones. The upstream area is divided into two zones: the regulation area and the merging area. The basic logic is that a large gap is more efficient in accommodating merging vehicles than several small and scattered gaps with the same total length. In the regulation area, a non-linear programming model is developed to balance both traffic capacity improvements and safety risks. A two-step solving algorithm is proposed for finding optimal solutions. In the merging area, the sorting algorithm is used to design lane changing trajectories based on the regulated platoons. A case study is conducted, and the results indicate that the proposed model is able to significantly improve work zone capacity with minor disturbances to the traffic.
|
|
| 15. |
- Chugh, Tushar, 1989, et al.
(författare)
-
Robust H-infinity Position Control for Vehicle Steering
- 2021
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a robust position controller for an electric power assisted steering and a steer-by-wire force-feedback system. A typical position controller is required for the driving automation and the vehicle motion control functions. The same controller could also be used to realize the haptic functions for steering feedback. The driver’s physical impedance causes a parametric uncertainty during the steering wheel coupling. As a consequence, a classical (single variable) position controller becomes less robust and suffers a tracking performance loss. Therefore, a multi-variable robust position controller is proposed to mitigate the effect of uncertainty. An investigation is performed by including the sensed torque signal in a classical position controller. Finally, a robust solution is synthesized using the LMI-H-infinity optimization. With this, a desired loop gain shape is achieved: (a) a large loop gain at low frequencies for performance; and (b) a small loop gain at high frequencies for robustness. Frequency response comparison of different controllers on real hardware is presented. Experiments and simulation results clearly illustrate the improvements in reference tracking and robustness with an optimal torque feedback in the proposed H-infinity position controller.
|
|
| 16. |
- Dabiri, Azita, et al.
(författare)
-
Incident indicators for freeway traffic flow models
- 2022
-
Ingår i: Communications in Transportation Research. - : Elsevier BV. - 2772-4247. ; 2:December
-
Tidskriftsartikel (refereegranskat)abstract
- Developed in this paper is a traffic flow model parametrised to describe abnormal traffic behaviour. In large traffic networks, the immediate detection and categorisation of traffic incidents/accidents is of capital importance to avoid breakdowns, further accidents. First, this claims for traffic flow models capable to capture abnormal traffic condition like accidents. Second, by means of proper real-time estimation technique, observing accident related parameters, one may even categorize the severity of accidents. Hence, in this paper, we suggest to modify the nominal Aw-Rascle (AR) traffic model by a proper incident related parametrisation. The proposed Incident Traffic Flow model (ITF) is defined by introducing the incident parameters modifying the anticipation and the dynamic speed relaxation terms in the speed equation of the AR model. These modifications is proven to have physical meaning. Furthermore, the characteristic properties of the ITF model is discussed in the paper. A multi stage numerical scheme is suggested to discretise in space and time the resulting non-homogeneous system of PDEs. The resulting systems of ODE is then combined with receding horizon estimation methods to reconstruct the incident parameters. Finally, the viability of the suggested incident parametrisation is validated in a simulation environment.
|
|
| 17. |
- Keskin, Furkan, 1988, et al.
(författare)
-
Altruistic Control of Connected Automated Vehicles in Mixed-Autonomy Multi-Lane Highway Traffic
- 2020
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 53:2, s. 14966-14971
-
Konferensbidrag (refereegranskat)abstract
- We consider the problem of altruistic control of connected automated vehicles (CAVs) on mixed-autonomy multi-lane highways to mitigate moving traffic jams resulting from car-following dynamics of human-driven vehicles (HDVs). In most of the existing studies on CAVs in multi-lane settings, vehicle controller design philosophy is based on a selfish driving strategy that exclusively addresses the ego vehicle objectives. To improve overall traffic smoothness, we propose an altruistic control strategy for CAVs that aims to maximize the driving comfort and traffic efficiency of both the ego vehicle and surrounding HDVs. We formulate the problem of altruistic control under a model predictive control (MPC) framework to optimize acceleration and lane change sequences of CAVs. In order to efficiently solve the resulting non-convex mixed-integer nonlinear programming (MINLP) problem, we decompose it into three non-convex subproblems, each of which can be transformed into a convex quadratic program via penalty based reformulation of the optimal velocity with relative velocity (OVRV) car-following model. Simulation results demonstrate significant improvements in traffic flow via altruistic CAV actions over selfish strategies on both single- and multi-lane roads.
|
|
| 18. |
- Lacombe, Rémi, 1995, et al.
(författare)
-
Bilevel optimization for bunching mitigation and eco-driving of electric bus lines
- 2022
-
Ingår i: IEEE Transactions on Intelligent Transportation Systems. - 1524-9050 .- 1558-0016. ; 23:8, s. 10662-10679
-
Tidskriftsartikel (refereegranskat)abstract
- The problems of bus bunching mitigation and of the energy management of groups of vehicles are traditionally treated separately in the literature, and formulated in two different frameworks. The present work bridges this gap by formulating the optimal control problem of the bus line eco-driving and regularity control as a smooth, multi-objective nonlinear program. Since this nonlinear program only has few coupling variables, it is shown how it can be solved in parallel aboard each bus such that only a marginal amount of computations need to be carried out centrally. This leverages the decentralized structure of a bus line by enabling parallel computations and reducing the communication loads between the buses, which makes the problem resolution scalable in terms of the number of buses. Closed-loop control is then achieved by embedding this procedure in a model predictive control. Stochastic simulations based on real passengers and travel times data are realized for several scenarios with different levels of bunching for a line of electric buses. Our method achieves fast recoveries to regular headways as well as energy savings of up to 9.3% when compared with traditional holding or speed control baselines.
|
|
| 19. |
- Lacombe, Rémi, 1995, et al.
(författare)
-
Conflict-free Charging and Real-time Control for an Electric Bus Network
- 2023
-
Ingår i: IFAC-PapersOnLine. - 2405-8963. ; 56:2, s. 6648-6653
-
Konferensbidrag (refereegranskat)abstract
- The rapid adoption of electric buses by transit agencies around the world is leading to new challenges in the planning and operation of bus networks. In particular, the limited driving range of electric vehicles imposes operational constraints such as the need to charge buses during service. Research on this topic has mostly focused on the strategic and tactical planning aspects until now, and very little work has been done on the real-time operational aspect. To remedy this, we propose integrating the charging scheduling problem with a real-time speed control strategy in this paper. The control problem is formulated as a mixed-integer linear program and solved to optimality with the branch-and-bound method. Simulations are carried out by repeatedly solving the control problem in a receding horizon fashion over a full day of operation. The results show that the proposed controller manages to anticipate and avoid potential conflicts where the charging demand exceeds the charger capacity. This feature makes the controller achieve lower operational costs, both in terms of service regularity and energy consumption, compared to a standard first-come, first-served charging scheme.
|
|
| 20. |
- Lacombe, Rémi, 1995, et al.
(författare)
-
Distributed eco-driving control of a platoon of electric vehicles through Riccati recursion
- 2023
-
Ingår i: IEEE Transactions on Intelligent Transportation Systems. - 1524-9050 .- 1558-0016. ; 24:3, s. 3048-3063
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a distributed optimization procedure for the cooperative eco-driving control problem of a platoon of electric vehicles subject to safety and travel time constraints. Individual optimal trajectories are generated for each platoon member to account for heterogeneous vehicles and for the road slope. By rearranging the problem variables, the Riccati recursion can be applied along the chain-like structure of the platoon and be used to solve the problem by repeatedly transmitting information up and down the platoon. Since each vehicle is only responsible for its own part of the computations, the proposed control strategy is privacy-preserving and could therefore be deployed by any group of vehicles to form a platoon spontaneously while driving. The energy efficiency of this control strategy is evaluated in numerical experiments for platoons of electric trucks with different masses and rated motor powers.
|
|
| 21. |
- Lacombe, Rémi, 1995, et al.
(författare)
-
Hierarchical Control of Electric Bus Lines
- 2020
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 53:2, s. 14179-14184
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we propose a hierarchical control strategy for a line of electric buses with the double objective of minimizing energy consumption and providing regular service to the passengers. The state-space model for the buses is formulated in space rather than in time, which alleviates the need for integer decision variables to capture their behavior at bus stops. This enables us to first assemble a fully-centralized multi-objective line problem in the continuous nonlinear optimization framework. It is then reassembled into a hierarchical structure with two levels of control in order to improve on scalability and reliability. This new supervisory structure consists of a centralized line level controller which handles the time headway regularity of the buses, and of decentralized bus level controllers which simultaneously manage the energy consumption of each individual bus. Our method demonstrates good battery energy savings and regularity performances when compared to a classical holding strategy.
|
|
| 22. |
- Lacombe, Rémi, 1995, et al.
(författare)
-
Integrated Charging Scheduling and Operational Control for an Electric Bus Network
- 2024
-
Ingår i: Transportation Research Part E: Logistics and Transportation Review. - 1366-5545. ; 186
-
Tidskriftsartikel (refereegranskat)abstract
- The last few years have seen the massive deployment of electric buses in many existing transit networks. However, the planning and operation of an electric bus system differ from that of a bus system with conventional vehicles, and some key problems have not yet been studied in the literature. In this work, we address the integrated operational control and charging scheduling problem for a network of electric buses with a limited opportunity charging capacity. We propose a hierarchical control framework to solve this problem, where the charging and operational decisions are taken jointly by solving a mixed-integer linear program in the high-level control layer. Since this optimization problem might become very large as more bus lines are considered, we propose to apply Lagrangian relaxation in such a way as to exploit the structure of the problem and enable a decomposition into independent subproblems. A local search heuristic is then deployed in order to generate good feasible solutions to the original problem. This entire Lagrangian heuristic procedure is shown to scale much better on transit networks with an increasing number of bus lines than trying to solve the original problem with an off-the-shelf solver. The proposed procedure is then tested in the high-fidelity microscopic traffic environment Vissim on a bus network constructed from an openly available dataset of the city of Chicago. The results show the benefits of combining the charging scheduling decisions together with the real-time operational control of the vehicles as the proposed control framework manages to achieve both a better level of service and lower charging costs over control baselines with predetermined charging schedules.
|
|
| 23. |
- Larsson, Jacob, et al.
(författare)
-
Pro-social control of connected automated vehicles in mixed-autonomy multi-lane highway traffic
- 2021
-
Ingår i: Communications in Transportation Research. - : Elsevier BV. - 2772-4247. ; 1:December
-
Tidskriftsartikel (refereegranskat)abstract
- We propose pro-social control strategies for connected automated vehicles (CAVs) to mitigate jamming waves in mixed-autonomy multi-lane traffic, resulting from car-following dynamics of human-driven vehicles (HDVs). Different from existing studies, which focus mostly on ego vehicle objectives to control CAVs in an individualistic manner, we devise a pro-social control algorithm. The latter takes into account the objectives (i.e., driving comfort and traffic ef ficiency) of both the ego vehicle and surrounding HDVs to improve smoothness of the entire observable traffic. Under a model predictive control (MPC) framework that uses acceleration and lane change sequences of CAVs as optimization variables, the problem of individualistic, altruistic, and pro-social control is formulated as a non-convex mixed-integer nonlinear program (MINLP) and relaxed to a convex quadratic program through converting the piece-wise-linear constraints due to the optimal velocity with relative velocity (OVRV) car-following model into linear constraints by introducing slack variables. Low-fidelity simulations using the OVRV model and high-fidelity simulations using PTV VISSIM simulator show that pro-social and altruistic control can provide significant performance gains over individualistic driving in terms of efficiency and comfort on both single- and multi-lane roads.
|
|
| 24. |
- Liptak, Gyorgy, et al.
(författare)
-
Traffic Reaction Model
- 2021
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- In this paper a novel non-negative finite volume discretization scheme is proposed for certain first order nonlinear partial differential equations describing conservation laws arising in traffic flow modelling. The spatially discretized model is shown to preserve several fundamentally important analytical properties of the conservation law (e.g., conservativeness, capacity) giving rise to a set of (second order) polynomial ODEs. Furthermore, it is shown that the discretized traffic flow model is formally kinetic and that it can be interpreted in a compartmental context. As a consequence, traffic networks can be represented as reaction graphs. It is shown that the model can be equipped with on- and off- ramps in a physically meaningful way, still preserving the advantageous properties of the discretization. Numerical case studies include empirical convergence tests, and the stability analysis presented in the paper paves the way to scalable observer and controller design.
|
|
| 25. |
- Luspay, T., et al.
(författare)
-
Set-based multi-objective control of metered ramps at ring road junctions
- 2020
-
Ingår i: Transportmetrica A: Transport Science. - : Informa UK Limited. - 2324-9943 .- 2324-9935. ; 16:2, s. 337-357
-
Tidskriftsartikel (refereegranskat)abstract
- A set-theoretical approach is presented for a multi-objective control design of the local ramp metering problem. Two control objectives are specified: first, the optimization of traffic performance, by the minimization of total time spent. Second, the emission factor of CO2 needs to be minimized. The optimal state for traffic emission however lies in the unstable domain of the dynamic system. To dissolve this inconsistency, the control problem is formalized for the multi-objective optimization problem by using set-theoretical methods. For this purpose, the non-linear model METANET is rewritten in a shifted coordinate frame with a parameter-varying, polytopic representation. Bounds on state-, input- and disturbance variables are expressed by convex polytopes. These sets are then used for the design of an interpolated Hinf controller that is capable of improving traffic conditions according to the prescribed multi-objective criteria
|
|
| 26. |
- McCabe, Dan, et al.
(författare)
-
Minimum-Delay Opportunity Charging Scheduling for Electric Buses
- 2024
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Transit agencies that operate battery-electric buses must carefully manage fast-charging infrastructure to extend daily bus range without degrading on-time performance. To support this need, we propose a mixed-integer linear programming model to schedule opportunity charging that minimizes the amount of departure delay in all trips served by electric buses. Our novel approach directly tracks queuing at chargers in order to set and propagate departure delays. Allowing but minimizing delays makes it possible to optimize performance when delays due to traffic conditions and charging needs are inevitable, in contrast with existing methods that require charging to occur during scheduled layover time. To solve the model, we develop two algorithms based on decomposition. The first is an exact solution method based on Combinatorial Benders (CB) decomposition, which avoids directly enumerating the model's logic-based "big M" constraints and their inevitable computational challenges. The second, inspired by the CB approach but more efficient, is a polynomial-time heuristic based on linear programming that we call 3S. Computational experiments on both a simple notional transit network and the real bus system of King County, Washington, USA demonstrate the performance of both methods. The 3S method appears particularly promising for creating good charging schedules quickly at real-world scale.
|
|
| 27. |
- Peng, Bile, 1985, et al.
(författare)
-
Connected autonomous vehicles for improving mixed traffic efficiency in unsignalized intersections with deep reinforcement learning
- 2021
-
Ingår i: Communications in Transportation Research. - : Elsevier BV. - 2772-4247.
-
Tidskriftsartikel (refereegranskat)abstract
- Human driven vehicles (HDVs) with selfish objectives cause low traffic efficiency in an un-signalized intersection. On the other hand, autonomous vehicles can overcome this inefficiency through perfect coordination. In this paper, we propose an intermediate solution, where we use vehicular communication and a small number of autonomous vehicles to improve the transportation system efficiency in such intersections. In our solution, two connected autonomous vehicles (CAVs) lead multiple HDVs in a double-lane intersection in order to avoid congestion in front of the intersection. The CAVs are able to communicate and coordinate their behavior, which is controlled by a deep reinforcement learning (DRL) agent. We design an altruistic reward function which enables CAVs to adjust their velocities flexibly in order to avoid queuing in front of the intersection. The proximal policy optimization (PPO) algorithm is applied to train the policy and the generalized advantage estimation (GAE) is used to estimate state values. Training results show that two CAVs are able to achieve significantly better traffic efficiency compared to similar scenarios without and with one altruistic autonomous vehicle.
|
|
| 28. |
- Pereira, Mike, 1992, et al.
(författare)
-
Parameter and density estimation from real-world traffic data: A kinetic compartmental approach
- 2022
-
Ingår i: Transportation Research Part B: Methodological. - : Elsevier BV. - 0191-2615. ; 155, s. 210-239
-
Tidskriftsartikel (refereegranskat)abstract
- The main motivation of this work is to assess the validity of a LWR traffic flow model to model measurements obtained from trajectory data, and propose extensions of this model to improve it. A formulation for a discrete dynamical system is proposed aiming at reproducing the evolution in time of the density of vehicles along a road, as observed in the measurements. This system is formulated as a chemical reaction network where road cells are interpreted as compartments, the transfer of vehicles from one cell to the other is seen as a chemical reaction between adjacent compartment and the density of vehicles is seen as a concentration of reactant. Several degrees of flexibility on the parameters of this system, which basically consist of the reaction rates between the compartments, can be considered: a constant value or a function depending on time and/or space. Density measurements coming from trajectory data are then interpreted as observations of the states of this system at consecutive times. Optimal reaction rates for the system are then obtained by minimizing the discrepancy between the output of the system and the state measurements. This approach was tested both on simulated and real data, proved successful in recreating the complexity of traffic flows despite the assumptions on the flux-density relation.
|
|
| 29. |
- Pereira, Mike, 1992, et al.
(författare)
-
Short-term traffic prediction using physics-aware neural networks
- 2022
-
Ingår i: Transportation Research, Part C: Emerging Technologies. - : Elsevier BV. - 0968-090X. ; 142
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, we propose an algorithm performing short-termpredictions of the flow and speed of vehicles on a stretch of road, using past measurements of these quantities. This algorithm is based on a physics-aware recurrent neural network. Adiscretization of a macroscopic traffic flowmodel (using the so-called Traffic Reaction Model) is embedded in the architecture of the network and yields traffic state estimations and predictions for the flow and speed of vehicles, which are physically-constrained by the macroscopic traffic flow model and based on estimated and predicted space-time dependent traffic parameters. These parameters are themselves obtained using a succession of LSTM recurrent neural networks. The algorithm is tested on raw flow measurements obtained from loop detectors.
|
|
| 30. |
- Pereira, Mike, 1992, et al.
(författare)
-
The Traffic Reaction Model: A kinetic compartmental approach to road traffic modeling
- 2024
-
Ingår i: Transportation Research, Part C: Emerging Technologies. - 0968-090X. ; 158
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, a family of finite volume discretization schemes for LWR-type first order traffic flow models (with possible on- and off-ramps) is proposed: the Traffic Reaction Model (TRM). These schemes yield systems of ODEs that are formally equivalent to the kinetic systems used to model chemical reaction networks. An in-depth numerical analysis of the TRM is performed. On the one hand, the analytical properties of the scheme (nonnegative, conservative, capacitypreserving, monotone) and its relation to more traditional schemes for traffic flow models (Godunov, CTM) are presented. Finally, the link between the TRM and kinetic systems is exploited to offer a novel compartmental interpretation of traffic models. In particular, kinetic theory is used to derive dynamical properties (namely persistence and Lyapunov stability) of the TRM for a specific road configuration. Two extensions of the proposed model, to networks and changing driving conditions, are also described.
|
|
| 31. |
- Polcz, Peter, et al.
(författare)
-
Induced L2-gain computation for rational LPV systems using Finsler's lemma and minimal generators
- 2020
-
Ingår i: Systems and Control Letters. - : Elsevier BV. - 0167-6911. ; 142
-
Tidskriftsartikel (refereegranskat)abstract
- This paper proposes a novel method to compute an upper bound on the induced L2- gain for a linear parameter varying (LPV) system with rational parameter dependence. The proposed method relies on a standard dissipation inequality condition. The storage function is a quadratic function of the state and a rational function of the parameters. The specific parameter dependence is restricted to involve (fixed) rational functions and an affine term with free decision variables. Finsler's lemma and affine annihilators are used to formulate sufficient linear matrix inequality (LMI) conditions for the dissipativity relation. The dimension and conservatism of the resulting LMI problem are reduced by the joint application of minimal generators and maximal annihilators. An LPV model of a pendulum-cart system is used to demonstrate the proposed method and compare it to existing techniques in the literature.
|
|
| 32. |
- Themistoklis, Charalambous, et al.
(författare)
-
Back-Pressure Traffic Signal Control in the Presence of Noisy Queue Information
- 2023
-
Ingår i: IFAC-PapersOnLine. - 2405-8963. ; 56:2, s. 10491-10496
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we consider decentralized traffic signal control policies using the max-weight algorithm when the queue size measurement is noisy. We first show analytically that the standard max-weight algorithm is throughput optimal even under noisy queue measurements. However, the average steady-state queue lengths and subsequently the average delays are increased. In order to alleviate the effect of these noisy measurements we add filtering to the max-weight algorithm; more specifically, we propose the Filtered-max-weight algorithm, which is based on particle filtering. We demonstrate via simulations that the Filtered-max-weight algorithm performs better than the standard max-weight algorithm in the presence of noisy measurements.
|
|
| 33. |
- Tingstad Jacobsen, Sten Elling, 1994, et al.
(författare)
-
A Predictive Chance Constraint Rebalancing Approach to Mobility-on-Demand Services
- 2022
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- This paper considers the problem of supply-demand imbalances in Autonomous Mobility-on-Demand systems (AMoD) where demand uncertainty compromises both the service provider's and the customer objectives. The key idea is to include estimated stochastic travel demand patterns into receding horizon AMoD optimization problems. More precisely, we first estimate passenger demand using Gaussian Process Regression (GPR). GPR provides demand uncertainty bounds for time pattern prediction. Second, we integrate demand predictions with uncertainty bounds into a receding horizon AMoD optimization. In order to guarantee constraint satisfaction in the above optimization under estimated stochastic demand prediction, we employ a probabilistic constraining method with user defined confidence interval. Receding horizon AMoD optimization with probabilistic constraints thereby calls for Chance Constrained Model Predictive Control (CCMPC). The benefit of the proposed method is twofold. First, travel demand uncertainty prediction from data can naturally be embedded into AMoD optimization. Second, CCMPC can further be relaxed into a Mixed-Integer-Linear-Program (MILP) that can efficiently be solved. We show, through high-fidelity transportation simulation, that by tuning the confidence bound on the chance constraint close to "optimal" oracle performance can be achieved. The median wait time is reduced by 4% compared to using only the mean prediction of the GP.
|
|
| 34. |
- Tingstad Jacobsen, Sten Elling, 1994, et al.
(författare)
-
A Predictive Chance Constraint Rebalancing Approach to Mobility-on-Demand Services
- 2023
-
Ingår i: Communications in Transportation Research. - 2772-4247. ; 3
-
Tidskriftsartikel (refereegranskat)abstract
- This paper considers the problem of supply-demand imbalances in Mobility-on-Demand (MoD) services, such as Uber or DiDi Rider. Such imbalances are due to uneven stochastic travel demand and can be prevented by proactively rebalance empty vehicles. To this end we propose a method that include estimated stochastic travel demand patterns into stochastic model predictive control (SMPC) for rebalancing of empty vehicles MoD ride-hailing service. More precisely, we first estimate passenger travel demand using Gaussian Process Regression (GPR), which provides demand uncertainty bounds for time pattern prediction. We then formulate a SMPC for the autonomous ride-hailing service and integrate demand predictions with uncertainty bounds into a receding horizon MoD optimization. In order to guarantee constraint satisfaction in the above optimization under estimated stochastic demand prediction, we employ a probabilistic constraining method with user defined confidence interval. Receding horizon MoD optimization with probabilistic constraints thereby calls for Chance Constrained Model Predictive Control (CCMPC). The benefits of the proposed method are twofold. First, travel demand uncertainty prediction from data can naturally be embedded into the MoD optimization framework. We show that for a given minimal fleet size the imbalance in each station can be kept below a certain threshold with a user defined probability. Second, CCMPC can further be relaxed into a Mixed-Integer-LP (MILP) and we show that the MILP can be solved as a corresponding Linear-Program which always admits a integral solution. Finally, we demonstrate through high-fidelity transportation simulations, that by tuning the confidence bound on the chance constraint close to optimal oracle performance can be achieved. The corresponding median customer wait time is reduced by 4% compared to using only the mean prediction of the GPR.
|
|
| 35. |
- Wu, Jiaming, 1989, et al.
(författare)
-
A Modular, Adaptive, and Autonomous Transit System (MAATS): A In-motion Transfer Strategy and Performance Evaluation in Urban Grid Transit Networks
- 2021
-
Ingår i: Transportation Research Part A: General. - : Elsevier BV. - 0965-8564. ; 151, s. 81-98
-
Tidskriftsartikel (refereegranskat)abstract
- Dynamic traffic demand has been a longstanding challenge for the conventional transit system design and operation. The recent development of autonomous vehicles (AVs) makes it increasingly realistic to develop the next generation of transportation systems with the potential to improve operational performance and flexibility. In this study, we propose an innovative transit system with autonomous modular buses (AMBs) that is adaptive to dynamic traffic demands and not restricted to fixed routes and timetables. A unique transfer operation, termed as “in-motion transfer”, is introduced in this paper to transfer passengers between coupled modular buses in motion. A two-stage model is developed to facilitate in-motion transfer operations in optimally designing passenger transfer plans and AMB trajectories at intersections. In the proposed AMB system, all passengers can travel in the shortest path smoothly without having to actually alight and transfer between different bus lines. Numerical experiments demonstrate that the proposed transit system results in shorter travel time and a significantly reduced average number of transfers. While enjoying the above-mentioned benefits, the modular, adaptive, and autonomous transit system (MAATS) does not impose substantially higher energy consumption in comparison to the conventional bus system
|
|
| 36. |
- Wu, Jiaming, 1989, et al.
(författare)
-
Emergency vehicle lane pre-clearing: From microscopic cooperation to routing decision making
- 2020
-
Ingår i: Transportation Research Part B: Methodological. - : Elsevier BV. - 0191-2615. ; 141, s. 223-239
-
Tidskriftsartikel (refereegranskat)abstract
- Emergency vehicles (EVs) play a crucial role in providing timely help for the general public in saving lives and avoiding property loss. However, very few efforts have been made for EV prioritization on normal road segments, such as the road section between intersections or highways between ramps. In this paper, we propose an EV lane pre-clearing strategy to prioritize EVs on such roads through cooperative driving with surrounding connected vehicles (CVs). The cooperative driving problem is formulated as a mixed-integer nonlinear programming (MINP) problem aiming at (i) guaranteeing the desired speed of EVs, and (ii) minimizing the disturbances on CVs. To tackle this NP-hard MINP problem, we formulate the model in a bi-level optimization manner to address these two objectives, respectively. In the lower-level problem, CVs in front of the emergency vehicle will be divided into several blocks. For each block, we developed an EV sorting algorithm to design optimal merging trajectories for CVs. With resultant sorting trajectories, a constrained optimization problem is solved in the upper-level to determine the initiation time/distance to conduct the sorting trajectories. Case studies show that with the proposed algorithm, emergency vehicles are able to drive at a desired speed while minimizing disturbances on normal traffic flows. We further reveal a linear relationship between the optimal solution and road density, which could help to improve EV routing decision makings when high-resolution data is not available.
|
|
| 37. |
- Zhou, Fangting, 1993, et al.
(författare)
-
Collaborative electric vehicle routing with meet points
- 2024
-
Ingår i: Communications in Transportation Research. - 2772-4247.
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper, we develop a profit-sharing-based optimal routing mechanism to incentivize horizontal collaboration among urban goods distributors. The core of this mechanism is based on exchanging goods at meet points, which is optimally planned en route. We propose a Collaborative Electric Vehicle Routing Problem with Meet Points (CoEVRPMP) considering constraints such as time windows, opportunity charging, and meet-point synchronization. The proposed CoEVRPMP is formulated as a mixed-integer nonlinear programming model. We present an exact method via branching and a matheuristic that combines adaptive large neighborhood search with linear programming. The viability and scalability of the collaborative method are demonstrated through numerical case studies, including a real-world case and a large-scale experiment with up to 500 customers. The findings underscore the significance of horizontal collaboration among delivery companies in attaining both higher individual profits and lower total costs. Moreover, collaboration helps to reduce the environmental footprint by decreasing travel distance.
|
|
