An Independent Trajectory Advisory System in a Mixed-Traffic Condition: A Reinforcement Learning-Based Approach

This study focuses on the comprehensive investigation of stop-and-go waves appearing in closed-circuit ring road traffic wherein we evaluate various longitudinal dynamical models for vehicles. It is known that the behavior of human-driven vehicles, with other traffic elements such as density held constant, could stimulate stop-and-go waves, which do not dissipate on the circuit ring road. Stop-and-go waves can be dissipated by adding automated vehicles (AVs) to the ring. Thorough investigations of the performance of AV longitudinal control algorithms were carried out in Flow, which is an integrated platform for reinforcement learning on traffic control. Ten AV algorithms presented in the literature are evaluated. For each AV algorithm, experiments are carried out by varying distributions and penetration rates of AVs. Two different distributions of AVs are studied. For the first distribution scenario, AVs are placed consecutively. Penetration rates are varied from 1 AV (5%) to all AVs (100%). For the second distribution scenario, AVs are placed with even distribution of human-driven vehicles in between any two AVs. In this scenario, penetration rates are varied from 2 AVs (10%) to 11 AVs (50%). Multiple runs (10 runs) are simulated to average out the randomness in the results. From more than 3,000 simulation experiments, we investigated how AV algorithms perform differently with varying distributions and penetration rates while all AV algorithms remained fixed under all distributions and penetration rates. Time to stabilize, maximum headway, vehicle miles traveled, and fuel economy are used to evaluate their performance. Using these metrics, we find that the traffic condition improvement is not necessarily dependent on the distribution for most of the AV controllers, particularly when no cooperation among AVs is considered. Traffic condition is generally improved with a higher AV penetration rate with only one of the AV algorithms showing a contrary trend. Among all AV algorithms in this study, the reinforcement learning controller shows the most consistent improvement under all distributions and penetration rates.

Download Full-text

Equivalency Factor Based on Acceleration Noise for Mixed Traffic Condition

Transportation in Developing Economies ◽

10.1007/s40890-019-0073-9 ◽

2019 ◽

Vol 5 (2) ◽

Author(s):

S. Salini ◽

R. Ashalatha ◽

S. Aswathy Mohan

Keyword(s):

Mixed Traffic ◽

Traffic Condition

Download Full-text

Saturation Flow Model for Signalized Intersection under Mixed Traffic Condition

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198118777407 ◽

2018 ◽

Vol 2672 (15) ◽

pp. 55-65 ◽

Cited By ~ 7

Author(s):

Sabyasachi Biswas ◽

Souvik Chakraborty ◽

Indrajit Ghosh ◽

Satish Chandra

Keyword(s):

Conventional Method ◽

Detailed Comparison ◽

Heterogeneous Traffic ◽

Signalized Intersection ◽

Percentage Error ◽

Mixed Traffic ◽

Kriging Method ◽

Traffic Condition ◽

Saturation Flow ◽

The Impact

Saturation flow is one of the most important functional parameters at signalized intersections. It is to be noted that saturation flow is a functional measure of the intersection operation, which indicates the probable capacity if working in an ideal situation. However, determination of the saturation flow is a challenging task in developing countries like India where vehicles with diverse static and dynamic characteristics use the same carriageway. At the same time, it is influenced by several other factors. In this context, the present research is carried out to examine the effects of traffic composition, approach width and right-turning movements on saturation flow under heterogeneous traffic conditions. This paper proposes a model for computing saturation flow at the signalized intersection under mixed traffic condition based on Kriging approach. A detailed comparison of the mean saturation flow values obtained by the conventional method, regression method, and Kriging method has also been presented. Low mean absolute percentage error values (<5%) have been obtained for saturation flow by Kriging method with respect to the conventional method. Finally, the proposed models are used to evaluate the impact of right-turning vehicles on saturation flow under shared lane condition.

Download Full-text

Intelligently managing mixed traffic flows at intersections Proposal of a platoon-based round-robin algorithm with priorities

10.36227/techrxiv.13525853.v1 ◽

2021 ◽

Author(s):

Hossein Moradi ◽

Sara Sasaninejad ◽

Sabine Wittevrongel ◽

Joris Walraevens

Keyword(s):

Traffic Control ◽

Autonomous Vehicles ◽

State Of The Art ◽

Control Methods ◽

Mixed Traffic ◽

Traffic Flows ◽

Traffic Conditions ◽

Advisory System ◽

Intersection Control ◽

Integration Effort

The importance of addressing the complexities of mixed traffic conditions by providing innovative approaches, models, and algorithms for traffic control has been well highlighted in the state-of-the-art literature. Accordingly, the first aim of this study has been to enhance the traditional intersection control methods for the incorporation of autonomous vehicles and wireless communications. For this purpose, we have introduced a novel framework labeled by “PRRP-framework”. The PRRP-framework also enables flexible preferential treatments for some special vehicles within an implementable range of complexity while it addresses the stochastic nature of traffic flow. Moreover, the PRRP-framework has been coupled with a speed advisory system that brings complementary strengths leading to even better performance. Further simulations reported in this manuscript, confirmed that such an integration effort is a prerequisite to move towards sustainable results.

Download Full-text

Autonomous PEV Charging Scheduling Using Deep-Q Network and Dyna-Q Reinforcement Learning

10.32920/ryerson.14661024 ◽

2021 ◽

Author(s):

Fan Wang

Keyword(s):

Reinforcement Learning ◽

Transition Probabilities ◽

Real Life ◽

Future Price ◽

Traffic Condition ◽

Data Set ◽

User Behaviour ◽

Model Free ◽

Behaviour Data

This paper proposes a demand response method that aims to reduce the long-term charging cost of a plug-in electric vehicle (PEV) while overcoming obstacles such as the stochastic nature of the user’s driving be- haviour, traffic condition, energy usage, and energy price. The problem is formulated as a Markov Decision Process (MDP) with unknown transition probabilities and solved using deep reinforcement learning (RL) techniques. Existing methods using machine learning either requires initial user behaviour data, or converges far too slowly. This method does not require any initial data on the PEV owner’s driving behaviour and shows improvement on learning speed. A combination of both model-based and model-free learning called Dyna-Q algorithm is utilized. Every time a real experience is obtained, the model is updated and the RL agent will learn from both real data set and “imagined” experience from the model. Due to the vast amount of state space, a table-look up method is impractical and a value approximation method using deep neural networks is employed for estimating the long-term expected reward of all state-action pairs. An average of historical price is used to predict future price. Three different user behaviour without any initial PEV owner behaviour data are simulated. A purely model-free DQN method is shown to run out of battery during trips very often, and is impractical for real life charging scenarios. Simulation results demonstrate the effectiveness of the proposed approach and its ability to reach an optimal policy quicker while avoiding state of charge (SOC) depleting during trips when compared to existing PEV charging schemes for all three different users profiles.

Download Full-text