Search

The literature on green mobility and eco-driving in urban areas has burgeoned in recent years, with special attention to using infrastructure to vehicle (I2V) communications to obtain optimal speed trajectory which minimize the economic and environmental costs. This article shares the concept with these studies but turns the spotlight on cyclists. It examines the problem of finding optimal speed trajectory for a cyclist in signalised urban areas. Unlike the available studies on motorised vehicles which predominantly designed for pre-defined, fixed traffic lights timing, this article uses an algorithm based on stochastic dynamic programming to explicitly address uncertainty in traffic light timing. Moreover, through a comprehensive set of simulation experiments, the article examines the impact of the speed advice's starting point as well as the cyclist's willingness for changing his/her speed on enhancing the performance. The proposed approach targets various performance metrics such as minimising the total travel time, energy consumption, or the probability of stopping at a red light. Hence, the resulting speed advice can be tailored according to the personal preferences of each cyclist. In a simulation case study, the results of the proposed approach is also compared with an existing approach in the literature., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Team Azita Dabiri, Transport and Planning, Transport and Planning

Being a safe and healthy alternative for polluting and space-inefficient motorised vehicles, cycling can strongly improve living conditions in urban areas. Idling in front of traffic lights is seen as one of the major inconveniences of commuting by bicycle. By giving personalised speed advice, the probability of catching a green light can be increased whilst taking the cyclist preferences into account. Due to its adaptive properties, Reinforcement learning (\acs{RL}) is a suited algorithm for developing optimal speed advice policies when dealing with a dynamic traffic environment and unique cyclist preferences. Generally, a large amount of training samples is required to successfully train a \acs{RL} algorithm. This poses a problem for this specific application since training samples must be generated by humans and are therefore scarce. Moreover, exploration of the environment is challenging since humans will not comply with irrational speed advice. These factors currently restrain the practical implementation of \acs{RL} algorithms for giving speed advice. This thesis aims to overcome these problems whilst maintaining a competitive performance compared to conventional \acs{RL} algorithms. This is done by using function approximators and a combined planning and learning method called Dyna. During a case study, three different function approximators are compared to reduce the amount of required training samples, namely polynomial functions, radial basis functions, and artificial neural networks. Secondly, the effectiveness of Dyna to improve the quality of the speed advice in an unknown environment is assessed. Finally, these methods are applied in a framework focused on the practical implementation of \acs{RL} for giving speed advice. It was concluded that function approximation method can significantly reduce the amount of required training samples to train a \acs{RL} algorithm. Dyna can increase user retention by providing cyclists with a high quality speed a, Mechanical Engineering | Systems and Control

This thesis proposes a traffic signal optimization method for balancing the interests of cyclists and motorized traffic. Traditionally, in bicycle traffic has not been given the same priority as motorized traffic in the signalization system planning. As a consequence, cyclists have to stop many times during their journey, which leads to a waste of energy and causes inconvenience, and at the same time experience long waiting times. In other words, stopping for a red light is a primary discouragement to cycling, since it costs a great deal of extra time and energy. This research relies on this ascertainment and focuses on designing a system which takes into account both types of road users, cyclists and motorized vehicles. Specifically, the proposed system receives the required data from the network, speeds of motorized vehicles and position of both road users, and based on a multi-objective optimization changes the green times of the traffic lights and gives comfortable speed advice to cyclists in order to cross the intersection without having to stop. For the aforementioned optimization the various objectives, namely delay of motorized vehicles and delay, number of stops and deviation between the desired and the advised speed of cyclists, are formulated and are combined as a weighted sum, as a function of green times and individual speed advice. The delay of both road users is formulated as the sum of the delay because of the traffic signal, the delay because of the queues formed at the intersection and the overflow delay, i.e. the additional delay caused when the arrival rate is greater than the service rate at the traffic signal. In regard to the number of stops, each cyclist receives a cost, every time that he has to stop. Last but not least, each cyclist has a desired speed and deviations of it come at a cost. This cost is higher for speeds higher than the desired speed than for speeds lower than the desired speed. The optimization is performed individually in e, Transport and Planning, Transport & Planning, Civil Engineering and Geosciences

Stops en route are a main concern for cyclists as they want to travel in the most comfortable fashion possible. The braking and acceleration at traffic lights cause losses of kinetic energy and make the trips of cyclists more strenuous than they would have been without stops. By reducing the number of stops for cyclists, the attraction of the bicycle as transport mode could be increased. This research will focus on the reduction of stops by implementing a speed advice for cyclists that will help the cyclist to arrive at intersections when the traffic light is green. The design of a system that can reduce the number of stops is presented for the situation with a fixed time controller and an vehicle actuated controller. The design for the fixed time controller consists of a speed advice that is given once to the cyclist approaching the traffic light. The cyclist can approach the traffic light with this speed to arrive at the intersection with a green light. The advice is given by a road side sign that can be read by the cyclist. Reductions in the fraction of stopped cyclists are in the order of 10-20%. The actuated controller asks for a more flexible structure of the speed advice in which the cyclist should adjust its speed dependent on the state of the traffic light controller. The speed advice system must be implemented in a way that the consequence of the state of the controller for the advice of the cyclist can be distributed to the cyclist at the moment this change of state occurs. The flexible appearance of the system allows it to adjust its speed advice to the preferences of the user. This is done by a score function that takes into account the probability to catch the green light and the sacrifice the cyclist has to make in his desired speed to end up at the green traffic light. The reductions in fraction of stopped cyclists are largely dependent on the chosen values for the attributes in the speed advice system. The tested scenarios indicate a maximum reducti, Transport and Planning, Transport & Planning, Civil Engineering and Geosciences

Transport & Planning, Civil Engineering and Geosciences