Modeling Lane-Changing Behavior in a Connected Environment: A Game Theory Approach
TL;DR: A lane-changing model based on a game-theoretical approach that endogenously accounts for the flow of information in a connected vehicular environment is presented and provides a greater level of realism than a basic gap-acceptance model.
Abstract: Vehicle-to-Vehicle communications provide the opportunity to create an internet of cars through the recent advances in communication technologies, processing power, and sensing technologies. A connected vehicle receives real-time information from surrounding vehicles; such information can improve drivers’ awareness about their surrounding traffic condition and lead to safer and more efficient driving maneuvers. Lane-changing behavior,as one of the most challenging driving maneuvers to understand and to predict, and a major source of congestion and collisions, can benefit from this additional information.This paper presents a lane-changing model based on a game-theoretical approach that endogenously accounts for the flow of information in a connected vehicular environment.A calibration approach based on the method of simulated moments is presented and a simplified version of the proposed framework is calibrated against Next Generation Simulation (NGSIM) data. The prediction capability of the simplified model is validated. It is concluded the presented framework is capable of predicting lane-changing behavior with limitations that still need to be addressed. Finally, a simulation framework based on the fictitious play is proposed. The simulation results revealed that the presented lane-changing model provides a greater level of realism than a basic gap-acceptance model.
Citations
More filters
TL;DR: This study applied the CV concept on a congested expressway (SR408) in Florida to improve traffic safety and showed that both CV approaches significantly improved the longitudinal safety in the studied expressway compared to the non-CV scenario.
181 citations
TL;DR: This study develops a game theory-based mandatory lane-changing model (AZHW model) for the traditional environment and extends it for the connected environment and reveals that the AZHW models developed in this study outperform existing models.
Abstract: The connected environment provides real-time information about surrounding traffic; such information can be helpful in complex driving manoeuvres, such as lane-changing, that require information about surrounding vehicles. Lane-changing modelling in the connected environment has so far received little attention. This is due to the novelty of connected environment, and the consequent scarcity of data. A behaviourally sound lane-changing model is not even available for the traditional environment; that is, an environment without driving aids. To address this need, this study develops a game theory-based mandatory lane-changing model (AZHW model) for the traditional environment and extends it for the connected environment. The CARRS-Q advanced driving simulator is used to collect high-quality vehicle trajectory data for the connected environment. The developed models (for traditional environment and connected environment) are calibrated using NGSIM and simulator data in a bi-level calibration framework. The performance of the models has been rigorously evaluated using various performance indicators. These include the true positive, false positive, detection rate, false alarm rate, time prediction error, and location prediction error. Results consistently show that the developed game theory-based models can effectively capture mandatory lane-changing decisions with a high degree of accuracy. Furthermore, the performance of the developed AZHW models is compared with representative game theory-based lane-changing models in the literature. The comparative analysis reveals that the AZHW models developed in this study outperform existing models.
112 citations
TL;DR: A novel algorithm combining the hidden Markov model (HMM) and Bayesian filtering techniques to recognize a driver’s lane changing intention and can achieve a recognition accuracy of 93.5% and 90.3% which is a significant improvement compared with the HMM-only algorithm.
Abstract: Poor driving habits such as not using turn signals when changing lanes present a major challenge to advanced driver assistance systems that rely on turn signals. To address this problem, we propose a novel algorithm combining the hidden Markov model (HMM) and Bayesian filtering (BF) techniques to recognize a driver’s lane changing intention. In the HMM component, the grammar definition is inspired by speech recognition models, and the output is a preliminary behavior classification. As for the BF component, the final behavior classification is produced based on the current and preceding outputs of the HMMs. A naturalistic data set is used to train and validate the proposed algorithm. The results reveal that the proposed HMM–BF framework can achieve a recognition accuracy of 93.5% and 90.3% for right and left lane changing, respectively, which is a significant improvement compared with the HMM-only algorithm. The recognition time results show that the proposed algorithm can recognize a behavior correctly at an early stage.
110 citations
TL;DR: The effects of decentralized cooperative lane-changing decision-making framework on traffic stability, efficiency, homogeneity, and safety are investigated in a numerical simulation experiment and show the high potential of the proposed framework in traffic dynamics.
Abstract: In this paper, we proposed a decentralized cooperative lane-changing decision-making framework for connected autonomous vehicles, which is composed of three modules, i.e., state prediction, candidate decision generation, and coordination. In other words, each connected autonomous vehicle makes cooperative lane-changing decision independently. In the state prediction module, we employed existing cooperative car-following models to predict the vehicles' future state. In the candidate decision generation module, we proposed incentive based model to generate a candidate decision. In the candidate decision coordination module, we proposed an algorithm to avoid candidate lane-changing decision that may lead to a vehicle collision or traffic deterioration to be final decision. Moreover, the effects of decentralized cooperative lane-changing decision-making framework on traffic stability, efficiency, homogeneity, and safety are investigated in a numerical simulation experiment. Some stability, efficiency, homogeneity, and safety indicators are evaluated and show the high potential of our proposed framework in traffic dynamics.
97 citations
Cites methods from "Modeling Lane-Changing Behavior in ..."
...The game theoretic approach was employed to endogenously account for the flow of information in a connected vehicle environment, and the proposed lane change model could evaluate whether a lane changewas beneficial through the acceleration of both the subject vehicle and its four surrounding vehicles [13]....
[...]
TL;DR: A deep learning model, long short-term memory (LSTM) neural networks, is adopted to model the two basic behaviors simultaneously of car-following and lane-changing, and the results show that HRC LSTM model can accurately estimate CF and LC behaviors simultaneously with low longitudinal trajectories error and high LC prediction accuracy compared with the classical models.
Abstract: Car-following (CF) and lane-changing (LC) behaviors are two basic movements in traffic flow which are generally modeled separately in the literature, and thus the interaction between the two behaviors may be easily ignored in separated models and lead to unrealistic traffic flow description. In this paper, we adopt a deep learning model, long short-term memory (LSTM) neural networks, to model the two basic behaviors simultaneously. By only observing the position information of the six vehicles surrounding the subject vehicle, the LSTM can extract the significant features that influence the CF and LC behaviors automatically and predict the vehicles behaviors with time-series data and memory effects. In addition, we propose a hybrid retraining constrained (HRC) training method to further optimize the LSTM model. With the I-80 trajectory data of NGSIM dataset we train and test the HRC LSTM model, while the results show that HRC LSTM model can accurately estimate CF and LC behaviors simultaneously with low longitudinal trajectories error and high LC prediction accuracy compared with the classical models. We also evaluate the transferability of the proposed model with the US101 dataset and a good transferability result is obtained as well.
91 citations
References
More filters
TL;DR: In this paper, the authors present a critique of expected utility theory as a descriptive model of decision making under risk, and develop an alternative model, called prospect theory, in which value is assigned to gains and losses rather than to final assets and in which probabilities are replaced by decision weights.
Abstract: This paper presents a critique of expected utility theory as a descriptive model of decision making under risk, and develops an alternative model, called prospect theory. Choices among risky prospects exhibit several pervasive effects that are inconsistent with the basic tenets of utility theory. In particular, people underweight outcomes that are merely probable in comparison with outcomes that are obtained with certainty. This tendency, called the certainty effect, contributes to risk aversion in choices involving sure gains and to risk seeking in choices involving sure losses. In addition, people generally discard components that are shared by all prospects under consideration. This tendency, called the isolation effect, leads to inconsistent preferences when the same choice is presented in different forms. An alternative theory of choice is developed, in which value is assigned to gains and losses rather than to final assets and in which probabilities are replaced by decision weights. The value function is normally concave for gains, commonly convex for losses, and is generally steeper for losses than for gains. Decision weights are generally lower than the corresponding probabilities, except in the range of low prob- abilities. Overweighting of low probabilities may contribute to the attractiveness of both insurance and gambling. EXPECTED UTILITY THEORY has dominated the analysis of decision making under risk. It has been generally accepted as a normative model of rational choice (24), and widely applied as a descriptive model of economic behavior, e.g. (15, 4). Thus, it is assumed that all reasonable people would wish to obey the axioms of the theory (47, 36), and that most people actually do, most of the time. The present paper describes several classes of choice problems in which preferences systematically violate the axioms of expected utility theory. In the light of these observations we argue that utility theory, as it is commonly interpreted and applied, is not an adequate descriptive model and we propose an alternative account of choice under risk. 2. CRITIQUE
35,067 citations
27,773 citations
"Modeling Lane-Changing Behavior in ..." refers methods in this paper
...Talebpour et al. (Talebpour et al., 2011) modeled this decision making process using Kahneman and Tversky’s prospect theory (Kahneman and Tversky, 1979)....
[...]
TL;DR: In this article, it was shown that the set of equilibrium points of a two-person zero-sum game can be defined as a set of all pairs of opposing "good" strategies.
Abstract: we would call cooperative. This theory is based on an analysis of the interrelationships of the various coalitions which can be formed by the players of the game. Our theory, in contradistinction, is based on the absence of coalitions in that it is assumed that each participant acts independently, without collaboration or communication with any of the others. The notion of an equilibrium point is the basic ingredient in our theory. This notion yields a generalization of the concept of the solution of a two-person zerosum game. It turns out that the set of equilibrium points of a two-person zerosum game is simply the set of all pairs of opposing "good strategies." In the immediately following sections we shall define equilibrium points and prove that a finite non-cooperative game always has at least one equilibrium point. We shall also introduce the notions of solvability and strong solvability of a non-cooperative game and prove a theorem on the geometrical structure of the set of equilibrium points of a solvable game. As an example of the application of our theory we include a solution of a
6,577 citations
"Modeling Lane-Changing Behavior in ..." refers background in this paper
...The approach assumes that drivers play a repeated game until a Nash equilibrium is reached (Nash, 1951)....
[...]
TL;DR: It is shown that the results of the microscopic model can be understood by formulating the theoretical phase diagram for bottlenecks in a more general way, and a local drop of the road capacity induced by parameter variations has essentially the same effect as an on-ramp.
Abstract: We present data from several German freeways showing different kinds of congested traffic forming near road inhomogeneities, specifically lane closings, intersections, or uphill gradients. The states are localized or extended, homogeneous or oscillating. Combined states are observed as well, like the coexistence of moving localized clusters and clusters pinned at road inhomogeneities, or regions of oscillating congested traffic upstream of nearly homogeneous congested traffic. The experimental findings are consistent with a recently proposed theoretical phase diagram for traffic near on-ramps [D. Helbing, A. Hennecke, and M. Treiber, Phys. Rev. Lett. 82, 4360 (1999)]. We simulate these situations with a continuous microscopic single-lane model, the ``intelligent driver model,'' using empirical boundary conditions. All observations, including the coexistence of states, are qualitatively reproduced by describing inhomogeneities with local variations of one model parameter. We show that the results of the microscopic model can be understood by formulating the theoretical phase diagram for bottlenecks in a more general way. In particular, a local drop of the road capacity induced by parameter variations has essentially the same effect as an on-ramp.
3,432 citations
Additional excerpts
...…parameters such as desired acceleration, desired gap size, and comfortable deceleration are considered in this model (Kesting et al., 2010; Treiber et al., 2000): ⎥ ⎥ ⎦ ⎤ ⎢ ⎢ ⎣ ⎡ ⎟ ⎟ ⎠ ⎞ ⎜ ⎜ ⎝ ⎛ Δ −⎟ ⎟ ⎠ ⎞ ⎜ ⎜ ⎝ ⎛ −=Δ 2* 0 ),(1),,( n nn n n nnnn n IDM s vvs v vavvsa nδ (25.a) nn nn nn n…...
[...]
TL;DR: The paper develops a new theory for the analysis of games with incomplete information where the players are uncertain about some important parameters of the game situation, such as the payoff functions, the strategies available to various players, the information other players have about the game, etc.
Abstract: (This article originally appeared in Management Science, November 1967, Volume 14, Number 3, pp. 159-182, published by The Institute of Management Sciences.)
The paper develops a new theory for the analysis of games with incomplete information where the players are uncertain about some important parameters of the game situation, such as the payoff functions, the strategies available to various players, the information other players have about the game, etc. However, each player has a subjective probability distribution over the alternative possibilities.
In most of the paper it is assumed that these probability distributions entertained by the different players are mutually "consistent," in the sense that they can be regarded as conditional probability distributions derived from a certain "basic probability distribution" over the parameters unknown to the various players. But later the theory is extended also to cases where the different players' subjective probability distributions fail to satisfy this consistency assumption.
In cases where the consistency assumption holds, the original game can be replaced by a game where nature first conducts a lottery in accordance with the basic probability distribution, and the outcome of this lottery will decide which particular subgame will be played, i.e., what the actual values of the relevant parameters will be in the game. Yet, each player will receive only partial information about the outcome of the lottery, and about the values of these parameters. However, every player will know the "basic probability distribution" governing the lottery. Thus, technically, the resulting game will be a game with complete information. It is called the Bayes-equivalent of the original game. Part I of the paper describes the basic model and discusses various intuitive interpretations for the latter. Part II shows that the Nash equilibrium points of the Bayes-equivalent game yield "Bayesian equilibrium points" for the original game. Finally, Part III considers the main properties of the "basic probability distribution."
2,710 citations