|
| | Modeling Approaches | Challenges and Directions |
|
| Lane changing | (i) Lane changing literature reviews and classification [4, 5].
(ii) Rule-based approaches using Gipps Model with the lane changing process as a decision tree with a series of fixed conditions [31]. Other rule-based schemes include Cellular automata [32] and game theory based models [33].
(iii) Discrete-choice models based on probabilities include [34, 35].
(iv) Fuzzy-logic and artificial neural networks have been used in [4, 36, 37], to account for uncertainty and facilitate unsupervised training on real data.
(v) Incentive-based models that incorporate factors such as the desire to follow a route, gain speed, and keep right [39] and politeness factors [38]. | (i) Incorporating personal driving incentives and preferences, with contextual factors such as weather and lighting, is needed to develop more personalized lane changing models.
(ii) Works addressing more the less common and complex driving tasks such as ramp merging and multiple lane changing. |
|
| Intersection decision-making | (i) Identifying the degree of stopping violations at intersections based on Speed Distance Regression (SDR) classification [52]. Field-test based characterization of driver stopping decisions for different age groups and genders [53].
(ii) Driver behavior classification at intersections based on SVMs and HMMs. Validation performed on a large naturalistic dataset [23].
(iii) Recognizing other behaviors at intersections, for example, turning and stopping [42, 43] and left turns at signaled intersections [44].
(iv) Predicting multiple situations using case-based reasoning [45]. Modeling the evolution of an intersection using situation assessment and behavior prediction [46]. | (i) Developing cooperative models that leverage information from multiple vehicles to enable collective behavior at intersections.
(ii) Coupling intervehicular communications with driver behavior modeling.
(iii) Developing unified standard datasets to evaluate different intersection behaviors. This will offer a platform for researchers to compare and evaluate their modeling techniques. |
|
| Driver profiling | (i) Detecting aggressive driver behavior and competence using probabilistic ARX models [54].
(ii) Measuring in-vehicle acceleration using smartphone sensors to count events of sudden acceleration, braking, and sharp turning [10].
(iii) Fuzzy-logic based scoring mechanisms to profile driver aggressiveness [11].
(iv) Using an onboard diagnostic reader and an inertial measurement unit along with a Bayes classifier to model aggressiveness [12]. | (i) Trading off accuracy versus cost for use of traditional cell-phone sensors versus advanced in-vehicle sensors and OBD.
(ii) Differentiating between aggressive behaviors and skilled maneuvers that include acceleration. |
|
| Router choice modeling | (i) Survey on the current literature on route choice models with the focus on using fuzzy-logic and genetic algorithms [55].
(ii) Classification of literature according to the considered user preferences, for example, travel time, the number of intersections, traffic lights, and roadside aesthetics [56].
(iii) Incorporating feedback to learn user preferences [58] and exploring the evolution of driver route choices with time [57]. | (i) Building distributed end-to-end travel assistance systems that incorporate real-time sensing of traffic, weather, and road conditions.
(ii) Developing more sophisticated personalized navigation and travel systems that learn and model user preferences. |
|
