1 Introduction
-
to explore the feasibility of modeling mixed traffic conditions using data–driven models
-
to compare the performance of data–driven models versus conventional models, in particular Gipps model
-
to estimate model efficiency considering the difference in following behavior across different vehicle pairs
-
to introduce the concept of temporary virtual lanes based on identification of significant lateral changes.
2 Literature review
3 Methodology
3.1 Virtual lanes and leader–follower pair identification
3.1.1 Determination of virtual lanes
3.1.2 Identification of leader–follower vehicles
3.1.3 Operationalization process
3.2 Data–driven modeling
3.3 Evaluation
4 Case study set–up
4.1 Data collection
4.2 Data processing
4.3 Estimation of conventional models
a/a | Vehicle type | Sample 1 | Sample 2 | Sample 3 |
---|---|---|---|---|
1 | Motorcycle | 2665 | 2701 | 2626 |
2 | Car | 1347 | 1292 | 1347 |
3 | Bus | 145 | 156 | 156 |
4 | Truck | 41 | 29 | 15 |
5 | Light commercial vehicle | 56 | 59 | 78 |
6 | Auto–rickshaw | 746 | 763 | 778 |
Parameters | Initial values | Constraints | Opt. values | Mean values | |||
---|---|---|---|---|---|---|---|
Min | Max | Sample 1 | Sample 2 | Sample 3 | |||
α
| 0.8 | 0.8 | -2.6 | 0.81 | 0.82 | 0.82 | 0.82 |
b | -3.2 | -5.2 | -1.6 | -5.18 | -5.17 | -5.08 | -5.14 |
V | 14.4 | 10.4 | 29.6 | 10.45 | 10.44 | 10.44 | 10.44 |
s | 5.9 | 5.6 | 7.5 | 5.62 | 5.60 | 5.60 | 5.61 |
b | -3.1 | -4.5 | -3.0 | -3.01 | -3.01 | -3.00 | -3.01 |
RMSN | - | - | - | 0.21 | 0.22 | 0.21 | - |