The Experts below are selected from a list of 165 Experts worldwide ranked by ideXlab platform
Edwin Olson - One of the best experts on this subject based on the ideXlab platform.
-
ICRA - MPDM: Multipolicy decision-making in dynamic, uncertain environments for autonomous driving
2015 IEEE International Conference on Robotics and Automation (ICRA), 2015Co-Authors: Alexander G. Cunningham, Ryan M. Rm Eustice, Enric Galceran, Edwin OlsonAbstract:Real-world autonomous driving in city traffic must cope with dynamic environments including other agents with uncertain intentions. This poses a challenging decision-making problem, e.g., deciding when to perform a Passing Maneuver or how to safely merge into traffic. Previous work in the literature has typically approached the problem using ad-hoc solutions that do not consider the possible future states of other agents, and thus have difficulty scaling to complex traffic scenarios where the actions of participating agents are tightly conditioned on one another. In this paper we present multipolicy decision-making (MPDM), a decision-making algorithm that exploits knowledge from the autonomous driving domain to make decisions online for an autonomous vehicle navigating in traffic. By assuming the controlled vehicle and other traffic participants execute a policy from a set of plausible closed-loop policies at every timestep, the algorithm selects the best available policy for the controlled vehicle to execute. We perform policy election using forward simulation of both the controlled vehicle and other agents, efficiently sampling from the high-likelihood outcomes of their interactions. We then score the resulting outcomes using a user-defined cost function to accommodate different driving preferences, and select the policy with the highest score. We demonstrate the algorithm on a real-world autonomous vehicle performing Passing Maneuvers and in a simulated merging scenario.
-
MPDM: Multipolicy decision-making in dynamic, uncertain environments for autonomous driving
Proceedings - IEEE International Conference on Robotics and Automation, 2015Co-Authors: Alexander G. Cunningham, Ryan M. Rm Eustice, Enric Galceran, Edwin OlsonAbstract:— Real-world autonomous driving in city traffic must cope with dynamic environments including other agents with uncertain intentions. This poses a challenging decision-making problem, e.g., deciding when to perform a Passing Maneuver or how to safely merge into traffic. Previous work in the literature has typically approached the problem using ad-hoc solutions that do not consider the possible future states of other agents, and thus have difficulty scaling to complex traffic scenarios where the actions of participating agents are tightly conditioned on one another. In this paper we present multipolicy decision-making (MPDM), a decision-making algorithm that exploits knowledge from the autonomous driving domain to make decisions online for an autonomous vehicle navigating in traffic. By assuming the controlled vehicle and other traffic participants execute a policy from a set of plausible closed-loop policies at every timestep, the algorithm selects the best available policy for the controlled vehicle to execute. We perform policy election using forward simulation of both the controlled vehicle and other agents, efficiently sampling from the high-likelihood outcomes of their interactions. We then score the resulting outcomes using a user-defined cost function to accommodate different driving preferences, and select the policy with the highest score. We demonstrate the algorithm on a real-world autonomous vehicle performing Passing Maneuvers and in a simulated merging scenario.
Alfredo Garcia - One of the best experts on this subject based on the ideXlab platform.
-
design criteria for minimum Passing zone lengths operational efficiency and safety considerations
Transportation Research Record, 2015Co-Authors: Ana Tsui Moreno, Carlos Llorca, Annique Lenorzer, Jordi Casas, Alfredo GarciaAbstract:Passing zones are provided to improve operational efficiency of two-lane highways. Minimum Passing zone lengths of 120 m were established by FHWA and AASHTO. Some studies indicate that lengths may need to be increased, but no changes have been recommended, pending further research. The objective of this study was to develop design and marking criteria for minimum Passing zone lengths, with traffic operational efficiency and safety taken into consideration. First, a traffic microsimulation was conducted with AIMSUN software. The calibration and validation included the observation of 1,750 Passing Maneuvers in Spain. Results indicated that Passing zones shorter than 250 m added little to operational efficiency. Second, a reliability analysis was applied. The analysis quantified the probability that a Passing Maneuver was completed beyond the end of the Passing zone (noncompliant Passing Maneuver). Then the number of noncompliant Passing Maneuvers was calculated. Traffic flow and Passing zone length were con...
-
development of a new microscopic Passing Maneuver model for two lane rural roads
Transportation Research Part C-emerging Technologies, 2015Co-Authors: Carlos Llorca, Ana Tsui Moreno, Annique Lenorzer, Jordi Casas, Alfredo GarciaAbstract:Microsimulation is a useful tool to analyze traffic operation. On two-lane highways, the complexity of Passing and the interaction with oncoming traffic requires specific models. This study focused on the development of a Passing desire, decision and execution model. Results of the observation of 1752 Maneuvers on 10 rural roads in Spain were used for this development. The model incorporated the effect of new factors such as available sight distance, delay and remaining travel time until the end of the highway segment. Outputs of the model were compared to observed data: firstly, individual Passing Maneuvers; secondly, traffic flow, percent followers and number of Passing Maneuvers in four single Passing zones with two different traffic levels. The model was validated in four alternative Passing zones.
Alexander G. Cunningham - One of the best experts on this subject based on the ideXlab platform.
-
ICRA - MPDM: Multipolicy decision-making in dynamic, uncertain environments for autonomous driving
2015 IEEE International Conference on Robotics and Automation (ICRA), 2015Co-Authors: Alexander G. Cunningham, Ryan M. Rm Eustice, Enric Galceran, Edwin OlsonAbstract:Real-world autonomous driving in city traffic must cope with dynamic environments including other agents with uncertain intentions. This poses a challenging decision-making problem, e.g., deciding when to perform a Passing Maneuver or how to safely merge into traffic. Previous work in the literature has typically approached the problem using ad-hoc solutions that do not consider the possible future states of other agents, and thus have difficulty scaling to complex traffic scenarios where the actions of participating agents are tightly conditioned on one another. In this paper we present multipolicy decision-making (MPDM), a decision-making algorithm that exploits knowledge from the autonomous driving domain to make decisions online for an autonomous vehicle navigating in traffic. By assuming the controlled vehicle and other traffic participants execute a policy from a set of plausible closed-loop policies at every timestep, the algorithm selects the best available policy for the controlled vehicle to execute. We perform policy election using forward simulation of both the controlled vehicle and other agents, efficiently sampling from the high-likelihood outcomes of their interactions. We then score the resulting outcomes using a user-defined cost function to accommodate different driving preferences, and select the policy with the highest score. We demonstrate the algorithm on a real-world autonomous vehicle performing Passing Maneuvers and in a simulated merging scenario.
-
MPDM: Multipolicy decision-making in dynamic, uncertain environments for autonomous driving
Proceedings - IEEE International Conference on Robotics and Automation, 2015Co-Authors: Alexander G. Cunningham, Ryan M. Rm Eustice, Enric Galceran, Edwin OlsonAbstract:— Real-world autonomous driving in city traffic must cope with dynamic environments including other agents with uncertain intentions. This poses a challenging decision-making problem, e.g., deciding when to perform a Passing Maneuver or how to safely merge into traffic. Previous work in the literature has typically approached the problem using ad-hoc solutions that do not consider the possible future states of other agents, and thus have difficulty scaling to complex traffic scenarios where the actions of participating agents are tightly conditioned on one another. In this paper we present multipolicy decision-making (MPDM), a decision-making algorithm that exploits knowledge from the autonomous driving domain to make decisions online for an autonomous vehicle navigating in traffic. By assuming the controlled vehicle and other traffic participants execute a policy from a set of plausible closed-loop policies at every timestep, the algorithm selects the best available policy for the controlled vehicle to execute. We perform policy election using forward simulation of both the controlled vehicle and other agents, efficiently sampling from the high-likelihood outcomes of their interactions. We then score the resulting outcomes using a user-defined cost function to accommodate different driving preferences, and select the policy with the highest score. We demonstrate the algorithm on a real-world autonomous vehicle performing Passing Maneuvers and in a simulated merging scenario.
Haneen Farah - One of the best experts on this subject based on the ideXlab platform.
-
Passing Behavior on Two-Lane Highways
2020Co-Authors: Haneen Farah, Tomer ToledoAbstract:Two-lane highways make up a substantial proportion of the road network in most of the world. Passing is among the most significant driving behaviors on two-lane highways. It substantially impacts the highway performance. Despite the importance of the problem, few studies attempted to model Passing behavior. In this research, a model that attempts to capture both drivers' desire to pass and their gap acceptance decisions to complete a desired Passing Maneuver is developed and estimated using data on Passing Maneuvers collected with a driving simulator. 16 different scenarios were used in the experiment in order to capture the impact of factors related to the various vehicles involved, the road geometry and the driver characteristics in the model. A Passing behavior model is developed that includes choices in two levels: the desire to pass and the decision whether or not to accept an available Passing gap. The probability to complete a Passing Maneuver is modeled as the product of the probabilities of a positive decision on both these choices. The estimation results show that modeling the drivers' desire to pass the vehicle in front has a statistically significant contribution in explaining their Passing behavior. The two sub-models incorporate variables that capture the impact of the attributes of the specific Passing gap that the driver evaluates and the relevant vehicles, the geometric characteristics of the road section and the driver characteristics and account for unobserved heterogeneity in the driver population.
-
effect of Passing zone length on operation and safety of two lane rural highways in uganda
Iatss Research, 2017Co-Authors: Haneen Farah, Godfrey Mwesige, Umaru Bagampadde, Haris N KoutsopoulosAbstract:This paper presents a methodology to assess the effect of the length of Passing zone on the operation and safety of two-lane rural highways based on the probability and the rate of Passing Maneuvers ending in a no-Passing zone. The methodology was applied using observed Passing Maneuver data collected with tripod-mounted camcorders at Passing zones in Uganda. Findings show that the rate at which Passing Maneuvers end in a no-Passing zone increases with traffic volume and unequal distribution of traffic in the two directions, absolute vertical grade, and percent of heavy vehicles in the subject direction. Additionally, the probability of Passing Maneuvers ending in a no-Passing zone reaches 0.50 when the remaining sight distance from the beginning of the Passing zone is 245. m for passenger cars or short trucks (2-3 axles), and 300. m for long trucks (4-7 axles) as the passed vehicles. These results suggest policy changes in design and marking of Passing zones to enhance safety and operation of two-lane rural highways.
-
Risk appraisal of Passing zones on two-lane rural highways and policy applications
Accident Analysis & Prevention, 2016Co-Authors: Godfrey Mwesige, Haneen Farah, Haris N KoutsopoulosAbstract:Abstract Passing on two-lane rural highways is associated with risks of head-on collision resulting from unsafe completion of Passing Maneuvers in the opposite traffic lane. In this paper, we explore the use of time-to-collision (TTC) as a surrogate safety measure of the risk associated with Passing Maneuvers. Logistic regression models to predict the probability to end the Passing Maneuver with TTC less than 2 or 3 s-threshold were developed with the time-gap from initiation of the Maneuver to arrival of the opposite vehicle (effective accepted gap), and the Passing duration as explanatory variables. The data used for model estimation was collected using stationary tripod-mounted camcorders at 19 Passing zones in Uganda. Results showed that Passing Maneuvers completed with TTC less than 3 s are unsafe and often involved sudden speed reduction, flashing headlights, and lateral shift to shoulders. Model sensitivity analysis was conducted for observed Passing durations involving passenger cars or short trucks (2–3 axles), and long trucks (4–7 axles) as the passed vehicles for 3 s TTC-threshold. Three risk levels were proposed based on the probability to complete Passing Maneuvers with TTC less than 3 s for a range of opposite direction traffic volumes. Applications of the results for safety improvements of two-lane rural highways are also discussed.
-
Safety analysis of Passing Maneuvers using extreme value theory
2015Co-Authors: Haneen Farah, Carlos Lima AzevedoAbstract:The increased availability of detailed trajectory data sets from naturalistic, observational and simulation-based studies are a key source for potential improvements in the development of detailed safety models that explicitly account for vehicle conflict interactions and the various driving Maneuvers. Despite the well-recognized research findings on both crash frequency estimation and traffic conflicts analysis carried out over the last decades, only recently researchers have started to study and model the link between the two. This link is typically made by statistical association between aggregated conflicts and crashes, which still relies on crash data and ignores heterogeneity in the estimation procedure. More recently, an Extreme Value (EV) approach has been used to link the probability of crash occurrence to the frequency of conflicts estimated from observed variability of crash proximity, using a probabilistic framework and without using crash records. In this on-going study the Generalized Extreme Value (GEV) distribution and the Generalized Pareto Distribution (GPD)-based estimation, in the peak over threshold approach, are tested and compared as EV methods using the minimum time-to-collision with the opposing vehicle during Passing Maneuvers. Detailed trajectory data of the Passing, passed and opposite vehicles from a fixed-based driving simulator experiment was used in this study. One hundred experienced drivers from different demographic strata participated in this experiment on a voluntary base. Several two-lane rural highway layouts and traffic conditions were also considered in the design of the simulator environment. Raw data was collected at a resolution of 0.1 s and included the longitudinal and lateral position, speed and acceleration of all vehicles in the scenario. From this raw data, the minimum time-to-collision with the opposing vehicle at the end of the Passing, Maneuver was calculated. GEV distributions based on the Block Maxima approach and GPD distributions under the POT approach were tested for the estimation of head-on collision probabilities in Passing Maneuvers with different results. While the GEV approach achieved satisfactory fitting results, the tested POT underestimated the expected number of head-on collisions. Finally, the estimated GEV distributions were validated using a second set of data extracted from an additional driving simulator experiment. The results indicate that this is a promising approach for safety evaluation. On-going work of the authors will attempt to generalize this method to other safety measures related to Passing Maneuvers, test it for the detailed analysis of the effect of demographic factors on Passing Maneuvers’ crash probability and for its usefulness in a traffic simulation environment
-
ITSC - Using Extreme Value Theory for the Prediction of Head-On Collisions During Passing Maneuvres
2015 IEEE 18th International Conference on Intelligent Transportation Systems, 2015Co-Authors: Carlos Lima Azevedo, Haneen FarahAbstract:This paper tests the Generalized Extreme Value (GEV) distribution as an EV method using the minimum time-to-collision with the opposing vehicle during Passing Maneuvers. Detailed trajectory data of the Passing, passed and opposite vehicles from a fixed-based driving simulator experiment were used in this study. One hundred experienced drivers from different demographic strata participated in this experiment on a voluntary base. Raw data were collected at a resolution of 0.1 s and included the longitudinal and lateral position, speed and acceleration of all vehicles in the scenario. From this raw data, the minimum time-to-collision with the opposing vehicle at the end of the Passing, Maneuver was calculated. GEV distribution based on the Block Maxima approach was tested for the estimation of head-on collision probabilities in Passing Maneuvers. The estimation results achieved good fit with respect to head-on collisions' prediction indicating that this is a promising approach for safety evaluation.
Haris N Koutsopoulos - One of the best experts on this subject based on the ideXlab platform.
-
effect of Passing zone length on operation and safety of two lane rural highways in uganda
Iatss Research, 2017Co-Authors: Haneen Farah, Godfrey Mwesige, Umaru Bagampadde, Haris N KoutsopoulosAbstract:This paper presents a methodology to assess the effect of the length of Passing zone on the operation and safety of two-lane rural highways based on the probability and the rate of Passing Maneuvers ending in a no-Passing zone. The methodology was applied using observed Passing Maneuver data collected with tripod-mounted camcorders at Passing zones in Uganda. Findings show that the rate at which Passing Maneuvers end in a no-Passing zone increases with traffic volume and unequal distribution of traffic in the two directions, absolute vertical grade, and percent of heavy vehicles in the subject direction. Additionally, the probability of Passing Maneuvers ending in a no-Passing zone reaches 0.50 when the remaining sight distance from the beginning of the Passing zone is 245. m for passenger cars or short trucks (2-3 axles), and 300. m for long trucks (4-7 axles) as the passed vehicles. These results suggest policy changes in design and marking of Passing zones to enhance safety and operation of two-lane rural highways.
-
Risk appraisal of Passing zones on two-lane rural highways and policy applications
Accident Analysis & Prevention, 2016Co-Authors: Godfrey Mwesige, Haneen Farah, Haris N KoutsopoulosAbstract:Abstract Passing on two-lane rural highways is associated with risks of head-on collision resulting from unsafe completion of Passing Maneuvers in the opposite traffic lane. In this paper, we explore the use of time-to-collision (TTC) as a surrogate safety measure of the risk associated with Passing Maneuvers. Logistic regression models to predict the probability to end the Passing Maneuver with TTC less than 2 or 3 s-threshold were developed with the time-gap from initiation of the Maneuver to arrival of the opposite vehicle (effective accepted gap), and the Passing duration as explanatory variables. The data used for model estimation was collected using stationary tripod-mounted camcorders at 19 Passing zones in Uganda. Results showed that Passing Maneuvers completed with TTC less than 3 s are unsafe and often involved sudden speed reduction, flashing headlights, and lateral shift to shoulders. Model sensitivity analysis was conducted for observed Passing durations involving passenger cars or short trucks (2–3 axles), and long trucks (4–7 axles) as the passed vehicles for 3 s TTC-threshold. Three risk levels were proposed based on the probability to complete Passing Maneuvers with TTC less than 3 s for a range of opposite direction traffic volumes. Applications of the results for safety improvements of two-lane rural highways are also discussed.