Chris Schwarz

Steering in a random forest: ensemble learning for detecting drowsiness-related lane departures

Objective: The aim of this study was to design and evaluate an algorithm for detecting drowsiness-related lane departures by applying a random forest classifier to steering wheel angle data. Background: Although algorithms exist to detect and mitigate driver drowsiness, the high rate of false alarms and missed detection of drowsiness represent persistent challenges. Current algorithms use a variety of data sources, definitions of drowsiness, and machine learning approaches to detect drowsiness. Method: We develop a new approach for detecting drowsiness-related lane departures using steering wheel angle data that employ an ensemble definition of drowsiness and a random forest algorithm. Data collected from 72 participants driving the National Advanced Driving Simulator are used to train and evaluate the model. The model’s performance was assessed relative to a commonly used algorithm, percentage eye closure (PERCLOS). Results: The random forest steering algorithm had a higher classification accuracy and area under the receiver operating characteristic curve than PERCLOS and had comparable positive predictive value. The algorithm succeeds at identifying two key scenarios associated with the drowsiness detection task. These two scenarios consist of instances when drivers depart their lane because they fail to modulate their steering behavior according to the demands of the simulated road and instances when drivers correctly modulate their steering behavior according to the demands of the road. Conclusion: The random forest steering algorithm is a promising approach to detect driver drowsiness. The algorithm’s ties to consequences of drowsy driving suggest that it can be easily paired with mitigation systems.

Real-time detection of drowsiness related lane departures using steering wheel angle

Drowsy driving is a significant factor in many motor vehicle crashes in the United States and across the world. Efforts to reduce these crashes have developed numerous algorithms to detect both acute and chronic drowsiness. These algorithms employ behavioral and physiological data, and have used different machine learning techniques. This work proposes a new approach for detecting drowsiness related lane departures, which uses unfiltered steering wheel angle data and a random forest algorithm. Using a data set from the National Advanced Driving Simulator the algorithm was compared with a commonly used algorithm, PERCLOS and a simpler algorithm constructed from distribution parameters. The random forest algorithm had higher accuracy and Area Under the receiver operating characteristic Curve (AUC) than PERCLOS and had comparable positive predictive value. The results show that steering-angle can be used to predict drowsiness related lane-departures six seconds before they occur, and suggest that the random forest algorithm, when paired with an alert system, could significantly reduce vehicle crashes.

Optimum subband coding of cyclostationary signals

We consider the optimal orthonormal subband coding of zero mean cyclostationary signals, with N-periodic second order statistics. A 2-channel uniform filter bank, with N-periodic analysis and synthesis filters, is used as the subband coder. A dynamic scheme involving N-periodic bit allocation is employed. An average variance condition is used to measure the output distortion. The conditions for maximizing the coding gain parallel those for the case when the signals are wide sense stationary (WSS) and the analysis and synthesis filters and the bit allocation time invariant, in that the blocked subband signals must be decorrelated and the subband power spectral densities must obey an ordering. Some additional conditions on this ordering, over and above those required for the WSS case, are needed.

A contextual and temporal algorithm for driver drowsiness detection

This study designs and evaluates a contextual and temporal algorithm for detecting drowsiness-related lane. The algorithm uses steering angle, pedal input, vehicle speed and acceleration as input. Speed and acceleration are used to develop a real-time measure of driving context. These measures are integrated with a Dynamic Bayesian Network that considers the time dependencies in transitions between drowsiness and awake states. The Dynamic Bayesian Network algorithm is validated with data collected from 72 participants driving the National Advanced Driving Simulator. The algorithm has a significantly lower false positive rate than PERCLOS-the current gold standard-and baseline, non-contextual, algorithms under design parameters that prioritize drowsiness detection. Under these parameters, the algorithm reduces false positive rate in highway and rural environments, which are typically problematic for vehicle-based detection algorithms. This algorithm is a promising new approach to driver impairment detection and suggests contextual factors should be considered in subsequent algorithm development processes. It may be combined with comprehensive mitigation methods to improve driving safety.

Evaluating driver drowsiness countermeasures

ABSTRACT Objective: Driver drowsiness contributes to a substantial number of fatal and nonfatal crashes, with recent estimates attributing up to 21% of fatal crashes to drowsiness. This article describes recent NHTSA research on in-vehicle drowsiness countermeasures. Recent advances in technology and state detection algorithms have shown success in detecting drowsiness using a variety of data sources, including camera-based eye tracking, steering wheel position, yaw rate, and vehicle lane position. However, detection is just the first step in reducing drowsy driving crashes. Countermeasures are also needed to provide feedback to the driver, modify driver behavior, and prevent crashes. The goal of this study was to evaluate the effectiveness of in-vehicle drowsiness countermeasures in reducing drowsy lane departures. The tested countermeasures included different warning modalities in either a discrete or staged interface. Methods: Data were collected from 72 young adult drivers (age 21–32) in the high-fidelity full-motion National Advanced Driving Simulator. Drivers completed a 45-min simulated nighttime drive at 2 time points, late night and early morning, where drowsiness was manipulated by continuous hours awake. Forty-eight drivers were exposed to one of 6 countermeasures that varied along 2 dimensions, type and modality. The countermeasures relied on a steering-based drowsiness detection algorithm developed in prior NHTSA research. Twenty-four drivers received no countermeasure and were used as a baseline comparison. System effectiveness was measured by lane departures and standard deviation in lateral position (SDLP). Results: There was a reduction in drowsy lane departure frequency and lane position variability for drivers with countermeasures compared to the baseline no-countermeasure group. Importantly, the data suggest that multistage alerts, which provide an indication of increasing urgency, were more effective in reducing drowsy lane departures than single-stage discrete alerts, particularly during early morning drives when drivers were drowsier. Conclusions: The results indicate that simple in-vehicle countermeasures, such as an auditory–visual coffee cup icon, can reduce the frequency of drowsy lane departures in the context of relatively short drives. An important next step is to evaluate the impact of drowsiness countermeasures in the context of longer, multiple-hour drives. In these cases, it may not be possible to keep drivers awake via feedback warnings and it is important to understand whether countermeasures prompt drivers to stop to rest. The next phase of this research project will examine the role of drowsiness countermeasures over longer drives using a protocol that replicates the motivational conditions of drowsy driving.

Steer or Brake? Modeling Drivers’ Collision-Avoidance Behavior by Using Perceptual Cues

Driver models have been developed to capture collision-avoidance behaviors, yet there is a lack of understanding of what perceptual processes influence drivers’ choices to brake or steer. A statistical model of these decisions was developed with cluster analysis and multinomial logistic regression with data from a simulator study of drivers’ responses to rear-end collisions. Drivers’ choices of responses were clustered on the basis of the maximum values of the magnitude of braking and steering forces, starting from the time at which the driver looked back to the road, just before initiating the avoidance maneuver, to the end of the maneuver. The clusters identified three types of responses: medium to high braking with medium to high steering, medium to high braking with mild steering, and mild braking with medium to high steering. The perceptual variables such as the optical angle, the expansion rate of the optical angle, and their ratio were used to predict the drivers’ choice of response. The results show that, of the perceptual variables, the combination of optical angle and tau performs as well as or better than others in predicting the choice of response. The mode and timing of an alert from a collision-warning system did not influence the drivers’ choices. These results can inform driver behavior models to guide design and assess benefits of advanced driver assistance systems.

Creating Pedestrian Crash Scenarios in a Driving Simulator Environment

Objective: In 2012 in the United States, pedestrian injuries accounted for 3.3% of all traffic injuries but, disproportionately, pedestrian fatalities accounted for roughly 14% of traffic-related deaths (NHTSA 2014). In many other countries, pedestrians make up more than 50% of those injured and killed in crashes. This research project examined driver response to crash-imminent situations involving pedestrians in a high-fidelity, full-motion driving simulator. This article presents a scenario development method and discusses experimental design and control issues in conducting pedestrian crash research in a simulation environment. Driving simulators offer a safe environment in which to test driver response and offer the advantage of having virtual pedestrian models that move realistically, unlike test track studies, which by nature must use pedestrian dummies on some moving track. Methods: An analysis of pedestrian crash trajectories, speeds, roadside features, and pedestrian behavior was used to create 18 unique crash scenarios representative of the most frequent and most costly crash types. For the study reported here, we only considered scenarios where the car is traveling straight because these represent the majority of fatalities. We manipulated driver expectation of a pedestrian both by presenting intersection and mid-block crossing as well as by using features in the scene to direct the drivers visual attention toward or away from the crossing pedestrian. Three visual environments for the scenarios were used to provide a variety of roadside environments and speed: a 20–30 mph residential area, a 55 mph rural undivided highway, and a 40 mph urban area. Results: Many variables of crash situations were considered in selecting and developing the scenarios, including vehicle and pedestrian movements; roadway and roadside features; environmental conditions; and characteristics of the pedestrian, driver, and vehicle. The driving simulator scenarios were subjected to iterative testing to adjust time to arrival triggers for the pedestrian actions. This article discusses the rationale behind creating the simulator scenarios and some of the procedural considerations for conducting this type of research. Conclusions: Crash analyses can be used to construct test scenarios for driver behavior evaluations using driving simulators. By considering trajectories, roadway, and environmental conditions of real-world crashes, representative virtual scenarios can serve as safe test beds for advanced driver assistance systems. The results of such research can be used to inform pedestrian crash avoidance/mitigation systems by identifying driver error, driver response time, and driver response choice (i.e., steering vs. braking).

A new normalized relatively stable lattice structure

This paper proposes a new lattice filter structure that has the following properties. When the filter is linear time invariant (LTI), it is equivalent to the celebrated Gray-Markel lattice. When the lattice parameters vary with time, it sustains arbitrary rates of time variations without sacrificing a prescribed degree of stability, provided that the lattice coefficients are magnitude bounded in a region where all LTI lattices have the same degree of stability. We also show that the resulting LTV lattice obeys an energy contraction condition. This structure thus generalizes the normalized Gray-Markel lattice, which has similar properties but only with respect to stability as opposed to relative stability.

A lattice structure for perfect reconstruction linear time varying filter banks with all pass analysis banks

We consider a multi-input, multi-output lattice realization for linear time-varying analysis banks which are all pass. Such a realization was given by Vaidyanathan and Mitra (1985) for linear time invariance (LTI) systems; and under certain conditions generalizes to the linear time varying (LTV) case. Moreover, our implementation is simpler than the one presented by Vaidyanathan et al. Finally, we describe the anticausal inverse of a lattice realization which is used in the synthesis bank.

Training and Education: Human Factors Considerations for Automated Driving Systems

Vehicles with partial automation, forerunners to those with higher levels of automation, are already being deployed by automakers. These current deployments, although incremental, have the potential to disrupt how people interact with vehicles. This chapter reports on a discussion of related issues that was held as part of the Human Factors Breakout session at the 2017 Automated Vehicle Symposium. The session, titled “Automated Vehicle Challenges: How can Human Factors Research Help Inform Designers, Road Users, and Policy Makers?”, included discussions between industry experts and human factors researchers and professionals on immediate human factors issues surrounding deployment of vehicles with Automated Driving Systems (ADS).