We investigate the feasibility of classifying (inferring) the emergency braking situations in road vehicles from the motion pattern of the accelerator pedal. We trained and compared several classifiers and employed genetic algorithms to tune their associated hyperparameters. Using offline time series data of the dynamics of the accelerator pedal as the test set, the experimental results suggest that the evolved classifiers detect the emergency braking situation with at least 93% accuracy. The best performing classifier could be integrated into the agent that perceives the dynamics of the accelerator pedal in real time and—if emergency braking is detected—acts by applying full brakes well before the driver would have been able to apply them.

We investigate the feasibility of inferring the intention of the human driver of road motor vehicles to apply emergency braking solely by analyzing the dynamics of lifting the accelerator pedal. Focusing on building the system that reliably classifies the emergency braking situations, we employed evolutionary algorithms (EA) to coevolve both (i) the set of features that optimally characterize the movement of accelerator pedal and (ii) the values of the hyperparameters of the classifier. The experimental results demonstrate the superiority of the coevolutionary approach over the analogical approaches that rely on an a priori defined set of features and values of hyperparameters. By using simultaneous evolution of both features and hyperparameters, the learned classifier inferred the emergency braking situations in previously unforeseen dynamics of the accelerator pedal with an accuracy of about 95%. We consider the obtained results as a step towards the development of a brake-assisting system, which would perceive the dynamics of the accelerator pedal in a real-time and in case of a foreseen emergency braking situation, would apply the brakes automatically well before the human driver would have been able to apply them.

ExponentialFamilyManifolds.jl implements exponential family natural parameter spaces as Riemannian manifolds, enabling geometric optimization over probability distributions. The package automatically manages parameter constraints, such as ensuring the positive definiteness of precision matrices for normal distributions. By representing exponential family distributions as manifolds that conform to the ManifoldsBase.jl interface, it allows users to leverage optimization techniques from Manopt.jl for these manifolds. Applications in maximum likelihood estimation and variational inference highlight the package's practical utility.