Driving behavior has a large impact on vehicle fuel consumption. Dedicated study on relationship between driving behavior and fuel consumption can contribute to decrease the energy cost of transportation and the development of the behavior assessment technology for the ADAS system. So, it is vital to evaluate this relationship in order to develop more ecological driving assistance systems and improve vehicle fuel economy. However, modeling driving behavior under dynamic driving conditions is complex, making quantitative analysis of the relationship between driving behavior and fuel consumption difficult. In this paper, we introduce two kinds of machine learning methods for evaluating the fuel efficiency of driving behavior using naturalistic driving data. In the first stage, we use an unsupervised spectral clustering algorithm to study the macroscopic relationship between driving behavior and fuel consumption, using data collected during the natural driving process. In the second stage, dynamic information from the driving environment and natural driving data are integrated to generate a model of the relationship between various driving behaviors and the corresponding fuel consumption features. The dynamic environment factors are coded into a processible, digital form using a deep learning-based object detection method, so that the environmental data can be linked with the vehicle’s operating signal data to provide the training data for the deep learning network. The training data is labeled according to its fuel consumption feature distribution, which is obtained from road segment data and historical driving data. This deep learning-based model can then be used as a predictor of the fuel consumption associated with different driving behaviors. Our results show that the proposed method can effectively identify the relationship between driving behavior and fuel consumption on both macro and micro levels, allowing for end-to-end fuel consumption feature prediction, which can then be applied in advanced driving assistance systems.

Research on how risk is perceived by drivers is vital to driving behavior research and driving safety. As risk can be divided into subjective and objective risk, in this paper we focus on modeling subjective risk perception by drivers using a deep learning method. Different drivers often perceive different levels of subjective risk under the same driving conditions. In addition, different driving conditions or driving events will have different effects on drivers. Based on these two risk perception features, in this paper we first design an experiment on a city road with two lanes to assess the level of subjective risk perceived by drivers belonging to different groups. We then use a deep learning network based method to abstract features of the driving environment. These environmental features are integrated with driver risk perception data and this information is used as training and testing data for the learning network. Finally, a Long Short Term Memory based method is adopted to model the subjective risk perception of individual drivers based on traffic conditions and vehicle operation data from the driver’s vehicle. Our results show that the proposed method can effectively model the subjective risk perception behavior of drivers, allowing for end-to-end risk perception prediction in future driving assistance systems.

In this paper, a novel transformable leg-wheel mechanism is proposed. It has three active joints, among which the hip roll joint is directly driven, the hip pitch joint is driven by gear transmission, and the knee joint is driven by synchronous belt transmission. All the actuators are mounted on the body to reduce the weight of the leg-wheel mechanism as possible, so that the motion of the leg-wheel mechanism will be slightly affected by the inertia. The proposed mechanism has two characteristics, the big wheel radius and the reduced actuator. The design and kinematics modeling methods of the leg-wheel mechanism are described. A half-a-heart shape trajectory is proposed to plan the foot motion of the leg-wheel mechanism in the legged locomotion. To make the locomotion mode transition smooth, the transition strategy is designed. Simulation and experimental results verify the feasibility of the proposed leg-wheel mechanism.