This paper presents a new energy management system based on equivalent consumption minimization strategy (ECMS) for hybrid electric vehicles. The aim is to enhance fuel economy and impose state of charge (SoC) charge-sustainability. First, the relationship between the equivalent factor (EF) of ECMS and the co-state of pontryagin’s minimum principle (PMP) is derived. Second, a new method of implementing the adaptation law using fuzzy proportional plus integral (PI) controller is developed to adjust EF for ECMS in real-time. This adaptation law is more robust than one with constant EF due to the variation of EF as well as driving cycle. Finally, simulations for two driving cycles using ECMS are conducted as opposed to the commonly used rule-based (RB) control strategy, indicating that the proposed adaptation law can provide a promising blend in terms of fuel economy and charge-sustainability. The results confirm that ECMS with Fuzzy PI adaptation law is more robust than ECMS with constant EF as well as PI adaptation law and it achieves significant improvements compared with RB in terms of fuel economy, which is enhanced by 4.44% and 14.7% for china city bus cycle and economic commission of Europe (ECE) cycle, respectively.

As an important component of land transportation systems, tracked vehicles (TRVs) and wheeled vehicles (WVs) have developed independently in parallel, particularly in the modeling of vehicle-ground interactions. However, their differences are not as significant as they appear. This paper introduces a simplified terramechanics-based track-ground interaction model for the motion control of TRVs on firm ground. The simplified interaction model addresses the problem that the terramechanicsbased models are too complex to be applied to optimizationbased real-time control algorithms. Interestingly, the proposed track-ground interaction model closely resembles to the tire model used for WVs. Through comparison, we present the unified mechanisms underlying vehicle-ground interactions. In our approach, TRVs can be treated as a special type of skid-steer WV, which benefits the theories and methods of wheel vehicles to be deployed in the TRV domain. Finally, we verify the proposed interaction model with extensive dynamic data from a real dual motor-driven TRV to demonstrate its effectiveness.

This paper presents an efficient and risk-aware search-optimization hierarchical trajectory planning method for automated vehicles in different road structures. The proposed approach incorporates a time-series motion risk field, capturing diverse road structures through a spatiotemporal map. Then, an adaptive motion primitive is developed, dynamically adjusting action time windows based on evolving risk and expected deviation during the search process. This enables efficient and accurate initial trajectory generation. Additionally, a bilevel corridor is introduced to extract the drivable area and re-represent the risk field, enabling trajectory smoothing to consider motion risk without resorting to non-convex optimization methods. Simulation results in structured and unstructured scenarios demonstrate that the proposed method improves efficiency, flexibility, and optimization quality compared to fixed-step search and single-level corridor-based optimization approaches. Real-world experiments on autonomous vehicles validated the dynamic characteristics and effectiveness of the proposed method in the actual environment.

An object-level attention prediction framework for drivers in the urban environment with rich semantic and motion information is proposed in this article. The proposed framework is based on the visual working memory mechanism, which decomposes the perception process into three phases, external stimuli, cognitive constructing, and memory search. In the external stimuli phase, semantic and motion information of surrounding objects is obtained. In the cognitive constructing phase, the neighbor-based hierarchical clustering method is applied to extract both independent and dependent features of traffic participants and driving events. In the memory search phase, the heterogeneous motif graph neural network is utilized to construct visual memory layers and integrate multilevel features for attention reasoning. Finally, the feature embedding is fed into a multilayer perceptron to predict the object-level visual attention. Training and testing data are collected from crowded and dynamic traffic scenes. Experimental results show that the proposed framework can achieve a superior object-level prediction performance in the information-rich environments compared with the state-of-the-art methods. In addition, the proposed framework can reduce the time bias of visual attention effectively.

Wall climbing represents a crucial task in a heavy unmanned ground vehicle (HUGV) working under poor road conditions. Inspired by the human perception-action behavior, this study proposes an effective human-like planning system for solving the wall-climbing problem in the HUGVs. In the proposed model, the Gaussian mixture model (GMM) and hidden semi-Markov model (HSMM) are combined to imitate the stochastic dynamic driving behavior. Based on the decision made by the GMM-HSMM-based driver model, the speed planner uses the dynamic motion primitive (DMP) to generate the expected speed curve. Furthermore, in the climbing-over process, the DMP is employed to predict the motor torque curve. This study considers a driver's perception of acceleration, which strengthens the planning system's adaptability and flexibility. The proposed method is verified by experiments with a real electric tracked HUGV. The experimental results show that the proposed system with duration constraints can maintain a reasonable acceleration rate, balancing driving safety and efficiency in the wall-climbing task. Moreover, the proposed method can adapt well to different road conditions without using a vehicle dynamics model.

Road network extraction from remote sensing images can provide precise map information for global positioning and planning. While existing transformer-based methods show promising performance in road network extraction, they suffer from misleading results of crossroad and low generalization ability. In our study, a prompt-based multi-modal Transformer for road network extraction (PT-RE) is proposed. In PT-RE, a swin transformer is used as the backbone network to extract image features from remote sensing images. Then, a fine-tuned prompt-based method is employed to generate the road topology classification contexts. The prompt-based information generation and cross-modal loss function are designed to deal with the fine-tuning task. Compared with the original uni-modal loss function in fine-tuning, the cross-modal method processes the different modals information and improves the generalization ability. Finally, the topology decoder utilizes cross-attention architecture to predict the relationship by the information from images and classification contexts. With the help of different views and modals information, the framework strengthens the accuracy of crossroad detection rather than the uni-modal type. The proposed topological road network extraction method demonstrates superior accuracy across 20 US City datasets and SpaceNet datasets, showcasing its accuracy and generalization ability.