Search

Car-following is the most common driving scenario where a following vehicle follows a lead vehicle in the same lane. One crucial factor of car-following behavior is driving style which affects speed and gap selection, acceleration pattern, and fuel consumption. However, existing car-following research used limited categories of driving style through pre-defined patterns and failed to encode driving style into data-driven car-following models. To address these limitations, we propose the Aggressiveness Informed Car-Following (AICF) modeling approach, which embeds driving style as a dynamic input feature in data-driven car-following models. In detail, We design driving aggressiveness tokens using four physical quantities (jerk, acceleration, relative speed, and relative spacing) to capture the heterogeneity of driving aggressiveness. These tokens were then embedded into a physics-informed Long Short-Term Memory (LSTM) based car-following model for trajectory prediction. To evaluate the effectiveness of our approach, we conducted extensive experiments based on 12,540 car-following events extracted from the HighD dataset and 24,093 events from the Lyft dataset. Compared to models devoid of considerations for driving aggressiveness levels, AICF exhibits superior efficacy in mitigating the Mean Square Error (MSE) of spacing and collision rate. To the best of our knowledge, this is the first work to directly incorporate real-time driving aggressiveness tokens as input features into data-driven car-following models, enabling a more comprehensive understanding of aggressiveness in car-following behavior.

To ensure safe driving in dynamic environments, autonomous vehicles should possess the capability to accurately predict the lane change intentions of surrounding vehicles in advance and forecast their future trajectories. Existing motion prediction approaches have ample room for improvement, particularly in terms of long-term prediction accuracy and interpretability. In this paper, we address these challenges by proposing LC-LLM, an explainable lane change prediction model that leverages the strong reasoning capabilities and self-explanation abilities of Large Language Models (LLMs). Essentially, we reformulate the lane change prediction task as a language modeling problem, processing heterogeneous driving scenario information in natural language as prompts for input into the LLM and employing a supervised fine-tuning technique to tailor the LLM specifically for our lane change prediction task. This allows us to utilize the LLM's powerful common sense reasoning abilities to understand complex interactive information, thereby improving the accuracy of long-term predictions. Furthermore, we incorporate explanatory requirements into the prompts in the inference stage. Therefore, our LC-LLM model not only can predict lane change intentions and trajectories but also provides explanations for its predictions, enhancing the interpretability. Extensive experiments on the large-scale highD dataset demonstrate the superior performance and interpretability of our LC-LLM in lane change prediction task. To the best of our knowledge, this is the first attempt to utilize LLMs for predicting lane change behavior. Our study shows that LLMs can encode comprehensive interaction information for driving behavior understanding.

Accurate trajectory prediction is crucial for the safe and efficient operation of autonomous vehicles. The growing popularity of deep learning has led to the development of numerous methods for trajectory prediction. While deter-ministic deep learning models have been widely used, deep generative models have gained popularity as they learn data distributions from training data and account for trajectory uncertainties. In this study, we propose EquiDiff, a deep generative model for predicting future vehicle trajectories. EquiDiff is based on the conditional diffusion model, which generates future trajectories by incorporating historical information and random Gaussian noise. The backbone model of EquiDiff is an SO(2)-equivariant transformer that fully utilizes the geometric properties of location coordinates. In addition, we employ Recurrent Neural Networks and Graph Attention Networks to extract social interactions from historical trajectories. To evaluate the performance of EquiDiff, we conduct extensive experiments on the NGSIM dataset. Our results demonstrate that EquiDiff outperforms other baseline models in shortterm prediction, but has slightly higher errors for long-term prediction. Furthermore, we conduct an ablation study to investigate the contribution of each component of EquiDiff to the prediction accuracy. Additionally, we present a visualization of the generation process of our diffusion model, providing insights into the uncertainty of the prediction. © 2023 IEEE.

Car-following is a control process in which a following vehicle (FV) adjusts its acceleration to keep a safe distance from the lead vehicle (LV). Recently, there has been a booming of data-driven models that enable more accurate modeling of car-following through real-world driving datasets. Although there are several public datasets available, their formats are not always consistent, making it challenging to determine the state-of-the-art models and how well a new model performs compared to existing ones. In contrast, research fields such as image recognition and object detection have benchmark datasets like ImageNet, Microsoft COCO, and KITTI. To address this gap and promote the development of microscopic traffic flow modeling, we establish a public benchmark dataset for car-following behavior modeling. The benchmark consists of more than 80K car-following events extracted from five public driving datasets using the same criteria. These events cover diverse situations including different road types, various weather conditions, and mixed traffic flows with autonomous vehicles. Moreover, to give an overview of current progress in car-following modeling, we implemented and tested representative baseline models with the benchmark. Results show that the deep deterministic policy gradient (DDPG) based model performs competitively with a lower MSE for spacing compared to traditional intelligent driver model (IDM) and Gazis-Herman-Rothery (GHR) models, and a smaller collision rate compared to fully connected neural network (NN) and long short-term memory (LSTM) models in most datasets. The established benchmark will provide researchers with consistent data formats and metrics for cross-comparing different car-following models, promoting the development of more accurate models. We open-source our dataset and implementation code in https://github.com/HKUST-DRIVE-AI-LAB/FollowNet.

Car-following is a control process in which a following vehicle adjusts its acceleration to keep a safe distance from the lead vehicle. Recently, there has been a booming of data-driven models that enable more accurate modeling of car-following through real-world driving datasets. Although there are several public datasets available, their formats are not always consistent, making it challenging to determine the state-of-the-art models and how well a new model performs compared to existing ones. To address this gap and promote the development of microscopic traffic flow modeling, we establish the first public benchmark dataset for car-following behavior modeling. This benchmark consists of more than 80 K car-following events extracted from five public driving datasets under the same criteria. To give an overview of current progress in car-following modeling, we implemented and tested representative baseline models within the benchmark. The established benchmark provides researchers with consistent data formats and metrics for cross-comparing different car-following models, coming with open datasets and codes. © 2023, The Author(s).

Prediction, decision-making, and motion planning are essential for autonomous driving. In most contemporary works, they are considered as individual modules or combined into a multi-task learning paradigm with a shared backbone but separate task heads. However, we argue that they should be integrated into a comprehensive framework. Although several recent approaches follow this scheme, they suffer from complicated input representations and redundant framework designs. More importantly, they can not make long-term predictions about future driving scenarios. To address these issues, we rethink the necessity of each module in an autonomous driving task and incorporate only the required modules into a minimalist autonomous driving framework. We propose BEVGPT, a generative pre-trained large model that integrates driving scenario prediction, decision-making, and motion planning. The model takes the bird's-eye-view (BEV) images as the only input source and makes driving decisions based on surrounding traffic scenarios. To ensure driving trajectory feasibility and smoothness, we develop an optimization-based motion planning method. We instantiate BEVGPT on Lyft Level 5 Dataset and use Woven Planet L5Kit for realistic driving simulation. The effectiveness and robustness of the proposed framework are verified by the fact that it outperforms previous methods in 100% decision-making metrics and 66% motion planning metrics. Furthermore, the ability of our framework to accurately generate BEV images over the long term is demonstrated through the task of driving scenario prediction. To the best of our knowledge, this is the first generative pre-trained large model for autonomous driving prediction, decision-making, and motion planning with only BEV images as input., Comment: AAAI2024

Car-following models have made significant contributions to our understanding of longitudinal driving behavior. However, they often exhibit limited accuracy and flexibility, as they cannot fully capture the complexity inherent in car-following processes, or may falter in unseen scenarios due to their reliance on confined driving skills present in training data. It is worth noting that each car-following model possesses its own strengths and weaknesses depending on specific driving scenarios. Therefore, we propose EnsembleFollower, a hierarchical planning framework for achieving advanced human-like car-following. The EnsembleFollower framework involves a high-level Reinforcement Learning-based agent responsible for judiciously managing multiple low-level car-following models according to the current state, either by selecting an appropriate low-level model to perform an action or by allocating different weights across all low-level components. Moreover, we propose a jerk-constrained kinematic model for more convincing car-following simulations. We evaluate the proposed method based on real-world driving data from the HighD dataset. The experimental results illustrate that EnsembleFollower yields improved accuracy of human-like behavior and achieves effectiveness in combining hybrid models, demonstrating that our proposed framework can handle diverse car-following conditions by leveraging the strengths of various low-level models., Comment: 12 pages, 10 figures

Accurate trajectory prediction is crucial for the safe and efficient operation of autonomous vehicles. The growing popularity of deep learning has led to the development of numerous methods for trajectory prediction. While deterministic deep learning models have been widely used, deep generative models have gained popularity as they learn data distributions from training data and account for trajectory uncertainties. In this study, we propose EquiDiff, a deep generative model for predicting future vehicle trajectories. EquiDiff is based on the conditional diffusion model, which generates future trajectories by incorporating historical information and random Gaussian noise. The backbone model of EquiDiff is an SO(2)-equivariant transformer that fully utilizes the geometric properties of location coordinates. In addition, we employ Recurrent Neural Networks and Graph Attention Networks to extract social interactions from historical trajectories. To evaluate the performance of EquiDiff, we conduct extensive experiments on the NGSIM dataset. Our results demonstrate that EquiDiff outperforms other baseline models in short-term prediction, but has slightly higher errors for long-term prediction. Furthermore, we conduct an ablation study to investigate the contribution of each component of EquiDiff to the prediction accuracy. Additionally, we present a visualization of the generation process of our diffusion model, providing insights into the uncertainty of the prediction.

With the increasing number of people studying online, self-aid learning platforms which help customers（users）study by themselves are more and more prevalent in China. Self-aid online learning is a relatively innovative field which has not been widely and thoroughly researched. This paper used Shanbay which is one of the largest self-aid English learning platforms in China as an example to investigate what and how factors influence customer satisfaction leading to their (re)purchase intention. Based on the previous models and empirical studies of some related fields, this paper outlined a new framework and generated eight propositions to explore these two research questions. Both free users and premium users of Shanbay were interviewed to gather the research material, and the data got from the interview were analyzed to develop the propositions. This paper found that positive service experience can facilitate customer satisfaction from their perceived utilitarian value and hedonic value. Among the proposed five factors influencing the two values, perceived usefulness was considered as the most important factor while perceived playfulness was the least one. What’ more, the relationship between customer satisfaction and (re)purchase intention was suggested to be positive in this paper.

With the increasing number of people studying online, self-aid learning platforms which help customers（users）study by themselves are more and more prevalent in China. Self-aid online learning is a relatively innovative field which has not been widely and thoroughly researched. This paper used Shanbay which is one of the largest self-aid English learning platforms in China as an example to investigate what and how factors influence customer satisfaction leading to their (re)purchase intention. Based on the previous models and empirical studies of some related fields, this paper outlined a new framework and generated eight propositions to explore these two research questions. Both free users and premium users of Shanbay were interviewed to gather the research material, and the data got from the interview were analyzed to develop the propositions. This paper found that positive service experience can facilitate customer satisfaction from their perceived utilitarian value and hedonic value. Among the proposed five factors influencing the two values, perceived usefulness was considered as the most important factor while perceived playfulness was the least one. What’ more, the relationship between customer satisfaction and (re)purchase intention was suggested to be positive in this paper.