Autonomous vehicle decision and control through reinforcement learning with traffic flow randomization

Most of the current studies on autonomous vehicle decision-making and control tasks based on reinforcement learning are conducted in simulated environments. The training and testing of these studies are carried out under rule-based microscopic traffic flow, with little consideration of migrating them to real or near-real environments to test their performance. It may lead to a degradation in performance when the trained model is tested in more realistic traffic scenes. In this study, we propose a method to randomize the driving style and behavior of surrounding vehicles by randomizing certain parameters of the car-following model and the lane-changing model of rule-based microscopic traffic flow in SUMO. We trained policies with deep reinforcement learning algorithms under the domain randomized rule-based microscopic traffic flow in freeway and merging scenes, and then tested them separately in rule-based microscopic traffic flow and high-fidelity microscopic traffic flow. Results indicate that the policy trained under domain randomization traffic flow has significantly better success rate and calculative reward compared to the models trained under other microscopic traffic flows.

Safe Hybrid-Action Reinforcement Learning-Based Decision and Control for Discretionary Lane Change

Autonomous lane-change, a key feature of advanced driver-assistance systems, can enhance traffic efficiency and reduce the incidence of accidents. However, safe driving of autonomous vehicles remains challenging in complex environments. How to perform safe and appropriate lane change is a popular topic of research in the field of autonomous driving. Currently, few papers consider the safety of reinforcement learning in autonomous lane-change scenarios. We introduce safe hybrid-action reinforcement learning into discretionary lane change for the first time and propose Parameterized Soft Actor-Critic with PID Lagrangian (PASAC-PIDLag) algorithm. Furthermore, we conduct a comparative analysis of the Parameterized Soft Actor-Critic (PASAC), which is an unsafe version of PASAC-PIDLag. Both algorithms are employed to train the lane-change strategy of autonomous vehicles to output discrete lane-change decision and longitudinal vehicle acceleration. Our simulation results indicate that at a traffic density of 15 vehicles per kilometer (15 veh/km), the PASAC-PIDLag algorithm exhibits superior safety with a collision rate of 0%, outperforming the PASAC algorithm, which has a collision rate of 1%. The outcomes of the generalization assessments reveal that at low traffic density levels, both the PASAC-PIDLag and PASAC algorithms are proficient in attaining a 0% collision rate. Under conditions of high traffic flow density, the PASAC-PIDLag algorithm surpasses PASAC in terms of both safety and optimality.

Discretionary Lane-Change Decision and Control via Parameterized Soft Actor-Critic for Hybrid Action Space

This study focuses on a crucial task in the field of autonomous driving, autonomous lane change. Autonomous lane change plays a pivotal role in improving traffic flow, alleviating driver burden, and reducing the risk of traffic accidents. However, due to the complexity and uncertainty of lane-change scenarios, the functionality of autonomous lane change still faces challenges. In this research, we conduct autonomous lane-change simulations using both Deep Reinforcement Learning (DRL) and Model Predictive Control (MPC). Specifically, we propose the Parameterized Soft Actor-Critic (PASAC) algorithm to train a DRL-based lane-change strategy to output both discrete lane-change decision and continuous longitudinal vehicle acceleration. We also use MPC for lane selection based on predictive car-following costs for different lanes. For the first time, we compare the performance of DRL and MPC in the context of lane-change decision. Simulation results indicate that, under the same reward/cost functions and traffic flow, both MPC and PASAC achieve a collision rate of 0\%. PASAC demonstrates comparable performance to MPC in terms of episodic rewards/costs and average vehicle speeds.

Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards

The selection of a reward function in Reinforcement Learning (RL) has garnered significant attention because of its impact on system performance. Issues of steady-state error often manifest when quadratic reward functions are employed. Although existing solutions using absolute-value-type reward functions partially address this problem, they tend to induce substantial fluctuations in specific system states, leading to abrupt changes. In response to this challenge, this study proposes an approach that introduces an integral term. By integrating this term into quadratic-type reward functions, the RL algorithm is adeptly tuned, augmenting the system's consideration of long-term rewards and, consequently, alleviating concerns related to steady-state errors. Through experiments and performance evaluations on the Adaptive Cruise Control (ACC) model and lane change models, we validate that the proposed method not only effectively diminishes steady-state errors but also results in smoother variations in system states.

AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering

We propose a novel and challenging benchmark, AutoEval-Video, to comprehensively evaluate large vision-language models in open-ended video question answering. The comprehensiveness of AutoEval-Video is demonstrated in two aspects: 1) AutoEval-Video constructs open-ended video-questions across 9 skill dimensions, addressing capabilities of perception, comprehension, and generation. 2) AutoEval-Video contains newly collected videos that cover over 40 distinct themes. To efficiently evaluate responses to the open-ended questions, we employ an LLM-based evaluation approach, but instead of merely providing a reference answer, we annotate unique evaluation rules for every single instance (video-question pair). To maximize the robustness of these rules, we develop a novel adversarial annotation mechanism. By using instance-specific rules as prompt, GPT-4, as an automatic evaluator, can achieve a stable evaluation accuracy of around 97.0\%, comparable to the 94.9\% - 97.5\% accuracy of a human evaluator. Furthermore, we assess the performance of eight large vision-language models on AutoEval-Video. Among them, GPT-4V(ision) significantly outperforms other models, achieving an accuracy of 32.2\%. However, there is still substantial room for improvement compared to human accuracy of 72.8\%. By conducting an extensive case study, we uncover several drawbacks of GPT-4V, such as limited temporal and dynamic comprehension, and overly general responses. Code is available at \href{https://github.com/Xiuyuan-Chen/AutoEval-Video}{\color{magenta}https://github.com/Xiuyuan-Chen/AutoEval-Video}.

Bi-Preference Learning Heterogeneous Hypergraph Networks for Session-based Recommendation

Session-based recommendation intends to predict next purchased items based on anonymous behavior sequences. Numerous economic studies have revealed that item price is a key factor influencing user purchase decisions. Unfortunately, existing methods for session-based recommendation only aim at capturing user interest preference, while ignoring user price preference. Actually, there are primarily two challenges preventing us from accessing price preference. Firstly, the price preference is highly associated to various item features (i.e., category and brand), which asks us to mine price preference from heterogeneous information. Secondly, price preference and interest preference are interdependent and collectively determine user choice, necessitating that we jointly consider both price and interest preference for intent modeling. To handle above challenges, we propose a novel approach Bi-Preference Learning Heterogeneous Hypergraph Networks (BiPNet) for session-based recommendation. Specifically, the customized heterogeneous hypergraph networks with a triple-level convolution are devised to capture user price and interest preference from heterogeneous features of items. Besides, we develop a Bi-Preference Learning schema to explore mutual relations between price and interest preference and collectively learn these two preferences under the multi-task learning architecture. Extensive experiments on multiple public datasets confirm the superiority of BiPNet over competitive baselines. Additional research also supports the notion that the price is crucial for the task.

Mixed-Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Vehicle Energy Management

Many optimal control problems require the simultaneous output of continuous and discrete control variables. Such problems are usually formulated as mixed-integer optimal control (MIOC) problems, which are challenging to solve due to the complexity of the solution space. Numerical methods such as branch-and-bound are computationally expensive and unsuitable for real-time control. This paper proposes a novel continuous-discrete reinforcement learning (CDRL) algorithm, twin delayed deep deterministic actor-Q (TD3AQ), for MIOC problems. TD3AQ combines the advantages of both actor-critic and Q-learning methods, and can handle the continuous and discrete action spaces simultaneously. The proposed algorithm is evaluated on a hybrid electric vehicle (HEV) energy management problem, where real-time control of the continuous variable engine torque and discrete variable gear ratio is essential to maximize fuel economy while satisfying driving constraints. Simulation results on different drive cycles show that TD3AQ can achieve near-optimal solutions compared to dynamic programming (DP) and outperforms the state-of-the-art discrete RL algorithm Rainbow, which is adopted for MIOC by discretizing continuous actions into a finite set of discrete values.

Half of an image is enough for quality assessment

Deep networks have demonstrated promising results in the field of Image Quality Assessment (IQA). However, there has been limited research on understanding how deep models in IQA work. This study introduces a novel positional masked transformer for IQA and provides insights into the contribution of different regions of an image towards its overall quality. Results indicate that half of an image may play a trivial role in determining image quality, while the other half is critical. This observation is extended to several other CNN-based IQA models, revealing that half of the image regions can significantly impact the overall image quality. To further enhance our understanding, three semantic measures (saliency, frequency, and objectness) were derived and found to have high correlation with the importance of image regions in IQA.

A Masked Bounding-Box Selection Based ResNet Predictor for Text Rotation Prediction

The existing Optical Character Recognition (OCR) systems are capable of recognizing images with horizontal texts. However, when the rotation of the texts increases, it becomes harder to recognizing these texts. The performance of the OCR systems decreases. Thus predicting the rotations of the texts and correcting the images are important. Previous work mainly uses traditional Computer Vision methods like Hough Transform and Deep Learning methods like Convolutional Neural Network. However, all of these methods are prone to background noises commonly existing in general images with texts. To tackle this problem, in this work, we introduce a new masked bounding-box selection method, that incorporating the bounding box information into the system. By training a ResNet predictor to focus on the bounding box as the region of interest (ROI), the predictor learns to overlook the background noises. Evaluations on the text rotation prediction tasks show that our method improves the performance by a large margin.