Chen Lv

Yanchao Xu, Wenbo Shao, Jun Li et al.

Intersection is one of the most challenging scenarios for autonomous driving tasks. Due to the complexity and stochasticity, essential applications (e.g., behavior modeling, motion prediction, safety validation, etc.) at intersections rely heavily on data-driven techniques. Thus, there is an intense demand for trajectory datasets of traffic participants (TPs) in intersections. Currently, most intersections in urban areas are equipped with traffic lights. However, there is not yet a large-scale, high-quality, publicly available trajectory dataset for signalized intersections. Therefore, in this paper, a typical two-phase signalized intersection is selected in Tianjin, China. Besides, a pipeline is designed to construct a Signalized INtersection Dataset (SIND), which contains 7 hours of recording including over 13,000 TPs with 7 types. Then, the behaviors of traffic light violations in SIND are recorded. Furthermore, the SIND is also compared with other similar works. The features of the SIND can be summarized as follows: 1) SIND provides more comprehensive information, including traffic light states, motion parameters, High Definition (HD) map, etc. 2) The category of TPs is diverse and characteristic, where the proportion of vulnerable road users (VRUs) is up to 62.6% 3) Multiple traffic light violations of non-motor vehicles are shown. We believe that SIND would be an effective supplement to existing datasets and can promote related research on autonomous driving.The dataset is available online via: https://github.com/SOTIF-AVLab/SinD

Long Chen, Yuchen Li, Chao Huang et al.

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks, lack of systematic summary and research directions in the future. Here we propose a Survey of Surveys (SoS) for total technologies of AD and IVs that reviews the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. To our knowledge, this article is the first SoS with milestones in AD and IVs, which constitutes our complete research work together with two other technical surveys. We anticipate that this article will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future.

Wenhui Huang, Yanxin Zhou, Xiangkun He et al.

Despite some successful applications of goal-driven navigation, existing deep reinforcement learning (DRL)-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled from the perception module and directly introduced as a condition of decision-making, resulting in the goal-irrelevant features of the scene representation playing an adversary role during the learning process. In light of this, we present a novel Goal-guided Transformer-enabled reinforcement learning (GTRL) approach by considering the physical goal states as an input of the scene encoder for guiding the scene representation to couple with the goal information and realizing efficient autonomous navigation. More specifically, we propose a novel variant of the Vision Transformer as the backbone of the perception system, namely Goal-guided Transformer (GoT), and pre-train it with expert priors to boost the data efficiency. Subsequently, a reinforcement learning algorithm is instantiated for the decision-making system, taking the goal-oriented scene representation from the GoT as the input and generating decision commands. As a result, our approach motivates the scene representation to concentrate mainly on goal-relevant features, which substantially enhances the data efficiency of the DRL learning process, leading to superior navigation performance. Both simulation and real-world experimental results manifest the superiority of our approach in terms of data efficiency, performance, robustness, and sim-to-real generalization, compared with other state-of-the-art (SOTA) baselines. The demonstration video (https://www.youtube.com/watch?v=aqJCHcsj4w0) and the source code (https://github.com/OscarHuangWind/DRL-Transformer-SimtoReal-Navigation) are also provided.

Wenbo Shao, Yanchao Xu, Jun Li et al.

An accurate trajectory prediction is crucial for safe and efficient autonomous driving in complex traffic environments. In recent years, artificial intelligence has shown strong capabilities in improving prediction accuracy. However, its characteristics of inexplicability and uncertainty make it challenging to determine the traffic environmental effect on prediction explicitly, posing significant challenges to safety-critical decision-making. To address these challenges, this study proposes a trajectory prediction framework with the epistemic uncertainty estimation ability that outputs high uncertainty when confronting unforeseeable or unknown scenarios. The proposed framework is used to analyze the environmental effect on the prediction algorithm performance. In the analysis, the traffic environment is considered in terms of scenario features and shifts, respectively, where features are divided into kinematic features of a target agent, features of its surrounding traffic participants, and other features. In addition, feature correlation and importance analyses are performed to study the above features' influence on the prediction error and epistemic uncertainty. Further, a cross-dataset case study is conducted using multiple intersection datasets to investigate the impact of unavoidable distributional shifts in the real world on trajectory prediction. The results indicate that the deep ensemble-based method has advantages in improving prediction robustness and estimating epistemic uncertainty. The consistent conclusions are obtained by the feature correlation and importance analyses, including the conclusion that kinematic features of the target agent have relatively strong effects on the prediction error and epistemic uncertainty. Furthermore, the prediction failure caused by distributional shifts and the potential of the deep ensemble-based method are analyzed.

Jingda Wu, Wenhui Huang, Niels de Boer et al.

Decision-making is critical for lane change in autonomous driving. Reinforcement learning (RL) algorithms aim to identify the values of behaviors in various situations and thus they become a promising pathway to address the decision-making problem. However, poor runtime safety hinders RL-based decision-making strategies from complex driving tasks in practice. To address this problem, human demonstrations are incorporated into the RL-based decision-making strategy in this paper. Decisions made by human subjects in a driving simulator are treated as safe demonstrations, which are stored into the replay buffer and then utilized to enhance the training process of RL. A complex lane change task in an off-ramp scenario is established to examine the performance of the developed strategy. Simulation results suggest that human demonstrations can effectively improve the safety of decisions of RL. And the proposed strategy surpasses other existing learning-based decision-making strategies with respect to multiple driving performances.

Haochen Liu, Zhiyu Huang, Xiaoyu Mo et al.

Decision-making for urban autonomous driving is challenging due to the stochastic nature of interactive traffic participants and the complexity of road structures. Although reinforcement learning (RL)-based decision-making scheme is promising to handle urban driving scenarios, it suffers from low sample efficiency and poor adaptability. In this paper, we propose Scene-Rep Transformer to improve the RL decision-making capabilities with better scene representation encoding and sequential predictive latent distillation. Specifically, a multi-stage Transformer (MST) encoder is constructed to model not only the interaction awareness between the ego vehicle and its neighbors but also intention awareness between the agents and their candidate routes. A sequential latent Transformer (SLT) with self-supervised learning objectives is employed to distill the future predictive information into the latent scene representation, in order to reduce the exploration space and speed up training. The final decision-making module based on soft actor-critic (SAC) takes as input the refined latent scene representation from the Scene-Rep Transformer and outputs driving actions. The framework is validated in five challenging simulated urban scenarios with dense traffic, and its performance is manifested quantitatively by the substantial improvements in data efficiency and performance in terms of success rate, safety, and efficiency. The qualitative results reveal that our framework is able to extract the intentions of neighbor agents to help make decisions and deliver more diversified driving behaviors.

Shiyu Fang, Jiaqi Liu, Mingyu Ding et al.

At present, Connected Autonomous Vehicles (CAVs) have begun to open road testing around the world, but their safety and efficiency performance in complex scenarios is still not satisfactory. Cooperative driving leverages the connectivity ability of CAVs to achieve synergies greater than the sum of their parts, making it a promising approach to improving CAV performance in complex scenarios. However, the lack of interaction and continuous learning ability limits current cooperative driving to single-scenario applications and specific Cooperative Driving Automation (CDA). To address these challenges, this paper proposes CoDrivingLLM, an interactive and learnable LLM-driven cooperative driving framework, to achieve all-scenario and all-CDA. First, since Large Language Models(LLMs) are not adept at handling mathematical calculations, an environment module is introduced to update vehicle positions based on semantic decisions, thus avoiding potential errors from direct LLM control of vehicle positions. Second, based on the four levels of CDA defined by the SAE J3216 standard, we propose a Chain-of-Thought (COT) based reasoning module that includes state perception, intent sharing, negotiation, and decision-making, enhancing the stability of LLMs in multi-step reasoning tasks. Centralized conflict resolution is then managed through a conflict coordinator in the reasoning process. Finally, by introducing a memory module and employing retrieval-augmented generation, CAVs are endowed with the ability to learn from their past experiences. We validate the proposed CoDrivingLLM through ablation experiments on the negotiation module, reasoning with different shots experience, and comparison with other cooperative driving methods.

Songyan Zhang, Wenhui Huang, Zhan Chen et al.

Recently, two-stage fine-tuning strategies, e.g., acquiring essential driving knowledge through supervised fine-tuning (SFT) and further enhancing decision-making and planning via reinforcement fine-tuning (RFT), have shown strong potential in advancing the knowledge-driven autonomous driving (AD) paradigm. However, the learning nature of SFT still limits the generalization of reasoning, thereby constraining the full potential of driving performance. Meanwhile, current RFT approaches are primarily applied to downstream tasks, since scene understanding is an open-ended problem where corresponding rewards are difficult to quantify. To address these limitations, we propose OpenREAD, an OPEN-ended REasoning reinforced vision-language model (VLM)-based autonomous driving (AD) framework that enables end-to-end RFT across the full spectrum from high-level reasoning to low-level trajectory planning. Specifically, we begin by constructing large-scale Chain-of-Thought (CoT) annotations on open-source driving-related knowledge datasets, and employ the powerful Qwen3 large language model (LLM) as the critic in RFT to quantify reasoning quality for open-ended questions during reward modeling. Extensive experiments confirm that joint end-to-end RFT yields substantial improvements in both upstream and downstream tasks, enabling OpenREAD to achieve state-of-the-art performance on reasoning and planning benchmarks.

Yining Ma, Wei Jiang, Lingtong Zhang et al.

Interaction between the background vehicles (BVs) and automated vehicles (AVs) in scenario-based testing plays a critical role in evaluating the intelligence of the AVs. Current testing scenarios typically employ predefined or scripted BVs, which inadequately reflect the complexity of human-like social behaviors in real-world driving scenarios, and also lack a systematic metric for evaluating the comprehensive intelligence of AVs. Therefore, this paper proposes an evolving scenario generation method that utilizes deep reinforcement learning (DRL) to create human-like BVs for testing and intelligence evaluation of AVs. Firstly, a class of driver models with human-like competitive, cooperative, and mutual driving motivations is designed. Then, utilizing an improved "level-k" training procedure, the three distinct driver models acquire game-based interactive driving policies. And these models are assigned to BVs for generating evolving scenarios in which all BVs can interact continuously and evolve diverse contents. Next, a framework including safety, driving efficiency, and interaction utility are presented to evaluate and quantify the intelligence performance of 3 systems under test (SUTs), indicating the effectiveness of the evolving scenario for intelligence testing. Finally, the complexity and fidelity of the proposed evolving testing scenario are validated. The results demonstrate that the proposed evolving scenario exhibits the highest level of complexity compared to other baseline scenarios and has more than 85% similarity to naturalistic driving data. This highlights the potential of the proposed method to facilitate the development and evaluation of high-level AVs in a realistic and challenging environment.

Haochen Liu, Zhiyu Huang, Chen Lv

Forecasting the future states of surrounding traffic participants is a crucial capability for autonomous vehicles. The recently proposed occupancy flow field prediction introduces a scalable and effective representation to jointly predict surrounding agents' future motions in a scene. However, the challenging part is to model the underlying social interactions among traffic agents and the relations between occupancy and flow. Therefore, this paper proposes a novel Multi-modal Hierarchical Transformer network that fuses the vectorized (agent motion) and visual (scene flow, map, and occupancy) modalities and jointly predicts the flow and occupancy of the scene. Specifically, visual and vector features from sensory data are encoded through a multi-stage Transformer module and then a late-fusion Transformer module with temporal pixel-wise attention. Importantly, a flow-guided multi-head self-attention (FG-MSA) module is designed to better aggregate the information on occupancy and flow and model the mathematical relations between them. The proposed method is comprehensively validated on the Waymo Open Motion Dataset and compared against several state-of-the-art models. The results reveal that our model with much more compact architecture and data inputs than other methods can achieve comparable performance. We also demonstrate the effectiveness of incorporating vectorized agent motion features and the proposed FG-MSA module. Compared to the ablated model without the FG-MSA module, which won 2nd place in the 2022 Waymo Occupancy and Flow Prediction Challenge, the current model shows better separability for flow and occupancy and further performance improvements.

Wenhui Huang, Cong Zhang, Jingda Wu et al.

Massive practical works addressed by Deep Q-network (DQN) algorithm have indicated that stochastic policy, despite its simplicity, is the most frequently used exploration approach. However, most existing stochastic exploration approaches either explore new actions heuristically regardless of Q-values or inevitably introduce bias into the learning process to couple the sampling with Q-values. In this paper, we propose a novel preference-guided $ε$-greedy exploration algorithm that can efficiently learn the action distribution in line with the landscape of Q-values for DQN without introducing additional bias. Specifically, we design a dual architecture consisting of two branches, one of which is a copy of DQN, namely the Q-branch. The other branch, which we call the preference branch, learns the action preference that the DQN implicit follows. We theoretically prove that the policy improvement theorem holds for the preference-guided $ε$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values. Consequently, preference-guided $ε$-greedy exploration motivates the DQN agent to take diverse actions, i.e., actions with larger Q-values can be sampled more frequently whereas actions with smaller Q-values still have a chance to be explored, thus encouraging the exploration. We assess the proposed method with four well-known DQN variants in nine different environments. Extensive results confirm the superiority of our proposed method in terms of performance and convergence speed. Index Terms- Preference-guided exploration, stochastic policy, data efficiency, deep reinforcement learning, deep Q-learning.

Qingfan Wang, Dongyang Xu, Gaoyuan Kuang et al.

Trajectory prediction is significant for intelligent vehicles to achieve high-level autonomous driving, and a lot of relevant research achievements have been made recently. Despite the rapid development, most existing studies solely focused on normal safe scenarios while largely neglecting safety-critical scenarios, particularly those involving imminent collisions. This oversight may result in autonomous vehicles lacking the essential predictive ability in such situations, posing a significant threat to safety. To tackle these, this paper proposes a risk-aware trajectory prediction framework tailored to safety-critical scenarios. Leveraging distinctive hazardous features, we develop three core risk-aware components. First, we introduce a risk-incorporated scene encoder, which augments conventional encoders with quantitative risk information to achieve risk-aware encoding of hazardous scene contexts. Next, we incorporate endpoint-risk-combined intention queries as prediction priors in the decoder to ensure that the predicted multimodal trajectories cover both various spatial intentions and risk levels. Lastly, an auxiliary risk prediction task is implemented for the ultimate risk-aware prediction. Furthermore, to support model training and performance evaluation, we introduce a safety-critical trajectory prediction dataset and tailored evaluation metrics. We conduct comprehensive evaluations and compare our model with several SOTA models. Results demonstrate the superior performance of our model, with a significant improvement in most metrics. This prediction advancement enables autonomous vehicles to execute correct collision avoidance maneuvers under safety-critical scenarios, eventually enhancing road traffic safety.

Jie Bai, Jianwu Fang, Yisheng Lv et al.

Pedestrian Crossing Prediction (PCP) in driving scenes plays a critical role in ensuring the safe operation of intelligent vehicles. Due to the limited observations of pedestrian crossing behaviors in typical situations, recent studies have begun to leverage synthetic data with flexible variation to boost prediction performance, employing domain adaptation frameworks. However, different domain knowledge has distinct cross-domain distribution gaps, which necessitates suitable domain knowledge adaption ways for PCP tasks. In this work, we propose a Gated Syn-to-Real Knowledge transfer approach for PCP (Gated-S2R-PCP), which has two aims: 1) designing the suitable domain adaptation ways for different kinds of crossing-domain knowledge, and 2) transferring suitable knowledge for specific situations with gated knowledge fusion. Specifically, we design a framework that contains three domain adaption methods including style transfer, distribution approximation, and knowledge distillation for various information, such as visual, semantic, depth, location, etc. A Learnable Gated Unit (LGU) is employed to fuse suitable cross-domain knowledge to boost pedestrian crossing prediction. We construct a new synthetic benchmark S2R-PCP-3181 with 3181 sequences (489,740 frames) which contains the pedestrian locations, RGB frames, semantic images, and depth images. With the synthetic S2R-PCP-3181, we transfer the knowledge to two real challenging datasets of PIE and JAAD, and superior PCP performance is obtained to the state-of-the-art methods.

Lei Yang, Xinyu Zhang, Jun Li et al.

Modern autonomous vehicle perception systems often struggle with occlusions and limited perception range. Previous studies have demonstrated the effectiveness of cooperative perception in extending the perception range and overcoming occlusions, thereby enhancing the safety of autonomous driving. In recent years, a series of cooperative perception datasets have emerged; however, these datasets primarily focus on cameras and LiDAR, neglecting 4D Radar, a sensor used in single-vehicle autonomous driving to provide robust perception in adverse weather conditions. In this paper, to bridge the gap created by the absence of 4D Radar datasets in cooperative perception, we present V2X-Radar, the first large-scale, real-world multi-modal dataset featuring 4D Radar. V2X-Radar dataset is collected using a connected vehicle platform and an intelligent roadside unit equipped with 4D Radar, LiDAR, and multi-view cameras. The collected data encompasses sunny and rainy weather conditions, spanning daytime, dusk, and nighttime, as well as various typical challenging scenarios. The dataset consists of 20K LiDAR frames, 40K camera images, and 20K 4D Radar data, including 350K annotated boxes across five categories. To support various research domains, we have established V2X-Radar-C for cooperative perception, V2X-Radar-I for roadside perception, and V2X-Radar-V for single-vehicle perception. Furthermore, we provide comprehensive benchmarks across these three sub-datasets. We will release all datasets and benchmark codebase at https://huggingface.co/datasets/yanglei18/V2X-Radar and https://github.com/yanglei18/V2X-Radar.

Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang et al.

Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.

Zhonghua Jiang, Kui Chen, Kunxi Li et al.

Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension, resulting in a larger key-value (KV) cache compared to static image embedding. A naive optimization strategy is to selectively focus on and retain KV caches of audio or video based on task. However, in the experiment, we observed that the attention of AV-LLMs to various modalities in the high layers is not strictly dependent on the task. In higher layers, the attention of AV-LLMs shifts more towards the video modality. In addition, we also found that directly integrating temporal KV of audio and spatial-temporal KV of video may lead to information confusion and significant performance degradation of AV-LLMs. If audio and video are processed indiscriminately, it may also lead to excessive compression or reservation of a certain modality, thereby disrupting the alignment between modalities. To address these challenges, we propose AccKV, an Adaptive-Focusing and Cross-Calibration KV cache optimization framework designed specifically for efficient AV-LLMs inference. Our method is based on layer adaptive focusing technology, selectively focusing on key modalities according to the characteristics of different layers, and enhances the recognition of heavy hitter tokens through attention redistribution. In addition, we propose a Cross-Calibration technique that first integrates inefficient KV caches within the audio and video modalities, and then aligns low-priority modalities with high-priority modalities to selectively evict KV cache of low-priority modalities. The experimental results show that AccKV can significantly improve the computational efficiency of AV-LLMs while maintaining accuracy.

Jianwu Fang, Lei-lei Li, Junfei Zhou et al.

We present MM-AU, a novel dataset for Multi-Modal Accident video Understanding. MM-AU contains 11,727 in-the-wild ego-view accident videos, each with temporally aligned text descriptions. We annotate over 2.23 million object boxes and 58,650 pairs of video-based accident reasons, covering 58 accident categories. MM-AU supports various accident understanding tasks, particularly multimodal video diffusion to understand accident cause-effect chains for safe driving. With MM-AU, we present an Abductive accident Video understanding framework for Safe Driving perception (AdVersa-SD). AdVersa-SD performs video diffusion via an Object-Centric Video Diffusion (OAVD) method which is driven by an abductive CLIP model. This model involves a contrastive interaction loss to learn the pair co-occurrence of normal, near-accident, accident frames with the corresponding text descriptions, such as accident reasons, prevention advice, and accident categories. OAVD enforces the causal region learning while fixing the content of the original frame background in video generation, to find the dominant cause-effect chain for certain accidents. Extensive experiments verify the abductive ability of AdVersa-SD and the superiority of OAVD against the state-of-the-art diffusion models. Additionally, we provide careful benchmark evaluations for object detection and accident reason answering since AdVersa-SD relies on precise object and accident reason information.

Songyan Zhang, Wenhui Huang, Zihui Gao et al.

The emergence of general human knowledge and impressive logical reasoning capacity in rapidly progressed vision-language models (VLMs) have driven increasing interest in applying VLMs to high-level autonomous driving tasks, such as scene understanding and decision-making. However, an in-depth study on the relationship between knowledge proficiency, especially essential driving expertise, and closed-loop autonomous driving performance requires further exploration. In this paper, we investigate the effects of the depth and breadth of fundamental driving knowledge on closed-loop trajectory planning and introduce WiseAD, a specialized VLM tailored for end-to-end autonomous driving capable of driving reasoning, action justification, object recognition, risk analysis, driving suggestions, and trajectory planning across diverse scenarios. We employ joint training on driving knowledge and planning datasets, enabling the model to perform knowledge-aligned trajectory planning accordingly. Extensive experiments indicate that as the diversity of driving knowledge extends, critical accidents are notably reduced, contributing 11.9% and 12.4% improvements in the driving score and route completion on the Carla closed-loop evaluations, achieving state-of-the-art performance. Moreover, WiseAD also demonstrates remarkable performance in knowledge evaluations on both in-domain and out-of-domain datasets.

Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang et al.

In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL). However, state-of-the-art (SOTA) RL techniques with Temporal-Difference (TD) learning frameworks often suffer from learning inefficiency, due to the significant expansion of the augmented state space with the delay. To improve learning efficiency without sacrificing performance, this work introduces a novel framework called Variational Delayed Policy Optimization (VDPO), which reformulates delayed RL as a variational inference problem. This problem is further modelled as a two-step iterative optimization problem, where the first step is TD learning in the delay-free environment with a small state space, and the second step is behaviour cloning which can be addressed much more efficiently than TD learning. We not only provide a theoretical analysis of VDPO in terms of sample complexity and performance, but also empirically demonstrate that VDPO can achieve consistent performance with SOTA methods, with a significant enhancement of sample efficiency (approximately 50\% less amount of samples) in the MuJoCo benchmark.

Dian Zheng, Cheng Zhang, Xiao-Ming Wu et al.

Generating 360-degree panoramas from narrow field of view (NFoV) image is a promising computer vision task for Virtual Reality (VR) applications. Existing methods mostly assess the generated panoramas with InceptionNet or CLIP based metrics, which tend to perceive the image quality and is \textbf{not suitable for evaluating the distortion}. In this work, we first propose a distortion-specific CLIP, named Distort-CLIP to accurately evaluate the panorama distortion and discover the \textbf{``visual cheating''} phenomenon in previous works (\ie, tending to improve the visual results by sacrificing distortion accuracy). This phenomenon arises because prior methods employ a single network to learn the distinct panorama distortion and content completion at once, which leads the model to prioritize optimizing the latter. To address the phenomenon, we propose \textbf{PanoDecouple}, a decoupled diffusion model framework, which decouples the panorama generation into distortion guidance and content completion, aiming to generate panoramas with both accurate distortion and visual appeal. Specifically, we design a DistortNet for distortion guidance by imposing panorama-specific distortion prior and a modified condition registration mechanism; and a ContentNet for content completion by imposing perspective image information. Additionally, a distortion correction loss function with Distort-CLIP is introduced to constrain the distortion explicitly. The extensive experiments validate that PanoDecouple surpasses existing methods both in distortion and visual metrics.

Chaoyue Niu, Yucheng Ding, Junhui Lu et al.

The conventional cloud-based large model learning framework is increasingly constrained by latency, cost, personalization, and privacy concerns. In this survey, we explore an emerging paradigm: collaborative learning between on-device small model and cloud-based large model, which promises low-latency, cost-efficient, and personalized intelligent services while preserving user privacy. We provide a comprehensive review across hardware, system, algorithm, and application layers. At each layer, we summarize key problems and recent advances from both academia and industry. In particular, we categorize collaboration algorithms into data-based, feature-based, and parameter-based frameworks. We also review publicly available datasets and evaluation metrics with user-level or device-level consideration tailored to collaborative learning settings. We further highlight real-world deployments, ranging from recommender systems and mobile livestreaming to personal intelligent assistants. We finally point out open research directions to guide future development in this rapidly evolving field.

Hang Zeng, Chaoyue Niu, Fan Wu et al.

Existing work on large language model (LLM) personalization assigned different responding roles to LLMs, but overlooked the diversity of queriers. In this work, we propose a new form of querier-aware LLM personalization, generating different responses even for the same query from different queriers. We design a dual-tower model architecture with a cross-querier general encoder and a querier-specific encoder. We further apply contrastive learning with multi-view augmentation, pulling close the dialogue representations of the same querier, while pulling apart those of different queriers. To mitigate the impact of query diversity on querier-contrastive learning, we cluster the dialogues based on query similarity and restrict the scope of contrastive learning within each cluster. To address the lack of datasets designed for querier-aware personalization, we also build a multi-querier dataset from English and Chinese scripts, as well as WeChat records, called MQDialog, containing 173 queriers and 12 responders. Extensive evaluations demonstrate that our design significantly improves the quality of personalized response generation, achieving relative improvement of 8.4% to 48.7% in ROUGE-L scores and winning rates ranging from 54% to 82% compared with various baseline methods.

Long Chen, Yuchen Li, Chao Huang et al.

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks and lack systematic summaries and research directions in the future. Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. This is the second part (Part I for this technical survey) to review the development of control, computing system design, communication, High Definition map (HD map), testing, and human behaviors in IVs. In addition, the third part (Part II for this technical survey) is to review the perception and planning sections. The objective of this paper is to involve all the sections of AD, summarize the latest technical milestones, and guide abecedarians to quickly understand the development of AD and IVs. Combining the SoS and Part II, we anticipate that this work will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future.

Boxue Xiao, Zhuoran Zheng, Xiang Chen et al.

Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time. To address the problem, we introduce the principle of infinite approximation of Taylor's theorem with the Laplace pyramid pattern to build a model which is capable of handling 4K hazy images in real-time. The N branch networks of the pyramid network correspond to the N constraint terms in Taylor's theorem. Low-order polynomials reconstruct the low-frequency information of the image (e.g. color, illumination). High-order polynomials regress the high-frequency information of the image (e.g. texture). In addition, we propose a Tucker reconstruction-based regularization term that acts on each branch network of the pyramid model. It further constrains the generation of anomalous signals in the feature space. Extensive experimental results demonstrate that our approach can not only run 4K images with haze in real-time on a single GPU (80FPS) but also has unparalleled interpretability. The developed method achieves state-of-the-art (SOTA) performance on two benchmarks (O/I-HAZE) and our updated 4KID dataset while providing the reliable groundwork for subsequent optimization schemes.

Peng Hang, Yiran Zhang, Chen Lv

In this paper, a human-like driving framework is designed for autonomous vehicles (AVs), which aims to make AVs better integrate into the transportation ecology of human driving and eliminate the misunderstanding and incompatibility of human drivers to autonomous driving. Based on the analysis of the real world INTERACTION dataset, a driving aggressiveness estimation model is established with the fuzzy inference approach. Then, a human-like driving model, which integrates the brain emotional learning circuit model (BELCM) with the two-point preview model, is designed. In the human-like lane-change decision-making algorithm, the cost function is designed comprehensively considering driving safety and travel efficiency. Based on the cost function and multi-constraint, the dynamic game algorithm is applied to modelling the interaction and decision making between AV and human driver. Additionally, to guarantee the lane-change safety of AVs, an artificial potential field model is built for collision risk assessment. Finally, the proposed algorithm is evaluated through human-in-the-loop experiments on a driving simulator, and the results demonstrated the feasibility and effectiveness of the proposed method.

Jingda Wu, Zhiyu Huang, Wenhui Huang et al.

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising way to improve learning performance. In this paper, a comprehensive human guidance-based reinforcement learning framework is established. A novel prioritized experience replay mechanism that adapts to human guidance in the reinforcement learning process is proposed to boost the efficiency and performance of the reinforcement learning algorithm. To relieve the heavy workload on human participants, a behavior model is established based on an incremental online learning method to mimic human actions. We design two challenging autonomous driving tasks for evaluating the proposed algorithm. Experiments are conducted to access the training and testing performance and learning mechanism of the proposed algorithm. Comparative results against the state-of-the-art methods suggest the advantages of our algorithm in terms of learning efficiency, performance, and robustness.

Zhiyu Huang, Xiaoyu Mo, Chen Lv

Predicting the behaviors of other agents on the road is critical for autonomous driving to ensure safety and efficiency. However, the challenging part is how to represent the social interactions between agents and output different possible trajectories with interpretability. In this paper, we introduce a neural prediction framework based on the Transformer structure to model the relationship among the interacting agents and extract the attention of the target agent on the map waypoints. Specifically, we organize the interacting agents into a graph and utilize the multi-head attention Transformer encoder to extract the relations between them. To address the multi-modality of motion prediction, we propose a multi-modal attention Transformer encoder, which modifies the multi-head attention mechanism to multi-modal attention, and each predicted trajectory is conditioned on an independent attention mode. The proposed model is validated on the Argoverse motion forecasting dataset and shows state-of-the-art prediction accuracy while maintaining a small model size and a simple training process. We also demonstrate that the multi-modal attention module can automatically identify different modes of the target agent's attention on the map, which improves the interpretability of the model.

Xiaoyu Mo, Yang Xing, Chen Lv

Integrating trajectory prediction to the decision-making and planning modules of modular autonomous driving systems is expected to improve the safety and efficiency of self-driving vehicles. However, a vehicle's future trajectory prediction is a challenging task since it is affected by the social interactive behaviors of neighboring vehicles, and the number of neighboring vehicles can vary in different situations. This work proposes a GNN-RNN based Encoder-Decoder network for interaction-aware trajectory prediction, where vehicles' dynamics features are extracted from their historical tracks using RNN, and the inter-vehicular interaction is represented by a directed graph and encoded using a GNN. The parallelism of GNN implies the proposed method's potential to predict multi-vehicular trajectories simultaneously. Evaluation on the dataset extracted from the NGSIM US-101 dataset shows that the proposed model is able to predict a target vehicle's trajectory in situations with a variable number of surrounding vehicles.

Jingda Wu, Zhiyu Huang, Chen Lv

To further improve the learning efficiency and performance of reinforcement learning (RL), in this paper we propose a novel uncertainty-aware model-based RL (UA-MBRL) framework, and then implement and validate it in autonomous driving under various task scenarios. First, an action-conditioned ensemble model with the ability of uncertainty assessment is established as the virtual environment model. Then, a novel uncertainty-aware model-based RL framework is developed based on the adaptive truncation approach, providing virtual interactions between the agent and environment model, and improving RL's training efficiency and performance. The developed algorithms are then implemented in end-to-end autonomous vehicle control tasks, validated and compared with state-of-the-art methods under various driving scenarios. The validation results suggest that the proposed UA-MBRL method surpasses the existing model-based and model-free RL approaches, in terms of learning efficiency and achieved performance. The results also demonstrate the good ability of the proposed method with respect to the adaptiveness and robustness, under various autonomous driving scenarios.

Xiaoyu Mo, Yang Xing, Chen Lv

Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for the safe and efficient operation of connected automated vehicles under complex driving situations in the real world. The multi-agent prediction task is challenging, as the motions of traffic participants are affected by many factors, including their individual dynamics, their interactions with surrounding agents, the traffic infrastructures, and the number and modalities of the target agents. To further advance the trajectory prediction techniques, in this work we propose a three-channel framework together with a novel Heterogeneous Edge-enhanced graph ATtention network (HEAT), which is able to deal with the heterogeneity of the target agents and traffic participants involved. Specifically, the agent's dynamics are extracted from their historical states using type-specific encoders. The inter-agent interactions are represented with a directed edge-featured heterogeneous graph, and then interaction features are extracted using the proposed HEAT network. Besides, the map features are shared across all agents by introducing a selective gate mechanism. And finally, the trajectories of multi-agent are executed simultaneously. Validations using both urban and highway driving datasets show that the proposed model can realize simultaneous trajectory predictions for multiple agents under complex traffic situations, and achieve state-of-the-art performance with respect to prediction accuracy, demonstrating its feasibility and effectiveness.

Jingda Wu, Zhiyu Huang, Chao Huang et al.

Due to the limited smartness and abilities of machine intelligence, currently autonomous vehicles are still unable to handle all kinds of situations and completely replace drivers. Because humans exhibit strong robustness and adaptability in complex driving scenarios, it is of great importance to introduce humans into the training loop of artificial intelligence, leveraging human intelligence to further advance machine learning algorithms. In this study, a real-time human-guidance-based deep reinforcement learning (Hug-DRL) method is developed for policy training of autonomous driving. Leveraging a newly designed control transfer mechanism between human and automation, human is able to intervene and correct the agent's unreasonable actions in real time when necessary during the model training process. Based on this human-in-the-loop guidance mechanism, an improved actor-critic architecture with modified policy and value networks is developed. The fast convergence of the proposed Hug-DRL allows real-time human guidance actions to be fused into the agent's training loop, further improving the efficiency and performance of deep reinforcement learning. The developed method is validated by human-in-the-loop experiments with 40 subjects and compared with other state-of-the-art learning approaches. The results suggest that the proposed method can effectively enhance the training efficiency and performance of the deep reinforcement learning algorithm under human guidance, without imposing specific requirements on participant expertise and experience.

Zhiyu Huang, Jingda Wu, Chen Lv

Deep reinforcement learning (DRL) is a promising way to achieve human-like autonomous driving. However, the low sample efficiency and difficulty of designing reward functions for DRL would hinder its applications in practice. In light of this, this paper proposes a novel framework to incorporate human prior knowledge in DRL, in order to improve the sample efficiency and save the effort of designing sophisticated reward functions. Our framework consists of three ingredients, namely expert demonstration, policy derivation, and reinforcement learning. In the expert demonstration step, a human expert demonstrates their execution of the task, and their behaviors are stored as state-action pairs. In the policy derivation step, the imitative expert policy is derived using behavioral cloning and uncertainty estimation relying on the demonstration data. In the reinforcement learning step, the imitative expert policy is utilized to guide the learning of the DRL agent by regularizing the KL divergence between the DRL agent's policy and the imitative expert policy. To validate the proposed method in autonomous driving applications, two simulated urban driving scenarios (unprotected left turn and roundabout) are designed. The strengths of our proposed method are manifested by the training results as our method can not only achieve the best performance but also significantly improve the sample efficiency in comparison with the baseline algorithms (particularly 60\% improvement compared to soft actor-critic). In testing conditions, the agent trained by our method obtains the highest success rate and shows diverse and human-like driving behaviors as demonstrated by the human expert.

Haochen Liu, Zhiyu Huang, Jingda Wu et al.

Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent decisions. However, current RL and IL approaches still have their own drawbacks, such as low data efficiency for RL and poor generalization capability for IL. In light of this, this paper proposes a novel learning-based method that combines deep reinforcement learning and imitation learning from expert demonstrations, which is applied to longitudinal vehicle motion control in autonomous driving scenarios. Our proposed method employs the soft actor-critic and modifies the learning process of the policy network to incorporate both the goals of maximizing reward and imitating the expert. Moreover, an adaptive prioritized experience replay is designed to sample experience from both the agent's self-exploration and expert demonstration, in order to improve sample efficiency. The proposed method is validated in a simulated urban roundabout scenario and compared with various prevailing RL and IL baselines. The results manifest that the proposed method has a faster training speed, as well as better performance in navigating safely and time-efficiently.

Xiaoyu Mo, Yang Xing, Chen Lv

Predicting the future trajectory of surrounding vehicles is essential for the navigation of autonomous vehicles in complex real-world driving scenarios. It is challenging as a vehicle's motion is affected by many factors, including its surrounding infrastructures and vehicles. In this work, we develop the ReCoG (Recurrent Convolutional and Graph Neural Networks), which is a general scheme that represents vehicle interactions with infrastructure information as a heterogeneous graph and applies graph neural networks (GNNs) to model the high-level interactions for trajectory prediction. Nodes in the graph contain corresponding features, where a vehicle node contains its sequential feature encoded using Recurrent Neural Network (RNN), and an infrastructure node contains spatial feature encoded using Convolutional Neural Network (CNN). Then the ReCoG predicts the future trajectory of the target vehicle by jointly considering all of the features. Experiments are conducted by using the INTERACTION dataset. Experimental results show that the proposed ReCoG outperforms other state-of-the-art methods in terms of different types of displacement error, validating the feasibility and effectiveness of the developed approach.

Zhiyu Huang, Jingda Wu, Chen Lv

Driving behavior modeling is of great importance for designing safe, smart, and personalized autonomous driving systems. In this paper, an internal reward function-based driving model that emulates the human's decision-making mechanism is utilized. To infer the reward function parameters from naturalistic human driving data, we propose a structural assumption about human driving behavior that focuses on discrete latent driving intentions. It converts the continuous behavior modeling problem to a discrete setting and thus makes maximum entropy inverse reinforcement learning (IRL) tractable to learn reward functions. Specifically, a polynomial trajectory sampler is adopted to generate candidate trajectories considering high-level intentions and approximate the partition function in the maximum entropy IRL framework. An environment model considering interactive behaviors among the ego and surrounding vehicles is built to better estimate the generated trajectories. The proposed method is applied to learn personalized reward functions for individual human drivers from the NGSIM highway driving dataset. The qualitative results demonstrate that the learned reward functions are able to explicitly express the preferences of different drivers and interpret their decisions. The quantitative results reveal that the learned reward functions are robust, which is manifested by only a marginal decline in proximity to the human driving trajectories when applying the reward function in the testing conditions. For the testing performance, the personalized modeling method outperforms the general modeling approach, significantly reducing the modeling errors in human likeness (a custom metric to gauge accuracy), and these two methods deliver better results compared to other baseline methods.

Zhongxu Hu, Yang Xing, Chen Lv et al.

Head pose estimation is a crucial problem for many tasks, such as driver attention, fatigue detection, and human behaviour analysis. It is well known that neural networks are better at handling classification problems than regression problems. It is an extremely nonlinear process to let the network output the angle value directly for optimization learning, and the weight constraint of the loss function will be relatively weak. This paper proposes a novel Bernoulli heatmap for head pose estimation from a single RGB image. Our method can achieve the positioning of the head area while estimating the angles of the head. The Bernoulli heatmap makes it possible to construct fully convolutional neural networks without fully connected layers and provides a new idea for the output form of head pose estimation. A deep convolutional neural network (CNN) structure with multiscale representations is adopted to maintain high-resolution information and low-resolution information in parallel. This kind of structure can maintain rich, high-resolution representations. In addition, channelwise fusion is adopted to make the fusion weights learnable instead of simple addition with equal weights. As a result, the estimation is spatially more precise and potentially more accurate. The effectiveness of the proposed method is empirically demonstrated by comparing it with other state-of-the-art methods on public datasets.

Peng Hang, Chen Lv, Yang Xing et al.

Considering that human-driven vehicles and autonomous vehicles (AVs) will coexist on roads in the future for a long time, how to merge AVs into human drivers traffic ecology and minimize the effect of AVs and their misfit with human drivers, are issues worthy of consideration. Moreover, different passengers have different needs for AVs, thus, how to provide personalized choices for different passengers is another issue for AVs. Therefore, a human-like decision making framework is designed for AVs in this paper. Different driving styles and social interaction characteristics are formulated for AVs regarding driving safety, ride comfort and travel efficiency, which are considered in the modeling process of decision making. Then, Nash equilibrium and Stackelberg game theory are applied to the noncooperative decision making. In addition, potential field method and model predictive control (MPC) are combined to deal with the motion prediction and planning for AVs, which provides predicted motion information for the decision-making module. Finally, two typical testing scenarios of lane change, i.e., merging and overtaking, are carried out to evaluate the feasibility and effectiveness of the proposed decision-making framework considering different human-like behaviors. Testing results indicate that both the two game theoretic approaches can provide reasonable human-like decision making for AVs. Compared with the Nash equilibrium approach, under the normal driving style, the cost value of decision making using the Stackelberg game theoretic approach is reduced by over 20%.

Peng Hang, Chen Lv, Chao Huang et al.

This paper presents a novel integrated approach to deal with the decision making and motion planning for lane-change maneuvers of autonomous vehicle (AV) considering social behaviors of surrounding traffic occupants. Reflected by driving styles and intentions of surrounding vehicles, the social behaviors are taken into consideration during the modelling process. Then, the Stackelberg Game theory is applied to solve the decision-making, which is formulated as a non-cooperative game problem. Besides, potential field is adopted in the motion planning model, which uses different potential functions to describe surrounding vehicles with different behaviors and road constrains. Then, Model Predictive Control (MPC) is utilized to predict the state and trajectory of the autonomous vehicle. Finally, the decision-making and motion planning is then integrated into a constrained multi-objective optimization problem. Three testing scenarios considering different social behaviors of surrounding vehicles are carried out to validate the performance of the proposed approach. Testing results show that the integrated approach is able to address different social interactions with other traffic participants, and make proper and safe decisions and planning for autonomous vehicles, demonstrating its feasibility and effectiveness.

Zhiyu Huang, Chen Lv, Yang Xing et al.

This study aims to improve the performance and generalization capability of end-to-end autonomous driving with scene understanding leveraging deep learning and multimodal sensor fusion techniques. The designed end-to-end deep neural network takes as input the visual image and associated depth information in an early fusion level and outputs the pixel-wise semantic segmentation as scene understanding and vehicle control commands concurrently. The end-to-end deep learning-based autonomous driving model is tested in high-fidelity simulated urban driving conditions and compared with the benchmark of CoRL2017 and NoCrash. The testing results show that the proposed approach is of better performance and generalization ability, achieving a 100% success rate in static navigation tasks in both training and unobserved situations, as well as better success rates in other tasks than the prior models. A further ablation study shows that the model with the removal of multimodal sensor fusion or scene understanding pales in the new environment because of the false perception. The results verify that the performance of our model is improved by the synergy of multimodal sensor fusion with scene understanding subtask, demonstrating the feasibility and effectiveness of the developed deep neural network with multimodal sensor fusion.