arXiv subjects

Chen Lv

Publications and source records attributed to Chen Lv.

At least 109 records · Page 6Linked to original sources

arXiv2023

Occupancy Prediction-Guided Neural Planner for Autonomous Driving

Forecasting the scalable future states of surrounding traffic participants in complex traffic scenarios is a critical capability for autonomous vehicles, as it enables safe and feasible decision-making. Recent successes in learning-based prediction and planning have introduced two primary challenges: generating accurate joint predictions for the environment and integrating prediction guidance for planning purposes. To address these challenges, we propose a two-stage integrated neural planning framework, termed OPGP, that incorporates joint prediction guidance from occupancy forecasting. The preliminary planning phase simultaneously outputs the predicted occupancy for various types of traffic actors based on imitation learning objectives, taking into account shared interactions, scene context, and actor dynamics within a unified Transformer structure. Subsequently, the transformed occupancy prediction guides optimization to further inform safe and smooth planning under Frenet coordinates. We train our planner using a large-scale, real-world driving dataset and validate it in open-loop configurations. Our proposed planner outperforms strong learning-based methods, exhibiting improved performance due to occupancy prediction guidance.

cs.RO↗

arXiv2023

Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys

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.

cs.RO↗

arXiv2023

Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Driving

Making safe and human-like decisions is an essential capability of autonomous driving systems, and learning-based behavior planning presents a promising pathway toward achieving this objective. Distinguished from existing learning-based methods that directly output decisions, this work introduces a predictive behavior planning framework that learns to predict and evaluate from human driving data. This framework consists of three components: a behavior generation module that produces a diverse set of candidate behaviors in the form of trajectory proposals, a conditional motion prediction network that predicts future trajectories of other agents based on each proposal, and a scoring module that evaluates the candidate plans using maximum entropy inverse reinforcement learning (IRL). We validate the proposed framework on a large-scale real-world urban driving dataset through comprehensive experiments. The results show that the conditional prediction model can predict distinct and reasonable future trajectories given different trajectory proposals and the IRL-based scoring module can select plans that are close to human driving. The proposed framework outperforms other baseline methods in terms of similarity to human driving trajectories. Additionally, we find that the conditional prediction model improves both prediction and planning performance compared to the non-conditional model. Lastly, we note that learning the scoring module is crucial for aligning the evaluations with human drivers.

cs.RO↗

arXiv2023

Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving

Predicting the future states of surrounding traffic participants and planning a safe, smooth, and socially compliant trajectory accordingly is crucial for autonomous vehicles. There are two major issues with the current autonomous driving system: the prediction module is often separated from the planning module and the cost function for planning is hard to specify and tune. To tackle these issues, we propose a differentiable integrated prediction-planning framework (DIPP) that can also learn the cost function from data. Specifically, our framework uses a differentiable nonlinear optimizer as the motion planner, which takes as input the predicted trajectories of surrounding agents given by the neural network and optimizes the trajectory for the autonomous vehicle, enabling all operations to be differentiable, including the cost function weights. The proposed framework is trained on a large-scale real-world driving dataset to imitate human driving trajectories in the entire driving scene and validated in both open-loop and closed-loop manners. The open-loop testing results reveal that the proposed method outperforms the baseline methods across a variety of metrics and delivers planning-centric prediction results, allowing the planning module to output trajectories close to those of human drivers. In closed-loop testing, the proposed method outperforms various baseline methods, showing the ability to handle complex urban driving scenarios and robustness against the distributional shift. Importantly, we find that joint training of planning and prediction modules achieves better performance than planning with a separate trained prediction module in both open-loop and closed-loop tests. Moreover, the ablation study indicates that the learnable components in the framework are essential to ensure planning stability and performance.

cs.RO↗

arXiv2023

Learning Interaction-aware Motion Prediction Model for Decision-making in Autonomous Driving

Predicting the behaviors of other road users is crucial to safe and intelligent decision-making for autonomous vehicles (AVs). However, most motion prediction models ignore the influence of the AV's actions and the planning module has to treat other agents as unalterable moving obstacles. To address this problem, this paper proposes an interaction-aware motion prediction model that is able to predict other agents' future trajectories according to the ego agent's future plan, i.e., their reactions to the ego's actions. Specifically, we employ Transformers to effectively encode the driving scene and incorporate the AV's plan in decoding the predicted trajectories. To train the model to accurately predict the reactions of other agents, we develop an online learning framework, where the ego agent explores the environment and collects other agents' reactions to itself. We validate the decision-making and learning framework in three highly interactive simulated driving scenarios. The results reveal that our decision-making method significantly outperforms the reinforcement learning methods in terms of data efficiency and performance. We also find that using the interaction-aware model can bring better performance than the non-interaction-aware model and the exploration process helps improve the success rate in testing.

cs.RO↗

arXiv2023

How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction?

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.

cs.CV↗

arXiv2022

Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving

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.

cs.LG↗

arXiv2022

Adaptive Leading Cruise Control in Mixed Traffic Considering Human Behavioral Diversity

This paper presents an adaptive leading cruise control strategy for the connected and automated vehicle (CAV) and first considers its impact on the following human-driven vehicle (HDV) with diverse driving characteristics in the unified optimization framework for improved holistic energy efficiency. The car-following behaviors of HDV are statistically calibrated using the Next Generation Simulation dataset. In a typical single-lane car-following scenario where CAVs and HDVs share the road, the longitudinal speed control of CAVs can substantially reduce the energy consumption of the following HDV by avoiding unnecessary acceleration and braking. Moreover, apart from the objectives including car-following safety and traffic efficiency, the energy efficiencies of both CAV and HDV are incorporated into the reward function of reinforcement learning. The specific driving pattern of the following HDV is learned in real-time from historical speed information to predict its acceleration and power consumption in the optimization horizon. A comprehensive simulation is conducted to statistically verify the positive impacts of CAV on the holistic energy efficiency of the mixed traffic flow with uncertain and diverse human driving behaviors. Simulation results indicate that the holistic energy efficiency is improved by 4.38% on average.

eess.SY↗

arXiv2022

STrajNet: Multi-modal Hierarchical Transformer for Occupancy Flow Field Prediction in Autonomous Driving

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.

cs.CV↗

arXiv2022

SIND: A Drone Dataset at Signalized Intersection in China

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

cs.CV↗

arXiv2022

Safe Decision-making for Lane-change of Autonomous Vehicles via Human Demonstration-aided Reinforcement Learning

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.

cs.RO↗

arXiv2022

ReCoAt: A Deep Learning-based Framework for Multi-Modal Motion Prediction in Autonomous Driving Application

This paper proposes a novel deep learning framework for multi-modal motion prediction. The framework consists of three parts: recurrent neural networks to process the target agent's motion process, convolutional neural networks to process the rasterized environment representation, and a distance-based attention mechanism to process the interactions among different agents. We validate the proposed framework on a large-scale real-world driving dataset, Waymo open motion dataset, and compare its performance against other methods on the standard testing benchmark. The qualitative results manifest that the predicted trajectories given by our model are accurate, diverse, and in accordance with the road structure. The quantitative results on the standard benchmark reveal that our model outperforms other baseline methods in terms of prediction accuracy and other evaluation metrics. The proposed framework is the second-place winner of the 2021 Waymo open dataset motion prediction challenge.

cs.RO↗

arXiv2022

Multi-task Driver Steering Behaviour Modeling Using Time-Series Transformer

Human intention prediction provides an augmented solution for the design of assistants and collaboration between the human driver and intelligent vehicles. In this study, a multi-task sequential learning framework is developed to predict future steering torques and steering postures based on the upper limb neuromuscular Electromyography (EMG) signals. A single-right-hand driving mode is particularly studied. For this driving mode, three different driving postures are also evaluated. Then, a multi-task time-series transformer network (MTS-Trans) is developed to predict the steering torques and driving postures. To evaluate the multi-task learning performance, four different frameworks are assessed. Twenty-one participants are involved in the driving simulator-based experiment. The proposed model achieved accurate prediction results on the future steering torque prediction and driving postures recognition for single-hand driving modes. The proposed system can contribute to the development of advanced driver steering assistant systems and ensure mutual understanding between human drivers and intelligent vehicles.

cs.HC↗

arXiv2022

Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration

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.

cs.LG↗

arXiv2022

Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving

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.

cs.RO↗

arXiv2022

Driving Conflict Resolution of Autonomous Vehicles at Unsignalized Intersections: A Differential Game Approach

Considering personalized driving preferences, a new decision-making framework is developed using a differential game approach to resolve the driving conflicts of autonomous vehicles (AVs) at unsignalized intersections. To realize human-like driving and personalized decision-making, driving aggressiveness is first defined for AVs. To improve driving safety, a Gaussian potential field model is built for collision risk assessment. Besides, in the proposed decision making framework, the collision risk assessment model is further used to reduce the computational complexity based on an event-triggered mechanism. In the construction of payoff function, both driving safety and passing efficiency are comprehensively considered, and the driving aggressiveness is also reflected. Two kinds of equilibrium solution to the differential game, i.e., the Nash equilibrium and Stackelberg equilibrium, are discussed and solved. Finally, the proposed decision making algorithm is tested through a hardware-in-the-loop testing platform, and its feasibility, effectiveness and real-time implementation performance are validated.

eess.SY↗

arXiv2022

RHONN Modelling-enabled Nonlinear Predictive Control for Lateral Dynamics Stabilization of An In-wheel Motor Driven Vehicle

Featuring the fast response and flexibility in control allocation, an electric vehicle with in-wheel motors is a good platform for implementing advanced vehicle dynamics control. Among many active safety functions of an in-wheel motor driven vehicle (IMDV), lateral stability control is a key technology, which can be realized through torque vectoring. To further advance the lateral stabilization performance of the IMDV, in this paper a novel data-driven nonlinear model predictive control (NMPC) is proposed based the recurrent high-order neural network (RHONN) modelling method. First, the new RHONN model is developed to represent vehicle's nonlinear dynamic behaviors. Different from the conventional physics-based modelling method, the RHONN model only needs data and forms high-order polynomials. Based on the RHONN model, the steady-state responses of vehicle's yaw rate and sideslip angle are iteratively optimized and set as the control objectives for low-level controller, aiming to improve the system robustness. Besides, a nonlinear model predictive controller is designed based on the RHONN, which is expected to improve the prediction accuracy during the receding horizon control. Further, a constrained optimization problem is formulated to derive the required yaw moment for vehicle lateral dynamics stabilization. Finally, the performance of the developed RHONN-based nonlinear MPC is validated on an IMDV in the CarSim/Simulink simulation environment. The validation results show that the developed approach outperforms the conventional method, and further improves the stable margin of the system. It is able to enhance the lateral stabilization performance of the IMDV under various driving scenarios, demonstrating the feasibility and effectiveness of the proposed approach.

eess.SY↗

arXiv2022

Single UHD Image Dehazing via Interpretable Pyramid Network

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.

cs.CV↗