Lu Xiong

Hansheng Chen, Wei Tian, Pichao Wang et al.

Locating 3D objects from a single RGB image via Perspective-n-Point (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, allowing for partial learning of 2D-3D point correspondences by backpropagating the gradients of pose loss. Yet, learning the entire correspondences from scratch is highly challenging, particularly for ambiguous pose solutions, where the globally optimal pose is theoretically non-differentiable w.r.t. the points. In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose with differentiable probability density on the SE(3) manifold. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle generalizes previous approaches, and resembles the attention mechanism. EPro-PnP can enhance existing correspondence networks, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation benchmark. Furthermore, EPro-PnP helps to explore new possibilities of network design, as we demonstrate a novel deformable correspondence network with the state-of-the-art pose accuracy on the nuScenes 3D object detection benchmark. Our code is available at https://github.com/tjiiv-cprg/EPro-PnP-v2.

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.

Peiyuan Fang, Weiqi Zhang, Lu Xiong et al.

This paper introduces the Generalized Action Governor (AG), a supervisory scheme that augments a nominal closed-loop system with the capability to enforce state and input constraints through online action adjustment. We develop a generalized AG theory for discrete-time systems under bounded uncertainties, and relax the usual requirement of positive invariance to returnability of a safe set. Based on the theory, we present tailored AG design procedures for linear systems and for discrete systems with finite state and action spaces. We further study safe online learning enabled by the AG and present two safe learning strategies, namely safe Q-learning and safe data-driven Koopman operator-based control, both integrated with the AG to guarantee constraint satisfaction during learning. Numerical results illustrate the proposed methods.

Guirong Zhuo, Shouyi Lu, Huanyu Zhou et al.

Four-dimensional (4D) radar--visual odometry (4DRVO) integrates complementary information from 4D radar and cameras, making it an attractive solution for achieving accurate and robust pose estimation. However, 4DRVO may exhibit significant tracking errors owing to three main factors: 1) sparsity of 4D radar point clouds; 2) inaccurate data association and insufficient feature interaction between the 4D radar and camera; and 3) disturbances caused by dynamic objects in the environment, affecting odometry estimation. In this paper, we present 4DRVO-Net, which is a method for 4D radar--visual odometry. This method leverages the feature pyramid, pose warping, and cost volume (PWC) network architecture to progressively estimate and refine poses. Specifically, we propose a multi-scale feature extraction network called Radar-PointNet++ that fully considers rich 4D radar point information, enabling fine-grained learning for sparse 4D radar point clouds. To effectively integrate the two modalities, we design an adaptive 4D radar--camera fusion module (A-RCFM) that automatically selects image features based on 4D radar point features, facilitating multi-scale cross-modal feature interaction and adaptive multi-modal feature fusion. In addition, we introduce a velocity-guided point-confidence estimation module to measure local motion patterns, reduce the influence of dynamic objects and outliers, and provide continuous updates during pose refinement. We demonstrate the excellent performance of our method and the effectiveness of each module design on both the VoD and in-house datasets. Our method outperforms all learning-based and geometry-based methods for most sequences in the VoD dataset. Furthermore, it has exhibited promising performance that closely approaches that of the 64-line LiDAR odometry results of A-LOAM without mapping optimization.

Baoyun Wang, Zhuoren Li, Ming Liu et al.

End-to-end diffusion planning has shown strong potential for autonomous driving, but the physical feasibility of generated trajectories remains insufficiently addressed. In particular, generated trajectories may exhibit local geometric irregularities, violate trajectory-level kinematic constraints, or deviate from the drivable area, indicating that the commonly used noise-centric formulation in diffusion planning is not yet well aligned with the trajectory space where feasibility is more naturally characterized. To address this issue, we propose FeaXDrive, a feasibility-aware trajectory-centric diffusion planning method for end-to-end autonomous driving. The core idea is to treat the clean trajectory as the unified object for feasibility-aware modeling throughout the diffusion process. Built on this trajectory-centric formulation, FeaXDrive integrates adaptive curvature-constrained training to improve intrinsic geometric and kinematic feasibility, drivable-area guidance within reverse diffusion sampling to enhance consistency with the drivable area, and feasibility-aware GRPO post-training to further improve planning performance while balancing trajectory-space feasibility. Experiments on the NAVSIM benchmark show that FeaXDrive achieves strong closed-loop planning performance while substantially improving trajectory-space feasibility. These findings highlight the importance of explicitly modeling trajectory-space feasibility in end-to-end diffusion planning and provide a step toward more reliable and physically grounded autonomous driving planners.

Hongyang Li, Yang Li, Huijie Wang et al.

With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem. Current autonomous driving datasets can broadly be categorized into two generations. The first-generation autonomous driving datasets are characterized by relatively simpler sensor modalities, smaller data scale, and is limited to perception-level tasks. KITTI, introduced in 2012, serves as a prominent representative of this initial wave. In contrast, the second-generation datasets exhibit heightened complexity in sensor modalities, greater data scale and diversity, and an expansion of tasks from perception to encompass prediction and control. Leading examples of the second generation include nuScenes and Waymo, introduced around 2019. This comprehensive review, conducted in collaboration with esteemed colleagues from both academia and industry, systematically assesses over seventy open-source autonomous driving datasets from domestic and international sources. It offers insights into various aspects, such as the principles underlying the creation of high-quality datasets, the pivotal role of data engine systems, and the utilization of generative foundation models to facilitate scalable data generation. Furthermore, this review undertakes an exhaustive analysis and discourse regarding the characteristics and data scales that future third-generation autonomous driving datasets should possess. It also delves into the scientific and technical challenges that warrant resolution. These endeavors are pivotal in advancing autonomous innovation and fostering technological enhancement in critical domains. For further details, please refer to https://github.com/OpenDriveLab/DriveAGI.

Hansheng Chen, Pichao Wang, Fan Wang et al.

Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, so that 2D-3D point correspondences can be partly learned by backpropagating the gradient w.r.t. object pose. Yet, learning the entire set of unrestricted 2D-3D points from scratch fails to converge with existing approaches, since the deterministic pose is inherently non-differentiable. In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose on the SE(3) manifold, essentially bringing categorical Softmax to the continuous domain. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle unifies the existing approaches and resembles the attention mechanism. EPro-PnP significantly outperforms competitive baselines, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation and nuScenes 3D object detection benchmarks.

Bo Leng, Weiqi Zhang, Zhuoren Li et al.

Reinforcement learning has demonstrated significant potential in the field of autonomous driving. However, it suffers from defects such as training instability and unsafe action outputs when faced with autonomous racing environments characterized by high dynamics and strong nonlinearities. To this end, this paper proposes a trajectory guidance and dynamics constraints Reinforcement Learning (TraD-RL) method for autonomous racing. The key features of this method are as follows: 1) leveraging the prior expert racing line to construct an augmented state representation and facilitate reward shaping, thereby integrating domain knowledge to stabilize early-stage policy learning; 2) embedding explicit vehicle dynamic priors into a safe operating envelope formulated via control barrier functions to enable safety-constrained learning; and 3) adopting a multi-stage curriculum learning strategy that shifts from expert-guided learning to autonomous exploration, allowing the learned policy to surpass expert-level performance. The proposed method is evaluated in a high-fidelity simulation environment modeled after the Tempelhof Airport Street Circuit. Experimental results demonstrate that TraD-RL effectively improves both lap speed and driving stability of the autonomous racing vehicle, achieving a synergistic optimization of racing performance and safety.

Haojie Feng, Peizhi Zhang, Mengjie Tian et al.

The evolution of autonomous driving towards full automation demands robust interactive capabilities; however, the development of Vision-Language-Action (VLA) models is constrained by the sparsity of interactive scenarios and inadequate multimodal alignment in existing data. To this end, this paper proposes the Interactive Enhanced Driving Dataset (IEDD). We develop a scalable pipeline to mine million-level interactive segments from naturalistic driving data based on interactive trajectories, and design metrics to quantify the interaction processes. Furthermore, the IEDD-VQA dataset is constructed by generating synthetic Bird's Eye View (BEV) videos where semantic actions are strictly aligned with structured language. Benchmark results evaluating ten mainstream Vision Language Models (VLMs) are provided to demonstrate the dataset's reuse value in assessing and fine-tuning the reasoning capabilities of autonomous driving models.

Jianfeng Li, Junqiao Zhao, Tiantian Feng et al.

In this paper, we proposed an unsupervised learning method for estimating the optical flow between video frames, especially to solve the occlusion problem. Occlusion is caused by the movement of an object or the movement of the camera, defined as when certain pixels are visible in one video frame but not in adjacent frames. Due to the lack of pixel correspondence between frames in the occluded area, incorrect photometric loss calculation can mislead the optical flow training process. In the video sequence, we found that the occlusion in the forward ($t\rightarrow t+1$) and backward ($t\rightarrow t-1$) frame pairs are usually complementary. That is, pixels that are occluded in subsequent frames are often not occluded in the previous frame and vice versa. Therefore, by using this complementarity, a new weighted loss is proposed to solve the occlusion problem. In addition, we calculate gradients in multiple directions to provide richer supervision information. Our method achieves competitive optical flow accuracy compared to the baseline and some supervised methods on KITTI 2012 and 2015 benchmarks. This source code has been released at https://github.com/jianfenglihg/UnOpticalFlow.git.

Boyuan Zheng, Shouyi Lu, Renbo Huang et al.

We introduce R2LDM, an innovative approach for generating dense and accurate 4D radar point clouds, guided by corresponding LiDAR point clouds. Instead of utilizing range images or bird's eye view (BEV) images, we represent both LiDAR and 4D radar point clouds using voxel features, which more effectively capture 3D shape information. Subsequently, we propose the Latent Voxel Diffusion Model (LVDM), which performs the diffusion process in the latent space. Additionally, a novel Latent Point Cloud Reconstruction (LPCR) module is utilized to reconstruct point clouds from high-dimensional latent voxel features. As a result, R2LDM effectively generates LiDAR-like point clouds from paired raw radar data. We evaluate our approach on two different datasets, and the experimental results demonstrate that our model achieves 6- to 10-fold densification of radar point clouds, outperforming state-of-the-art baselines in 4D radar point cloud super-resolution. Furthermore, the enhanced radar point clouds generated by our method significantly improve downstream tasks, achieving up to 31.7% improvement in point cloud registration recall rate and 24.9% improvement in object detection accuracy.

Guizhe Jin, Zhuoren Li, Bo Leng et al.

Reinforcement Learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving, which is increasingly applied in diverse driving scenarios. However, driving is a multi-attribute problem, leading to challenges in achieving multi-objective compatibility for current RL methods, especially in both policy updating and policy execution. On the one hand, a single value evaluation network limits the policy updating in complex scenarios with coupled driving objectives. On the other hand, the common single-type action space structure limits driving flexibility or results in large behavior fluctuations during policy execution. To this end, we propose a Multi-objective Ensemble-Critic reinforcement learning method with Hybrid Parametrized Action for multi-objective compatible autonomous driving. Specifically, an advanced MORL architecture is constructed, in which the ensemble-critic focuses on different objectives through independent reward functions. The architecture integrates a hybrid parameterized action space structure, and the generated driving actions contain both abstract guidance that matches the hybrid road modality and concrete control commands. Additionally, an uncertainty-based exploration mechanism that supports hybrid actions is developed to learn multi-objective compatible policies more quickly. Experimental results demonstrate that, in both simulator-based and HighD dataset-based multi-lane highway scenarios, our method efficiently learns multi-objective compatible autonomous driving with respect to efficiency, action consistency, and safety.

Zhuoren Li, Guizhe Jin, Ran Yu et al.

Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion planning (MoP) challenges in autonomous driving (AD). Despite rapid advancements in RL and AD, a systematic description and interpretation of the RL design process tailored to diverse driving tasks remains underdeveloped. This survey provides a comprehensive review of RL-based MoP for AD, focusing on lessons from task-specific perspectives. We first outline the fundamentals of RL methodologies, and then survey their applications in MoP, analyzing scenario-specific features and task requirements to shed light on their influence on RL design choices. Building on this analysis, we summarize key design experiences, extract insights from various driving task applications, and provide guidance for future implementations. Additionally, we examine the frontier challenges in RL-based MoP, review recent efforts to addresse these challenges, and propose strategies for overcoming unresolved issues.

Jiaqi Zhu, Shouyi Lu, Ziyao Li et al.

Global Navigation Satellite Systems (GNSS) are vital for reliable urban positioning. However, multipath and non-line-of-sight reception often introduce large measurement errors that degrade accuracy. Learning-based methods for predicting and compensating pseudorange errors have gained traction, but their performance is limited by complex error distributions. To address this challenge, we propose Diff-GNSS, a coarse-to-fine GNSS measurement (pseudorange) error estimation framework that leverages a conditional diffusion model to capture such complex distributions. Firstly, a Mamba-based module performs coarse estimation to provide an initial prediction with appropriate scale and trend. Then, a conditional denoising diffusion layer refines the estimate, enabling fine-grained modeling of pseudorange errors. To suppress uncontrolled generative diversity and achieve controllable synthesis, three key features related to GNSS measurement quality are used as conditions to precisely guide the reverse denoising process. We further incorporate per-satellite uncertainty modeling within the diffusion stage to assess the reliability of the predicted errors. We have collected and publicly released a real-world dataset covering various scenes. Experiments on public and self-collected datasets show that DiffGNSS consistently outperforms state-of-the-art baselines across multiple metrics. To the best of our knowledge, this is the first application of diffusion models to pseudorange error estimation. The proposed diffusion-based refinement module is plug-and-play and can be readily integrated into existing networks to markedly improve estimation accuracy.

Guizhe Jin, Zhuoren Li, Bo Leng et al.

Reinforcement Learning (RL) is increasingly used in autonomous driving (AD) and shows clear advantages. However, most RL-based AD methods overlook policy structure design. An RL policy that only outputs short-timescale vehicle control commands results in fluctuating driving behavior due to fluctuations in network outputs, while one that only outputs long-timescale driving goals cannot achieve unified optimality of driving behavior and control. Therefore, we propose a multi-timescale hierarchical reinforcement learning approach. Our approach adopts a hierarchical policy structure, where high- and low-level RL policies are unified-trained to produce long-timescale motion guidance and short-timescale control commands, respectively. Therein, motion guidance is explicitly represented by hybrid actions to capture multimodal driving behaviors on structured road and support incremental low-level extend-state updates. Additionally, a hierarchical safety mechanism is designed to ensure multi-timescale safety. Evaluation in simulator-based and HighD dataset-based highway multi-lane scenarios demonstrates that our approach significantly improves AD performance, effectively increasing driving efficiency, action consistency and safety.

Shuangfu Song, Junqiao Zhao, Tiantian Feng et al.

The scale ambiguity problem is inherently unsolvable to monocular SLAM without the metric baseline between moving cameras. In this paper, we present a novel scale estimation approach based on an object-level SLAM system. To obtain the absolute scale of the reconstructed map, we derive a nonlinear optimization method to make the scaled dimensions of objects conforming to the distribution of their sizes in the physical world, without relying on any prior information of gravity direction. We adopt the dual quadric to represent objects for its ability to fit objects compactly and accurately. In the proposed monocular object-level SLAM system, dual quadrics are fastly initialized based on constraints of 2-D detections and fitted oriented bounding box and are further optimized to provide reliable dimensions for scale estimation.

Jiafeng Cui, Tengfei Huang, Yingfeng Cai et al.

LiDAR-based place recognition is an essential and challenging task both in loop closure detection and global relocalization. We propose Deep Scan Context (DSC), a general and discriminative global descriptor that captures the relationship among segments of a point cloud. Unlike previous methods that utilize either semantics or a sequence of adjacent point clouds for better place recognition, we only use raw point clouds to get competitive results. Concretely, we first segment the point cloud egocentrically to acquire centroids and eigenvalues of the segments. Then, we introduce a graph neural network to aggregate these features into an embedding representation. Extensive experiments conducted on the KITTI dataset show that DSC is robust to scene variants and outperforms existing methods.

Hansheng Chen, Yuyao Huang, Wei Tian et al.

Object localization in 3D space is a challenging aspect in monocular 3D object detection. Recent advances in 6DoF pose estimation have shown that predicting dense 2D-3D correspondence maps between image and object 3D model and then estimating object pose via Perspective-n-Point (PnP) algorithm can achieve remarkable localization accuracy. Yet these methods rely on training with ground truth of object geometry, which is difficult to acquire in real outdoor scenes. To address this issue, we propose MonoRUn, a novel detection framework that learns dense correspondences and geometry in a self-supervised manner, with simple 3D bounding box annotations. To regress the pixel-related 3D object coordinates, we employ a regional reconstruction network with uncertainty awareness. For self-supervised training, the predicted 3D coordinates are projected back to the image plane. A Robust KL loss is proposed to minimize the uncertainty-weighted reprojection error. During testing phase, we exploit the network uncertainty by propagating it through all downstream modules. More specifically, the uncertainty-driven PnP algorithm is leveraged to estimate object pose and its covariance. Extensive experiments demonstrate that our proposed approach outperforms current state-of-the-art methods on KITTI benchmark.

Junqiao Zhao, Chen Ye, Yan Wu et al.

TiEV is an autonomous driving platform implemented by Tongji University of China. The vehicle is drive-by-wire and is fully powered by electricity. We devised the software system of TiEV from scratch, which is capable of driving the vehicle autonomously in urban paths as well as on fast express roads. We describe our whole system, especially novel modules of probabilistic perception fusion, incremental mapping, the 1st and the 2nd planning and the overall safety concern. TiEV finished 2016 and 2017 Intelligent Vehicle Future Challenge of China held at Changshu. We show our experiences on the development of autonomous vehicles and future trends.