Zhong Cao

Weitao Zhou, Zhong Cao, Yunkang Xu et al.

A typical trajectory planner of autonomous driving commonly relies on predicting the future behavior of surrounding obstacles. Recently, deep learning technology has been widely adopted to design prediction models due to their impressive performance. However, such models may fail in the "long-tail" driving cases where the training data is sparse or unavailable, leading to planner failures. To this end, this work proposes a trajectory planner to consider the prediction model uncertainty arising from insufficient data for safer performance. Firstly, an ensemble network structure estimates the prediction model's uncertainty due to insufficient training data. Then a trajectory planner is designed to consider the worst-case arising from prediction uncertainty. The results show that the proposed method can improve the safety of trajectory planning under the prediction uncertainty caused by insufficient data. At the same time, with sufficient data, the framework will not lead to overly conservative results. This technology helps to improve the safety and reliability of autonomous vehicles under the long-tail data distribution of the real world.

Chulin Xie, Zhong Cao, Yunhui Long et al.

Recent advances in machine learning have enabled its wide application in different domains, and one of the most exciting applications is autonomous vehicles (AVs), which have encouraged the development of a number of ML algorithms from perception to prediction to planning. However, training AVs usually requires a large amount of training data collected from different driving environments (e.g., cities) as well as different types of personal information (e.g., working hours and routes). Such collected large data, treated as the new oil for ML in the data-centric AI era, usually contains a large amount of privacy-sensitive information which is hard to remove or even audit. Although existing privacy protection approaches have achieved certain theoretical and empirical success, there is still a gap when applying them to real-world applications such as autonomous vehicles. For instance, when training AVs, not only can individually identifiable information reveal privacy-sensitive information, but also population-level information such as road construction within a city, and proprietary-level commercial secrets of AVs. Thus, it is critical to revisit the frontier of privacy risks and corresponding protection approaches in AVs to bridge this gap. Following this goal, in this work, we provide a new taxonomy for privacy risks and protection methods in AVs, and we categorize privacy in AVs into three levels: individual, population, and proprietary. We explicitly list out recent challenges to protect each of these levels of privacy, summarize existing solutions to these challenges, discuss the lessons and conclusions, and provide potential future directions and opportunities for both researchers and practitioners. We believe this work will help to shape the privacy research in AV and guide the privacy protection technology design.

Zhijie Qiao, Haowei Li, Zhong Cao et al.

Vision-Language Models (VLMs) have demonstrated significant potential for end-to-end autonomous driving. However, the field still lacks a practical platform that enables dynamic model updates, rapid validation, fair comparison, and intuitive performance assessment. To that end, we introduce LightEMMA, a Lightweight End-to-End Multimodal Model for Autonomous driving. LightEMMA provides a unified, VLM-based autonomous driving framework without ad hoc customizations, enabling easy integration with evolving state-of-the-art commercial and open-source models. We construct twelve autonomous driving agents using various VLMs and evaluate their performance on the challenging nuScenes prediction task, comprehensively assessing computational metrics and providing critical insights. Illustrative examples show that, although VLMs exhibit strong scenario interpretation capabilities, their practical performance in autonomous driving tasks remains a concern. Additionally, increased model complexity and extended reasoning do not necessarily lead to better performance, emphasizing the need for further improvements and task-specific designs. The code is available at https://github.com/michigan-traffic-lab/LightEMMA.

Xiang Li, Gang Liu, Weitao Zhou et al.

Imitation learning (IL) has emerged as a central paradigm in autonomous driving. While IL excels in matching expert behavior in open-loop settings by minimizing per-step prediction errors, its performance degrades unexpectedly in closed-loop due to the gradual accumulation of small, often imperceptible errors over time.Over successive planning cycles, these errors compound, potentially resulting in severe failures.Current research efforts predominantly rely on increasingly sophisticated network architectures or high-fidelity training datasets to enhance the robustness of IL planners against error accumulation, focusing on the state-level robustness at a single time point. However, autonomous driving is inherently a continuous-time process, and leveraging the temporal scale to enhance robustness may provide a new perspective for addressing this issue.To this end, we propose a method termed Sequence of Experts (SoE), a temporal alternation policy that enhances closed-loop performance without increasing model size or data requirements. Our experiments on large-scale autonomous driving benchmarks nuPlan demonstrate that SoE method consistently and significantly improves the performance of all the evaluated models, and achieves state-of-the-art performance.This module may provide a key and widely applicable support for improving the training efficiency of autonomous driving models.

Minghan Zhu, Maani Ghaffari, Yuanxin Zhong et al.

This paper reports a new continuous 3D loss function for learning depth from monocular images. The dense depth prediction from a monocular image is supervised using sparse LIDAR points, which enables us to leverage available open source datasets with camera-LIDAR sensor suites during training. Currently, accurate and affordable range sensor is not readily available. Stereo cameras and LIDARs measure depth either inaccurately or sparsely/costly. In contrast to the current point-to-point loss evaluation approach, the proposed 3D loss treats point clouds as continuous objects; therefore, it compensates for the lack of dense ground truth depth due to LIDAR's sparsity measurements. We applied the proposed loss in three state-of-the-art monocular depth prediction approaches DORN, BTS, and Monodepth2. Experimental evaluation shows that the proposed loss improves the depth prediction accuracy and produces point-clouds with more consistent 3D geometric structures compared with all tested baselines, implying the benefit of the proposed loss on general depth prediction networks. A video demo of this work is available at https://youtu.be/5HL8BjSAY4Y.

Zhijie Qiao, Zhong Cao, Henry X. Liu

End-to-end (E2E) autonomous driving heavily relies on closed-loop simulation, where perception, planning, and control are jointly trained and evaluated in interactive environments. Yet, most existing datasets are collected from the real world under non-interactive conditions, primarily supporting open-loop learning while offering limited value for closed-loop testing. Due to the lack of standardized, large-scale, and thoroughly verified datasets to facilitate learning of meaningful intermediate representations, such as bird's-eye-view (BEV) features, closed-loop E2E models remain far behind even simple rule-based baselines. To address this challenge, we introduce nuCarla, a large-scale, nuScenes-style BEV perception dataset built within the CARLA simulator. nuCarla features (1) full compatibility with the nuScenes format, enabling seamless transfer of real-world perception models; (2) a dataset scale comparable to nuScenes, but with more balanced class distributions; (3) direct usability for closed-loop simulation deployment; and (4) high-performance BEV backbones that achieve state-of-the-art detection results. By providing both data and models as open benchmarks, nuCarla substantially accelerates closed-loop E2E development, paving the way toward reliable and safety-aware research in autonomous driving.

Shuying Chen, Sen Cui, Zhong Cao

In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat each guideline page as an independent evidence unit and directly retrieve page images, preserving tables, flowcharts, and layout information. We further design a controllable retrieval framework with routing and filtering, which selectively introduces external evidence and reduces noise. The system integrates query decomposition, query rewriting, retrieval, reranking, and multimodal reasoning, and provides traceable outputs with guideline page references. We evaluate our method on HealthBench using a doctor-based scoring protocol. On the hard subset, our approach improves the overall score from 0.2969 to 0.3861 (+0.0892, +30.0%) compared to GPT-5.2, and achieves higher accuracy, improving from 0.5956 to 0.6576 (+0.0620, +10.4%). Compared to GPT-5.4, our method achieves a larger accuracy gain of +0.1289 (+24.4%). These results show that our method is more effective on challenging cases that require precise, evidence-based reasoning. Ablation studies further show that reranking, routing, and retrieval design are critical for stable performance, especially under difficult settings. Overall, we show how combining visionbased retrieval with controllable reasoning can improve evidence grounding and robustness in clinical AI applications,while pointing out that further work is needed to be more complete.

Yuheng Luo, Shuyan Li, Zhong Cao

Feature selection remains a major challenge in medical prediction, where existing approaches such as LASSO often lack robustness and interpretability. We introduce GRASP, a novel framework that couples Shapley value driven attribution with group $L_{21}$ regularization to extract compact and non-redundant feature sets. GRASP first distills group level importance scores from a pretrained tree model via SHAP, then enforces structured sparsity through group $L_{21}$ regularized logistic regression, yielding stable and interpretable selections. Extensive comparisons with LASSO, SHAP, and deep learning based methods show that GRASP consistently delivers comparable or superior predictive accuracy, while identifying fewer, less redundant, and more stable features.

Yuquan Zhang, Zhong Cao, Feng Wang et al.

The Chinese Space Station Telescope (abbreviated as CSST) is a future advanced space telescope. Real-time identification of galaxy and nebula/star cluster (abbreviated as NSC) images is of great value during CSST survey. While recent research on celestial object recognition has progressed, the rapid and efficient identification of high-resolution local celestial images remains challenging. In this study, we conducted galaxy and NSC image classification research using deep learning methods based on data from the Hubble Space Telescope. We built a Local Celestial Image Dataset and designed a deep learning model named HR-CelestialNet for classifying images of the galaxy and NSC. HR-CelestialNet achieved an accuracy of 89.09% on the testing set, outperforming models such as AlexNet, VGGNet and ResNet, while demonstrating faster recognition speeds. Furthermore, we investigated the factors influencing CSST image quality and evaluated the generalization ability of HR-CelestialNet on the blurry image dataset, demonstrating its robustness to low image quality. The proposed method can enable real-time identification of celestial images during CSST survey mission.

Jiawei Wang, Xintao Yan, Yao Mu et al.

Generating safety-critical scenarios in high-fidelity simulations offers a promising and cost-effective approach for efficient testing of autonomous vehicles. Existing methods typically rely on manipulating a single vehicle's trajectory through sophisticated designed objectives to induce adversarial interactions, often at the cost of realism and scalability. In this work, we propose the Risk-Adjustable Driving Environment (RADE), a simulation framework that generates statistically realistic and risk-adjustable traffic scenes. Built upon a multi-agent diffusion architecture, RADE jointly models the behavior of all agents in the environment and conditions their trajectories on a surrogate risk measure. Unlike traditional adversarial methods, RADE learns risk-conditioned behaviors directly from data, preserving naturalistic multi-agent interactions with controllable risk levels. To ensure physical plausibility, we incorporate a tokenized dynamics check module that efficiently filters generated trajectories using a motion vocabulary. We validate RADE on the real-world rounD dataset, demonstrating that it preserves statistical realism across varying risk levels and naturally increases the likelihood of safety-critical events as the desired risk level grows up. Our results highlight RADE's potential as a scalable and realistic tool for AV safety evaluation.

Boqi Li, Siyuan Li, Weiyi Wang et al.

With the rapid progress of foundation models and robotics, vision-language navigation (VLN) has emerged as a key task for embodied agents with broad practical applications. We address VLN in continuous environments, a particularly challenging setting where an agent must jointly interpret natural language instructions, perceive its surroundings, and plan low-level actions. We propose a zero-shot framework that integrates a simplified yet effective waypoint predictor with a multimodal large language model (MLLM). The predictor operates on an abstract obstacle map, producing linearly reachable waypoints, which are incorporated into a dynamically updated topological graph with explicit visitation records. The graph and visitation information are encoded into the prompt, enabling reasoning over both spatial structure and exploration history to encourage exploration and equip MLLM with local path planning for error correction. Extensive experiments on R2R-CE and RxR-CE show that our method achieves state-of-the-art zero-shot performance, with success rates of 41% and 36%, respectively, outperforming prior state-of-the-art methods.

Weitao Zhou, Bo Zhang, Zhong Cao et al.

With the increasing presence of automated vehicles on open roads under driver supervision, disengagement cases are becoming more prevalent. While some data-driven planning systems attempt to directly utilize these disengagement cases for policy improvement, the inherent scarcity of disengagement data (often occurring as a single instances) restricts training effectiveness. Furthermore, some disengagement data should be excluded since the disengagement may not always come from the failure of driving policies, e.g. the driver may casually intervene for a while. To this end, this work proposes disengagement-reason-augmented reinforcement learning (DRARL), which enhances driving policy improvement process according to the reason of disengagement cases. Specifically, the reason of disengagement is identified by a out-of-distribution (OOD) state estimation model. When the reason doesn't exist, the case will be identified as a casual disengagement case, which doesn't require additional policy adjustment. Otherwise, the policy can be updated under a reason-augmented imagination environment, improving the policy performance of disengagement cases with similar reasons. The method is evaluated using real-world disengagement cases collected by autonomous driving robotaxi. Experimental results demonstrate that the method accurately identifies policy-related disengagement reasons, allowing the agent to handle both original and semantically similar cases through reason-augmented training. Furthermore, the approach prevents the agent from becoming overly conservative after policy adjustments. Overall, this work provides an efficient way to improve driving policy performance with disengagement cases.

Nanshan Deng, Weitao Zhou, Bo Zhang et al.

Current autonomous vehicles operate primarily within limited regions, but there is increasing demand for broader applications. However, as models scale, their limited capacity becomes a significant challenge for adapting to novel scenarios. It is increasingly difficult to improve models for new situations using a single monolithic model. To address this issue, we introduce the concept of dynamically enhancing a basic driving planner with local driving data, without permanently modifying the planner itself. This approach, termed the Dynamically Local-Enhancement (DLE) Planner, aims to improve the scalability of autonomous driving systems without significantly expanding the planner's size. Our approach introduces a position-varying Markov Decision Process formulation coupled with a graph neural network that extracts region-specific driving features from local observation data. The learned features describe the local behavior of the surrounding objects, which is then leveraged to enhance a basic reinforcement learning-based policy. We evaluated our approach in multiple scenarios and compared it with a one-for-all driving model. The results show that our method outperforms the baseline policy in both safety (collision rate) and average reward, while maintaining a lighter scale. This approach has the potential to benefit large-scale autonomous vehicles without the need for largely expanding on-device driving models.

Weitao Zhou, Zhong Cao, Nanshan Deng et al.

Self-driving vehicles (SDVs) are becoming reality but still suffer from "long-tail" challenges during natural driving: the SDVs will continually encounter rare, safety-critical cases that may not be included in the dataset they were trained. Some safety-assurance planners solve this problem by being conservative in all possible cases, which may significantly affect driving mobility. To this end, this work proposes a method to automatically adjust the conservative level according to each case's "long-tail" rate, named dynamically conservative planner (DCP). We first define the "long-tail" rate as an SDV's confidence to pass a driving case. The rate indicates the probability of safe-critical events and is estimated using the statistics bootstrapped method with historical data. Then, a reinforcement learning-based planner is designed to contain candidate policies with different conservative levels. The final policy is optimized based on the estimated "long-tail" rate. In this way, the DCP is designed to automatically adjust to be more conservative in low-confidence "long-tail" cases while keeping efficient otherwise. The DCP is evaluated in the CARLA simulator using driving cases with "long-tail" distributed training data. The results show that the DCP can accurately estimate the "long-tail" rate to identify potential risks. Based on the rate, the DCP automatically avoids potential collisions in "long-tail" cases using conservative decisions while not affecting the average velocity in other typical cases. Thus, the DCP is safer and more efficient than the baselines with fixed conservative levels, e.g., an always conservative planner. This work provides a technique to guarantee SDV's performance in unexpected driving cases without resorting to a global conservative setting, which contributes to solving the "long-tail" problem practically.

Weitao Zhou, Zhong Cao, Nanshan Deng et al.

Deep reinforcement learning (DRL) has emerged as a promising approach for developing more intelligent autonomous vehicles (AVs). A typical DRL application on AVs is to train a neural network-based driving policy. However, the black-box nature of neural networks can result in unpredictable decision failures, making such AVs unreliable. To this end, this work proposes a method to identify and protect unreliable decisions of a DRL driving policy. The basic idea is to estimate and constrain the policy's performance uncertainty, which quantifies potential performance drop due to insufficient training data or network fitting errors. By constraining the uncertainty, the DRL model's performance is always greater than that of a baseline policy. The uncertainty caused by insufficient data is estimated by the bootstrapped method. Then, the uncertainty caused by the network fitting error is estimated using an ensemble network. Finally, a baseline policy is added as the performance lower bound to avoid potential decision failures. The overall framework is called uncertainty-bound reinforcement learning (UBRL). The proposed UBRL is evaluated on DRL policies with different amounts of training data, taking an unprotected left-turn driving case as an example. The result shows that the UBRL method can identify potentially unreliable decisions of DRL policy. The UBRL guarantees to outperform baseline policy even when the DRL policy is not well-trained and has high uncertainty. Meanwhile, the performance of UBRL improves with more training data. Such a method is valuable for the DRL application on real-road driving and provides a metric to evaluate a DRL policy.

Weilin Liu, Ye Mu, Chao Yu et al.

Discovering hazardous scenarios is crucial in testing and further improving driving policies. However, conducting efficient driving policy testing faces two key challenges. On the one hand, the probability of naturally encountering hazardous scenarios is low when testing a well-trained autonomous driving strategy. Thus, discovering these scenarios by purely real-world road testing is extremely costly. On the other hand, a proper determination of accident responsibility is necessary for this task. Collecting scenarios with wrong-attributed responsibilities will lead to an overly conservative autonomous driving strategy. To be more specific, we aim to discover hazardous scenarios that are autonomous-vehicle responsible (AV-responsible), i.e., the vulnerabilities of the under-test driving policy. To this end, this work proposes a Safety Test framework by finding Av-Responsible Scenarios (STARS) based on multi-agent reinforcement learning. STARS guides other traffic participants to produce Av-Responsible Scenarios and make the under-test driving policy misbehave via introducing Hazard Arbitration Reward (HAR). HAR enables our framework to discover diverse, complex, and AV-responsible hazardous scenarios. Experimental results against four different driving policies in three environments demonstrate that STARS can effectively discover AV-responsible hazardous scenarios. These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.

Haipeng Zhang, Zhong Cao, Ziang Yan et al.

For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting sufficient training samples could be time-consuming and expensive. To solve this problem, in this paper we propose a novel neural network architecture called Separating-Illumination Network (Sill-Net). Sill-Net learns to separate illumination features from images, and then during training we augment training samples with these separated illumination features in the feature space. Experimental results demonstrate that our approach outperforms current state-of-the-art methods in several object classification benchmarks.

Zhong Cao, Shaobing Xu, Songan Zhang et al.

Safeguard functions such as those provided by advanced emergency braking (AEB) can provide another layer of safety for autonomous vehicles (AV). A smart safeguard function should adapt the activation conditions to the driving policy, to avoid unnecessary interventions as well as improve vehicle safety. This paper proposes a driving-policy adaptive safeguard (DPAS) design, including a collision avoidance strategy and an activation function. The collision avoidance strategy is designed in a reinforcement learning framework, obtained by Monte-Carlo Tree Search (MCTS). It can learn from past collisions and manipulate both braking and steering in stochastic traffics. The driving-policy adaptive activation function should dynamically assess current driving policy risk and kick in when an urgent threat is detected. To generate this activation function, MCTS' exploration and rollout modules are designed to fully evaluate the AV's current driving policy, and then explore other safer actions. In this study, the DPAS is validated with two typical highway-driving policies. The results are obtained through and 90,000 times in the stochastic and aggressive simulated traffic. The results are calibrated by naturalistic driving data and show that the proposed safeguard reduces the collision rate significantly without introducing more interventions, compared with the state-based benchmark safeguards. In summary, the proposed safeguard leverages the learning-based method in stochastic and emergent scenarios and imposes minimal influence on the driving policy.

Yuhai Song, Zhong Cao, Kailun Wu et al.

The idea of unfolding iterative algorithms as deep neural networks has been widely applied in solving sparse coding problems, providing both solid theoretical analysis in convergence rate and superior empirical performance. However, for sparse nonlinear regression problems, a similar idea is rarely exploited due to the complexity of nonlinearity. In this work, we bridge this gap by introducing the Nonlinear Learned Iterative Shrinkage Thresholding Algorithm (NLISTA), which can attain a linear convergence under suitable conditions. Experiments on synthetic data corroborate our theoretical results and show our method outperforms state-of-the-art methods.