arXiv subjects

Zejian Deng

Publications and source records attributed to Zejian Deng.

7 recordsLinked to original sources

arXiv2026

DRIFT: Driving Risk Inference via Field Transmission for Human-like Autonomous Driving

Risk fields offer spatially structured alternatives to scalar safety metrics. However, hand-crafted static risk field models struggle with occlusion and topology-driven propagation. We present DRIFT, a spatiotemporal risk field governed by an advection-diffusion-reaction partial differential equation (PDE), with an optional telegrapher term. DRIFT draws on three sources: anisotropic Gaussian kernels to capture velocity-induced risk, occlusion-aware latent hazards behind large vehicles, and topology-coupled merge-zone conflict pressure. We further introduce field-centric evaluation metrics to complement the existing Surrogate Safety Measures (SSMs), including Lane-Change Risk Differential, Temporal Anticipation Index, Occlusion Sensitivity Index, and Occlusion Response Latency. Experiments on real-world traffic datasets show that DRIFT reduces occlusion response latency and lowers the near-collision rate under occlusion compared with selected baselines in synthetic scenarios.

eess.SY↗

arXiv2026

Map-Agnostic And Interactive Safety-Critical Scenario Generation via Multi-Objective Tree Search

Generating safety-critical scenarios is essential for validating the robustness of autonomous driving systems, yet existing methods often struggle to produce collisions that are both realistic and diverse while ensuring explicit interaction logic among traffic participants. This paper presents a novel framework for traffic-flow level safety-critical scenario generation via multi-objective Monte Carlo Tree Search (MCTS). We reframe trajectory feasibility and naturalistic behavior as optimization objectives within a unified evaluation function, enabling the discovery of diverse collision events without compromising realism. A hybrid Upper Confidence Bound (UCB) and Lower Confidence Bound (LCB) search strategy is introduced to balance exploratory efficiency with risk-averse decision-making. Furthermore, our method is map-agnostic and supports interactive scenario generation with each vehicle individually powered by SUMO's microscopic traffic models, enabling realistic agent behaviors in arbitrary geographic locations imported from OpenStreetMap. We validate our approach across four high-risk accident zones in Hong Kong's complex urban environments. Experimental results demonstrate that our framework achieves an 85\% collision failure rate while generating trajectories with superior feasibility and comfort metrics. The resulting scenarios exhibit greater complexity, as evidenced by increased vehicle mileage and CO\(_2\) emissions. Our work provides a principled solution for stress testing autonomous vehicles through the generation of realistic yet infrequent corner cases at traffic-flow level.

cs.RO↗

arXiv2025

Generalizable Trajectory Prediction via Inverse Reinforcement Learning with Mamba-Graph Architecture

Accurate driving behavior modeling is fundamental to safe and efficient trajectory prediction, yet remains challenging in complex traffic scenarios. This paper presents a novel Inverse Reinforcement Learning (IRL) framework that captures human-like decision-making by inferring diverse reward functions, enabling robust cross-scenario adaptability. The learned reward function is utilized to maximize the likelihood of output by integrating Mamba blocks for efficient long-sequence dependency modeling with graph attention networks to encode spatial interactions among traffic agents. Comprehensive evaluations on urban intersections and roundabouts demonstrate that the proposed method not only outperforms various popular approaches in terms of prediction accuracy but also achieves 2.3 times higher generalization performance to unseen scenarios compared to other baselines, achieving adaptability in Out-of-Distribution settings that is competitive with fine-tuning.

cs.LG↗

arXiv2025

ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving

This paper presents ARTEMIS, an end-to-end autonomous driving framework that combines autoregressive trajectory planning with Mixture-of-Experts (MoE). Traditional modular methods suffer from error propagation, while existing end-to-end models typically employ static one-shot inference paradigms that inadequately capture the dynamic changes of the environment. ARTEMIS takes a different method by generating trajectory waypoints sequentially, preserves critical temporal dependencies while dynamically routing scene-specific queries to specialized expert networks. It effectively relieves trajectory quality degradation issues encountered when guidance information is ambiguous, and overcomes the inherent representational limitations of singular network architectures when processing diverse driving scenarios. Additionally, we use a lightweight batch reallocation strategy that significantly improves the training speed of the Mixture-of-Experts model. Through experiments on the NAVSIM dataset, ARTEMIS exhibits superior competitive performance, achieving 87.0 PDMS and 83.1 EPDMS with ResNet-34 backbone, demonstrates state-of-the-art performance on multiple metrics.

cs.RO↗

arXiv2025

CHARMS: A Cognitive Hierarchical Agent for Reasoning and Motion Stylization in Autonomous Driving

To address the challenge of insufficient interactivity and behavioral diversity in autonomous driving decision-making, this paper proposes a Cognitive Hierarchical Agent for Reasoning and Motion Stylization (CHARMS). By leveraging Level-k game theory, CHARMS captures human-like reasoning patterns through a two-stage training pipeline comprising reinforcement learning pretraining and supervised fine-tuning. This enables the resulting models to exhibit diverse and human-like behaviors, enhancing their decision-making capacity and interaction fidelity in complex traffic environments. Building upon this capability, we further develop a scenario generation framework that utilizes the Poisson cognitive hierarchy theory to control the distribution of vehicles with different driving styles through Poisson and binomial sampling. Experimental results demonstrate that CHARMS is capable of both making intelligent driving decisions as an ego vehicle and generating diverse, realistic driving scenarios as environment vehicles. The code for CHARMS is released at https://github.com/chuduanfeng/CHARMS.

cs.RO↗

arXiv2024

Multi-Agent Trajectory Prediction with Difficulty-Guided Feature Enhancement Network

Trajectory prediction is crucial for autonomous driving as it aims to forecast the future movements of traffic participants. Traditional methods usually perform holistic inference on the trajectories of agents, neglecting the differences in prediction difficulty among agents. This paper proposes a novel Difficulty-Guided Feature Enhancement Network (DGFNet), which leverages the prediction difficulty differences among agents for multi-agent trajectory prediction. Firstly, we employ spatio-temporal feature encoding and interaction to capture rich spatio-temporal features. Secondly, a difficulty-guided decoder controls the flow of future trajectories into subsequent modules, obtaining reliable future trajectories. Then, feature interaction and fusion are performed through the future feature interaction module. Finally, the fused agent features are fed into the final predictor to generate the predicted trajectory distributions for multiple participants. Experimental results demonstrate that our DGFNet achieves state-of-the-art performance on the Argoverse 1\&2 motion forecasting benchmarks. Ablation studies further validate the effectiveness of each module. Moreover, compared with SOTA methods, our method balances trajectory prediction accuracy and real-time inference speed.

cs.RO↗

arXiv2020

Reinforcement Learning-Enabled Decision-Making Strategies for a Vehicle-Cyber-Physical-System in Connected Environment

As a typical vehicle-cyber-physical-system (V-CPS), connected automated vehicles attracted more and more attention in recent years. This paper focuses on discussing the decision-making (DM) strategy for autonomous vehicles in a connected environment. First, the highway DM problem is formulated, wherein the vehicles can exchange information via wireless networking. Then, two classical reinforcement learning (RL) algorithms, Q-learning and Dyna, are leveraged to derive the DM strategies in a predefined driving scenario. Finally, the control performance of the derived DM policies in safety and efficiency is analyzed. Furthermore, the inherent differences of the RL algorithms are embodied and discussed in DM strategies.

eess.SP↗