Aug 2026· Engineering Research Express· Vol 8· 0 citations· 31 references
Physics
TL;DR
A vision-based end-to-end autonomous parking framework trained through imitation learning that introduces a historical context fusion encoder to capture temporal dependencies from past vehicle motions, a dual-stream attention decoder to enhance interaction between scene features and trajectory representations, and kinematic-aware auxiliary losses to enforce smooth and feasible trajectory generation.
Abstract
Autonomous parking requires accurate perception, reliable trajectory generation, and physically feasible vehicle motion in highly constrained environments. Existing end-to-end parking methods mainly rely on single-frame scene understanding and often neglect temporal motion priors and vehicle kinematic characteristics, limiting their planning accuracy and deployment robustness. To address these limitations, this paper proposes a vision-based end-to-end autonomous parking framework trained through imitation learning. The proposed framework introduces a historical context fusion encoder to capture temporal dependencies from past vehicle motions, a dual-stream attention decoder to enhance interaction between scene features and trajectory representations, and kinematic-aware auxiliary losses to enforce smooth and feasible trajectory generation. These components jointly improve trajectory prediction accuracy while maintaining vehicle manoeuvrability in parking scenarios. Extensive experiments demonstrate that the proposed method achieves over 25% lower trajectory prediction error than the baseline model on the ParkingE2E dataset and attains an 89.84% parking success rate in closed-loop CARLA simulations. The results verify the effectiveness of combining temporal context modeling, attention-based feature interaction, and kinematic constraint learning for end-to-end autonomous parking.
Due to the absence of traffic signal control and the difficulty in accurately estimating the future movements of surrounding vehicles, autonomous vehicle decision-making faces challenges at unsignalized intersections. This study proposes a trajectory prediction-aided deep reinforcement learning framework. First, a composite prioritized replay mechanism is introduced into the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, jointly considering temporal-difference error and reward-based event severity to enhance critical-experience reuse. Second, a convolutional multi-layer long short-term memory (CM-LSTM) model predicts surrounding-vehicle trajectories through convolutional local-motion encoding and stacked LSTM temporal modeling, and the predicted trajectories are incorporated into the deep reinforcement learning state representation. A multi-objective reward function is designed to balance collision avoidance, passing efficiency, lane keeping, and task completion. In CARLA go-straight and left-turn tests, CLS-TD3 achieves success rates of 93.8% and 90.2%, collision rates of 2.5% and 4.2%, and average passing times of 5.18 s and 5.58 s. Compared with TD3, the success rates increase by 6.3 and 8.6 percentage points, while average passing times decrease by 18.8% and 20.5%. These results demonstrate that the proposed framework improves the safety and crossing efficiency of autonomous vehicle decision-making at unsignalized intersections.
Shufeng Wang, Yuhang Wang, Yongxin Lei et al.· Machines· 0 citations
A Stochastic Gating Decoder for multimodal latent variable sampling, adaptively fusing kinematics and data-driven paths to capture driver intention uncertainty while maintaining kinematic consistency is introduced.
Comprehensive experiments on the NGSIM dataset validate the proposed model, demonstrating robust performance across structured highway driving scenarios and both the accuracy and computational efficiency of the proposed architecture.
Yang Li, Chengqian Jin, Zhikang Li· IEEE Access· 0 citations
Autonomous navigation in cluttered environments is hampered by partial observability and dynamic constraints. This paper presents PILOT, a constraint-aware privileged imitation learning framework for vision-based end-to-end UAV motion planning under partial observability. The framework distills planning strategies from a computationally intensive optimal control expert into a student policy regularized toward safety and dynamic requirements via a dual-objective loss function. To mitigate partial observability, a spatiotemporal perception fusion module using a Temporal Convolutional Network (TCN) is developed to integrate historical depth images and odometry. This module infers task-relevant latent context from historical observations, enhancing spatial awareness beyond the instantaneous FOV without maintaining persistent map memory. A trajectory parameterization layer mapping network outputs to a structured trajectory, while enabling explicit continuity, dynamic-consistency, and obstacle soft penalties during training, encouraging constraint satisfaction for unseen observations without formal guarantees. Simulations on quadrotor and fixed-wing aircraft demonstrate that PILOT achieves performance comparable to the privileged expert while reducing computational overhead by over 80\%. Successful indoor and outdoor zero-shot deployment confirms the practical feasibility and cross-domain generalization of the planner.
Qingrui Zhang, Feng Xue, Xiang Zhou et al.· 0 citations
End-to-end models that map multimodal inputs directly to future trajectories/maneuvers have emerged as an increasingly prominent research paradigm in autonomous driving. This class of models includes both Vision-Language-Action models and trajectory-generative planners. Unlike classic machine learning applications, autonomous vehicles operate in safety-critical and interaction-intensive environments where traditional open-loop imitation of expert demonstrations is not sufficient to ensure reliability. In particular, small execution errors can accumulate over time, while recovery behaviors are scarce in training data. In addition, long-horizon objectives such as safety and driving comfort are not captured by pointwise labels either. These limitations have motivated a shift toward post-training techniques, which further refine driving policies beyond pure imitation. This survey presents a unified view of post-training for autonomous driving by defining its scope and organizing the existing literature into four major families based on the form of supervision they use. For each family, we discuss its capabilities, limitations, and open challenges. We aim to facilitate a systematic understanding of this emerging area and stimulate future research on reliable and efficient post-training for autonomous driving.A collection of related papers is available at https://github.com/RYNing/Awesome-Post-Training-In-Autonomous-Driving-Papers.
Ruining Yang, Muxing Wang, Yixiao Chen et al.· 1 citation
A large language model (LLM) enhanced differentiable trajectory planning framework for IoT-enabled autonomous driving is proposed and a surrounding agent centric data augmentation strategy is introduced to reorganize sur rounding agent trajectories as additional planning supervision, thereby improving the training distribution without collecting additional raw data.
Shihao Zhang, Jing Yang, Ziyu Song et al.· IEEE Internet of Things Jour...· 1 citation