Research on Perception and Decision-Making Methods for Autonomous Driving

Qinwen Qiu

doi:10.47297/taposatWSP2633-456914.20250606

PDF
Export
Share
Collection
Album

Research on Perception and Decision-Making Methods for Autonomous Driving

Volume 6, Issue 6

Views: 0 Downloads: 0

Research on Perception and Decision-Making Methods for Autonomous Driving
Research on Perception and Decision-Making Methods for Autonomous Driving
School of Management and engineering, Nanjing University, Industrial Intelligence and System Integration, Nanjing, Jiangsu, 210000, China
Vol. 6, Issue 6, Pages: 69-74(2025)
Published：30 June 2025
DOI：10.47297/taposatWSP2633-456914.20250606
Accepted：

Scan QR Code

Qiu Qinwen.Research on Perception and Decision-Making Methods for Autonomous Driving[J].Theory and Practice of Science and Technology,2025,06(06):69-74.
DOI：

Qiu Qinwen.Research on Perception and Decision-Making Methods for Autonomous Driving[J].Theory and Practice of Science and Technology,2025,06(06):69-74. DOI： 10.47297/taposatWSP2633-456914.20250606.

摘要

Abstract

Addressing the issues of insufficient perception robustness and limited decision-making real-time performance in autonomous driving systems under complex conditions (such as extreme weather and dynamic interactive environments)

this review focuses on the synergistic optimization of multi-modal perception fusion and deep reinforcement learning (DRL) technologies. First

we review the development of multimodal perception fusion technologies

including perception mechanisms

feature alignment

BEV mapping

and dynamic weighting mechanisms. We then analyze typical models

policy optimization

curriculum learning mechanisms

and practical deployment issues of deep reinforcement learning in autonomous driving decision-making. Finally

we systematically summarize the research progress of perception and decision-making collaborative systems. This review summarizes current mainstream methods

existing issues

and future development directions

providing a reference for research on intelligent autonomous driving systems.

关键词

Keywords

references

J. Zhang and S. Singh, "LOAM: Lidar Odometry and Mapping in Real-time," in Robotics: Science and Systems (RSS), 2014.

S. Lefèvre, D. Vasquez, and C. Laugier, "A survey on motion prediction and risk assessment for intelligent vehicles," in Robotics and Autonomous Systems, vol. 58 , no. 9 , pp. 1372 - 1385 , 2010 .

A. Kendall, M. Grimes, and R. Cipolla, "PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization," in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015.

Y. Zhou and O. Tuzel, "VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

Z. Liu et al., "BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation," in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

K. Chitta et al., "Multi-Modal Fusion Transformer for End-to-End Autonomous Driving," in Conference on Robot Learning (CoRL), 2021.

Mnih, V. et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533.

Lillicrap, T. P., et al. "Continuous control with deep reinforcement learning." ICML 2016.

Mnih, V., et al. "Asynchronous methods for deep reinforcement learning."ICML 2016.

Haarnoja, T., et al. "Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor." ICML 2018.

Florensa, C., et al."Automatic Goal Generation for Reinforcement Learning Agents."ICML 2017.

Finn, C., et al. "Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization." ICML 2016.

Van den Oord, A., et al. "Neural Discrete Representation Learning." NeurIPS 2017.

Tobin, J., et al. "Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World." IROS 2017.

Dalal, G., et al. "Safe Exploration in Continuous Action Spaces." AISTATS 2018.

Li, Y., et al."DeepFusion: Lidar-Camera Fusion via Depth-aware Gating for 3D Object Detection."CVPR 2022.

Philion, J., & Fidler, S."Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D."ECCV 2020.

Dosovitskiy, A., et al."CARLA: An Open Urban Driving Simulator."CoRL 2017.

Huang, Z., et al."BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via SpatiotemporalTransformers."ECCV 2022.

Chen, Z., et al."SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot."International Conference on Machine Learning (ICML), 2023.

Shalev-Shwartz, S., Shammah, S., Shashua, A."On a Formal Model of Safe and Scalable Self-driving Cars"Robotics: Science and Systems (RSS), 2018.

Zhou, B., et al."MetaDrive: Sim-to-Real Generalization via Task-Agnostic Meta-Learning"Robotics: Science and Systems (RSS), 2023.

Hawke, J., et al."GAIA-1: Generative World Model for Autonomous Driving" Wayve Technical Report, 2023.

Euro NCAP Test Protocol v3.1 Annex F (Table F.2, 2023).

Alert me when the article has been cited

Submit

Research on intelligent maintenance technology of eindustrial robot claw based on Internet of Things and deep reinforcement learning

Advantages and Challenges in BEV Algorithm Technology for Autonomous Vehicles from Environment Sensing

Research on Path Planning Algorithm Combining Deep Reinforcement Learning and Theta* Algorithm

CNN-based lane detection

Application of sensors in autonomous driving technology

Related Author

Jundan Wang University of Science and Technology Liaoning

Aobo Zhang University of Science and Technology Liaoning

Jikai Xin University of Science and Technology Liaoning

Baowei Yu University of Science and Technology Liaoning

Zhen Quan University of Science and Technology Liaoning

Yuexin Pan School of Sports Engineering, Beijing Sport University

Haoyang Qin School of Software, Shandong University

Yanliang Liu Wuhan University of Technology

Related Institution

University of Science and Technology Liaoning

School of Sports Engineering, Beijing Sport University

School of Software, Shandong University

Wuhan University of Technology

College of Energy and Electrical Engineering, Chang'an University

⁰