Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations

2024-01-22 · Zuojin Tang, Xiaoyu Chen, Yongqiang Li, Jianyu Chen

An intelligent driving system should dynamically formulate appropriate driving strategies based on the current environment and vehicle status while ensuring system security and reliability. However, methods based on reinforcement learning and imitation learning often suffer from high sample complexity, poor generalization, and low safety. To address these challenges, this paper introduces an efficient and generalized end-to-end autonomous driving system (EGADS) for complex and varied scenarios. The RL agent in our EGADS combines variational inference with normalizing flows, which are independent of distribution assumptions. This combination allows the agent to capture historical information relevant to driving in latent space effectively, thereby significantly reducing sample complexity. Additionally, we enhance safety by formulating robust safety constraints and improve generalization and performance by integrating RL with expert demonstrations. Experimental results demonstrate that, compared to existing methods, EGADS significantly reduces sample complexity, greatly improves safety performance, and exhibits strong generalization capabilities in complex urban scenarios. Particularly, we contributed an expert dataset collected through human expert steering wheel control, specifically using the G29 steering wheel.

📄 PDF Abstract BibTeX arXiv:2401.11792

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDeep Reinforcement LearningImitation Learningreinforcement-learningVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

InDRiVE: Intrinsic Disagreement based Reinforcement for Vehicle Exploration through Curiosity Driven Generalized World Model

2025-03-07 · Feeza Khan Khanzada, Jaerock Kwon

Model-based Reinforcement Learning (MBRL) has emerged as a promising paradigm for autonomous driving, where data efficiency and robustness are critical. Yet, existing solutions often rely on carefully crafted, task speci…

Autonomous Driving Collision Avoidance Model-based Reinforcement Learning

Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships

2020-11-09 · Xiaobai Ma, Jiachen Li, Mykel J. Kochenderfer, David Isele 외

Deep reinforcement learning (DRL) provides a promising way for learning navigation in complex autonomous driving scenarios. However, identifying the subtle cues that can indicate drastically different outcomes remains an…

Autonomous Driving Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning

2020-01-23 · Jianyu Chen, Shengbo Eben Li, Masayoshi Tomizuka

Unlike popular modularized framework, end-to-end autonomous driving seeks to solve the perception, decision and control problems in an integrated way, which can be more adapting to new scenarios and easier to generalize …

Autonomous Driving Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving

2026-03-25 · Pengxuan Yang, Yupeng Zheng, Deheng Qian, Zebin Xing 외 arxiv

We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 - achieving 80x speedup while main…

Reinforcement Learning Autonomous Driving Video Generation

WAD: A Deep Reinforcement Learning Agent for Urban Autonomous Driving

2021-08-27 · Arjit Sharma, Sahil Sharma

Urban autonomous driving is an open and challenging problem to solve as the decision-making system has to account for several dynamic factors like multi-agent interactions, diverse scene perceptions, complex road geometr…

Atari Games Autonomous Driving Decision Making Deep Reinforcement Learning+3