arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.11467cs.MA
收藏

自动驾驶车辆的适应性决策:交互环境中的学习增强博弈论方法

Adaptive Decision-Making for Autonomous Vehicles: A Learning-Enhanced Game-Theoretic Approach in Interactive Environments

Heye Huang, Jinxin Liu, Guanya Shi, Shiyue Zhao, Boqi Li, Jianqiang Wang

AI总结:

本文提出一种基于非合作博弈论和最大熵逆强化学习的自适应决策方法,通过在线参数学习使自动驾驶车辆在交互环境中实现高类人行为决策,实验验证相似率达81.73%。

摘要:

本文提出了一种面向自动驾驶车辆(AVs)的自适应行为决策方法,重点关注复杂的汇入场景。利用非合作博弈论原理,我们开发了一个车辆交互行为模型,该模型定义了关键交通要素并整合了多因素奖励函数。采用最大熵逆强化学习(IRL)进行行为模型参数优化。利用交互行为特征向量和车辆交互模型输出的行为概率,可以获得最优匹配参数。此外,提出了一种适应动态环境的行为决策方法。通过建立多个环境变量与模型参数之间的映射模型,该方法实现了参数的在线学习和识别,并能够输出自动驾驶车辆的交互行为概率。利用自然驾驶数据集(highD和exiD)和实车测试数据进行的定量分析验证了该模型与人类决策的高度一致性。在188个测试的交互场景中,平均类人相似率为81.73%,其中在highD数据集中达到了显著的83.12%。此外,在145个动态交互中,该方法与人类决策的匹配率为77.12%,包含6913个一致实例。在实车测试中,获得了72.73%的相似率和0%的安全违规率。结果表明,我们提出的方法能够有效使自动驾驶车辆在交互环境中做出明智的自适应行为决策。

英文摘要:

This paper proposes an adaptive behavioral decision-making method for autonomous vehicles (AVs) focusing on complex merging scenarios. Leveraging principles from non-cooperative game theory, we develop a vehicle interaction behavior model that defines key traffic elements and integrates a multifactorial reward function. Maximum entropy inverse reinforcement learning (IRL) is employed for behavior model parameter optimization. Optimal matching parameters can be obtained using the interaction behavior feature vector and the behavior probabilities output by the vehicle interaction model. Further, a behavioral decision-making method adapted to dynamic environments is proposed. By establishing a mapping model between multiple environmental variables and model parameters, it enables parameters online learning and recognition, and achieves to output interactive behavior probabilities of AVs. Quantitative analysis employing naturalistic driving datasets (highD and exiD) and real-vehicle test data validates the model's high consistency with human decision-making. In 188 tested interaction scenarios, the average human-like similarity rate is 81.73%, with a notable 83.12% in the highD dataset. Furthermore, in 145 dynamic interactions, the method matches human decisions at 77.12%, with 6913 consistence instances. Moreover, in real-vehicle tests, a 72.73% similarity with 0% safety violations are obtained. Results demonstrate the effectiveness of our proposed method in enabling AVs to make informed adaptive behavior decisions in interactive environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑