arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.04823cs.LGcs.AIcs.RO
收藏

面向城市环境自动驾驶的基于中层输入生成的分层生成对抗模仿学习

Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban Environments

Federal University of Santa Catarina(圣卡塔琳娜联邦大学)

Gustavo Claudio Karl Couto, Eric Aislan Antonelo

AI总结:

本文提出分层生成对抗模仿学习架构hGAIL,通过GAN生成鸟瞰视图中层表示并与GAIL联合训练,解决城市自动驾驶中从原始图像直接学习控制策略不稳定的问题,在CARLA中实现跨城市98%交叉口成功导航。

摘要:

为现实城市导航场景推导鲁棒控制策略并非易事。在端到端方法中,这些策略必须将来自车辆摄像头的高维图像映射为低级动作,例如转向和油门。虽然纯强化学习(RL)方法完全基于人工设计的奖励,但生成对抗模仿学习(GAIL)智能体在与环境交互的同时从专家演示中学习,这使得GAIL在难以推导奖励信号的任务(例如自动驾驶)上更具优势。然而,在RL任务中直接从原始图像训练深度网络已知是不稳定且困难的。为了解决这一问题,本工作提出了一种基于GAIL的分层架构(hGAIL),该架构将表示学习与驾驶任务解耦,以解决车辆的自主导航问题。所提出的架构由两个模块组成:一个GAN(生成对抗网络),用于生成抽象的中层输入表示,即车辆周围环境的鸟瞰视图(BEV);以及GAIL,它基于来自GAN的BEV预测作为输入来学习控制车辆。hGAIL能够在智能体与环境交互的同时学习策略和中层表示。我们在CARLA仿真环境中进行的实验表明,仅使用摄像头(没有BEV)的GAIL甚至无法学会该任务,而hGAIL在仅在一个城市上训练后,能够在训练阶段未使用的新城市中98%的交叉口成功自主导航。视频和代码可在以下网址获取:https://sites.google.com/view/hgail

英文摘要:

Deriving robust control policies for realistic urban navigation scenarios is not a trivial task. In an end-to-end approach, these policies must map high-dimensional images from the vehicle's cameras to low-level actions such as steering and throttle. While pure Reinforcement Learning (RL) approaches are based exclusively on engineered rewards, Generative Adversarial Imitation Learning (GAIL) agents learn from expert demonstrations while interacting with the environment, which favors GAIL on tasks for which a reward signal is difficult to derive, such as autonomous driving. However, training deep networks directly from raw images on RL tasks is known to be unstable and troublesome. To deal with that, this work proposes a hierarchical GAIL-based architecture (hGAIL) which decouples representation learning from the driving task to solve the autonomous navigation of a vehicle. The proposed architecture consists of two modules: a GAN (Generative Adversarial Net) which generates an abstract mid-level input representation, which is the Bird's-Eye View (BEV) from the surroundings of the vehicle; and the GAIL which learns to control the vehicle based on the BEV predictions from the GAN as input. hGAIL is able to learn both the policy and the mid-level representation simultaneously as the agent interacts with the environment. Our experiments made in the CARLA simulation environment have shown that GAIL exclusively from cameras (without BEV) fails to even learn the task, while hGAIL, after training exclusively on one city, was able to autonomously navigate successfully in 98% of the intersections of a new city not used in training phase. Videos and code available at: https://sites.google.com/view/hgail

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。

↑