arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.00993cs.ROcs.LGcs.MA
收藏

MADRaS:多智能体驾驶模拟器

MADRaS : Multi Agent Driving Simulator

Indian Institute of Technology Kharagpur(印度理工学院卡拉格普尔分校);Microsoft(微软);University of Alberta(阿尔伯塔大学);Intel Labs, Intel(英特尔实验室,英特尔);Indian Institute of Technology Madras(印度理工学院马德拉斯分校)

Anirban Santara, Sohan Rudra, Sree Aditya Buridi, Meha Kaushik, Abhishek Naik, Bharat Kaul, Balaraman Ravindran

摘要:

在这项工作中,我们提出了MADRaS,一个开源的多智能体驾驶模拟器,用于自动驾驶的运动规划算法的设计和评估。MADRaS提供了一个用于构建各种公路和轨道驾驶场景的平台,其中多个驾驶代理可以使用强化学习和其他机器学习算法针对运动规划任务进行训练。MADRaS是建立在TORCS,一个开源的赛车模拟器。TORCS提供具有不同动态特性的各种汽车以及具有不同几何形状和表面特性的行驶轨道。MADRaS继承了TORCS的这些功能,并引入了对多智能体训练、车辆间通信、噪声观测、随机行为和自定义交通车辆的支持,这些车辆的行为可以通过编程来模拟现实世界中遇到的具有挑战性的交通条件。MADRaS可用于创建驾驶任务,其复杂性可沿八个轴以明确定义的步骤进行调整。这使得它特别适合课程和持续学习。MADRaS是轻量级的,它提供了一个方便的OpenAI Gym接口,用于独立控制每辆车。除了原始的转向加速制动控制模式的TORCS,MADRaS提供了一个分层的跟踪位置速度控制,可以用来实现更好的泛化。MADRaS使用多处理来运行每个代理作为一个并行过程,以提高效率,并与流行的强化学习库(如RLLib)集成良好。

英文摘要:

In this work, we present MADRaS, an open-source multi-agent driving simulator for use in the design and evaluation of motion planning algorithms for autonomous driving. MADRaS provides a platform for constructing a wide variety of highway and track driving scenarios where multiple driving agents can train for motion planning tasks using reinforcement learning and other machine learning algorithms. MADRaS is built on TORCS, an open-source car-racing simulator. TORCS offers a variety of cars with different dynamic properties and driving tracks with different geometries and surface properties. MADRaS inherits these functionalities from TORCS and introduces support for multi-agent training, inter-vehicular communication, noisy observations, stochastic actions, and custom traffic cars whose behaviours can be programmed to simulate challenging traffic conditions encountered in the real world. MADRaS can be used to create driving tasks whose complexities can be tuned along eight axes in well-defined steps. This makes it particularly suited for curriculum and continual learning. MADRaS is lightweight and it provides a convenient OpenAI Gym interface for independent control of each car. Apart from the primitive steering-acceleration-brake control mode of TORCS, MADRaS offers a hierarchical track-position -- speed control that can potentially be used to achieve better generalization. MADRaS uses multiprocessing to run each agent as a parallel process for efficiency and integrates well with popular reinforcement learning libraries like RLLib.

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。

↑