arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.07481cs.RO
收藏

使用图像内容弥合Sim2Real差距,实现端到端自动驾驶任务

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving

Ola Electric(奥拉电气)

Unnikrishnan R Nair, Sarthak Sharma, Udit Singh Parihar, Midhun S Menon, Srikanth Vidapanakal

摘要:

我们为NeurIPS 2021 - AWS Deepracer挑战赛颁发了一等奖解决方案。在这次比赛中,任务是训练一个强化学习代理(即自动驾驶汽车),它通过与环境(模拟轨道)交互来学习驾驶,通过在给定状态下采取行动来最大化预期奖励。然后,该模型在现实世界的赛道上使用微型AWS Deepracer汽车进行测试。我们的目标是训练出一个能在不脱离赛道的情况下尽可能快地完成一圈的模特。Deepracer挑战赛是自动驾驶汽车领域一系列具身智能竞赛的一部分,称为AI驾驶奥运会(AI-DO)。AI-DO的总体目标是提供可访问的机制,用于对应用于自动驾驶任务的自动驾驶进展进行基准测试。这个挑战的棘手部分是学习技能的sim 2 real转移。为了减少观测空间中的域间隙,除了裁剪掉不必要的背景信息之外,我们还做了一个谨慎的边缘检测。我们将该问题建模为行为克隆任务,并使用MLP-MIXER来优化运行时。我们通过仔细过滤训练数据来确保我们的模型能够处理控制噪声,这给了我们一个鲁棒的模型,即使50%的命令被随机改变,也能够完成跟踪。该模型的整体运行时间在现代CPU上仅为2- 3 ms。

英文摘要:

We present the first prize solution to NeurIPS 2021 - AWS Deepracer Challenge. In this competition, the task was to train a reinforcement learning agent (i.e. an autonomous car), that learns to drive by interacting with its environment, a simulated track, by taking an action in a given state to maximize the expected reward. This model was then tested on a real-world track with a miniature AWS Deepracer car. Our goal is to train a model that can complete a lap as fast as possible without going off the track. The Deepracer challenge is a part of a series of embodied intelligence competitions in the field of autonomous vehicles, called The AI Driving Olympics (AI-DO). The overall objective of the AI-DO is to provide accessible mechanisms for benchmarking progress in autonomy applied to the task of autonomous driving. The tricky section of this challenge was the sim2real transfer of the learned skills. To reduce the domain gap in the observation space we did a canny edge detection in addition to cropping out of the unnecessary background information. We modeled the problem as a behavioral cloning task and used MLP-MIXER to optimize for runtime. We made sure our model was capable of handling control noise by careful filtration of the training data and that gave us a robust model capable of completing the track even when 50% of the commands were randomly changed. The overall runtime of the model was only 2-3ms on a modern CPU.

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。

↑