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 2406.03769cs.LGcs.RO
收藏

物理赛道上的 DeepRacer:参数探索与性能评估

DeepRacer on Physical Track: Parameters Exploration and Performance Evaluation

Western Sydney University(西悉尼大学)

Sinan Koparan, Bahman Javadi

AI总结:

本文通过两组实验评估 AWS DeepRacer 在物理赛道上的表现,发现批量大小 128 与 Huber 损失更优,并指出物理环境中的物体避让仍是开放挑战。

摘要:

本文聚焦于 AWS DeepRacer 的物理赛道能力,并进行了两组独立实验。第一组实验(实验 I)重点评估超参数对物理环境的影响,系统地改变梯度下降批量大小、损失类型等超参数以及训练时间设置。第二组实验(实验 II)重点探索 AWS DeepRacer 在物理环境中的物体避让能力。研究发现,在模拟环境中,梯度下降批量大小较大的模型性能优于批量大小较小的模型;而在物理环境中,梯度下降批量大小为 128 似乎更为可取。同时发现,在模拟环境和物理环境中,使用 Huber 损失类型的模型均优于使用 MSE 损失类型的模型。最后,模拟环境中的物体避让表现似乎有效;然而,当将这些模型部署到物理环境时,避让物体面临明显挑战。因此,物理环境中的物体避让仍是一个有待解决的开放性问题。

英文摘要:

This paper focuses on the physical racetrack capabilities of AWS DeepRacer. Two separate experiments were conducted. The first experiment (Experiment I) focused on evaluating the impact of hyperparameters on the physical environment. Hyperparameters such as gradient descent batch size and loss type were changed systematically as well as training time settings. The second experiment (Experiment II) focused on exploring AWS DeepRacer object avoidance in the physical environment. It was uncovered that in the simulated environment, models with a higher gradient descent batch size had better performance than models with a lower gradient descent batch size. Alternatively, in the physical environment, a gradient descent batch size of 128 appears to be preferable. It was found that models using the loss type of Huber outperformed models that used the loss type of MSE in both the simulated and physical environments. Finally, object avoidance in the simulated environment appeared to be effective; however, when bringing these models to the physical environment, there was a pronounced challenge to avoid objects. Therefore, object avoidance in the physical environment remains an open challenge.

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。

↑