arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.08712cs.LGcs.RO
收藏

CARNet:一种用于学习自动驾驶任务中潜在动力学的动态自动编码器

CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving Tasks

Georgia Institute of Technology(佐治亚理工学院);Ford Motor Company(福特汽车公司)

Andrey Pak, Hemanth Manjunatha, Dimitar Filev, Panagiotis Tsiotras

摘要:

自动驾驶在汽车行业受到了广泛关注,通常被视为交通运输的未来。配备有各种传感器的乘用车(例如,相机、前置雷达、LiDAR和IMU)变得越来越普遍。这些传感器提供了一系列高维、时间相关的数据,这对于可靠的自动驾驶至关重要。自动驾驶系统应该有效地使用从各种传感器收集的信息,以便形成对世界的抽象描述并保持态势感知。自动编码器等深度学习模型可以用于此目的,因为它们可以从传入数据流中学习紧凑的潜在表示。然而,大多数自动编码器模型独立地处理数据,而不假设任何时间上的相互依赖性。因此,需要在其架构中明确考虑数据的时间依赖性的深度学习模型。这项工作提出了CARNet,这是一种组合动态自动编码器网络架构,它利用自动编码器与递归神经网络相结合来学习当前的潜在表示,此外,还可以在自动驾驶的背景下预测未来的潜在表示。我们使用模拟和真实数据集在模仿和强化学习设置中证明了所提出的模型的有效性。我们的研究结果表明,该模型优于基线最先进的模型,同时具有显着更少的可训练参数。

英文摘要:

Autonomous driving has received a lot of attention in the automotive industry and is often seen as the future of transportation. Passenger vehicles equipped with a wide array of sensors (e.g., cameras, front-facing radars, LiDARs, and IMUs) capable of continuous perception of the environment are becoming increasingly prevalent. These sensors provide a stream of high-dimensional, temporally correlated data that is essential for reliable autonomous driving. An autonomous driving system should effectively use the information collected from the various sensors in order to form an abstract description of the world and maintain situational awareness. Deep learning models, such as autoencoders, can be used for that purpose, as they can learn compact latent representations from a stream of incoming data. However, most autoencoder models process the data independently, without assuming any temporal interdependencies. Thus, there is a need for deep learning models that explicitly consider the temporal dependence of the data in their architecture. This work proposes CARNet, a Combined dynAmic autoencodeR NETwork architecture that utilizes an autoencoder combined with a recurrent neural network to learn the current latent representation and, in addition, also predict future latent representations in the context of autonomous driving. We demonstrate the efficacy of the proposed model in both imitation and reinforcement learning settings using both simulated and real datasets. Our results show that the proposed model outperforms the baseline state-of-the-art model, while having significantly fewer trainable parameters.

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。

↑