arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.11728cs.LGcs.RO
收藏

PITA:物理信息轨迹自编码器

PITA: Physics-Informed Trajectory Autoencoder

Karlsruhe Institute for Technology(卡尔斯鲁厄理工学院);Research Center for Information Technology(信息技术研究中心)

Johannes Fischer, Kevin Rösch, Martin Lauer, Christoph Stiller

AI总结:

针对生成轨迹缺乏物理合理性的问题,提出物理信息轨迹自编码器PITA,将物理动力学模型融入损失函数,生成平滑且符合物理规律的轨迹,并在真实车辆轨迹数据集上验证其优于普通和行动空间自编码器。

摘要:

在安全关键应用中验证机器人系统需要在许多场景中进行测试,包括那些不太可能发生的罕见边缘情况,这要求将真实世界测试与仿真测试相结合。生成模型可以通过在学习的潜在空间中采样,用生成的数据增强真实世界数据集,以产生边缘情况场景。自编码器可以通过学习从低维中间表示重建输入数据,从而学习特定领域的潜在表示。然而,生成的轨迹不一定在物理上合理,而是通常包含输入轨迹中不存在的噪声。为解决这一问题,我们提出了新颖的物理信息轨迹自编码器(PITA)架构,该架构将物理动力学模型纳入自编码器的损失函数中。这产生了平滑的轨迹,这些轨迹不仅重建了输入轨迹,而且遵循物理模型。我们在真实世界的车辆轨迹数据集上评估了PITA,并将其性能与普通自编码器和最先进的行动空间自编码器进行了比较。

英文摘要:

Validating robotic systems in safety-critical appli-cations requires testing in many scenarios including rare edgecases that are unlikely to occur, requiring to complement real-world testing with testing in simulation. Generative models canbe used to augment real-world datasets with generated data toproduce edge case scenarios by sampling in a learned latentspace. Autoencoders can learn said latent representation for aspecific domain by learning to reconstruct the input data froma lower-dimensional intermediate representation. However, theresulting trajectories are not necessarily physically plausible, butinstead typically contain noise that is not present in the inputtrajectory. To resolve this issue, we propose the novel Physics-Informed Trajectory Autoencoder (PITA) architecture, whichincorporates a physical dynamics model into the loss functionof the autoencoder. This results in smooth trajectories that notonly reconstruct the input trajectory but also adhere to thephysical model. We evaluate PITA on a real-world dataset ofvehicle trajectories and compare its performance to a normalautoencoder and a state-of-the-art action-space autoencoder.

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。

↑