arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.00543cs.ROcs.CVcs.LG
收藏

VertiFormer:一种用于越野机器人移动性的数据高效多任务Transformer

VertiFormer: A Data-Efficient Multi-Task Transformer for Off-Road Robot Mobility

George Mason University(乔治梅森大学);DEVCOM Army Research Laboratory(DEVCOM陆军研究实验室);The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Mohammad Nazeri, Anuj Pokhrel, Alexandyr Card, Aniket Datar, Garrett Warnell, Xuesu Xiao

AI总结:

本文提出数据高效多任务Transformer模型VertiFormer,仅用一小时越野数据,通过可学习掩码建模与下一token预测同时完成位姿、动作和地形预测,支持正逆向运动动力学等多种越野移动任务,并在物理机器人上验证了其有效性。

摘要:

复杂的学习架构(例如Transformer)为机器人理解越野移动中复杂的车辆-地形运动动力学交互提供了独特的机会。虽然自然语言处理(NLP)和计算机视觉(CV)任务可以利用互联网规模的数据来训练Transformer,但通过物理机器人在越野地形上导航来获取真实世界的移动性数据十分困难。此外,在NLP和CV中专门为处理文本和图像数据而设计的训练技术可能并不适用于机器人移动性。在本文中,我们提出了VertiFormer,这是一种新颖的数据高效多任务Transformer模型,仅使用一小时的数据进行训练,以解决在极其崎岖、垂直挑战性的越野地形上将Transformer架构应用于机器人移动性所面临的挑战。具体而言,VertiFormer采用了一种新的可学习掩码建模和下一token预测范式来预测下一个位姿、动作和地形块,从而同时支持多种越野移动性任务,例如正向和逆向运动动力学建模。其非自回归设计缓解了自回归模型带来的计算瓶颈和误差传播问题。VertiFormer统一的模态表示还增强了对多样化时间映射和状态表示的学习,结合多个目标函数进一步提高了模型的泛化能力。我们的实验为在有限数据条件下有效利用Transformer进行越野机器人移动性提供了见解,并证明了我们高效训练的Transformer能够在物理移动机器人上支持多种越野移动性任务。

英文摘要:

Sophisticated learning architectures, e.g., Transformers, present a unique opportunity for robots to understand complex vehicle-terrain kinodynamic interactions for off-road mobility. While internet-scale data are available for Natural Language Processing (NLP) and Computer Vision (CV) tasks to train Transformers, real-world mobility data are difficult to acquire with physical robots navigating off-road terrain. Furthermore, training techniques specifically designed to process text and image data in NLP and CV may not apply to robot mobility. In this paper, we propose VertiFormer, a novel data-efficient multi-task Transformer model trained with only one hour of data to address such challenges of applying Transformer architectures for robot mobility on extremely rugged, vertically challenging, off-road terrain. Specifically, VertiFormer employs a new learnable masked modeling and next token prediction paradigm to predict the next pose, action, and terrain patch to enable a variety of off-road mobility tasks simultaneously, e.g., forward and inverse kinodynamics modeling. The non-autoregressive design mitigates computational bottlenecks and error propagation associated with autoregressive models. VertiFormer's unified modality representation also enhances learning of diverse temporal mappings and state representations, which, combined with multiple objective functions, further improves model generalization. Our experiments offer insights into effectively utilizing Transformers for off-road robot mobility with limited data and demonstrate our efficiently trained Transformer can facilitate multiple off-road mobility tasks onboard a physical mobile robot.

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。

↑