2023年10月17日 · GRIF enables a robot to utilize large amounts of unlabeled trajectory data to learn goal-conditioned policies, while providing a “language interface” to these policies via aligned language-goal task representations.

GRIF learns this representation structure explicitly through a contrastive task alignment term. Since task representations across language and image goal modalities have similar semantics, this approach allows us to use robot data collected without annotations to …

2024年9月2日 · 本文提出的方法名为“Goal Representations for Instruction Following”（GRIF），这是一种半监督学习策略，旨在解决机器人如何根据自然语言指令执行任务的问题。该方法特别关注如何在有限的标注数据和大量未标注数据的情况下，训练机器人执行复杂 …

GRIF learns manipulation skills conditioned on either language or image goal task representations. By aligning equivalent tasks, our approach is able to learn to follow instructions from a small labeled dataset of trajectories and a much larger unlabeled or autonomously collected dataset.

ANN based inverse dynamic model of the 6-PGK parallel robot manipulator. L Moldovan, A Gligor. International Journal of Computers Communications & Control 11 (1), 90-104, 2016. 18: ... Z Germán-Salló, HŞ Grif, A Gligor. Procedia Engineering 181, 1058-1063, 2017. 5: 2017: Hand posture mouse. HS Grif, Z German, A Gligor. Procedia Technology 19 ...

🤗 LeRobot aims to provide models, datasets, and tools for real-world robotics in PyTorch. The goal is to lower the barrier to entry to robotics so that everyone can contribute and benefit from sharing datasets and pretrained models.

2024年1月26日 · By aligning task representations across language and goal modalities, GRIF offers a versatile and robust solution for training generalist robots. While acknowledging current limitations, such as the handling of qualitative task instructions, the …

2020年10月24日 · In this paper, we propose a low-level sensor fusion 3D object detector that combines two Region of Interest (RoI) from radar and camera feature maps by a Gated RoI Fusion (GRIF) to perform robust vehicle detection.

This paper presents an inverse dynamic model estimation based on an artificial neural network of a complete new parallel robot manipulator prototype 6- PGK with six degrees of freedom, built at Petru

2023年10月2日 · We present a new platform for General Robot Intelligence Development (GRID) to address both of these issues. The platform enables robots to learn, compose and adapt skills to their physical capabilities, environmental constraints and goals. The platform addresses AI problems in robotics via foundation models that know the physical world.