Splatsim: Zero-shot sim2real transfer of rgb manipulation policies using gaussian splatting

MN Qureshi, S Garg, F Yandun, D Held… - arxiv preprint arxiv …, 2024 - arxiv.org
Sim2Real transfer, particularly for manipulation policies relying on RGB images, remains a
critical challenge in robotics due to the significant domain shift between synthetic and real …

Flare: Achieving masterful and adaptive robot policies with large-scale reinforcement learning fine-tuning

J Hu, R Hendrix, A Farhadi, A Kembhavi… - arxiv preprint arxiv …, 2024 - arxiv.org
In recent years, the Robotics field has initiated several efforts toward building generalist
robot policies through large-scale multi-task Behavior Cloning. However, direct deployments …

Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks

J Zhang, K Wang, S Wang, M Li, H Liu, S Wei… - arxiv preprint arxiv …, 2024 - arxiv.org
A practical navigation agent must be capable of handling a wide range of interaction
demands, such as following instructions, searching objects, answering questions, tracking …

[PDF][PDF] The One RING: a Robotic Indoor Navigation Generalist

A Eftekhar, L Weihs, R Hendrix… - arxiv preprint arxiv …, 2024 - one-ring-policy.allen.ai
Modern robots vary significantly in shape, size, and sensor configurations used to perceive
and interact with their environments. However, most navigation policies are embodiment …

BEINGS: Bayesian Embodied Image-goal Navigation with Gaussian Splatting

W Meng, T Wu, H Yin, F Zhang - arxiv preprint arxiv:2409.10216, 2024 - arxiv.org
Image-goal navigation enables a robot to reach the location where a target image was
captured, using visual cues for guidance. However, current methods either rely heavily on …