Augmentron: Scalable Multi-View Visual Augmentation for Robot Learning
arXiv:2611.09145v1 Announce Type: cross Abstract: Robot policies trained on visually narrow demonstrations can become sensitive to environmental features that a…
言栖资讯收录 230829 篇 AI、开发与建站文章,按发布时间排序,支持搜索与按语言筛选。
arXiv:2611.09145v1 Announce Type: cross Abstract: Robot policies trained on visually narrow demonstrations can become sensitive to environmental features that a…
arXiv:2611.08946v1 Announce Type: cross Abstract: Frontier language models are increasingly deployed as agents, and how well an agent performs depends not only …
arXiv:2611.08578v1 Announce Type: cross Abstract: We propose, HaNDF, object-conditional neural distance fields as data-driven priors for modeling the plausible …
arXiv:2611.06817v2 Announce Type: cross Abstract: Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw…
arXiv:2611.09892v1 Announce Type: new Abstract: Recent work on robot manipulation has focused on specialist policies trained on demonstrations. We show that gen…
arXiv:2611.09888v1 Announce Type: new Abstract: Scenario-based simulation is central to evaluating autonomous-driving policies, but a scenario scripted before e…
arXiv:2611.09877v1 Announce Type: new Abstract: Tendon-driven continuum robots can reach through constrained spaces, but contact along their bodies is invisible…
arXiv:2611.09864v1 Announce Type: new Abstract: Loco-manipulation, which requires mobile manipulators to coordinate locomotion and manipulation over long horizo…
arXiv:2611.09794v1 Announce Type: new Abstract: When should a robot look at the cup, and when at the portafilter? Spatial-reasoning benchmarks evaluate whether …
arXiv:2611.09708v1 Announce Type: new Abstract: Wearable haptic interfaces deliver physical stimuli to the skin, yet perceived locations vary widely across user…
arXiv:2611.09684v1 Announce Type: new Abstract: Vision-language-action (VLA) policies have become a promising paradigm for end-to-end robot control, but their e…
arXiv:2611.09679v1 Announce Type: new Abstract: Particle image velocimetry (PIV) reconstructs a flow field from the motion of tracer particles but the reconstru…
arXiv:2611.09672v1 Announce Type: new Abstract: Vision-language-action (VLA) models typically generate actions in chunks, organizing continuous robot execution …
arXiv:2611.09670v1 Announce Type: new Abstract: Robots increasingly choose actions by searching against a reward model learned from human preferences, in model-…
arXiv:2611.09605v1 Announce Type: new Abstract: Humanoid whole-body control requires a robot to track diverse reference motions while maintaining balance under …
arXiv:2611.09584v1 Announce Type: new Abstract: Inertial odometry is a compelling approach to state estimation for agile quadrotor flight due to its affordabili…
arXiv:2611.09561v1 Announce Type: new Abstract: Autonomous 3D exploration with UAVs requires efficient target selection under limited flight time and onboard co…
arXiv:2611.09490v1 Announce Type: new Abstract: Non-contact fruit sizing from RGB-D imagery reaches sub-centimetre accuracy on workstation hardware, but in-fiel…
arXiv:2611.09468v1 Announce Type: new Abstract: Robotic handling of delicate fruit benefits from compliant contact and quantitative sensing of the mechanical in…
arXiv:2611.09376v1 Announce Type: new Abstract: A language model can repair a robot policy's lexical instruction grounding by editing just 65 token-embedding ro…