Seer, a transformer-based PIDM pre-trained on large robotic datasets like DROID, outperforms prior methods on simulation and real-world robotic manipulation benchmarks with gains up to 43%.
Masked world models for visual control
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 2years
2024 2roles
background 1polarities
background 1representative citing papers
DP3 uses compact 3D representations from sparse point clouds inside diffusion policies to learn generalizable visuomotor skills from few demonstrations, reporting 24% gains in simulation and 85% success on real robots.
citing papers explorer
-
Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation
Seer, a transformer-based PIDM pre-trained on large robotic datasets like DROID, outperforms prior methods on simulation and real-world robotic manipulation benchmarks with gains up to 43%.
-
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
DP3 uses compact 3D representations from sparse point clouds inside diffusion policies to learn generalizable visuomotor skills from few demonstrations, reporting 24% gains in simulation and 85% success on real robots.