RT-1
Google Research / Robotics at Google
Scales instruction-conditioned robotic control with a transformer that emits discretized actions. Source ↗
Research chronology
VLA model timeline
Trace the development of vision-language-action models, related policy methods and tactile extensions, from RT-1 to the most recent paper in this reviewed selection.
By RoboSkin.ai Editorial Team · Source review:
Dates below are the first arXiv submission dates linked in each entry, rather than code-release or conference dates. This curated chronology shares its records with the model comparison matrix. It includes related planners and policies where labeled and is not an exhaustive claim about the newest model worldwide.
PaLM-E
Grounds a language model in continuous observations for embodied reasoning and high-level planning. Source ↗
Diffusion Policy
Columbia University, Toyota Research Institute and MIT
Generates action sequences by conditional denoising; an influential visuomotor policy rather than a language-conditioned VLA. Source ↗
RT-2
Represents robot actions as text tokens to transfer vision-language knowledge into control. Source ↗
Octo
UC Berkeley, Stanford, Carnegie Mellon and Google DeepMind
Provides an adaptable generalist policy with a diffusion head and configurable observation / action spaces. Source ↗
OpenVLA
Stanford, UC Berkeley, Toyota Research Institute, Google DeepMind, Physical Intelligence and MIT
Makes a pretrained vision-language backbone available for robot action prediction and adaptation. Source ↗
RDT (RDT-1B)
Scales a diffusion transformer and unified action representation for bimanual manipulation. Source ↗
π0 (pi0)
Combines pretrained vision-language knowledge with flow matching for continuous action chunks. Source ↗
OpenVLA-OFT
Optimizes VLA fine-tuning with parallel decoding, action chunking and continuous-action regression. Source ↗
GR00T N1
Couples a vision-language reasoning module to a diffusion action module for humanoid control. Source ↗
π0.5 (pi0.5)
Studies open-world generalization through heterogeneous co-training and hierarchical action prediction. Source ↗
VTLA
Samsung R&D Institute China–Beijing, BAAI and Institute of Automation, Chinese Academy of Sciences
Applies preference learning to a vision–tactile–language policy for contact-rich insertion. Source ↗
SmolVLA
Hugging Face with Sorbonne University, valeo.ai and ENS Paris-Saclay collaborators
Explores a compact VLA and asynchronous inference using accessible robot hardware and community data. Source ↗
VLA-Touch
National University of Singapore
Adds tactile feedback at planning and execution levels without fine-tuning the base VLA. Source ↗
OmniVTLA
Paxini Tech. and Shanghai Jiao Tong University
Aligns heterogeneous tactile signals with vision and language for contact-aware action generation. Source ↗
ForceVLA2
Combines force-aware prompting and hybrid force–position action control for contact-rich tasks. Source ↗
ViTaR
not found — institutional affiliation in the reviewed paper / project
Constrains touch to bounded residual selection and scaling around a frozen foundation policy. Source ↗
Vela
Fudan University, Shanghai Innovation Institute, CUHK and NovaXBot
Represents future actions with adaptive-horizon curves instead of fixed-rate action chunks. Source ↗
Evidence and corrections
This is an editorial reading aid based on the linked primary sources. Results are author-reported; RoboSkin has not reproduced these model evaluations. Artifact availability and license terms can change.