Get the latest tech news
OpenVLA is an open-source generalist robotics model
DeepMind, Stanford, and UC Berkeley release OpenVLA, a generalist open-source robotics model that can perform tasks in diverse environments.
The model reasons over the instruction and the visual input and decides which sequence of action tokens will enable the robot to accomplish the desired task. The researchers also experimented with efficient fine-tuning strategies for VLAs on seven manipulation tasks spanning from object pick-and-place to cleaning a table. “Notably, most prior works achieve strong performance only in either narrow single-instruction or diverse multi-instruction tasks, resulting in widely varying success rates,” the researchers write.
Or read this on Venture Beat