СледваСледващо ръководство
CLIP и Vision-Language модели
Визуален AI
РЪКОВОДСТВО за визуален AI
Vision-language-action (VLA) models condition robot actions on visual observations and language instructions.
Чуйте това ръководствоAI-разказан · ~2 min
The cited RT-2, π0, and Open X papers describe different architectures and evaluations.
Vision-language-action models condition robot actions on camera observations and language instructions. RT-2 represents robot actions as discretized tokens, including changes in end-effector position and rotation and gripper state. DeepMind co-fine-tuned a pretrained vision-language model using robotic data and web data, then reported more than 6,000 robotic evaluation trials. Its emergent-transfer examples concern the tested objects and instructions; they do not establish arbitrary task generalization. A separate system, π0, adds a flow-matching action expert that generates continuous action chunks. The paper reports control at frequencies up to 50 Hz for evaluated dexterous tasks such as laundry folding. Open X-Embodiment aggregates demonstrations from 22 robot embodiments to support cross-robot research. Dataset breadth, action representation and demonstrated transfer are different properties, each requiring evaluation in a specified setup.
Paper result: RT-2 represents discretized robot actions as tokens for a transformer.
Paper result: π0 uses a flow-matching action expert in its reported robot-control setup.
Paper resource: Open X-Embodiment aggregates demonstrations from multiple robot embodiments.
Illustrative: evaluate a trained policy on new objects only within a controlled, safe test protocol.
Evaluate VLA transfer on the target embodiment, objects, and instruction set. Report the robot, controls, and success criteria; results from one benchmark do not establish general-purpose deployment.
Безплатен бюлетин
Три проверени AI истории всяка делнична сутрин, написани на достъпен език. Безплатно завинаги, без реклами.
Един имейл всеки делничен ден. Отписване с едно кликване. Никога не продаваме и не споделяме вашия имейл адрес.
Тествайте себе си
Незабавна обратна връзка за всеки отговор и сертификат за споделяне с подлежащ на проверка идентификационен номер, след като преминете курс.
Подкрепете безплатното AI образование. AI Understanding е 501(c)(3) с нестопанска цел — без реклами, без платен достъп, никога. Направете дарение
Vision-language-action (VLA) models condition robot actions on visual observations and language instructions. The cited RT-2, π0, and Open X papers describe different architectures and evaluations.
VLA приема визия (изображения) плюс езикова цел и извежда действия (моторни команди), обединявайки възприятие, следване на инструкции и контрол.
RT-2 групира всяко измерение на действие в отделни символи (напр. 256 контейнера) и ги излъчва като низ, позволявайки на машината на езиковия модел да предвижда действия като думи.
RT-2 uses “emergent transfer” for evaluated cases where web-scale vision-language pretraining helped the robot respond to novel objects or instructions. This is a paper-scoped result, not a guarantee for arbitrary objects or commands.
The π0 paper reports chunked continuous actions from its flow-matching action expert at a 50 Hz control rate in the evaluated setup. This is a reported control detail, not a guarantee of better dexterity on every robot.
Open X-Embodiment aggregates robot demonstrations across multiple embodiments to support cross-robot research. Dataset diversity enables study; it does not guarantee that one policy transfers to every robot.
Продължавай да учиш
Още ръководства, избрани за тази тема
СледваСледващо ръководство
CLIP и Vision-Language модели
Визуален AI