kob0105/act_pusht is an open-source imitation-learning model for robotics, designed to predict short action chunks from teleoperated data. Below are 12 other ai apps with similar functionality to Act Pusht, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
act_DS3_1B1O_FV_removeidle_rand20 is an open-source model for robotic action chunking using imitation learning. It enables robotics researchers to implement and evaluate action chunking policies for efficient robot control.
act_task1_v2 is an open-source imitation learning policy for robotics, trained to predict action chunks from teleoperated data. It is designed for use with LeRobot and supports local inference and further training by robotics researchers and engineers.
act-hyak-test is an open-source imitation learning model for robotics, designed to predict action chunks from teleoperated data. It enables researchers and developers to run local inference and integrate advanced policy models into robotics workflows.
Pick1 Jenga1 Act is a model available on Hugging Face that implements Action Chunking with Transformers (ACT), an imitation-learning method for robotics. Rather than predicting individual action steps, ACT predicts short sequences of actions, referred to as action chunks. The model is trained using teleoperated data and is designed to enable policy inference and evaluation in robotics tasks. According to the evidence, Pick1 Jenga1 Act has been trained and uploaded to the Hugging Face Hub using LeRobot, and it can be used with various libraries, inference providers, notebooks, and local applications. The tool provides instructions for use with LeRobot, as well as compatibility with Google Colab and Kaggle notebooks. The model card mentions that users can train the model from scratch or evaluate its policy and run inference. Pick1 Jenga1 Act is released under the Apache 2.0 license. The model is intended for those working in robotics, particularly in contexts where learning from demonstration or teleoperation data is relevant. The documentation and guides referenced in the evidence provide resources for getting started with training and evaluation, but no further details about specific features, supported robotics platforms, or integration capabilities are provided. Pricing information is not mentioned, but the Apache 2.0 license indicates it is open source. Overall, Pick1 Jenga1 Act serves as an open-source imitation-learning model for robotics, focusing on predicting sequences of actions from teleoperated data, and is accessible through the Hugging Face platform.
act_subtask_g2 is an open-source model for imitation learning in robotics, focusing on predicting and executing short action chunks. It is intended for robotics researchers and developers who need to train or evaluate robotic policies using teleoperated data.
Act Policy is a model available on Hugging Face that implements Action Chunking with Transformers (ACT), an imitation learning approach designed to predict short sequences of actions, referred to as action chunks, rather than individual steps. The method is trained using teleoperated data, with the goal of achieving high success rates in robotic tasks. According to the evidence, this policy has been trained and uploaded to the Hugging Face Hub using LeRobot, a named library that can be used to train and run the model. The referenced robot type for this policy is 'omx_follower,' and it utilizes input from a camera labeled 'camera2.' The model is distributed under the Apache 2.0 license, making it open source. Users are provided with instructions for integrating the model with libraries, inference providers, notebooks, and local applications, with specific mentions of Google Colab and Kaggle as platforms where the model can be used. The evidence also points to documentation and guides for training and deploying the policy with LeRobot. No additional details about broader compatibility, pricing beyond the open-source license, or intended audience are explicitly stated in the evidence.
act_ego_1kitkat_hand_merge3_colabtest is an open-source robotics policy model for imitation learning and action chunking. It is designed for use with LeRobot and supports local inference for robotics research and development.
act_so101_pick_cube_v2 is an open-source imitation learning model designed for robotics applications. It predicts short action chunks for robots, enabling them to perform complex tasks by learning from teleoperated demonstrations. The model is available on Hugging Face under an Apache-2.0 license and can be integrated with robotics libraries such as LeRobot. It is intended for robotics researchers and developers seeking advanced policy models for robot control.
This Hugging Face model provides an imitation-learning policy for robotics, predicting action chunks from teleoperated data. It is open source and can be integrated into robotics workflows via API or CLI, supporting research and development in robotics automation.
act_so101_grasp_50_v2 is an open-source robotics model implementing Action Chunking with Transformers (ACT) for imitation learning. It predicts short action chunks from teleoperated data, helping robotics researchers and developers train and evaluate robotic policies efficiently. The model is available for use via Hugging Face and integrates with tools like LeRobot.
Task1 is a robotics policy model available on Hugging Face that implements Action Chunking with Transformers (ACT), an imitation learning approach designed to predict short sequences of actions, or action chunks, rather than individual steps. The model is trained using teleoperated data and is intended to achieve high success rates in robotic control tasks. Task1 has been trained and uploaded to the Hugging Face Hub, where it can be accessed and used with various libraries, including LeRobot, as well as through platforms such as Google Colab and Kaggle. The model is suitable for use with robots of type 'so_follower' and is compatible with side and window-side camera inputs. The model card provides information about the model’s inputs and outputs, training dataset, and configuration, as well as instructions for running the policy on a robot or training a custom policy. Task1 is distributed under the Apache-2.0 license, making it available for open-source use. The evidence does not specify further details about its intended audience or additional features beyond those mentioned.
topright-act is a transformer-based imitation-learning policy model for robotics, focused on action chunking. It allows robotics researchers and developers to implement and experiment with advanced policy learning techniques using open-source weights and documentation.
