Octo Model Team Dibya Ghosh* ,1 Homer Walke* ,1 Karl Pertsch* ,1,2 Kevin Black* ,1 Oier Mees* ,1 Sudeep Dasari 3 Joey Hejna 2 Tobias Kreiman 1 Charles Xu 1 Jianlan Luo 1 You Liang Tan 1 Dorsa Sadigh 2 Chelsea Finn 2 Sergey Levine 1 *denotes equal contribution, listed in alphabetical order 1. UC Berkeley 2. Stanford University 3. Carnegie Mellon University Report Code Colab Weights We introduce Octo , our ongoing effort for building open-source, widely applicable generalist policies for robotic manipulation
The design of the Octo model emphasizes flexibility and scale: the model is designed to support a variety of commonly used robots, sensor configurations, and actions, while providing a generic and scalable recipe that can be trained on large amounts of data. Octo supports both natural language instructions and goal images, observation histories, and multi-modal action distributions via diffusion decoding. Furthermore, we designed Octo specifically to support efficient finetuning to new robot setups, includi
We train Octo on a mixture of 25 datasets from the Open X-Embodiment Dataset, a diverse collection of robot learning datasets. Our training mixture includes data from a variety of robot embodiments, scenes, and tasks. These datasets are heterogeneous not just in terms of the robot type, but also in the sensors (e.g., including or not including wrist cameras) and labels (e.g., including or not including language instructions).
Karl Pertsch
Sudeep Dasari
Kevin Black
Dibya Ghosh
Charles Xu
Homer Walke
Toby Kreiman
Kevin Black
Joey Hejna
Joey Hejna