Papers › Octo: An Open-Source Generalist Robot Policy

Octo: An Open-Source Generalist Robot Policy

20 May 2024arXiv:2405.12213archive 2025-07-28

Octo Model Team, Dibya Ghosh, Homer Walke, Karl Pertsch, Kevin Black, Oier Mees, Sudeep Dasari, Joey Hejna, Tobias Kreiman, Charles Xu, Jianlan Luo, You Liang Tan, Lawrence Yunliang Chen, Pannag Sanketi, Quan Vuong, Ted Xiao, Dorsa Sadigh, Chelsea Finn, Sergey Levine

Large policies pretrained on diverse robot datasets have the potential to transform robotic learning: instead of training new policies from scratch, such generalist robot policies may be finetuned with only a little in-domain data, yet generalize broadly. However, to be widely applicable across a range of robotic learning scenarios, environments, and tasks, such policies need to handle diverse sensors and action spaces, accommodate a variety of commonly used robotic platforms, and finetune readily and efficiently to new domains. In this work, we aim to lay the groundwork for developing open-source, widely applicable, generalist policies for robotic manipulation. As a first step, we introduce Octo, a large transformer-based policy trained on 800k trajectories from the Open X-Embodiment dataset, the largest robot manipulation dataset to date. It can be instructed via language commands or goal images and can be effectively finetuned to robot setups with new sensory inputs and action spaces within a few hours on standard consumer GPUs. In experiments across 9 robotic platforms, we demonstrate that Octo serves as a versatile policy initialization that can be effectively finetuned to new observation and action spaces. We also perform detailed ablations of design decisions for the Octo model, from architecture to training data, to guide future research on building generalist robot models.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Robot Manipulation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Robot Manipulation SimplerEnv-Google Robot Octo-Base Variant Aggregation 0.012 #9 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot Octo-Base Variant Aggregation-Move Near 0.031 #9 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot Octo-Base Variant Aggregation-Open/Close Drawer 0.011 #9 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot Octo-Base Variant Aggregation-Pick Coke Can 0.006 #9 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot Octo-Base Visual Matching 0.168 #9 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot Octo-Base Visual Matching-Move Near 0.042 #9 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot Octo-Base Visual Matching-Open/Close Drawer 0.227 #9 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Google Robot Octo-Base Visual Matching-Pick Coke Can 0.170 #9 of 9 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X Octo-Small Average 0.300 #3 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X Octo-Small Put Carrot on Plate 0.097 #3 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X Octo-Small Put Spoon on Towel 0.472 #3 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X Octo-Small Stack Green Block on Yellow Block 0.042 #3 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X Octo-Base Average 0.160 #4 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X Octo-Base Put Carrot on Plate 0.083 #4 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X Octo-Base Put Spoon on Towel 0.125 #4 of 7 Archive leaderboard report
Robot Manipulation SimplerEnv-Widow X Octo-Base Stack Green Block on Yellow Block 0.000 #4 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections