IliaLarchenko/behavior-1k-solution
1st place solution of 2025 BEHAVIOR Challenge
This project provides a leading solution for training robots to perform complex household tasks, like making popcorn or watering plants, based on visual and physical feedback. It takes in demonstration data of these tasks (images and robot movements) and outputs a trained policy that enables a robot to successfully replicate these actions. Roboticists, AI researchers, and developers working on embodied AI would use this to advance robot autonomy.
254 stars.
Use this if you are a roboticist or AI researcher aiming to train robots for intricate, multi-stage manipulation tasks in simulated or real-world environments.
Not ideal if you are looking for a general-purpose robotic control library without specific interest in vision-language-action models or complex task execution.
Stars
254
Forks
29
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 24, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/IliaLarchenko/behavior-1k-solution"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
ShusenTang/BDC2019
2019中国高校计算机大赛——大数据挑战赛 第三名解决方案
fire717/hualubei2020-callingsmoking
2020中国华录杯·数据湖算法大赛—定向算法赛（吸烟打电话检测）决赛第二名开源
aasu14/Data-Science-Hackathon-And-Competition
Grandmaster in MachineHack (3rd Rank Best) | Top 70 in AnalyticsVidya & Zindi | Expert at Kaggle...
rbouadjenek/deakin-ai-challenge2023
The Deakin Simpsons challenge 2023 is a computer vision competition that is designed to provide...
seculayer/AutoAPE-challenge2
Kaggle 2차년도(2021)