Data

Tools

Indexes

Applications

Experiments

Repos

An open API service providing repository metadata for many open source software ecosystems.

Topic: "ai2thor-environment"

allenai/savn

Learning to Learn how to Learn: Self-Adaptive Visual Navigation using Meta-Learning (https://arxiv.org/abs/1812.00971)

Language: Python - Size: 18.3 MB - Last synced at: about 1 month ago - Pushed at: over 5 years ago - Stars: 185 - Forks: 55

allenai/manipulathor

ManipulaTHOR, a framework that facilitates visual manipulation of objects using a robotic arm

Language: Jupyter Notebook - Size: 113 MB - Last synced at: about 1 year ago - Pushed at: about 2 years ago - Stars: 86 - Forks: 13

TheMTank/cups-rl

Customisable Unified Physical Simulations (CUPS) for Reinforcement Learning. Experiments run on the ai2thor environment (http://ai2thor.allenai.org/) e.g. using A3C, RainbowDQN and A3C_GA (Gated Attention multi-modal fusion) for Task-Oriented Language Grounding (tasks specified by natural language instructions) e.g. "Pick up the Cup or else"

Language: Python - Size: 55.2 MB - Last synced at: over 1 year ago - Pushed at: about 5 years ago - Stars: 44 - Forks: 7

allenai/robustnav

Evaluating pre-trained navigation agents under corruptions

Language: Python - Size: 15.6 MB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 25 - Forks: 3

SamsonYuBaiJian/actionet

3D household task-based dataset created using customised AI2-THOR.

Language: C# - Size: 49.5 MB - Last synced at: 12 months ago - Pushed at: about 3 years ago - Stars: 13 - Forks: 4

our-projects-github/Safe-Deep-Learning-Based-Global-Path-Planning-Using-a-Fast-Collision-Free-Path-Generator

Implementation of "Safe Deep Learning-Based Global Path Planning Using a Fast Collision-Free Path Generator". We present a global path planning method in this project which is based on an LSTM model that predicts safe paths for the desired start and goal points in an environment with polygonal obstacles, using a new loss function (MSE-NER).

Language: Jupyter Notebook - Size: 31.7 MB - Last synced at: about 2 years ago - Pushed at: about 2 years ago - Stars: 3 - Forks: 0

nsidn98/LLaMAR

Code for our paper LLaMAR: LM-based Long-Horizon Planner for Multi-Agent Robotics

Language: Jupyter Notebook - Size: 58.2 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0

shirin-chehelgami/Global-path-planning

Implementation of "Safe Deep Learning-Based Global Path Planning Using a Fast Collision-Free Path Generator". We present a global path planning method in this project which is based on an LSTM model that predicts safe paths for the desired start and goal points in an environment with polygonal obstacles, using a new loss function (MSE-NER).

Language: Jupyter Notebook - Size: 31.7 MB - Last synced at: about 2 years ago - Pushed at: about 2 years ago - Stars: 0 - Forks: 0

Related Topics
artificial-intelligence 3 reinforcement-learning 2 robotics 2 embodied-ai 2 rrt 2 path-planning 2 obstacle-avoidance 2 motion-planning 2 lstm-neural-networks 2 loss-functions 2 ai2-thor 2 a-star 2 bug-algorithms 2 global-path-planning 2 collision-avoidance 2 deep-learning 2 vision-language-model 1 simulated-environments 1 simulation 1 transfer-learning 1 wrapper 1 meta-learning 1 self-adaptive 1 computer-vision 1 deep-reinforcement-learning 1 search-and-rescue 1 embodied-vision 1 visual-navigation 1 manipulathor 1 large-language-models 1 object-manipulation 1 dataset 1 embodied-artificial-intelligence 1 icip 1 neural-network 1 neural-networks 1 a3c 1 agent 1 cup 1 cups 1 model-based 1 model-free 1 multi-task-learning 1 natural-language-instructions 1 natural-language-processing 1 openai-gym-interface 1 pytorch 1 rainbow 1