Ram81

pirlnav

Code for training embodied agents using IL and RL finetuning at scale for ObjectNav

habitat-imitation-baselines

Code for training embodied agents using imitation learning at scale in Habitat-Lab

goat-bench

seeing-unseen

ram81.github.io

Portfolio

habitat-sim

frontier_exploration

Frontier exploration implemented in habitat

home-robot

Mobile manipulation research tools for roboticists

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

ovon

Open Vocabulary Object Navigation

zson

ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings. NeurIPS 2022

ai2thor

An open-source platform for Visual AI.

allenact

An open source framework for research in Embodied-AI from AI2.

custom_utils

env_utils

EvalAI

:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI

habitat-lab

A modular high-level library to train embodied AI agents across a variety of tasks, environments, and simulators.

habitat-web-sim

A flexible, high-performance 3D simulator for Embodied AI research.

harshm121.github.io

mmdetection

OpenMMLab Detection Toolbox and Benchmark

pointgoal-navigation

prior

🐍 A Python Package for Seamless Data Distribution in AI Workflows

procthor-100k

procthor-10k-hard-eval

procthor-1k

procthor-eval-generation

procthor-one-room

spot_rl_experiments

ViNL

Isaac Gym Environments for Legged Robots

vlar23_starter_code

Starter code with a baseline created using the SMART-101 codebase for testing the puzzles in the VLAR challenge.