srama2512 / EPC-SSL
Environment Predictive Coding for Visual Navigation. ICLR 2022.
☆15Updated last year
Related projects ⓘ
Alternatives and complementary repositories for EPC-SSL
- Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation. CVPR 2022☆28Updated 2 years ago
- Official implementation of the NRNS paper☆35Updated 2 years ago
- PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning. CVPR 2022 (Oral).☆86Updated last year
- Awesome habitat top down map work 🤩☆13Updated 7 months ago
- [ICCV 2023] PEANUT: Predicting and Navigating to Unseen Targets☆42Updated 8 months ago
- ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings. NeurIPS 2022☆61Updated last year
- Code for training embodied agents using IL and RL finetuning at scale for ObjectNav☆55Updated last year
- RL training scripts for learning an agent using ProcTHOR.☆16Updated 7 months ago
- Code for reproducing the results of NeurIPS 2020 paper "MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation”☆46Updated 3 years ago
- ☆34Updated 2 years ago
- Habitat-Web is a web application to collect human demonstrations for embodied tasks on Amazon Mechanical Turk (AMT) using the Habitat sim…☆50Updated 2 years ago
- Python implementation of the paper Learning hierarchical relationships for object-goal navigation☆42Updated last year
- ☆39Updated last year
- [CVPR 2023] We propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices,…☆59Updated 5 months ago
- [ICRA 2021] SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation☆41Updated 3 years ago
- https://xgxvisnav.github.io/☆16Updated 11 months ago
- ☆29Updated 2 years ago
- [CVPR 2023] CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation☆109Updated last year
- Code for training embodied agents using imitation learning at scale in Habitat-Lab☆34Updated 2 years ago
- ☆32Updated 3 years ago
- Official implementation of GridMM: Grid Memory Map for Vision-and-Language Navigation (ICCV'23).☆62Updated 7 months ago
- ☆15Updated 4 months ago
- ☆23Updated 2 years ago
- ☆32Updated last year
- Teaching robots to respond to open-vocab queries with CLIP and NeRF-like neural fields☆155Updated 8 months ago
- Open Vocabulary Object Navigation☆40Updated last month
- ☆75Updated 2 years ago
- Official implementation of Learning from Unlabeled 3D Environments for Vision-and-Language Navigation (ECCV'22).☆34Updated last year
- Public release for "Explore until Confident: Efficient Exploration for Embodied Question Answering"☆35Updated 4 months ago
- Last-Mile Embodied Visual Navigation https://jbwasse2.github.io/portfolio/SLING/☆26Updated 2 years ago