microsoft / COMPASS
COntrastive Multimodal Pretraining for AutonomouS Systems
☆52Updated 2 years ago
Related projects: ⓘ
- Perception-Action Causal Transformer☆58Updated last year
- BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robot…☆110Updated last year
- ☆40Updated 3 years ago
- ☆59Updated 2 years ago
- ☆56Updated last year
- Spot Sim2Real Infrastructure☆64Updated this week
- GRADE: Generating Animated Dynamic Environments for Robotics Research☆38Updated 11 months ago
- Implementation of Sim2Seg (John So*, Amber Xie*, Sunggoo Jung, Jeffrey Edlund, Rohan Thakker, Ali-akbar Agha-mohammad, Pieter Abbeel, Ste…☆30Updated last year
- [ICCV 2021] Official implementation of "The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation"☆67Updated 6 months ago
- Reshaping Robot Trajectories Using Natural Language Commands: A Study of Multi-Modal Data Alignment Using Transformers☆56Updated last year
- Implementation of the Belief State Encoder / Decoder in the new breakthrough robotics paper from ETH Zürich☆59Updated 2 years ago
- ☆12Updated last year
- ☆54Updated 9 months ago
- ☆34Updated 2 years ago
- Galactic Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second☆81Updated last year
- ☆39Updated 2 years ago
- Offcial code for the ECCV2024 paper "Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities"☆11Updated last month
- Webpage☆16Updated 7 months ago
- Code to reproduce results in the paper "Learning to Predict Navigational Patterns from Partial Observations" (RA-L 2023)☆12Updated last year
- Teaching robots to respond to open-vocab queries with CLIP and NeRF-like neural fields☆153Updated 6 months ago
- unified multi-threading inferencing nodes for monocular 3D object detection, depth prediction and semantic segmentation☆33Updated 3 months ago
- Task planning over 3D scene graphs☆16Updated 2 years ago
- Detic + SAM for open-vocabulary object detection and segmentation.☆17Updated 3 months ago
- ☆53Updated 3 months ago
- Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"☆66Updated 2 months ago
- A repository to keep track of Deep Learning based methods for visual odometry (pull requests are always welcome)☆91Updated last year
- ☆18Updated last year
- An AddOn for AirSim that includes all the tools to integrate a cinema oriented camera☆21Updated 2 years ago
- ☆92Updated 3 weeks ago
- Repository for Deep Active Localization research and benchmarks☆35Updated 4 years ago