PointGoal Navigation
14 papers with code • 1 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in PointGoal Navigation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find PointGoal Navigation models and implementations
Habitat Platform
Most implemented papers
Habitat: A Platform for Embodied AI Research
facebookresearch/habitat-sim
•
•
ICCV 2019
We present Habitat, a platform for research in embodied artificial intelligence (AI).
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
facebookresearch/habitat-api
•
•
ICLR 2020
We leverage this scaling to train an agent for 2. 5 Billion steps of experience (the equivalent of 80 years of human experience) -- over 6 months of GPU-time training in under 3 days of wall-clock time with 64 GPUs.
Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?
facebookresearch/habitat-api
•
•
Second, we investigate the sim2real predictivity of Habitat-Sim for PointGoal navigation.
Learning to Explore using Active Neural SLAM
devendrachaplot/Neural-SLAM
•
•
ICLR 2020
The use of learning provides flexibility with respect to input modalities (in the SLAM module), leverages structural regularities of the world (in global policies), and provides robustness to errors in state estimation (in local policies).
Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
When compared to existing photorealistic 3D datasets such as Replica, MP3D, Gibson, and ScanNet, images rendered from HM3D have 20 - 85% higher visual fidelity w. r. t.
Learning to Move with Affordance Maps
In this paper, we combine the best of both worlds with a modular approach that learns a spatial representation of a scene that is trained to be effective when coupled with traditional geometric planners.
Auxiliary Tasks Speed Up Learning PointGoal Navigation
joel99/habitat-pointnav-aux
•
•
PointGoal Navigation is an embodied task that requires agents to navigate to a specified point in an unseen environment.
Large Batch Simulation for Deep Reinforcement Learning
shacklettbp/bps-nav
•
•
ICLR 2021
We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19, 000 frames of experience per second on a single GPU and up to 72, 000 frames per second on a single eight-GPU machine.
Out of the Box: Embodied Navigation in the Real World
In this work, we detail how to transfer the knowledge acquired in simulation into the real world.
Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck
nicogrande/habitat-pointnav-via-ib
•
•
Under this setting, the agent incurs a penalty for using this privileged information, encouraging the agent to only leverage this information when it is crucial to learning.
