Abstract | ||
---|---|---|
State-of-the-art approaches to ObjectGoal navigation rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Potential functions for ObjectGoal Navigation with Interaction-free learning (PONI), a modular approach that disentangles the skills of `where to look?' for an object and `how to navigate to (x, y)?'. Our key insight is that `where to look?' can be treated purely as a perception problem, and learned without environment interactions. To address this, we propose a network that predicts two complementary potential functions conditioned on a semantic map and uses them to decide where to look for an unseen object. We train the potential function network using supervised learning on a passive dataset of top-down semantic maps, and integrate it into a modular framework to perform ObjectGoal navigation. Experiments on Gibson and Matterport3D demonstrate that our method achieves the state-of-the-art for ObjectGoal navigation while incurring up to 1,600x less computational cost for training. |
Year | Venue | DocType |
---|---|---|
2022 | IEEE Conference on Computer Vision and Pattern Recognition | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Santhosh K. Ramakrishnan | 1 | 4 | 1.82 |
Devendra Singh Chaplot | 2 | 134 | 11.58 |
Ziad Al-Halah | 3 | 78 | 8.73 |
Jitendra Malik | 4 | 39445 | 3782.10 |
Kristen Grauman | 5 | 6258 | 326.34 |