Timezone: »

 
Poster
Learning Affordance Landscapes for Interaction Exploration in 3D Environments
Tushar Nagarajan · Kristen Grauman

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #740
in Poster Session 3 »

Embodied agents operating in human spaces must be able to master how their environment works: what objects can the agent use, and how can it use them? We introduce a reinforcement learning approach for exploration for interaction, whereby an embodied agent autonomously discovers the affordance landscape of a new unmapped 3D environment (such as an unfamiliar kitchen). Given an egocentric RGB-D camera and a high-level action space, the agent is rewarded for maximizing successful interactions while simultaneously training an image-based affordance segmentation model. The former yields a policy for acting efficiently in new environments to prepare for downstream interaction tasks, while the latter yields a convolutional neural network that maps image regions to the likelihood they permit each action, densifying the rewards for exploration. We demonstrate our idea with AI2-iTHOR. The results show agents can learn how to use new home environments intelligently and that it prepares them to rapidly address various downstream tasks like "find a knife and put it in the drawer." Project page: http://vision.cs.utexas.edu/projects/interaction-exploration/

Keywords: Online Learning · Deep Learning · Algorithms -> Multitask and Transfer Learning; Algorithms

Author Information

Tushar Nagarajan (UT Austin)
Kristen Grauman (University of Texas at Austin)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors