Learning Affordance Landscapes for Interaction Exploration in 3D Environments

Abstract

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/

arXiv commentTo be published in NeurIPS 2020

References in corpus (13)

• Solving Rubik's Cube with a Robot Hand
• The Replica Dataset: A Digital Replica of Indoor Spaces
• Matterport3D: Learning from RGB-D Data in Indoor Environments
• AI2-THOR: An Interactive 3D Environment for Visual AI
• Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
• Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
• Learning to Explore using Active Neural SLAM
• Episodic Curiosity through Reachability
• HoME: a Household Multimodal Environment
• Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
• VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning
• Learning to Move with Affordance Maps
• Bootstrapping Robotic Ecological Perception from a Limited Set of Hypotheses Through Interactive Perception

Cited by in corpus (5)

• Learning Generalizable Visual Representations via Interactive Gameplay
• Deep Affordance Foresight: Planning Through What Can Be Done in the Future
• Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion
• FAME: 3D Shape Generation via Functionality-Aware Model Evolution
• One-Shot Object Affordance Detection in the Wild