Sequence-Agnostic Multi-Object Navigation

The Multi-Object Navigation (MultiON) task requires a robot to localize an instance (each) of multiple object classes. It is a fundamental task for an assistive robot in a home or a factory. Existing methods for MultiON have viewed this as a direct extension of Object Navigation (ON), the task of localising an instance of one object class, and are pre-sequenced, i. e. , the sequence in which the object classes are to be explored is provided in advance. This is a strong limitation in practical applications characterized by dynamic changes. This paper describes a deep reinforcement learning framework for sequence-agnostic MultiON based on an actor-critic architecture and a suitable reward specification. Our framework leverages past experiences and seeks to reward progress toward individual as well as multiple target object classes. We use photo-realistic scenes from the Gibson benchmark dataset in the AI Habitat 3D simulation environment to experimentally show that our method performs better than a pre-sequenced approach and a state of the art ON method extended to MultiON.

Authors

• Nandiraju Gireesh
• Ayush Agrawal
• Ahana Datta
• Snehasis Banerjee
• Mohan Sridharan
• Brojeshwar Bhowmick
• K. Madhava Krishna

Keywords

• Deep learning
• Solid modeling
• Three-dimensional displays
• Automation
• Navigation
• Reinforcement learning
• Benchmark testing
• Habitat
• Object Classification
• Multiple Objects
• Target Object
• Deep Learning Framework
• Deep Reinforcement Learning
• Navigation Task
• Deep Reinforcement Learning Framework
• Reduction In The Number
• Path Length
• Convolutional Layers
• Output Layer
• Qualitative Results
• Home Environment
• Shortest Path
• Point Cloud
• Long-term Goals
• Local Domain
• Actor Network
• Reward Function
• Class Instances
• Semantic Map
• Encoder Network
• Number Of Time Steps
• Object Instances
• Standard Performance Measures
• Critic Network
• Replay Buffer
• Specific Objectives
• Deep Reinforcement Learning Method
• Multi-object navigation
• Assistive robot
• Cognitive Robotics