Learning hierarchical relationships for object-goal navigation

Abstract

Direct search for objects as part of navigation poses a challenge for small items. Utilizing context in the form of object-object relationships enable hierarchical search for targets efficiently. Most of the current approaches tend to directly incorporate sensory input into a reward-based learning approach, without learning about object relationships in the natural environment, and thus generalize poorly across domains. We present Memory-utilized Joint hierarchical Object Learning for Navigation in Indoor Rooms (MJOLNIR), a target-driven navigation algorithm, which considers the inherent relationship between target objects, and the more salient contextual objects occurring in its surrounding. Extensive experiments conducted across multiple environment settings show an $82.9\%$ and $93.5\%$ gain over existing state-of-the-art navigation methods in terms of the success rate (SR), and success weighted by path length (SPL), respectively. We also show that our model learns to converge much faster than other algorithms, without suffering from the well-known overfitting problem. Additional details regarding the supplementary material and code are available at https://sites.google.com/eng.ucsd.edu/mjolnir.

arXiv commentPaper accepted at CoRL-2020

References in corpus (7)

• Semi-Supervised Classification with Graph Convolutional Networks
• On Evaluation of Embodied Navigation Agents
• AI2-THOR: An Interactive 3D Environment for Visual AI
• Challenges of Real-World Reinforcement Learning
• Benchmarking Classic and Learned Navigation in Complex 3D Environments
• Visual Semantic Navigation using Scene Priors
• To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments

Cited by in corpus (5)

• 3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs
• Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance
• Shaping embodied agent behavior with activity-context priors from egocentric video
• Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge
• Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph