Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Exploitation-Guided Exploration for Semantic Embodied Navigation

About

In the recent progress in embodied navigation and sim-to-robot transfer, modular policies have emerged as a de facto framework. However, there is more to compositionality beyond the decomposition of the learning load into modular components. In this work, we investigate a principled way to syntactically combine these components. Particularly, we propose Exploitation-Guided Exploration (XGX) where separate modules for exploration and exploitation come together in a novel and intuitive manner. We configure the exploitation module to take over in the deterministic final steps of navigation i.e. when the goal becomes visible. Crucially, an exploitation module teacher-forces the exploration module and continues driving an overridden policy optimization. XGX, with effective decomposition and novel guidance, improves the state-of-the-art performance on the challenging object navigation task from 70% to 73%. Along with better accuracy, through targeted analysis, we show that XGX is also more efficient at goal-conditioned exploration. Finally, we show sim-to-real transfer to robot hardware and XGX performs over two-fold better than the best baseline from simulation benchmarking. Project page: xgxvisnav.github.io

Justin Wasserman, Girish Chowdhary, Abhinav Gupta, Unnat Jain• 2023

Related benchmarks

TaskDatasetResultRank
Object Goal NavigationHM3D
Success Rate72.9
96
Object Goal NavigationHM3D v1 (val)
Success Rate (SR)72.9
65
Object NavigationHM3D (val)
SR72.9
26
Showing 3 of 3 rows

Other info

Follow for update