TY - GEN
T1 - Exploitation-Guided Exploration for Semantic Embodied Navigation
AU - Wasserman, Justin
AU - Chowdhary, Girish
AU - Gupta, Abhinav
AU - Jain, Unnat
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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
AB - 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
UR - http://www.scopus.com/inward/record.url?scp=85202445683&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85202445683&partnerID=8YFLogxK
U2 - 10.1109/ICRA57147.2024.10610117
DO - 10.1109/ICRA57147.2024.10610117
M3 - Conference contribution
AN - SCOPUS:85202445683
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 2901
EP - 2908
BT - 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
Y2 - 13 May 2024 through 17 May 2024
ER -