HomeRobot Open Vocabulary Mobile Manipulation Challenge 2023 Participant Report (Team KuzHum)
This work addresses incremental improvements for mobile manipulation in robotics, specifically for participants in the HomeRobot challenge.
The paper tackled improving the baseline for the HomeRobot Open Vocabulary Mobile Manipulation Challenge by enhancing semantic segmentation, place skill policy, and high-level heuristics, resulting in a 2.4% overall success rate increase (sevenfold improvement) and 8.2% partial success rate boost (1.75 times improvement) on the test dataset, achieving third place in both simulation and real-world stages.
We report an improvements to NeurIPS 2023 HomeRobot: Open Vocabulary Mobile Manipulation (OVMM) Challenge reinforcement learning baseline. More specifically, we propose more accurate semantic segmentation module, along with better place skill policy, and high-level heuristic that outperforms the baseline by 2.4% of overall success rate (sevenfold improvement) and 8.2% of partial success rate (1.75 times improvement) on Test Standard split of the challenge dataset. With aforementioned enhancements incorporated our agent scored 3rd place in the challenge on both simulation and real-world stages.