Stubborn: A Strong Baseline for Indoor Object Navigation
This work provides a strong baseline for researchers in robotics and AI working on indoor navigation tasks, though it is incremental as it builds on existing map-based methods.
The paper tackles the problem of indoor object navigation by addressing key failure modes of prior methods, resulting in a baseline that surpasses previously published performance on the Habitat Challenge.
We present a strong baseline that surpasses the performance of previously published methods on the Habitat Challenge task of navigating to a target object in indoor environments. Our method is motivated from primary failure modes of prior state-of-the-art: poor exploration, inaccurate object identification, and agent getting trapped due to imprecise map construction. We make three contributions to mitigate these issues: (i) First, we show that existing map-based methods fail to effectively use semantic clues for exploration. We present a semantic-agnostic exploration strategy (called Stubborn) without any learning that surprisingly outperforms prior work. (ii) We propose a strategy for integrating temporal information to improve object identification. (iii) Lastly, due to inaccurate depth observation the agent often gets trapped in small regions. We develop a multi-scale collision map for obstacle identification that mitigates this issue.