Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentation
This work addresses perception gaps in embodied AI for tasks such as object search, though it is incremental as it builds on existing methods.
The paper tackles the problem of overconfidence in perception models for embodied AI tasks like object search by introducing calibrated perception probabilities and uncertainty across aggregation and decision-making, resulting in methods that can be integrated with existing approaches without extra training cost.
Embodied AI has made significant progress acting in unexplored environments. However, tasks such as object search have largely focused on efficient policy learning. In this work, we identify several gaps in current search methods: They largely focus on dated perception models, neglect temporal aggregation, and transfer from ground truth directly to noisy perception at test time, without accounting for the resulting overconfidence in the perceived state. We address the identified problems through calibrated perception probabilities and uncertainty across aggregation and found decisions, thereby adapting the models for sequential tasks. The resulting methods can be directly integrated with pretrained models across a wide family of existing search approaches at no additional training cost. We perform extensive evaluations of aggregation methods across both different semantic perception models and policies, confirming the importance of calibrated uncertainties in both the aggregation and found decisions. We make the code and trained models available at https://semantic-search.cs.uni-freiburg.de.