Learning Semantic Priorities for Autonomous Target Search
Max Lodel, Nils Wilde, Robert Babuska, Javier Alonso-Mora
AI summary
Problem
Current semantic target search methods rely on large domain-specific datasets or computationally heavy foundation models, limiting adaptability to novel environments, while pure coverage exploration remains inefficient.
Approach
The method trains a semantic priority model from simulated expert waypoint interventions and integrates it into a combinatorial frontier planner that balances semantic guidance with guaranteed coverage.
Key results
- Framework for learning semantic priorities from expert interventions
- Novel combinatorial frontier planner prioritizing promising search locations
- Faster target recovery than coverage-driven exploration in unseen environments
- Robust performance across diverse simulated expert behaviors with minimal data
Why it matters
Provides a data-efficient, computationally lightweight alternative for autonomous search-and-rescue and inspection robots operating in unpredictable environments.
Abstract
The use of semantic features can improve the efficiency of target search in unknown environments for robotic search and rescue missions. Current target search methods rely on training with large datasets of similar domains, which limits the adaptability to diverse environments. However, human experts possess high-level knowledge about semantic relationships necessary to effectively guide a robot during target search missions in diverse and previously unseen environments. In this paper, we propose a target search method that leverages expert input to train a model of semantic priorities. By employing the learned priorities in a frontier exploration planner using combinatorial optimization, our approach achieves efficient target search driven by semantic features while ensuring robustness and complete coverage. The proposed semantic priority model is trained with several synthetic datasets of simulated expert guidance for target search. Simulation tests in previously unseen environments show that our method consistently achieves faster target recovery than a coverage- driven exploration planner.