TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making
This work addresses the challenge of complex real-world navigation tasks for embodied AI systems, though it appears incremental as it builds upon existing demand-driven navigation methods.
The paper tackles the problem of embodied AI navigation with multiple needs and personal choices by introducing TP-MDDN, a new benchmark, and AWMSystem, an autonomous decision-making system, which outperforms state-of-the-art baselines in perception accuracy and navigation robustness.
In daily life, people often move through spaces to find objects that meet their needs, posing a key challenge in embodied AI. Traditional Demand-Driven Navigation (DDN) handles one need at a time but does not reflect the complexity of real-world tasks involving multiple needs and personal choices. To bridge this gap, we introduce Task-Preferenced Multi-Demand-Driven Navigation (TP-MDDN), a new benchmark for long-horizon navigation involving multiple sub-demands with explicit task preferences. To solve TP-MDDN, we propose AWMSystem, an autonomous decision-making system composed of three key modules: BreakLLM (instruction decomposition), LocateLLM (goal selection), and StatusMLLM (task monitoring). For spatial memory, we design MASMap, which combines 3D point cloud accumulation with 2D semantic mapping for accurate and efficient environmental understanding. Our Dual-Tempo action generation framework integrates zero-shot planning with policy-based fine control, and is further supported by an Adaptive Error Corrector that handles failure cases in real time. Experiments demonstrate that our approach outperforms state-of-the-art baselines in both perception accuracy and navigation robustness.