Search

We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together. Based on the MAD paradigm, we design a multiple thinking (MT) model that leverages distinct thinking to abstract various meta-abilities. Our method decouples meta-abilities from three aspects: input, encoding, and reward while employing the multiple thinking collaboration (MTC) module to promote mutual cooperation between thinking. MAD introduces a novel qualitative and quantitative interpretability system for object navigation. Through extensive experiments on AI2-Thor and RoboTHOR, we demonstrate that our method outperforms state-of-the-art (SOTA) methods on both typical and zero-shot object navigation tasks., Comment: 17 pages

"Search for" or "Navigate to"? When finding an object, the two choices always come up in our subconscious mind. Before seeing the target, we search for the target based on experience. After seeing the target, we remember the target location and navigate to. However, recently methods in object navigation field almost only consider using object association to enhance "search for" phase while neglect the importance of "navigate to" phase. Therefore, this paper proposes the dual adaptive thinking (DAT) method to flexibly adjust the different thinking strategies at different navigation stages. Dual thinking includes search thinking with the object association ability and navigation thinking with the target location ability. To make the navigation thinking more effective, we design the target-oriented memory graph (TOMG) to store historical target information and the target-aware multi-scale aggregator (TAMSA) to encode the relative target position. We assess our methods on the AI2-Thor dataset. Compared with the state-of-the-art (SOTA) method, our method reports 10.8%, 21.5% and 15.7% increase in success rate (SR), success weighted by path length (SPL) and success weighted by navigation efficiency (SNE), respectively., Comment: 12 pages, ready for AAAI2023

In this paper, we are interested in the unbalanced assignment problem with constraints to agents. The modified Hungarian algorithm with dummy tasks and agents are most common methods to solve the unbalanced problem. However, it is impractical in the real scenarios sometimes since some tasks are unassigned actually using the above method. Instead, we propose a graph based twin cost matrices method with improved ant colony optimization algorithm to solve the assignment problem elegantly and uniformly. We start from the generation of the twin cost matrices, and modify the ant colony algorithm to be capable to assign tasks to agents with different numbers. Random mutation is conducted for the stable pheromones to help the ant colony keep diversity during the operation. Experiments demonstrates that using our proposed method to solve the unbalanced assignment problem can stably obtain better results than previous methods.