Abstract:Domestic service robots (DSRs) that support people in everyday environments have been widely investigated. However, their ability to predict and describe future risks resulting from their own actions remains insufficient. In this study, we focus on the linguistic explainability of DSRs. Most existing methods do not explicitly model the region of possible collisions; thus, they do not properly generate descriptions of these regions. In this paper, we propose the Nearest Neighbor Future Captioning Model that introduces the Nearest Neighbor Language Model for future captioning of possible collisions, which enhances the model output with a nearest neighbors retrieval mechanism. Furthermore, we introduce the Collision Attention Module that attends regions of possible collisions, which enables our model to generate descriptions that adequately reflect the objects associated with possible collisions. To validate our method, we constructed a new dataset containing samples of collisions that can occur when a DSR places an object in a simulation environment. The experimental results demonstrated that our method outperformed baseline methods, based on the standard metrics. In particular, on CIDEr-D, the baseline method obtained 25.09 points, whereas our method obtained 33.08 points.
Abstract:Rearranging objects (e.g. vase, door) back in their original positions is one of the most fundamental skills for domestic service robots (DSRs). In rearrangement tasks, it is crucial to detect the objects that need to be rearranged according to the goal and current states. In this study, we focus on Rearrangement Target Detection (RTD), where the model generates a change mask for objects that should be rearranged. Although many studies have been conducted in the field of Scene Change Detection (SCD), most SCD methods often fail to segment objects with complex shapes and fail to detect the change in the angle of objects that can be opened or closed. In this study, we propose a Co-Scale Cross-Attentional Transformer for RTD. We introduce the Serial Encoder which consists of a sequence of serial blocks and the Cross-Attentional Encoder which models the relationship between the goal and current states. We built a new dataset consisting of RGB images and change masks regarding the goal and current states. We validated our method on the dataset and the results demonstrated that our method outperformed baseline methods on $F_1$-score and mean IoU.
Abstract:This paper focuses on the DialFRED task, which is the task of embodied instruction following in a setting where an agent can actively ask questions about the task. To address this task, we propose DialMAT. DialMAT introduces Moment-based Adversarial Training, which incorporates adversarial perturbations into the latent space of language, image, and action. Additionally, it introduces a crossmodal parallel feature extraction mechanism that applies foundation models to both language and image. We evaluated our model using a dataset constructed from the DialFRED dataset and demonstrated superior performance compared to the baseline method in terms of success rate and path weighted success rate. The model secured the top position in the DialFRED Challenge, which took place at the CVPR 2023 Embodied AI workshop.