Recently, multimodal dialogue systems have engaged increasing attention in several domains such as retail, travel, etc. In spite of the promising performance of pioneer works, existing studies usually focus on utterance-level semantic representations with hierarchical structures, which ignore the context-aware dependencies of multimodal semantic elements, i.e., words and images. Moreover, when integrating the visual content, they only consider images of the current turn, leaving out ones of previous turns as well as their ordinal information. To address these issues, we propose a Multimodal diAlogue systems with semanTic Elements, MATE for short. Specifically, we unfold the multimodal inputs and devise a Multimodal Element-level Encoder to obtain the semantic representation at element-level. Besides, we take into consideration all images that might be relevant to the current turn and inject the sequential characteristics of images through position encoding. Finally, we make comprehensive experiments on a public multimodal dialogue dataset in the retail domain, and improve the BLUE-4 score by 9.49, and NIST score by 1.8469 compared with state-of-the-art methods.

In this paper, we propose a novel integrated task planning system for service robot in domestic domains. Given open-ended high-level user instructions in natural language, robots need to generate a plan, i.e., a sequence of low-level executable actions, to complete the required tasks. To address this, we exploit the knowledge on semantic roles of common verbs defined in semantic dictionaries such as FrameNet and integrate it with Answer Set Programming --- a task planning framework with both representation language and solvers. In the experiments, we evaluated our approach using common benchmarks on service tasks and showed that it can successfully handle much more tasks than the state-of-the-art solution. Notably, we deployed the proposed planning system on our service robot for the annual RoboCup@Home competitions and achieved very encouraging results.

Probabilistic graphical models, such as partially observable Markov decision processes (POMDPs), have been used in stochastic spoken dialog systems to handle the inherent uncertainty in speech recognition and language understanding. Such dialog systems suffer from the fact that only a relatively small number of domain variables are allowed in the model, so as to ensure the generation of good-quality dialog policies. At the same time, the non-language perception modalities on robots, such as vision-based facial expression recognition and Lidar-based distance detection, can hardly be integrated into this process. In this paper, we use a probabilistic commonsense reasoner to “guide” our POMDP-based dialog manager, and present a principled, multimodal dialog management (MDM) framework that allows the robot's dialog belief state to be seamlessly updated by both observations of human spoken language, and exogenous events such as the change of human facial expressions. The MDM approach has been implemented and evaluated both in simulation and on a real mobile robot using guidance tasks.

We consider here the problem of connecting natural language to the physical world for robotic object manipulation. This problem needs to be solved in robotic reasoning systems so that the robot can act in the real world. In this paper, we propose an architecture that combines grounding and planning to enable robots to solve such a problem. The grounding system of the architecture grounds the meaning of a natural language sentence in physical environment perceived by the robot’s sensors and generates a knowledge base of the physical environment. Then the planning system utilizes the knowledge base to infer a plan for object manipulation, which can be effectively generated by an Answer Set Programming (ASP) planner. We evaluate the overall architecture on several datasets and a task of RoboCup2014@home ( http://www.robocup2014.org/ ). The results show that the new architecture outperformed some other systems, and yielded acceptable performance in a real-world scenario.