Using the spatial structure of various indoor environments as prior knowledge, the robot would construct the map more efficiently. Autonomous mobile robots generally apply simultaneous localization and mapping (SLAM) methods to understand the reachable area in newly visited environments. However, conventional mapping approaches are limited by only considering sensor observation and control signals to estimate the current environment map. This paper proposes a novel SLAM method, map completion network-based SLAM (MCN-SLAM), based on a probabilistic generative model incorporating deep neural networks for map completion. These map completion networks are primarily trained in the framework of generative adversarial networks (GANs) to extract the global structure of large amounts of existing map data. We show in experiments that the proposed method can estimate the environment map 1.3 times better than the previous SLAM methods in the situation of partial observation.

In semantic mapping, which connects semantic information to an environment map, it is a challenging task for robots to deal with both local and global information of environments. In addition, it is important to estimate semantic information of unobserved areas from already acquired partial observations in a newly visited environment. On the other hand, previous studies on spatial concept formation enabled a robot to relate multiple words to places from bottom-up observations even when the vocabulary was not provided beforehand. However, the robot could not transfer global information related to the room arrangement between semantic maps from other environments. In this paper, we propose SpCoMapGAN, which generates the semantic map in a newly visited environment by training an inference model using previously estimated semantic maps. SpCoMapGAN uses generative adversarial networks (GANs) to transfer semantic information based on room arrangements to a newly visited environment. Our proposed method assigns semantics to the map of an unknown environment using the prior distribution of the map trained in known environments and the multimodal observations made in the unknown environment. We experimentally show in simulation that SpCoMapGAN can use global information for estimating the semantic map and is superior to previous methods. Finally, we also demonstrate in a real environment that SpCoMapGAN can accurately 1) deal with local information, and 2) acquire the semantic information of real places.

Human–robot interaction during general service tasks in home or retail environment has been proven challenging, partly because (1) robots lack high-level context-based cognition and (2) humans cannot intuit the perception state of robots as they can for other humans. To solve these two problems, we present a complete robot system that has been given the highest evaluation score at the Customer Interaction Task of the Future Convenience Store Challenge at the World Robot Summit 2018, which implements several key technologies: (1) a hierarchical spatial concepts formation for general robot task planning and (2) a mixed reality interface to enable users to intuitively visualize the current state of the robot perception and naturally interact with it. The results obtained during the competition indicate that the proposed system allows both non-expert operators and end users to achieve human–robot interactions in customer service environments. Furthermore, we describe a detailed scenario including employee operation and customer interaction which serves as a set of requirements for service robots and a road map for development. The system integration and task scenario described in this paper should be helpful for groups facing customer interaction challenges and looking for a successfully deployed base to build on. GRAPHICAL ABSTRACT

An autonomous robot performing tasks in a human environment needs to recognize semantic information about places. Semantic mapping is a task in which suitable semantic information is assigned to an environmental map so that a robot can communicate with people and appropriately perform tasks requested by its users. We propose a novel statistical semantic mapping method called SpCoMapping, which integrates probabilistic spatial concept acquisition based on multimodal sensor information and a Markov random field applied for learning the arbitrary shape of a place on a map.SpCoMapping can connect multiple words to a place in a semantic mapping process using user utterances without pre-setting the list of place names. We also develop a nonparametric Bayesian extension of SpCoMapping that can automatically estimate an adequate number of categories. In the experiment in the simulation environments, we showed that the proposed method generated better semantic maps than previous semantic mapping methods; our semantic maps have categories and shapes similar to the ground truth provided by the user. In addition, we showed that SpCoMapping could generate appropriate semantic maps in a real-world environment.

Many works attributed the successful reception of concurrent transmission (CT) to the constructive interference. However, due to the inevitable carrier frequency offset (CFO) and the resulted beating effect, the claim of constructive interference is actually not valid. To clarify the reason behind the successful receptions under CT, we conduct extensive evaluations and identify the following findings. 1) We show that the IEEE 802.15.4 receivers survive the beating effect mainly because of the direct sequence spread spectrum (DSSS), while systems without the protection of DSSS are not applicable to CT. 2) We identify a counterintuitive phenomenon that the IEEE 802.15.4 receiver could survive only the beating results from large CFO, while performing poorly when CFO is small. 3) We demonstrate that, even if the receivers survive, CT links lead to little performance improvements compared to conventional signal transmission links from the SNR point of view.

Concurrent transmission flooding (CTF), despite its high efficiency, has been considered to be only suitable for periodic traffic models. In this competition, we show that, with a sophisticated scheduling mechanism, CTF could become a reliable and efficient primitive for various traffic demands. Specifically, we demonstrate Choco, a CTF-based communication protocol that energy-efficiently supports burst and random traffic demands with 100 % end-to-end reliability. The scheduling mechanism of Choco dynamically adapts slot assignment according to packet losses and traffic loads, and ensures 100 % end-to-end reliability. Moreover, the mechanism instructs nodes to enter a deep sleep mode when there are no traffic to achieve efficiency even in light random traffic. Experiments that emulate the competition are conducted to prove the robustness of Choco. The results show that Choco consistently achieves 100 % reliability, while ORPL, the state-of-the-art routing-based protocol, suffers from 42 % of packet error rate in interfered environment.

We present a communication protocol called Choco, which efficiently supports various traffic demands with end-to-end reliability in multi-hop Wireless Sensor Networks (WSNs). To achieve this, Choco uses fine-grained scheduling based on the insight that acknowledgements (ACKs) between ends can be delivered with little overhead using concurrent transmission. Specifically, the slot assignment is dynamically scheduled up to several times a second according to traffic loads and packet losses. We show that Choco achieves higher efficiency and reliability than ORPL+BF, which is a state-of-the-art collection protocol, for periodic traffic environments. Also, we show that in a networked imaging application, which generates burst traffic, Choco can successfully collect 5 VGA images with high efficiency from 5 nodes in approximately 168~s in an average 4.0~hop network.

A dissemination protocol which guarantees integrity is essential for a reprogramming system in wireless sensor networks. The dissemination protocol must consist of 3 functions which are a reliable dissemination, a collection of end-to-end acknowledgement and time synchronization. In this paper, we propose a new dissemination protocol called DISCO, that realizes these 3 functions by extending a collection protocol called Choco and introducing concurrent transmission flooding and a scheduling system of traffic of uplink and downlink. This paper presents the implementation of a reprogramming system and our evaluation result on a testbed shows that DISCO can guarantee integrity and achieve the comparable dissemination time to a previous fast dissemination protocol.