Tetsuya Ogata

Masaki Murooka, Tomohiro Motoda, Ryoichi Nakajo et al.

We present RoboManipBaselines, an open-source software framework for imitation learning research in robotic manipulation. The framework supports the entire imitation learning pipeline, including data collection, policy training, and rollout, across both simulation and real-world environments. Its design emphasizes integration through a consistent workflow, generality across diverse environments and robot platforms, extensibility for easily adding new robots, tasks, and policies, and reproducibility through evaluations using publicly available datasets. RoboManipBaselines systematically implements the core components of imitation learning: environment, dataset, and policy. Through a unified interface, the framework supports multiple simulators and real robot environments, as well as multimodal sensors and a wide variety of policy models. We further present benchmark evaluations in both simulation and real-world environments and introduce several research applications, including data augmentation, integration with tactile models, interactive robotic systems, 3D sensing evaluation, and hardware extensions. These results demonstrate that RoboManipBaselines provides a useful foundation for advancing research and experimental validation in robotic manipulation using imitation learning. https://isri-aist.github.io/RoboManipBaselines-ProjectPage

Yukinori Yamamoto, Kazuya Nishimura, Tsukasa Fukusato et al.

Deep learning-based 3D medical image segmentation methods relies on large-scale labeled datasets, yet acquiring such data is difficult due to privacy constraints and the high cost of expert annotation. Formula-Driven Supervised Learning (FDSL) offers an appealing alternative by generating training data and labels directly from mathematical formulas. However, existing voxel-based approaches are limited in geometric expressiveness and cannot synthesize realistic textures. We introduce Formula-Driven supervised learning with Implicit Functions (FDIF), a framework that enables scalable pre-training without using any real data and medical expert annotations. FDIF introduces an implicit-function representation based on signed distance functions (SDFs), enabling compact modeling of complex geometries while exploiting the surface representation of SDFs to support controllable synthesis of both geometric and intensity textures. Across three medical image segmentation benchmarks (AMOS, ACDC, and KiTS) and three architectures (SwinUNETR, nnUNet ResEnc-L, and nnUNet Primus-M), FDIF consistently improves over a formula-driven method, and achieves performance comparable to self-supervised approaches pre-trained on large-scale real datasets. We further show that FDIF pre-training also benefits 3D classification tasks, highlighting implicit-function-based formula supervision as a promising paradigm for data-free representation learning. Code is available at https://github.com/yamanoko/FDIF.

Namiko Saito, Mayu Tatsumi, Ayuna Kubo et al.

To support humans in their daily lives, robots are required to autonomously learn, adapt to objects and environments, and perform the appropriate actions. We tackled on the task of cooking scrambled eggs using real ingredients, in which the robot needs to perceive the states of the egg and adjust stirring movement in real time, while the egg is heated and the state changes continuously. In previous works, handling changing objects was found to be challenging because sensory information includes dynamical, both important or noisy information, and the modality which should be focused on changes every time, making it difficult to realize both perception and motion generation in real time. We propose a predictive recurrent neural network with an attention mechanism that can weigh the sensor input, distinguishing how important and reliable each modality is, that realize quick and efficient perception and motion generation. The model is trained with learning from the demonstration, and allows the robot to acquire human-like skills. We validated the proposed technique using the robot, Dry-AIREC, and with our learning model, it could perform cooking eggs with unknown ingredients. The robot could change the method of stirring and direction depending on the status of the egg, as in the beginning it stirs in the whole pot, then subsequently, after the egg started being heated, it starts flipping and splitting motion targeting specific areas, although we did not explicitly indicate them.

Hyogo Hiruma, Hiroshi Ito, Hiroki Mori et al.

Sufficiently perceiving the environment is a critical factor in robot motion generation. Although the introduction of deep visual processing models have contributed in extending this ability, existing methods lack in the ability to actively modify what to perceive; humans perform internally during visual cognitive processes. This paper addresses the issue by proposing a novel robot motion generation model, inspired by a human cognitive structure. The model incorporates a state-driven active top-down visual attention module, which acquires attentions that can actively change targets based on task states. We term such attentions as role-based attentions, since the acquired attention directed to targets that shared a coherent role throughout the motion. The model was trained on a robot tool-use task, in which the role-based attentions perceived the robot grippers and tool as identical end-effectors, during object picking and object dragging motions respectively. This is analogous to a biological phenomenon called tool-body assimilation, in which one regards a handled tool as an extension of one's body. The results suggested an improvement of flexibility in model's visual perception, which sustained stable attention and motion even if it was provided with untrained tools or exposed to experimenter's distractions.

Kazuki Hori, Kanata Suzuki, Tetsuya Ogata

The application of the Large Language Model (LLM) to robot action planning has been actively studied. The instructions given to the LLM by natural language may include ambiguity and lack of information depending on the task context. It is possible to adjust the output of LLM by making the instruction input more detailed; however, the design cost is high. In this paper, we propose the interactive robot action planning method that allows the LLM to analyze and gather missing information by asking questions to humans. The method can minimize the design cost of generating precise robot instructions. We demonstrated the effectiveness of our method through concrete examples in cooking tasks. However, our experiments also revealed challenges in robot action planning with LLM, such as asking unimportant questions and assuming crucial information without asking. Shedding light on these issues provides valuable insights for future research on utilizing LLM for robotics.

Minori Toyoda, Kanata Suzuki, Yoshihiko Hayashi et al.

This study achieved bidirectional translation between descriptions and actions using small paired data from different modalities. The ability to mutually generate descriptions and actions is essential for robots to collaborate with humans in their daily lives, which generally requires a large dataset that maintains comprehensive pairs of both modality data. However, a paired dataset is expensive to construct and difficult to collect. To address this issue, this study proposes a two-stage training method for bidirectional translation. In the proposed method, we train recurrent autoencoders (RAEs) for descriptions and actions with a large amount of non-paired data. Then, we finetune the entire model to bind their intermediate representations using small paired data. Because the data used for pre-training do not require pairing, behavior-only data or a large language corpus can be used. We experimentally evaluated our method using a paired dataset consisting of motion-captured actions and descriptions. The results showed that our method performed well, even when the amount of paired data to train was small. The visualization of the intermediate representations of each RAE showed that similar actions were encoded in a clustered position and the corresponding feature vectors were well aligned.

Xianbo Cai, Hideyuki Ichiwara, Masaki Yoshikawa et al.

Real-world fine manipulation, particularly in bimanual manipulation, typically requires low-latency control and stable visual localization, while collecting large-scale data is costly and limited demonstrations may lead to localization drift. Existing approaches make different trade-offs: action-chunking policies such as ACT enable low-latency execution and data efficiency but rely on dense visual features without explicit spatial consistency, generative methods such as Diffusion Policy improve expressiveness but can incur iterative sampling latency, vision-language-action and voxel-based methods enhance generalization and geometric grounding but require higher computational cost and system complexity. We introduce a multistage spatial attention module that extracts stable 2D attention points and jointly predicts future attention sequences with a temporal alignment loss. Built upon ACT with a pretrained ResNet visual prior, a multistage attention module extracts task-relevant 2D attention points as a local spatial modality for action prediction. To maintain consistent object tracking, we introduce a self-supervised objective that aligns predicted attention sequences with visual features from future frames, suppressing drift without keypoint annotations and improving stability of the vision-to-action mapping under limited data. Experiments on simulated and real-world fine manipulation tasks, conducted on the ALOHA bimanual platform, evaluate task success, attention drift, inference latency, and robustness to visual disturbances. Results indicate improvements in localization stability and task performance while maintaining low-latency inference under the tested conditions.

Xianbo Cai, Hideyuki Ichiwara, Hyogo Hiruma et al.

Robots operating in open, unstructured real-world environments must rely on onboard visual perception while autonomously moving across different locations. Continuous changes in onboard camera viewpoints cause significant visual scale variations in target objects, affecting vision-based motion generation. In this work, we present a stereo multistage spatial attention-based deep predictive learning method for real-time mobile manipulation. The proposed methods extracts task-relevant spatial attention points from stereo images and integrates them with robot states through a hierarchical recurrent architecture for closed-loop action prediction. We evaluate the system on four real-world mobile manipulation tasks using a mobile manipulator, including rigid placement, articulated object manipulation, and deformable object interaction. Experiments under randomized initial positions and visual disturbance conditions demonstrate improved robustness and task success rates compared to representative imitation learning and vision-language-action baselines under identical control settings. The results indicate that structured stereo spatial attention combined with predictive temporal modeling provides an effective solution within the evaluated mobile manipulation scenarios.

Ryosuke Takanami, Petr Khrapchenkov, Shu Morikuni et al.

As robots transition from controlled settings to unstructured human environments, building generalist agents that can reliably follow natural language instructions remains a central challenge. Progress in robust mobile manipulation requires large-scale multimodal datasets that capture contact-rich and long-horizon tasks, yet existing resources lack synchronized force-torque sensing, hierarchical annotations, and explicit failure cases. We address this gap with the AIRoA MoMa Dataset, a large-scale real-world multimodal dataset for mobile manipulation. It includes synchronized RGB images, joint states, six-axis wrist force-torque signals, and internal robot states, together with a novel two-layer annotation schema of sub-goals and primitive actions for hierarchical learning and error analysis. The initial dataset comprises 25,469 episodes (approx. 94 hours) collected with the Human Support Robot (HSR) and is fully standardized in the LeRobot v2.1 format. By uniquely integrating mobile manipulation, contact-rich interaction, and long-horizon structure, AIRoA MoMa provides a critical benchmark for advancing the next generation of Vision-Language-Action models. The first version of our dataset is now available at https://huggingface.co/datasets/airoa-org/airoa-moma .

Kana Miyamoto, Kanata Suzuki, Tetsuya Ogata

Imitation learning for robotic tasks has relied primarily on policies trained only on successful demonstrations, although failures are unavoidable during human data collection. Many existing approaches for exploiting failure data require additional data processing or iterative policy updates through autonomous rollouts, making it difficult to directly and stably utilize failure data accumulated during data collection. In this work, we propose a method that learns latent representations of success-failure discrepancies and incorporates them into the attention mechanism. During inference, an appropriate latent mode is selected from the initial observation to improve action stability. Furthermore, we introduce a post-training metric that quantifies the attention discrepancy between each failure sample and successful demonstrations to select failure data. Simulation results show that the proposed method improves task success rates when trained with failure data and that the proposed metric identifies failure samples that are beneficial for learning when combined with successful demonstrations. These results suggest that the proposed method can support more efficient use of collected demonstrations in robotic data collection pipelines.

André Yuji Yasutomi, Hideyuki Ichiwara, Hiroshi Ito et al.

Anchor-bolt insertion is a peg-in-hole task performed in the construction field for holes in concrete. Efforts have been made to automate this task, but the variable lighting and hole surface conditions, as well as the requirements for short setup and task execution time make the automation challenging. In this study, we introduce a vision and proprioceptive data-driven robot control model for this task that is robust to challenging lighting and hole surface conditions. This model consists of a spatial attention point network (SAP) and a deep reinforcement learning (DRL) policy that are trained jointly end-to-end to control the robot. The model is trained in an offline manner, with a sample-efficient framework designed to reduce training time and minimize the reality gap when transferring the model to the physical world. Through evaluations with an industrial robot performing the task in 12 unknown holes, starting from 16 different initial positions, and under three different lighting conditions (two with misleading shadows), we demonstrate that SAP can generate relevant attention points of the image even in challenging lighting conditions. We also show that the proposed model enables task execution with higher success rate and shorter task completion time than various baselines. Due to the proposed model's high effectiveness even in severe lighting, initial positions, and hole conditions, and the offline training framework's high sample-efficiency and short training time, this approach can be easily applied to construction.

André Yuji Yasutomi, Hiroki Mori, Tetsuya Ogata

A method that enables an industrial robot to accomplish the peg-in-hole task for holes in concrete is proposed. The proposed method involves slightly detaching the peg from the wall, when moving between search positions, to avoid the negative influence of the concrete's high friction coefficient. It uses a deep neural network (DNN), trained via reinforcement learning, to effectively find holes with variable shape and surface finish (due to the brittle nature of concrete) without analytical modeling or control parameter tuning. The method uses displacement of the peg toward the wall surface, in addition to force and torque, as one of the inputs of the DNN. Since the displacement increases as the peg gets closer to the hole (due to the chamfered shape of holes in concrete), it is a useful parameter for inputting in the DNN. The proposed method was evaluated by training the DNN on a hole 500 times and attempting to find 12 unknown holes. The results of the evaluation show the DNN enabled a robot to find the unknown holes with average success rate of 96.1% and average execution time of 12.5 seconds. Additional evaluations with random initial positions and a different type of peg demonstrate the trained DNN can generalize well to different conditions. Analyses of the influence of the peg displacement input showed the success rate of the DNN is increased by utilizing this parameter. These results validate the proposed method in terms of its effectiveness and applicability to the construction industry.

Hayato Idei, Tamon Miyake, Tetsuya Ogata et al.

The rapid aging of societies is intensifying demand for autonomous care robots; however, most existing systems are task-specific and rely on handcrafted preprocessing, limiting their ability to generalize across diverse scenarios. A prevailing theory in cognitive neuroscience proposes that the human brain operates through hierarchical predictive processing, which underlies flexible cognition and behavior by integrating multimodal sensory signals. Inspired by this principle, we introduce a hierarchical multimodal recurrent neural network grounded in predictive processing under the free-energy principle, capable of directly integrating over 30,000-dimensional visuo-proprioceptive inputs without dimensionality reduction. The model was able to learn two representative caregiving tasks, rigid-body repositioning and flexible-towel wiping, without task-specific feature engineering. We demonstrate three key properties: (i) self-organization of hierarchical latent dynamics that regulate task transitions, capture variability in uncertainty, and infer occluded states; (ii) robustness to degraded vision through visuo-proprioceptive integration; and (iii) asymmetric interference in multitask learning, where the more variable wiping task had little influence on repositioning, whereas learning the repositioning task led to a modest reduction in wiping performance, while the model maintained overall robustness. Although the evaluation was limited to simulation, these results establish predictive processing as a universal and scalable computational principle, pointing toward robust, flexible, and autonomous caregiving robots while offering theoretical insight into the human brain's ability to achieve flexible adaptation in uncertain real-world environments.

Hyogo Hiruma, Hiroshi Ito, Tetsuya Ogata

Training robots to operate effectively in environments with uncertain states, such as ambiguous object properties or unpredictable interactions, remains a longstanding challenge in robotics. Imitation learning methods typically rely on successful examples and often neglect failure scenarios where uncertainty is most pronounced. To address this limitation, we propose the Uncertainty-driven Foresight Recurrent Neural Network (UF-RNN), a model that combines standard time-series prediction with an active "Foresight" module. This module performs internal simulations of multiple future trajectories and refines the hidden state to minimize predicted variance, enabling the model to selectively explore actions under high uncertainty. We evaluate UF-RNN on a door-opening task in both simulation and a real-robot setting, demonstrating that, despite the absence of explicit failure demonstrations, the model exhibits robust adaptation by leveraging self-induced chaotic dynamics in its latent space. When guided by the Foresight module, these chaotic properties stimulate exploratory behaviors precisely when the environment is ambiguous, yielding improved success rates compared to conventional stochastic RNN baselines. These findings suggest that integrating uncertainty-driven foresight into imitation learning pipelines can significantly enhance a robot's ability to handle unpredictable real-world conditions.

Hyogo Hiruma, Hiroshi Ito, Hiroki Mori et al.

This study investigates the developmental interaction between top-down (TD) and bottom-up (BU) visual attention in robotic learning. Our goal is to understand how structured, human-like attentional behavior emerges through the mutual adaptation of TD and BU mechanisms over time. To this end, we propose a novel attention model $A^3 RNN$ that integrates predictive TD signals and saliency-based BU cues through a bi-directional attention architecture. We evaluate our model in robotic manipulation tasks using imitation learning. Experimental results show that attention behaviors evolve throughout training, from saliency-driven exploration to prediction-driven direction. Initially, BU attention highlights visually salient regions, which guide TD processes, while as learning progresses, TD attention stabilizes and begins to reshape what is perceived as salient. This trajectory reflects principles from cognitive science and the free-energy framework, suggesting the importance of self-organizing attention through interaction between perception and internal prediction. Although not explicitly optimized for stability, our model exhibits more coherent and interpretable attention patterns than baselines, supporting the idea that developmental mechanisms contribute to robust attention formation.

Tomoki Ando, Hiroto Iino, Hiroki Mori et al.

We propose a new method for collision-free planning using Conditional Generative Adversarial Networks (cGANs) to transform between the robot's joint space and a latent space that captures only collision-free areas of the joint space, conditioned by an obstacle map. Generating multiple plausible trajectories is convenient in applications such as the manipulation of a robot arm by enabling the selection of trajectories that avoids collision with the robot or surrounding environment. In the proposed method, various trajectories that avoid obstacles can be generated by connecting the start and goal state with arbitrary line segments in this generated latent space. Our method provides this collision-free latent space, after which any planner, using any optimization conditions, can be used to generate the most suitable paths on the fly. We successfully verified this method with a simulated and actual UR5e 6-DoF robotic arm. We confirmed that different trajectories could be generated depending on optimization conditions.

Hyogo Hiruma, Hiroki Mori, Hiroshi Ito et al.

Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the dataset collection cost cannot be ignored. Existing visual attention models tackled the problem by employing a data efficient structure which learns to extract task relevant image areas. However, since the models cannot modify attention targets after training, it is difficult to apply to dynamically changing tasks. This paper proposed a novel Key-Query-Value formulated visual attention model. This model is capable of switching attention targets by externally modifying the Query representations, namely top-down attention. The proposed model is experimented on a simulator and a real-world environment. The model was compared to existing end-to-end robot vision models in the simulator experiments, showing higher performance and data efficiency. In the real-world robot experiments, the model showed high precision along with its scalability and extendibility.

Tomoki Ando, Hiroki Mori, Ryota Torishima et al.

We show a new method for collision-free path planning by cGANs by mapping its latent space to only the collision-free areas of the robot joint space. Our method simply provides this collision-free latent space after which any planner, using any optimization conditions, can be used to generate the most suitable paths on the fly. We successfully verified this method with a simulated two-link robot arm.

Hideyuki Ichiwara, Hiroshi Ito, Kenjiro Yamamoto et al.

We achieved contact-rich flexible object manipulation, which was difficult to control with vision alone. In the unzipping task we chose as a validation task, the gripper grasps the puller, which hides the bag state such as the direction and amount of deformation behind it, making it difficult to obtain information to perform the task by vision alone. Additionally, the flexible fabric bag state constantly changes during operation, so the robot needs to dynamically respond to the change. However, the appropriate robot behavior for all bag states is difficult to prepare in advance. To solve this problem, we developed a model that can perform contact-rich flexible object manipulation by real-time prediction of vision with tactility. We introduced a point-based attention mechanism for extracting image features, softmax transformation for predicting motions, and convolutional neural network for extracting tactile features. The results of experiments using a real robot arm revealed that our method can realize motions responding to the deformation of the bag while reducing the load on the zipper. Furthermore, using tactility improved the success rate from 56.7% to 93.3% compared with vision alone, demonstrating the effectiveness and high performance of our method.

Hayato Idei, Wataru Ohata, Yuichi Yamashita et al.

The brain attenuates its responses to self-produced exteroceptions (e.g., we cannot tickle ourselves). Is this phenomenon, known as sensory attenuation, enabled innately, or acquired through learning? Here, our simulation study using a multimodal hierarchical recurrent neural network model, based on variational free-energy minimization, shows that a mechanism for sensory attenuation can develop through learning of two distinct types of sensorimotor experience, involving self-produced or externally produced exteroceptions. For each sensorimotor context, a particular free-energy state emerged through interaction between top-down prediction with precision and bottom-up sensory prediction error from each sensory area. The executive area in the network served as an information hub. Consequently, shifts between the two sensorimotor contexts triggered transitions from one free-energy state to another in the network via executive control, which caused shifts between attenuating and amplifying prediction-error-induced responses in the sensory areas. This study situates emergence of sensory attenuation (or self-other distinction) in development of distinct free-energy states in the dynamic hierarchical neural system.

Satoshi Ohara, Tetsuya Ogata, Hiromitsu Awano

A neural network based flexible object manipulation system for a humanoid robot on FPGA is proposed. Although the manipulations of flexible objects using robots attract ever increasing attention since these tasks are the basic and essential activities in our daily life, it has been put into practice only recently with the help of deep neural networks. However such systems have relied on GPU accelerators, which cannot be implemented into the space limited robotic body. Although field programmable gate arrays (FPGAs) are known to be energy efficient and suitable for embedded systems, the model size should be drastically reduced since FPGAs have limited on-chip memory. To this end, we propose ``partially'' binarized deep convolutional auto-encoder technique, where only an encoder part is binarized to compress model size without degrading the inference accuracy. The model implemented on Xilinx ZCU102 achieves 41.1 frames per second with a power consumption of 3.1W, {\awano{which corresponds to 10x and 3.7x improvements from the systems implemented on Core i7 6700K and RTX 2080 Ti, respectively.

Namiko Saito, Tetsuya Ogata, Satoshi Funabashi et al.

Selection of appropriate tools and use of them when performing daily tasks is a critical function for introducing robots for domestic applications. In previous studies, however, adaptability to target objects was limited, making it difficult to accordingly change tools and adjust actions. To manipulate various objects with tools, robots must both understand tool functions and recognize object characteristics to discern a tool-object-action relation. We focus on active perception using multimodal sensorimotor data while a robot interacts with objects, and allow the robot to recognize their extrinsic and intrinsic characteristics. We construct a deep neural networks (DNN) model that learns to recognize object characteristics, acquires tool-object-action relations, and generates motions for tool selection and handling. As an example tool-use situation, the robot performs an ingredients transfer task, using a turner or ladle to transfer an ingredient from a pot to a bowl. The results confirm that the robot recognizes object characteristics and servings even when the target ingredients are unknown. We also examine the contributions of images, force, and tactile data and show that learning a variety of multimodal information results in rich perception for tool use.

Minori Toyoda, Kanata Suzuki, Hiroki Mori et al.

We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various linguistic expressions, including polysemous words, is an important ability for robots that interact with people via linguistic dialogue. Previous studies have shown that robots can use words that are not included in the action-description paired datasets by using pre-trained word embeddings. However, the word embeddings trained under the distributional hypothesis are not grounded, as they are derived purely from a text corpus. In this letter, we transform the pre-trained word embeddings to embodied ones by using the robot's sensory-motor experiences. We extend a bidirectional translation model for actions and descriptions by incorporating non-linear layers that retrofit the word embeddings. By training the retrofit layer and the bidirectional translation model alternately, our proposed model is able to transform the pre-trained word embeddings to adapt to a paired action-description dataset. Our results demonstrate that the embeddings of synonyms form a semantic cluster by reflecting the experiences (actions and environments) of a robot. These embeddings allow the robot to properly generate actions from unseen words that are not paired with actions in a dataset.

Kanata Suzuki, Momomi Kanamura, Yuki Suga et al.

In this study, we report the successful execution of in-air knotting of rope using a dual-arm two-finger robot based on deep learning. Owing to its flexibility, the state of the rope was in constant flux during the operation of the robot. This required the robot control system to dynamically correspond to the state of the object at all times. However, a manual description of appropriate robot motions corresponding to all object states is difficult to be prepared in advance. To resolve this issue, we constructed a model that instructed the robot to perform bowknots and overhand knots based on two deep neural networks trained using the data gathered from its sensorimotor, including visual and proximity sensors. The resultant model was verified to be capable of predicting the appropriate robot motions based on the sensory information available online. In addition, we designed certain task motions based on the Ian knot method using the dual-arm two-fingers robot. The designed knotting motions do not require a dedicated workbench or robot hand, thereby enhancing the versatility of the proposed method. Finally, experiments were performed to estimate the knotting performance of the real robot while executing overhand knots and bowknots on rope and its success rate. The experimental results established the effectiveness and high performance of the proposed method.

Hideyuki Ichiwara, Hiroshi Ito, Kenjiro Yamamoto et al.

Deep learning provides a powerful framework for automated acquisition of complex robotic motions. However, despite a certain degree of generalization, the need for vast amounts of training data depending on the work-object position is an obstacle to industrial applications. Therefore, a robot motion-generation model that can respond to a variety of work-object positions with a small amount of training data is necessary. In this paper, we propose a method robust to changes in object position by automatically extracting spatial attention points in the image for the robot task and generating motions on the basis of their positions. We demonstrate our method with an LBR iiwa 7R1400 robot arm on a picking task and a pick-and-place task at various positions in various situations. In each task, the spatial attention points are obtained for the work objects that are important to the task. Our method is robust to changes in object position. Further, it is robust to changes in background, lighting, and obstacles that are not important to the task because it only focuses on positions that are important to the task.

Kanata Suzuki, Tetsuya Ogata

In recent years, a variety of tasks have been accomplished by deep reinforcement learning (DRL). However, when applying DRL to tasks in a real-world environment, designing an appropriate reward is difficult. Rewards obtained via actual hardware sensors may include noise, misinterpretation, or failed observations. The learning instability caused by these unstable signals is a problem that remains to be solved in DRL. In this work, we propose an approach that extends existing DRL models by adding a subtask to directly estimate the variance contained in the reward signal. The model then takes the feature map learned by the subtask in a critic network and sends it to the actor network. This enables stable learning that is robust to the effects of potential noise. The results of experiments in the Atari game domain with unstable reward signals show that our method stabilizes training convergence. We also discuss the extensibility of the model by visualizing feature maps. This approach has the potential to make DRL more practical for use in noisy, real-world scenarios.

Pin-Chu Yang, Mohammed Al-Sada, Chang-Chieh Chiu et al.

Japanese character figurines are popular and have pivot position in Otaku culture. Although numerous robots have been developed, less have focused on otaku-culture or on embodying the anime character figurine. Therefore, we take the first steps to bridge this gap by developing Hatsuki, which is a humanoid robot platform with anime based design. Hatsuki's novelty lies in aesthetic design, 2D facial expressions, and anime-style behaviors that allows it to deliver rich interaction experiences resembling anime-characters. We explain our design implementation process of Hatsuki, followed by our evaluations. In order to explore user impressions and opinions towards Hatsuki, we conducted a questionnaire in the world's largest anime-figurine event. The results indicate that participants were generally very satisfied with Hatsuki's design, and proposed various use case scenarios and deployment contexts for Hatsuki. The second evaluation focused on imitation learning, as such method can provide better interaction ability in the real world and generate rich, context-adaptive behavior in different situations. We made Hatsuki learn 11 actions, combining voice, facial expressions and motions, through neuron network based policy model with our proposed interface. Results show our approach was successfully able to generate the actions through self-organized contexts, which shows the potential for generalizing our approach in further actions under different contexts. Lastly, we present our future research direction for Hatsuki, and provide our conclusion.

Kanata Suzuki, Hiroki Mori, Tetsuya Ogata

Robotic applications require both correct task performance and compensation for undefined behaviors. Although deep learning is a promising approach to perform complex tasks, the response to undefined behaviors that are not reflected in the training dataset remains challenging. In a human-robot collaborative task, the robot may adopt an unexpected posture due to collisions and other unexpected events. Therefore, robots should be able to recover from disturbances for completing the execution of the intended task. We propose a compensation method for undefined behaviors by switching between two controllers. Specifically, the proposed method switches between learning-based and model-based controllers depending on the internal representation of a recurrent neural network that learns task dynamics. We applied the proposed method to a pick-and-place task and evaluated the compensation for undefined behaviors. Experimental results from simulations and on a real robot demonstrate the effectiveness and high performance of the proposed method.

Kei Kase, Chris Paxton, Hammad Mazhar et al.

While robots can learn models to solve many manipulation tasks from raw visual input, they cannot usually use these models to solve new problems. On the other hand, symbolic planning methods such as STRIPS have long been able to solve new problems given only a domain definition and a symbolic goal, but these approaches often struggle on the real world robotic tasks due to the challenges of grounding these symbols from sensor data in a partially-observable world. We propose Deep Planning Domain Learning (DPDL), an approach that combines the strengths of both methods to learn a hierarchical model. DPDL learns a high-level model which predicts values for a large set of logical predicates consisting of the current symbolic world state, and separately learns a low-level policy which translates symbolic operators into executable actions on the robot. This allows us to perform complex, multi-step tasks even when the robot has not been explicitly trained on them. We show our method on manipulation tasks in a photorealistic kitchen scenario.

Nelson Yalta, Shinji Watanabe, Takaaki Hori et al.

Casual conversations involving multiple speakers and noises from surrounding devices are common in everyday environments, which degrades the performances of automatic speech recognition systems. These challenging characteristics of environments are the target of the CHiME-5 challenge. By employing a convolutional neural network (CNN)-based multichannel end-to-end speech recognition system, this study attempts to overcome the presents difficulties in everyday environments. The system comprises of an attention-based encoder-decoder neural network that directly generates a text as an output from a sound input. The multichannel CNN encoder, which uses residual connections and batch renormalization, is trained with augmented data, including white noise injection. The experimental results show that the word error rate is reduced by 8.5% and 0.6% absolute from a single channel end-to-end and the best baseline (LF-MMI TDNN) on the CHiME-5 corpus, respectively.

Zhihao Li, Toshiyuki Motoyoshi, Kazuma Sasaki et al.

Current end-to-end deep learning driving models have two problems: (1) Poor generalization ability of unobserved driving environment when diversity of training driving dataset is limited (2) Lack of accident explanation ability when driving models don't work as expected. To tackle these two problems, rooted on the believe that knowledge of associated easy task is benificial for addressing difficult task, we proposed a new driving model which is composed of perception module for \textit{see and think} and driving module for \textit{behave}, and trained it with multi-task perception-related basic knowledge and driving knowledge stepwisely. Specifically segmentation map and depth map (pixel level understanding of images) were considered as \textit{what \& where} and \textit{how far} knowledge for tackling easier driving-related perception problems before generating final control commands for difficult driving task. The results of experiments demonstrated the effectiveness of multi-task perception knowledge for better generalization and accident explanation ability. With our method the average sucess rate of finishing most difficult navigation tasks in untrained city of CoRL test surpassed current benchmark method for 15 percent in trained weather and 20 percent in untrained weathers. Demonstration video link is: https://www.youtube.com/watch?v=N7ePnnZZwdE

Namiko Saito, Kitae Kim, Shingo Murata et al.

We propose a tool-use model that can detect the features of tools, target objects, and actions from the provided effects of object manipulation. We construct a model that enables robots to manipulate objects with tools, using infant learning as a concept. To realize this, we train sensory-motor data recorded during a tool-use task performed by a robot with deep learning. Experiments include four factors: (1) tools, (2) objects, (3) actions, and (4) effects, which the model considers simultaneously. For evaluation, the robot generates predicted images and motions given information of the effects of using unknown tools and objects. We confirm that the robot is capable of detecting features of tools, objects, and actions by learning the effects and executing the task.

Nelson Yalta, Shinji Watanabe, Kazuhiro Nakadai et al.

Synthesizing human's movements such as dancing is a flourishing research field which has several applications in computer graphics. Recent studies have demonstrated the advantages of deep neural networks (DNNs) for achieving remarkable performance in motion and music tasks with little effort for feature pre-processing. However, applying DNNs for generating dance to a piece of music is nevertheless challenging, because of 1) DNNs need to generate large sequences while mapping the music input, 2) the DNN needs to constraint the motion beat to the music, and 3) DNNs require a considerable amount of hand-crafted data. In this study, we propose a weakly supervised deep recurrent method for real-time basic dance generation with audio power spectrum as input. The proposed model employs convolutional layers and a multilayered Long Short-Term memory (LSTM) to process the audio input. Then, another deep LSTM layer decodes the target dance sequence. Notably, this end-to-end approach has 1) an auto-conditioned decode configuration that reduces accumulation of feedback error of large dance sequence, 2) uses a contrastive cost function to regulate the mapping between the music and motion beat, and 3) trains with weak labels generated from the motion beat, reducing the amount of hand-crafted data. We evaluate the proposed network based on i) the similarities between generated and the baseline dancer motion with a cross entropy measure for large dance sequences, and ii) accurate timing between the music and motion beat with an F-measure. Experimental results revealed that, after training using a small dataset, the model generates basic dance steps with low cross entropy and maintains an F-measure score similar to that of a baseline dancer.

Junpei Zhong, Tetsuya Ogata, Angelo Cangelosi

Studies suggest that within the hierarchical architecture, the topological higher level possibly represents a conscious category of the current sensory events with slower changing activities. They attempt to predict the activities on the lower level by relaying the predicted information. On the other hand, the incoming sensory information corrects such prediction of the events on the higher level by the novel or surprising signal. We propose a predictive hierarchical artificial neural network model that examines this hypothesis on neurorobotic platforms, based on the AFA-PredNet model. In this neural network model, there are different temporal scales of predictions exist on different levels of the hierarchical predictive coding, which are defined in the temporal parameters in the neurons. Also, both the fast and the slow-changing neural activities are modulated by the active motor activities. A neurorobotic experiment based on the architecture was also conducted based on the data collected from the VRep simulator.

Junpei Zhong, Angelo Cangelosi, Xinzheng Zhang et al.

The predictive processing (PP) hypothesizes that the predictive inference of our sensorimotor system is encoded implicitly in the regularities between perception and action. We propose a neural architecture in which such regularities of active inference are encoded hierarchically. We further suggest that this encoding emerges during the embodied learning process when the appropriate action is selected to minimize the prediction error in perception. Therefore, this predictive stream in the sensorimotor loop is generated in a top-down manner. Specifically, it is constantly modulated by the motor actions and is updated by the bottom-up prediction error signals. In this way, the top-down prediction originally comes from the prior experience from both perception and action representing the higher levels of this hierarchical cognition. In our proposed embodied model, we extend the PredNet Network, a hierarchical predictive coding network, with the motor action units implemented by a multi-layer perceptron network (MLP) to modulate the network top-down prediction. Two experiments, a minimalistic world experiment, and a mobile robot experiment are conducted to evaluate the proposed model in a qualitative way. In the neural representation, it can be observed that the causal inference of predictive percept from motor actions can be also observed while the agent is interacting with the environment.

Kanata Suzuki, Hiroki Mori, Tetsuya Ogata

To ensure that a robot is able to accomplish an extensive range of tasks, it is necessary to achieve a flexible combination of multiple behaviors. This is because the design of task motions suited to each situation would become increasingly difficult as the number of situations and the types of tasks performed by them increase. To handle the switching and combination of multiple behaviors, we propose a method to design dynamical systems based on point attractors that accept (i) "instruction signals" for instruction-driven switching. We incorporate the (ii) "instruction phase" to form a point attractor and divide the target task into multiple subtasks. By forming an instruction phase that consists of point attractors, the model embeds a subtask in the form of trajectory dynamics that can be manipulated using sensory and instruction signals. Our model comprises two deep neural networks: a convolutional autoencoder and a multiple time-scale recurrent neural network. In this study, we apply the proposed method to manipulate soft materials. To evaluate our model, we design a cloth-folding task that consists of four subtasks and three patterns of instruction signals, which indicate the direction of motion. The results depict that the robot can perform the required task by combining subtasks based on sensory and instruction signals. And, our model determined the relations among these signals using its internal dynamics.

Francisco J. Arjonilla, Tetsuya Ogata

This paper proposes a formal cognitive framework for problem solving based on category theory. We introduce cognitive categories, which are categories with exactly one morphism between any two objects. Objects in these categories are interpreted as states and morphisms as transformations between states. Moreover, cognitive problems are reduced to the specification of two objects in a cognitive category: an outset (i.e. the current state of the system) and a goal (i.e. the desired state). Cognitive systems transform the target system by means of generators and evaluators. Generators realize cognitive operations over a system by grouping morphisms, whilst evaluators group objects as a way to generalize outsets and goals to partially defined states. Meta-cognition emerges when the whole cognitive system is self-referenced as sub-states in the cognitive category, whilst learning must always be considered as a meta-cognitive process to maintain consistency. Several examples grounded in basic AI methods are provided as well.

Junpei Zhong, Angelo Cangelosi, Tetsuya Ogata

The abstraction tasks are challenging for multi- modal sequences as they require a deeper semantic understanding and a novel text generation for the data. Although the recurrent neural networks (RNN) can be used to model the context of the time-sequences, in most cases the long-term dependencies of multi-modal data make the back-propagation through time training of RNN tend to vanish in the time domain. Recently, inspired from Multiple Time-scale Recurrent Neural Network (MTRNN), an extension of Gated Recurrent Unit (GRU), called Multiple Time-scale Gated Recurrent Unit (MTGRU), has been proposed to learn the long-term dependencies in natural language processing. Particularly it is also able to accomplish the abstraction task for paragraphs given that the time constants are well defined. In this paper, we compare the MTRNN and MTGRU in terms of its learning performances as well as their abstraction representation on higher level (with a slower neural activation). This was done by conducting two studies based on a smaller data- set (two-dimension time sequences from non-linear functions) and a relatively large data-set (43-dimension time sequences from iCub manipulation tasks with multi-modal data). We conclude that gated recurrent mechanisms may be necessary for learning long-term dependencies in large dimension multi-modal data-sets (e.g. learning of robot manipulation), even when natural language commands was not involved. But for smaller learning tasks with simple time-sequences, generic version of recurrent models, such as MTRNN, were sufficient to accomplish the abstraction task.

Junpei Zhong, Martin Peniak, Jun Tani et al.

The paper presents a neurorobotics cognitive model to explain the understanding and generalisation of nouns and verbs combinations when a vocal command consisting of a verb-noun sentence is provided to a humanoid robot. This generalisation process is done via the grounding process: different objects are being interacted, and associated, with different motor behaviours, following a learning approach inspired by developmental language acquisition in infants. This cognitive model is based on Multiple Time-scale Recurrent Neural Networks (MTRNN).With the data obtained from object manipulation tasks with a humanoid robot platform, the robotic agent implemented with this model can ground the primitive embodied structure of verbs through training with verb-noun combination samples. Moreover, we show that a functional hierarchical architecture, based on MTRNN, is able to generalise and produce novel combinations of noun-verb sentences. Further analyses of the learned network dynamics and representations also demonstrate how the generalisation is possible via the exploitation of this functional hierarchical recurrent network.

Tadahiro Taniguchi, Takayuki Nagai, Tomoaki Nakamura et al.

Humans can learn the use of language through physical interaction with their environment and semiotic communication with other people. It is very important to obtain a computational understanding of how humans can form a symbol system and obtain semiotic skills through their autonomous mental development. Recently, many studies have been conducted on the construction of robotic systems and machine-learning methods that can learn the use of language through embodied multimodal interaction with their environment and other systems. Understanding human social interactions and developing a robot that can smoothly communicate with human users in the long term, requires an understanding of the dynamics of symbol systems and is crucially important. The embodied cognition and social interaction of participants gradually change a symbol system in a constructive manner. In this paper, we introduce a field of research called symbol emergence in robotics (SER). SER is a constructive approach towards an emergent symbol system. The emergent symbol system is socially self-organized through both semiotic communications and physical interactions with autonomous cognitive developmental agents, i.e., humans and developmental robots. Specifically, we describe some state-of-art research topics concerning SER, e.g., multimodal categorization, word discovery, and a double articulation analysis, that enable a robot to obtain words and their embodied meanings from raw sensory--motor information, including visual information, haptic information, auditory information, and acoustic speech signals, in a totally unsupervised manner. Finally, we suggest future directions of research in SER.