The video gaming industry offers richer experiences through increasingly complex game mechanics, often hindering learnability. This research explores integrating an LLM-based chatbot, “Daisy,” in Stardew Valley, a narrative-rich role-playing game where learnability is critical. Over three weeks, 24 participants—14 new and 10 experienced players—engaged in a diary study and post-interviews. Analysis of diaries, chat logs, gameplay videos, and interviews revealed three themes: seeking information support, playing with chatbots, and addressing practical challenges. Findings show Daisy's potential to enhance learnability through natural conversations, fostering immersion and emotional engagement, though issues like hallucinations and context awareness require improvement. This work highlights preliminary insights for integrating LLMs into narrative-rich games.

In this paper, we propose a novel method for plane clustering specialized in cluttered scenes using an RGB-D camera and validate its effectiveness through robot grasping experiments. Unlike existing methods, which focus on large- scale indoor structures, our approach—Multi-Object RANSAC emphasizes cluttered environments that contain a wide range of objects with different scales. It enhances plane segmentation by generating subplanes in Deep Plane Clustering (DPC) module, which are then merged with the final planes by postprocessing. DPC rearranges the point cloud by voting layers to make subplane clusters, trained in a self-supervised manner using pseudo-labels generated from RANSAC. Multi-Object RANSAC demonstrates superior plane instance segmentation performances over other recent RANSAC applications. We conducted an experiment on robot suction-based grasping, comparing our method with vision-based grasping network and RANSAC applications. The results from this real-world scenario showed its remarkable performance surpassing the baseline methods, highlighting its potential for advanced scene understanding and manipulation.

When anger is abruptly triggered during driving, it becomes difficult to control one’s feelings. In this situation, other people can help mediate the angry emotional state through social interaction. However, it is not feasible to expect a passenger’s help for controlling the driver’s anger during every single drive. Failure to control the driver’s anger can lead to road rage, which can cause a critical danger. In this study, we addressed these concerns by designing and evaluating a driving companion bot that helps drivers control their anger. The bot was designed to deliver verbal comments which was developed based on five different cognitive coping strategies to the driver when the driver faced anger-inducing situations while driving. A within-subjects lab experiment was conducted with 38 participants who had driver’s licences. The results indicated that the use of a blaming others coping strategy was the most effective for anger reduction, perceived empathy, and companionship with no additional cognitive load compared to other strategies. Feedback from a post-experiment interview was also presented to discuss the long-term application of the study results. This includes theoretical findings and practical implications for designers and stakeholders focused on safe driving.

Spatial representation capable of learning a myriad of environmental features is a significant challenge for natural spatial understanding of mobile AI agents. Deep generative models have the potential of discovering rich representations of observed 3D scenes. However, previous approaches have been mainly evaluated on simple environments, or focused only on high-resolution rendering of small-scale scenes, hampering generalization of the representations to various spatial variability. To address this, we present PlaceNet, a neural representation that learns through random observations in a self-supervised manner, and represents observed scenes with triplet attention using visual, topographic, and semantic cues. We evaluate the proposed method on a large-scale multimodal scene dataset consisting of 120 million indoor scenes, and show that PlaceNet successfully generalizes to various environments with lower training loss, higher image quality and structural similarity of predicted scenes, compared to a competitive baseline model. Additionally, analyses of the representations demonstrate that PlaceNet activates more specialized and larger numbers of kernels in the spatial representation, capturing multimodal spatial properties in complex environments.

Object slip perception is essential for mobile manipulation robots to perform manipulation tasks reliably in the dynamic real-world. Traditional approaches to robot arms’ slip perception use tactile or vision sensors. However, mobile robots still have to deal with noise in their sensor signals caused by the robot’s movement in a changing environment. To solve this problem, we present an anomaly detection method that utilizes multisensory data based on a deep autoencoder model. The proposed framework integrates heterogeneous data streams collected from various robot sensors, including RGB and depth cameras, a microphone, and a force-torque sensor. The integrated data is used to train a deep autoencoder to construct latent representations of the multisensory data that indicate the normal status. Anomalies can then be identified by error scores measured by the difference between the trained encoder’s latent values and the latent values of reconstructed input data. In order to evaluate the proposed framework, we conducted an experiment that mimics an object slip by a mobile service robot operating in a real-world environment with diverse household objects and different moving patterns. The experimental results verified that the proposed framework reliably detects anomalies in object slip situations despite various object types and robot behaviors, and visual and auditory noise in the environment.

Facebook has the most active users as compared to any other social network. Despite its popularity, in recent years Facebook has been criticized for failing to develop user experience ("UX") continually. This failure resulted in a decrease in active users. In this study, 20 students and workers were interviewed to explore how Facebook users are currently using the app and changes that they experienced from their initial usage. The data generated by these interviews revealed not only challenges but also opportunities related to the user experience of social networks. This study would provide insights into the latest UX problems associated with the use of social networks and design guidelines for UX designers to overcome these problems as well.