This paper proposes a novel operation for controlling a mobile robot using a head-mounted device. Conventionally, robots are operated using computers or a joystick, which creates limitations in usability and flexibility because control equipment has to be carried by hand. This lack of flexibility may prevent workers from multitasking or carrying objects while operating the robot. To address this limitation, we propose a hands-free method to operate the mobile robot with a human gaze in an Augmented Reality (AR) environment. The proposed work is demonstrated using the HoloLens 2 to control the mobile robot, Robotnik Summit-XL, through the eye-gaze in AR. Stable speed control and navigation of the mobile robot were achieved through admittance control which was calculated using the gaze position. The experiment was conducted to compare the usability between the joystick and the proposed operation, and the results were validated through surveys (i.e., SUS, SEQ). The survey results from the participants after the experiments showed that the wearer of the HoloLens accurately operated the mobile robot in a collaborative manner. The results for both the joystick and the HoloLens were marked as easy to use with above-average usability. This suggests that the HoloLens can be used as a replacement for the joystick to allow hands-free robot operation and has the potential to increase the efficiency of human-robot collaboration in situations when hands-free controls are needed.
相關內容
Multiple object tracking (MOT) has been successfully investigated in computer vision. However, MOT for the videos captured by unmanned aerial vehicles (UAV) is still challenging due to small object size, blurred object appearance, and very large and/or irregular motion in both ground objects and UAV platforms. In this paper, we propose FOLT to mitigate these problems and reach fast and accurate MOT in UAV view. Aiming at speed-accuracy trade-off, FOLT adopts a modern detector and light-weight optical flow extractor to extract object detection features and motion features at a minimum cost. Given the extracted flow, the flow-guided feature augmentation is designed to augment the object detection feature based on its optical flow, which improves the detection of small objects. Then the flow-guided motion prediction is also proposed to predict the object's position in the next frame, which improves the tracking performance of objects with very large displacements between adjacent frames. Finally, the tracker matches the detected objects and predicted objects using a spatially matching scheme to generate tracks for every object. Experiments on Visdrone and UAVDT datasets show that our proposed model can successfully track small objects with large and irregular motion and outperform existing state-of-the-art methods in UAV-MOT tasks.
This paper considers the problem of inference in cluster randomized experiments when cluster sizes are non-ignorable. Here, by a cluster randomized experiment, we mean one in which treatment is assigned at the level of the cluster; by non-ignorable cluster sizes we mean that the distribution of potential outcomes, and the treatment effects in particular, may depend non-trivially on the cluster sizes. In order to permit this sort of flexibility, we consider a sampling framework in which cluster sizes themselves are random. In this way, our analysis departs from earlier analyses of cluster randomized experiments in which cluster sizes are treated as non-random. We distinguish between two different parameters of interest: the equally-weighted cluster-level average treatment effect, and the size-weighted cluster-level average treatment effect. For each parameter, we provide methods for inference in an asymptotic framework where the number of clusters tends to infinity and treatment is assigned using a covariate-adaptive stratified randomization procedure. We additionally permit the experimenter to sample only a subset of the units within each cluster rather than the entire cluster and demonstrate the implications of such sampling for some commonly used estimators. A small simulation study and empirical demonstration show the practical relevance of our theoretical results.
Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-shot action recognition methods have been proposed to transfer knowledge from a source dataset to a novel target dataset with only one or a few labeled videos. However, existing methods mainly focus on modeling the temporal relations between the query and support videos while ignoring the spatial relations. In this paper, we find that the spatial misalignment between objects also occurs in videos, notably more common than the temporal inconsistency. We are thus motivated to investigate the importance of spatial relations and propose a more accurate few-shot action recognition method that leverages both spatial and temporal information. Particularly, a novel Spatial Alignment Cross Transformer (SA-CT) which learns to re-adjust the spatial relations and incorporates the temporal information is contributed. Experiments reveal that, even without using any temporal information, the performance of SA-CT is comparable to temporal based methods on 3/4 benchmarks. To further incorporate the temporal information, we propose a simple yet effective Temporal Mixer module. The Temporal Mixer enhances the video representation and improves the performance of the full SA-CT model, achieving very competitive results. In this work, we also exploit large-scale pretrained models for few-shot action recognition, providing useful insights for this research direction.
This paper presents a modular approach to motion planning with provable stability guarantees for robots that move through changing environments via periodic locomotion behaviors. We focus on dynamic walkers as a paradigm for such systems, although the tools developed in this paper can be used to support general compositional approaches to robot motion planning with Dynamic Movement Primitives (DMPs). Our approach ensures a priori that the suggested plan can be stably executed. This is achieved by formulating the planning process as a Switching System with Multiple Equilibria (SSME) and proving that the system's evolution remains within explicitly characterized trapping regions in the state space under suitable constraints on the frequency of switching among the DMPs. These conditions effectively encapsulate the low-level stability limitations in a form that can be easily communicated to the planner to guarantee that the suggested plan is compatible with the robot's dynamics. Furthermore, we show how the available primitives can be safely composed online in a receding horizon manner to enable the robot to react to moving obstacles. The proposed framework is applied on 3D bipedal walking models under common modeling assumptions, and offers a modular approach towards stably integrating readily available low-level locomotion control and high-level planning methods.
We investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering. We selected three tasks: audio-visual speech recognition (AVSR), code-switched speech recognition (CS-ASR), and speech translation (ST) on unseen language pairs. We design task-specific prompts, by either leveraging another large-scale model, or simply manipulating the special tokens in the default prompts. Experiments show that compared to the default prompts, our proposed prompts improve performance by 10% to 45% on the three zero-shot tasks, and even outperform SotA supervised models on some datasets. In addition, our experiments reveal many interesting properties of Whisper, including its robustness to prompts, bias on accents, and the multilingual understanding in its latent space. Code is available at //github.com/jasonppy/PromptingWhisper
The Internet of Things (IoT) devices are rapidly increasing in popularity, with more individuals using Internet-connected devices that continuously monitor their activities. This work explores privacy concerns and expectations of end-users related to Trigger-Action platforms (TAPs) in the context of the Internet of Things (IoT). TAPs allow users to customize their smart environments by creating rules that trigger actions based on specific events or conditions. As personal data flows between different entities, there is a potential for privacy concerns. In this study, we aimed to identify the privacy factors that impact users' concerns and preferences for using IoT TAPs. To address this research objective, we conducted three focus groups with 15 participants and we extracted nine themes related to privacy factors using thematic analysis. Our participants particularly prefer to have control and transparency over the automation and are concerned about unexpected data inferences, risks and unforeseen consequences for themselves and for bystanders that are caused by the automation. The identified privacy factors can help researchers derive predefined and selectable profiles of privacy permission settings for IoT TAPs that represent the privacy preferences of different types of users as a basis for designing usable privacy controls for IoT TAPs.
Educational chatbots come with a promise of interactive and personalized learning experiences, yet their development has been limited by the restricted free interaction capabilities of available platforms and the difficulty of encoding knowledge in a suitable format. Recent advances in language learning models with zero-shot learning capabilities, such as ChatGPT, suggest a new possibility for developing educational chatbots using a prompt-based approach. We present a case study with a simple system that enables mixed-turn chatbot interactions and discuss the insights and preliminary guidelines obtained from initial tests. We examine ChatGPT's ability to pursue multiple interconnected learning objectives, adapt the educational activity to users' characteristics, such as culture, age, and level of education, and its ability to use diverse educational strategies and conversational styles. Although the results are encouraging, challenges are posed by the limited history maintained for the conversation and the highly structured form of responses by ChatGPT, as well as their variability, which can lead to an unexpected switch of the chatbot's role from a teacher to a therapist. We provide some initial guidelines to address these issues and to facilitate the development of effective educational chatbots.
NAND flash memory-based IoT devices inherently suffer from data retention issues. In IoT security, these retention issues are significant and require a robust solution for secure deletion. Secure deletion methods can be categorized into off-chip and on-chip schemes. Off-chip secure deletion schemes, based on block-level erasure operations, are unable to perform real-time trim operations. Consequently, they are vulnerable to hacking threats. On the other hand, on-chip secure deletion schemes enable real-time trim operations by performing deletion on a page-by-page basis. However, the on-chip scheme introduces a challenge of program disturbance for neighboring page data. The proposed on-chip deletion scheme tackles this problem by utilizing ECC code modulation through a partial program operation. This approach significantly reduces the program disturbance issue associated with neighboring page data. Moreover, the proposed code modulation secure deletion scheme allows for real-time verification of the deletion of original data.
5th Generation (5G) mobile communication systems operating at around 28 GHz have the potential to be applied to simultaneous localization and mapping (SLAM). Most existing 5G SLAM studies estimate environment as many point targets, instead of extended targets. In this paper, we focus on the performance analysis of 5G SLAM for multiple extended targets. To evaluate the mapping performance of multiple extended targets, a new mapping error metric, named extended targets generalized optimal sub-pattern assignment (ET-GOPSA), is proposed in this paper. Compared with the existing metrics, ET-GOPSA not only considers the accuracy error of target estimation, the cost of missing detection, the cost of false detection, but also the cost of matching the estimated point with the extended target. To evaluate the performance of 5G signal in SLAM, we analyze and simulate the mapping error of 5G signal sensing by ET-GOPSA. Simulation results show that, under the condition of SNR = 10 dB, 5G signal sensing can barely meet to meet the requirements of SLAM for multiple extended targets with the carrier frequency of 28 GHz, the bandwidth of 1.23 GHz, and the antenna size of 32.
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191