Reconfigurable robots are at the forefront of robotics innovation due to their unmatched versatility and adaptability in addressing various tasks through collaborative operations. This paper explores the design and implementation of a novel pendulum-based magnetic coupling system within a reconfigurable disk robot. Diverging from traditional designs, this system emphasizes enhancing coupling strength while maintaining the compactness of the outer shell. We employ parametric optimization techniques, including magnetic array simulations, to improve coupling performance. Additionally, we conduct a comprehensive analysis of the rolling robot's motion to assess its operational effectiveness in the coupling mechanism. This examination reveals intriguing new motion patterns driven by frictional and sliding effects between the rolling disk modules and the ground. Furthermore, the new setup introduces a novel problem in the area of nonprehensile manipulation.
相關內容
As learning-based methods for legged robots rapidly grow in popularity, it is important that we can provide safety assurances efficiently across different controllers and environments. Existing works either rely on a priori knowledge of the environment and safety constraints to ensure system safety or provide assurances for a specific locomotion policy. To address these limitations, we propose an observation-conditioned reachability-based (OCR) safety-filter framework. Our key idea is to use an OCR value network (OCR-VN) that predicts the optimal control-theoretic safety value function for new failure regions and dynamic uncertainty during deployment time. Specifically, the OCR-VN facilitates rapid safety adaptation through two key components: a LiDAR-based input that allows the dynamic construction of safe regions in light of new obstacles and a disturbance estimation module that accounts for dynamics uncertainty in the wild. The predicted safety value function is used to construct an adaptive safety filter that overrides the nominal quadruped controller when necessary to maintain safety. Through simulation studies and hardware experiments on a Unitree Go1 quadruped, we demonstrate that the proposed framework can automatically safeguard a wide range of hierarchical quadruped controllers, adapts to novel environments, and is robust to unmodeled dynamics without a priori access to the controllers or environments - hence, "One Filter to Deploy Them All". The experiment videos can be found on the project website.
With few exceptions, the path to deployment for any Internet technology requires that there be some benefit to unilateral adoption of the new technology. In an Internet where the technology is not fully deployed, is an individual better off sticking to the status quo, or adopting the new technology? This question is especially relevant in the context of the Low Latency, Low Loss, Scalable Throughput (L4S) architecture, where the full benefit is realized only when compatible protocols (scalable congestion control, accurate ECN, and flow isolation at queues) are adopted at both endpoints of a connection and also at the bottleneck router. In this paper, we consider the perspective of the sender of an L4S flow using scalable congestion control, without knowing whether the bottleneck router uses an L4S queue, or whether other flows sharing the bottleneck queue are also using scalable congestion control. We show that whether the sender uses TCP Prague or BBRv2 as the scalable congestion control, it cannot be assured that it will not harm or be harmed by another flow sharing the bottleneck link. We further show that the harm is not necessarily mitigated when a scalable flow shares a bottleneck with multiple classic flows. Finally, we evaluate the approach of BBRv3, where scalable congestion control is used only when the path delay is small, with ECN feedback ignored otherwise, and show that it does not solve the coexistence problem.
Deep reinforcement learning (DRL) has emerged as an innovative solution for controlling legged robots in challenging environments using minimalist architectures. Traditional control methods for legged robots, such as inverse dynamics, either directly manage joint torques or use proportional-derivative (PD) controllers to regulate joint positions at a higher level. In case of DRL, direct torque control presents significant challenges, leading to a preference for joint position control. However, this approach necessitates careful adjustment of joint PD gains, which can limit both adaptability and efficiency. In this paper, we propose GainAdaptor, an adaptive gain control framework that autonomously tunes joint PD gains to enhance terrain adaptability and energy efficiency. The framework employs a dual-actor algorithm to dynamically adjust the PD gains based on varying ground conditions. By utilizing a divided action space, GainAdaptor efficiently learns stable and energy-efficient locomotion. We validate the effectiveness of the proposed method through experiments conducted on a Unitree Go1 robot, demonstrating improved locomotion performance across diverse terrains.
Bipedal robots are gaining global recognition due to their potential applications and advancements in artificial intelligence, particularly through Deep Reinforcement Learning (DRL). While DRL has significantly advanced bipedal locomotion, the development of a unified framework capable of handling a wide range of tasks remains an ongoing challenge. This survey systematically categorises, compares, and analyses existing DRL frameworks for bipedal locomotion, organising them into end-to-end and hierarchical control schemes. End-to-end frameworks are evaluated based on their learning approaches, while hierarchical frameworks are examined in terms of layered structures that integrate learning-based or traditional model-based methods. We provide a detailed evaluation of the composition, strengths, limitations, and capabilities of each framework. Additionally, this survey identifies key research gaps and proposes future directions aimed at creating a more integrated and efficient framework for bipedal locomotion, with wide-ranging applications in real-world environments.
Organic optoelectronic materials are a promising avenue for next-generation electronic devices due to their solution processability, mechanical flexibility, and tunable electronic properties. In particular, near-infrared (NIR) sensitive molecules have unique applications in night-vision equipment and biomedical imaging. Molecular engineering has played a crucial role in developing non-fullerene acceptors (NFAs) such as the Y-series molecules, which have significantly improved the power conversion efficiency (PCE) of solar cells and enhanced spectral coverage in the NIR region. However, systematically designing molecules with targeted optoelectronic properties while ensuring synthetic accessibility remains a challenge. To address this, we leverage structural priors from domain-focused, patent-mined datasets of organic electronic molecules using a symmetry-aware fragment decomposition algorithm and a fragment-constrained Monte Carlo Tree Search (MCTS) generator. Our approach generates candidates that retain symmetry constraints from the patent dataset, while also exhibiting red-shifted absorption, as validated by TD-DFT calculations.
With the rapid development of artificial intelligence, robotics, and Internet of Things, multi-robot systems are progressively acquiring human-like environmental perception and understanding capabilities, empowering them to complete complex tasks through autonomous decision-making and interaction. However, the Internet of Robotic Things (IoRT) faces significant challenges in terms of spectrum resources, sensing accuracy, communication latency, and energy supply. To address these issues, a reconfigurable intelligent surface (RIS)-aided IoRT network is proposed to enhance the overall performance of robotic communication, sensing, computation, and energy harvesting. In the case studies, by jointly optimizing parameters such as transceiver beamforming, robot trajectories, and RIS coefficients, solutions based on multi-agent deep reinforcement learning and multi-objective optimization are proposed to solve problems such as beamforming design, path planning, target sensing, and data aggregation. Numerical results are provided to demonstrate the effectiveness of proposed solutions in improve communication quality, sensing accuracy, computation error, and energy efficiency of RIS-aided IoRT networks.
Learning from Demonstration (LfD) systems are commonly used to teach robots new tasks by generating a set of skills from user-provided demonstrations. These skills can then be sequenced by planning algorithms to execute complex tasks. However, LfD systems typically require a full demonstration of the entire task, even when parts of it are already known to the robot. This limitation comes from the system's inability to recognize which sub-tasks are already familiar, leading to a repetitive and burdensome demonstration process for users. In this paper, we introduce a new method for guided demonstrations that reduces this burden, by helping the robot to identify which parts of the task it already knows, considering the overall task goal and the robot's existing skills. In particular, through a combinatorial search, the method finds the smallest necessary change in the initial task conditions that allows the robot to solve the task with its current knowledge. This state is referred to as the excuse state. The human demonstrator is then only required to teach how to reach the excuse state (missing sub-task), rather than demonstrating the entire task. Empirical results and a pilot user study show that our method reduces demonstration time by 61% and decreases the size of demonstrations by 72%.
Intent inferral, the process by which a robotic device predicts a user's intent from biosignals, offers an effective and intuitive way to control wearable robots. Classical intent inferral methods treat biosignal inputs as unidirectional ground truths for training machine learning models, where the internal state of the model is not directly observable by the user. In this work, we propose reciprocal learning, a bidirectional paradigm that facilitates human adaptation to an intent inferral classifier. Our paradigm consists of iterative, interwoven stages that alternate between updating machine learning models and guiding human adaptation with the use of augmented visual feedback. We demonstrate this paradigm in the context of controlling a robotic hand orthosis for stroke, where the device predicts open, close, and relax intents from electromyographic (EMG) signals and provides appropriate assistance. We use LED progress-bar displays to communicate to the user the predicted probabilities for open and close intents by the classifier. Our experiments with stroke subjects show reciprocal learning improving performance in a subset of subjects (two out of five) without negatively impacting performance on the others. We hypothesize that, during reciprocal learning, subjects can learn to reproduce more distinguishable muscle activation patterns and generate more separable biosignals.
Quantum Key Distribution (QKD) is a promising technique for ensuring long-term security in communication systems. Unlike conventional key exchange methods like RSA, which quantum computers could theoretically break [1], QKD offers enhanced security based on quantum mechanics [2]. Despite its maturity and commercial availability, QKD devices often have undisclosed implementations and are tamper-protected. This thesis addresses the practical imperfections of QKD systems, such as low and fluctuating Secret Key Rates (SKR) and unstable performance. By applying theoretical SKR derivations to measurement data from a QKD system in Poland, we gain insights into current system performance and develop machine learning (ML) models to predict system behavior. Our methodologies include creating a theoretical QKD model [2] and implementing ML models using tools like Keras (TensorFlow [3]). Key findings reveal that while theoretical models offer foundational insights, ML models provide superior accuracy in forecasting QKD system performance, adapting to environmental and operational parameters. This thesis highlights the limitations of theoretical models and underscores the practical relevance of ML models for QKD systems. Future research should focus on developing a comprehensive physical layer model capable of doing long-term forcasting of the SKR. Such a model could prevent an encryption system form running out of keys if the SKR drops significantly. In summary, this thesis establishes a foundational approach for using ML models to predict QKD system performance, paving the way for future advancements in SKR long-term predictions.
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191