检索结果-内蒙古大学图书馆

What’s at Stake? Robot explanations matter for high but not low-stake scenarios

学校读者我要写书评

暂无评论

What’s at Stake? Robot explanations matter for high but not...

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Gaspar Isaac Melsion Rebecca Stower Katie Winkle Iolanda Leite Division of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden Department of Information Technology Uppsala University Sweden

Although the field of Explainable Artificial Intelligence (XAI) in Human-Robot Interaction is gathering increasing attention, how well different explanations compare across HRI scenarios is still not well understood. We conducted an exploratory online study with 335 participants analysing the interaction between type of explanation (counterfactual, feature-based, and no explanation), the stake of the scenario (high, low) and the application scenario (healthcare, industry). Participants viewed one of 12 different vignettes depicting a combination of these three factors and rated their system understanding and trust in the robot. Compared to no explanation, both counterfactual and feature-based explanations improved system understanding and performance trust (but not moral trust). Additionally, when no explanation was present, high-stake scenarios led to significantly worse performance trust and system understanding. These findings suggest that explanations can be used to calibrate users’ perceptions of the robot in high-stake scenarios.

关键词：

Hyperbolic Delaunay Geometric Alignment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Medbouhi, Aniss Aiman Marchetti, Giovanni Luca Polianskii, Vladislav Kravberg, Alexander Poklukar, Petra Varava, Anastasia Kragic, Danica Division of Robotics Perception and Learning Department of Intelligent Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden

Hyperbolic machine learning is an emerging field aimed at representing data with a hierarchical structure. However, there is a lack of tools for evaluation and analysis of the resulting hyperbolic data representations. To this end, we propose Hyperbolic Delaunay Geometric Alignment (HyperDGA) – a similarity score for comparing datasets in a hyperbolic space. The core idea is counting the edges of the hyperbolic Delaunay graph connecting datapoints across the given sets. We provide an empirical investigation on synthetic and real-life biological data and demonstrate that HyperDGA outperforms the hyperbolic version of classical distances between sets. Furthermore, we showcase the potential of HyperDGA for evaluating latent representations inferred by a Hyperbolic Variational Auto-Encoder. © 2024, CC BY.

关键词： Geometry

learning to Model Diverse Driving Behaviors in Highly Interactive Autonomous Driving Scenarios with Multi-Agent Reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Weiwei, Liu Wenxuan, Hu Wei, Jing Lanxin, Lei Lingping, Gao Yong, Liu The Advanced Perception on Robotics and Intelligent Learning Lab College of Control Science and Enginneering Zhejiang University Hangzhou310027 China The Advanced Perception on Robotics and Intelligent Learning Lab Huzhou Institute Zhejiang University Huzhou China College of Information Engineering Huzhou University Huzhou China Department of Autonomous Driving Lab Alibaba DAMO Academy Hangzhou China

Autonomous vehicles trained through Multi-Agent Reinforcement learning (MARL) have shown impressive results in many driving scenarios. However, the performance of these trained policies can be impacted when faced with diverse driving styles and personalities, particularly in highly interactive situations. This is because conventional MARL algorithms usually operate under the assumption of fully cooperative behavior among all agents and focus on maximizing team rewards during training. To address this issue, we introduce the Personality Modeling Network (PeMN), which includes a cooperation value function and personality parameters to model the varied interactions in high-interactive scenarios. The PeMN also enables the training of a background traffic flow with diverse behaviors, thereby improving the performance and generalization of the ego vehicle. Our extensive experimental studies, which incorporate different personality parameters in high-interactive driving scenarios, demonstrate that the personality parameters effectively model diverse driving styles and that policies trained with PeMN demonstrate better generalization compared to traditional MARL methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Personality-Adapted Language Generation for Social Robots

学校读者我要写书评

暂无评论

Personality-Adapted Language Generation for Social Robots

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Alessio Galatolo Iolanda Leite Katie Winkle Department of Information Technology Uppsala University Uppsala Sweden Division of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden

Previous works in Human-Robot Interaction have demonstrated the positive potential benefit of designing social robots which express specific personalities. In this work, we focus specifically on the adaptation of language (as the choice of words, their order, etc.) following the extraversion trait. We look to investigate whether current language models could support more autonomous generations of such personality-expressive robot output. We examine the performance of two models with user studies evaluating (i) raw text output and (ii) text output when used within multi-modal speech from the Furhat robot. We find that the ability to successfully manipulate perceived extraversion sometimes varies across different dialogue topics. We were able to achieve correct manipulation of robot personality via our language adaptation, but our results suggest further work is necessary to improve the automation and generalisation abilities of these models.

关键词：

Functional Equivalence with NARS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Johansson, Robert Hammer, Patrick Lofthouse, Tony Department of Psychology Stockholm University Sweden Department of Computer and Information Science Linköping University Linköping Sweden Division of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden

This study explores the concept of functional equivalence within the framework of the Non-Axiomatic Reasoning System (NARS), specifically through OpenNARS for Applications (ONA). Functional equivalence allows organisms to categorize and respond to varied stimuli based on their utility rather than perceptual similarity, thus enhancing cognitive efficiency and adaptability. In this study, ONA was modified to allow the derivation of functional equivalence. This paper provides practical examples of the capability of ONA to apply learned knowledge across different functional situations, demonstrating its utility in complex problem-solving and decision-making. An extended example is included, where training of ONA aimed to learn basic human-like language abilities, using a systematic procedure in relating spoken words, objects and written words. The research carried out as part of this study extends the understanding of functional equivalence in AGI systems, and argues for its necessity for level of flexibility in learning and adapting necessary for human-level AGI. © 2024, CC BY-NC-ND.

关键词： Decision making

TTT: A Temporal Refinement Heuristic for Tenuously Tractable Discrete Time Reachability Problems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sidrane, Chelsea Tumova, Jana The Division of Robotics Perception and Learning Intelligent Systems Department School of Electrical Engineering & Computer Science KTH Royal Institute of Technology Brinellvägen 8 Stockholm114 28 Sweden

Reachable set computation is an important tool for analyzing control systems. Simulating a control system can show that the system is generally functioning as desired, but a formal tool like reachability analysis can provide a guarantee of correctness. For linear systems, reachability analysis is straightforward and fast, but as more complex components are added to the control system such as nonlinear dynamics or a neural network controller, reachability analysis may slow down or become overly conservative. To address these challenges, much literature has focused on spatial refinement, e.g., tuning the discretization of the input sets and intermediate reachable sets. However, this paper addresses a different dimension: temporal refinement. The basic idea of temporal refinement is to automatically choose when along the horizon of the reachability problem to execute slow symbolic queries which incur less approximation error versus fast concrete queries which incur more approximation error. Temporal refinement can be combined with other refinement approaches and offers an additional "tuning knob" with which to trade off tractability and tightness in approximate reachable set computation. Here, we introduce an automatic framework for performing temporal refinement and we demonstrate the effectiveness of this technique on computing approximate reachable sets for nonlinear systems with neural network control policies. We demonstrate the calculation of reachable sets of varying approximation error under varying computational budget and show that our algorithm is able to generate approximate reachable sets with a similar amount of error to the baseline approach in 20-70% less time. © 2024, CC BY.

关键词： Linear systems

Unifying Complementarity Constraints and Control Barrier Functions for Safe Whole-Body Robot Control

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Muchacho, Rafael I Cabral Laha, Riddhiman Pokorny, Florian T. Figueredo, Luis F.C. Chakraborty, Nilanjan Division of Robotics Perception and Learning KTH Royal Institute of Technology Sweden Munich Institute of Robotics and Machine Intelligence TUM Germany School of Computer Science University of Nottingham United Kingdom Department of Mechanical Engineering Stony Brook University NY United States

Safety-critical whole-body robot control demands reactive methods that ensure collision avoidance in real-time. Complementarity constraints and control barrier functions (CBF) have emerged as core tools for ensuring such safety constraints, and each represents a well-developed field. Despite addressing similar problems, their connection remains largely unexplored. This paper bridges this gap by formally proving the equivalence between these two methodologies for sampled-data, first-order systems, considering both single and multiple constraint scenarios. By demonstrating this equivalence, we provide a unified perspective on these techniques. This unification has theoretical and practical implications, facilitating the cross-application of robustness guarantees and algorithmic improvements between complementarity and CBF frameworks. We discuss these synergistic benefits and motivate future work in the comparison of the methods in more general cases. Copyright © 2025, The Authors. All rights reserved.

关键词： Optimal control systems

ASFM: Augmented Social Force Model for Legged Robot Social Navigation 23

学校读者我要写书评

暂无评论

ASFM: Augmented Social Force Model for Legged Robot Social N...

23rd IEEE-RAS International Conference on Humanoid Robots, Humanoids 2024

作者： Ægidius, Sebastian Chacón-Quesada, Rodrigo Delfaki, Andromachi Maria Kanoulas, Dimitrios Demiris, Yiannis Imperial College London Personal Robotics Lab Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom University College London Robot Perception and Learning Lab Department of Computer Science Gower Street LondonWC1E 6BT United Kingdom Ai Centre Department of Computer Science Ucl United Kingdom Archimedes/Athena Rc Greece

ISBN: (纸本)9798350373578

Social navigation in robotics primarily involves guiding mobile robots through human-populated areas, with pedestrian comfort balanced with efficient path-finding. Although progress has been seen in this field, a solution for the seamless integration of robots into pedestrian settings remains elusive. In this paper, a social force model for legged robots is developed, utilizing visual perception for human localization. In particular, an augmented social force model is introduced, incorporating refined interpretations of repulsive forces and avoidance behaviors based on pedestrian actions, alongside a target following mechanism. Experimental evaluation on a quadruped robot, through various scenarios, including interactions with oncoming pedestrians, crowds, and obstructed paths, demonstrates that the proposed augmented model significantly improves upon previous baseline methods in terms of chosen path length, average velocity, and time-to-goal for effective and efficient social navigation. The code isopen-source, while video demonstrations can be found on the project's webpage: https://***/ASFM/ © 2024 IEEE.

关键词： Mobile robots

Temporally Robust Multi-Agent STL Motion Planning in Continuous Time

学校读者我要写书评

暂无评论

Temporally Robust Multi-Agent STL Motion Planning in Continu...

American Control Conference (ACC)

作者： Joris Verhagen Lars Lindemann Jana Tumova Division of Robotics Perception and Learning School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Computer Science University of Southern California Los Angeles CA USA

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

Signal Temporal Logic (STL) is a formal language over continuous-time signals (such as trajectories of a multiagent system) that allows for the specification of complex spatial and temporal system requirements (such as staying sufficiently close to each other within certain time intervals). To promote robustness in multi-agent motion planning with such complex requirements, we consider motion planning with the goal of maximizing the temporal robustness of their joint STL specification, i.e. maximizing the permissible time shifts of each agent's trajectory while still satisfying the STL specification. Previous methods presented temporally robust motion planning and control in a discrete-time optimization scheme. In contrast, we parameterize the trajectory by continuous Bézier curves, where the curvature and the time-traversal of the trajectory are parameterized individually. We show an algorithm generating continuous-time temporally robust trajectories and prove soundness of our approach. Moreover, we empirically show that our parametrization realizes this with a considerable speed-up compared to state-of-the-art methods based on constant interval time discretization.

关键词： Redundancy Formal languages Robustness Encoding Trajectory Planning Logic