Intelligent robots designed to interact with humans in real scenarios need to be able to refer to entities actively by natural language. In spatial referring expression generation, the ambiguity is unavoidable due to the diversity of reference frames, which will lead to an understanding gap between humans and robots. To narrow this gap, in this paper, we propose a novel perspective-corrected spatial referring expression generation (PcSREG) approach for human-robot interaction by considering the selection of reference frames. The task of referring expression generation is simplified into the process of generating diverse spatial relation units. First, we pick out all landmarks in these spatial relation units according to the entropy of preference and allow its updating through a stack model. Then all possible referring expressions are generated according to different reference frame strategies. Finally, we evaluate every expression using a probabilistic referring expression resolution model and find the best expression that satisfies both of the appropriateness and effectiveness. We implement the proposed approach on a robot system and empirical experiments show that our approach can generate more effective spatial referring expressions for practical applications.
Grasp What You Want: Embodied Dexterous Grasping System Driven by Your Voice
Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；South China University of Technology（华南理工大学）
Toward an Interaction-Centered Approach to Robot Trustworthiness
CONTACT, Italian Institute of Technology, Genoa, Italy and Digital Health Department, Nvision Systems & Technologies, S.L., Barcelona, Spain（意大利理工学院（CONTACT）、西班牙巴塞罗那Nvision系统与技术公司数字健康部）；Department of Informatics, University of Hamburg, Germany（德国汉堡大学信息学院）；Department of Applied Informatics, Comenius University Bratislava, Slovakia（斯洛伐克布拉迪斯拉发Comenius大学应用信息学院）
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
School of Software, Beihang University（北京航空航天大学软件学院）；State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（北京大学计算机学院）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension
Institute of Deep Perception Technology, JITRI（JITRI深度感知技术研究所）；University of Liverpool（利物浦大学）；University of Southampton（南安普顿大学）；Momoni AI（Momoni人工智能公司）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；Thrust of Artificial Intelligence, HKUST (GZ)（香港科技大学（广州）人工智能学域）；Thrust of Intelligent Transportation, HKUST (GZ)（香港科技大学（广州）智能交通学域）
Optimization-Based Reference Generator for Nonlinear Model Predictive Control of Legged Robots
Istituto Italiano di Tecnologia (IIT)（意大利技术研究院）；Università di Genova（热那亚大学）；Università di Trento（特伦托大学）；IMT School for Advanced Studies Lucca（卢卡IMT高等研究院）
模型预测控制（MPC）方法广泛用于机器人技术中，因为它们保证可行性并且允许在机器人移动时计算更新的轨迹。它们通常需要用于跟踪项的启发式参考和成本函数的参数的适当调整，以便获得良好的性能。例如，当足式机器人必须对来自环境的干扰作出反应时（例如，推后恢复）或以静态不稳定的步态跟踪特定目标，则算法的有效性会降低。在这项工作中，我们提出了一种新的基于优化的参考生成器，该参考生成器利用线性倒立摆（LIP）模型来计算质心的参考轨迹，同时考虑到步态可能的欠驱动（例如，in a trot）。所获得的轨迹被用作我们以前的工作中提出的非线性MPC的成本函数的参考。我们还提出了一个配方，确保保证响应时间，以达到一个目标，而不需要调整的成本条款的权重。此外，使用优化的参考来校正立足点，以驱动机器人朝向目标。我们证明了我们的方法在模拟和实验中的有效性，在不同的场景与Aliengo机器人。
Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment
GigaAI（极佳科技）；University of Chinese Academy of Sciences（中国科学院大学）；Hong Kong University of Science and Technology（香港科技大学）；University of Leeds（利兹大学）；Cornell University（康奈尔大学）；Tsinghua University（清华大学）；Nanjing University of Science and Technology（南京理工大学）；The Chinese University of Hong Kong（香港中文大学）；FAWTD（一汽技术开发部）
