Predicting driver intentions is a difficult and crucial task for advanced driver assistance systems. Traditional confidence measures on predictions often ignore the way predicted trajectories affect downstream decisions for safe driving. In this paper, we propose a novel multi-task intent recognition neural network that predicts not only probabilistic driver trajectories, but also utility statistics associated with the predictions for a given downstream task. We establish a decision criterion for parallel autonomy that takes into account the role of driver trajectory prediction in real-time decision making by reasoning about estimated task-specific utility statistics. We further improve the robustness of our system by considering uncertainties in downstream planning tasks that may lead to unsafe decisions. We test our online system on a realistic urban driving dataset, and demonstrate its advantage in terms of recall and fall-out metrics compared to baseline methods, and demonstrate its effectiveness in intervention and warning use cases.
A Safety-Aware Shared Autonomy Framework with BarrierIK Using Control Barrier Functions
Technical University of Darmstadt（德累斯顿技术大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Robotics Institute Germany (RIG)（德国机器人研究所）；Centre for Cognitive Science（认知科学中心）；Honda Research Institute Europe GmbH（本田欧洲研究机构）
DTRT: Enhancing Human Intent Estimation and Role Allocation for Physical Human-Robot Collaboration
CAS Engineering Laboratory for Intelligent Industrial Vision, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所CAS工程视觉实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
UAVs Meet Embodied Intelligence: Bridging Human Intents and Flying Dynamics Via Harnessing Physical-Digital AI Agents
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beihang University（北京航空航天大学）；Shanxi Datong University（山西大同大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Sanya（三亚学院）；Wenzhou-Kean University（温州肯恩大学）；Macau University of Science and Technology（澳门科技大学）；KOKONI 3D, Moxin Technology（魔芯科技KOKONI 3D）；University of Science and Technology of China（中国科学技术大学）
Utilizing Vision-Language Models as Action Models for Intent Recognition and Assistance
University of Birmingham（伯明翰大学）；Queen Mary University of London（伦敦大学女王学院）；Aston University（阿斯顿大学）；United Kingdom National Nuclear Laboratory Ltd.（英国国家核实验室有限公司）
Pride and Prejudice: Toward an Information-Theoretic Framework for Mutually Communicative Driver Behavior Modeling
State Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University（吉林大学汽车底盘集成与仿生国家重点实验室）；Beijing National Research Center for Information Science and Technology, Tsinghua University（清华大学北京信息科学与技术国家研究中心）；Department of Engineering, Brock University（布鲁克大学工程系）；Department of Automatics, Federal University of Lavras（拉夫拉斯联邦大学自动化系）
