Human Trajectory
Human trajectory research focuses on understanding, predicting, and generating the movement patterns of individuals and groups, primarily to improve safety and efficiency in human-robot interaction and autonomous systems. Current research emphasizes developing sophisticated models, including neural networks (like transformers and diffusion models), and employing techniques such as reinforcement learning, optimal transport, and game theory to achieve accurate and socially acceptable trajectory predictions. This field is crucial for advancing robotics, autonomous driving, crowd management, and urban planning by enabling safer and more efficient navigation in shared spaces.
Papers
Anticipating Human Behavior for Safe Navigation and Efficient Collaborative Manipulation with Mobile Service Robots
Simon Bultmann, Raphael Memmesheimer, Jan Nogga, Julian Hau, Sven Behnke
Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
Yew Ken Chia, Guizhen Chen, Weiwen Xu, Luu Anh Tuan, Soujanya Poria, Lidong Bing
Revisiting Synthetic Human Trajectories: Imitative Generation and Benchmarks Beyond Datasaurus
Bangchao Deng, Xin Jing, Tianyue Yang, Bingqing Qu, Philippe Cudre-Mauroux, Dingqi Yang
From Cognition to Precognition: A Future-Aware Framework for Social Navigation
Zeying Gong, Tianshuai Hu, Ronghe Qiu, Junwei Liang