首页|Study Data from Stanford University Provide New Insights into Robotics and Automation (Disentangled Neural Relational Inference for Interpretable Motion Prediction)
Study Data from Stanford University Provide New Insights into Robotics and Automation (Disentangled Neural Relational Inference for Interpretable Motion Prediction)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
IEEE
Current study results on Robotics - Robotics and Automation have been published. According to news reporting out of Stanford, California, by NewsRx editors, research stated, “Effective interaction modeling and behavior prediction of dynamic agents play a significant role in interactive motion planning for autonomous robots. Although existing methods have improved prediction accuracy, few research efforts have been devoted to enhancing prediction model interpretability and out-of-distribution (OOD) generalizability.” Financial support for this research came from Honda Research Institute, USA, Inc. Our news journalists obtained a quote from the research from Stanford University, “This work addresses these two challenging aspects by designing a variational auto-encoder framework that integrates graphbased representations and time-sequence models to efficiently capture spatio-temporal relations between interactive agents and predict their dynamics. Our model infers dynamic interaction graphs in a latent space augmented with interpretable edge features that characterize the interactions. Moreover, we aim to enhance model interpretability and performance in OOD scenarios by disentangling the latent space of edge features, thereby strengthening model versatility and robustness. We validate our approach through extensive experiments on both simulated and real-world datasets.”
StanfordCaliforniaUnited StatesNorth and Central AmericaRobotics and AutomationRoboticsStanford University
NETL
NSTL
IEEE
